Jiawei Liu, Xun Gong, Muli Yang, Xingrui Yu, Fen Fang, Xulei Yang, Ivor Tsang, Yunfeng hu, Hong Chen, Qing Guo. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

This paper presents a distributed economic model predictive control (DEMPC) approach for nonlinear subsystems that are dynamically coupled and subject to input constraints and bounded disturbances. In the proposed strategy, each subsystem computes its control action independently via local optimization problem, based on its nominal decoupled dynamics. To enhance robustness against disturbances and interconnections, the robustness constraint is involved in each local optimization problem. Given the non-convexity and lack of positive definiteness in economic stage costs, an auxiliary positive-definite function is introduced to bypass the strict dissipativity assumptionła condition notoriously difficult to verify for nonlinear coupled systems. This function is utilized to construct a tunable stability constraint within the local optimization problem, thereby guaranteeing closed-loop convergence without requiring reliance on system dissipativity. The recursive feasibility of the resulting control strategy and the stability of the closed-loop system are rigorously analyzed. Finally, the application of the proposed DEMPC scheme to the three-cart mass-spring-damper (MSD) system illustrates the possible improvement in control and economic performance while reducing the computational burden.

Moving Horizon Estimation (MHE) is widely used for state estimation due to its ability to effectively incorporate historical information. As a single-model approach, its accuracy depends not only on the quality of the model but also on factors such as sensor noise. However, a single model often struggles to accurately represent the complexity of real-world hybrid systems. Meanwhile, the noises are typically unknown and time-varying. In this regard, inheriting the advantages of interacting multiple model (IMM), this paper further develops an interacting multiple model-based moving horizon estimation with variational Bayesian (IMM-VBMHE). This approach enables real-time updates of noise covariance matrices (NCMs), thereby fulfilling the high-precision state estimation requirements for hybrid systems. It consists of four key aspects: interaction of combined NCMs, mode-matched VBMHE with adaptive NCMs update, model probability updating, and estimation fusion. In the traditional interaction step, the NCMs are interacted, deepening the interaction between models to improve response speed during model switching and increase the probability of selecting the most suitable model for the current system. The variational Bayesian method is applied within the MHE for each model, enabling adaptive updates of the NCMs and the calculation of initial values and state estimates at each timestep within the horizon. Subsequently, the parameter selection and numerical stability analysis of the proposed IMM-VBMHE are discussed. Numerical simulations and front vehicle state estimation experiments are implemented to verify the effectiveness of the proposed algorithm. Compared to estimation methods based on a single model, the proposed IMM-VBMHE effectively identifies the model that best matches the current system, thereby ensuring greater estimation accuracy. In comparison to multiple model estimation methods, the proposed algorithm achieves higher estimation accuracy, owing to the adaptive updating of the NCMs.

This article addresses the problem of distributed state estimation (DSE) for discrete-time interconnected systems, where the observed system is composed of subsystems interconnected through state-to-state and state-to-output couplings. Inspired by the leader-follower consensus method, we propose a distributed observer that enables each subsystem to estimate the entire state of the interconnected system. Under certain structural assumptions, we derive necessary and sufficient conditions for the stability of the estimation error dynamics. We further present a decentralized design of the proposed observer, where the operation and construction of the observer can be completed by each subsystem using its locally available information, including the system's basic configuration, local measurements, and data exchanged with neighboring subsystems. In addition, we demonstrate that our distributed estimation framework can be applied to solve the distributed estimation problem for linear time-invariant (LTI) systems with fixed composition by employing an observability decomposition method. Finally, we illustrate the effectiveness of our scheme by applying it to vehicle platooning.

Manipulability optimization is a critical index to avoid singular configuration of omnidirectional mobile redundant manipulator (OMRM). However, manipulability optimization is a nonlinear nonconvex function and its solution process is a challenge. In addition, existing manipulability optimization methods lack a systematic consideration of the known or unknown obstacle avoidance. To overcome these limitations, a noise suppression manipulability optimization and obstacle avoidance (NSMOOA) scheme is proposed, which not only ensures effective obstacle avoidance but also mitigates the risk of singular configurations in motion control. Subsequently, an adaptive fuzzy controller is designed to enhance the performance of the OMRM control system. Furthermore, the controller suppresses external disturbances and enables real-time control of the OMRM to stably avoids both known and unknown obstacles. The robustness and convergence of the proposed controller are rigorously proven in theory. Numerical and experimental results confirm the effectiveness and real-time stability of the proposed controller in enabling the OMRM to execute trajectory tracking and obstacle avoidance tasks.

In this paper, a hierarchical control scheme, including a decision-making layer and a control layer, is proposed for vehicle platoons executing vehicle-following, cut-in, and cut-out maneuvers. Based on a finite-state machine, the decision-making layer is designed to ensure collision avoidance for vehicle platoons. In the control layer, a distributed model predictive control strategy is employed in the outer-loop to generate a reference sequence, where a linear parameter-varying kinematic model is established to account for the coupling of the vehicle platoon. Incremental constraints are designed to ensure bumpless transfer control during phase switching. By selecting the sum of local cost functions as a Lyapunov candidate, the asymptotic consensus of the vehicle platoon is proven. Furthermore, considering the coupled longitudinal and lateral dynamics of vehicles, in the inner-loop, a nonlinear model predictive control strategy is proposed to track the reference sequence. The effectiveness of the hierarchical control scheme is validated through co-simulation using MATLAB and TruckSim.

Accurate prediction of cyclist trajectories is essential for safe and reliable autonomous driving and intelligent transportation systems (ITSs) in complex traffic scenarios. To address the challenges posed by cyclists’ diverse intentions and non-linear motion patterns, we propose PhysiCycle, a novel multi-task learning framework that jointly predicts future trajectories and turning intentions. This framework integrates interpretable physical modeling with deep learning to enhance both prediction accuracy and behavioral consistency. Our model integrates a dual-path encoder to extract temporal motion cues and behavioral features, an intention classifier module, and a physically consistent decoder with bicycle kinematics consistency constraints. Experimental results on a real-world cyclist action dataset demonstrate that our method significantly outperforms baseline models in both intention classification and trajectory accuracy, achieving strong physical plausibility and generalization performance.

The effectiveness of existing testing methods is under scrutiny due to significant limitations, notably the discrepancy between action distributions and actual distributions caused by inadequate environmental understanding. Additionally, the lack of a scheme prioritizing fidelity while coordinating testing efficiency results in considerable divergence between test and natural scenarios. To address these issues, this paper proposes a Directed Graph Reinforcement Learning approach with action constraint optimization (DGRL) to generate critical scenarios, balancing efficiency and fidelity. By incorporating directed graph convolutional networks, the model encodes environmental states within the observation interval, providing spatiotemporal insights and reducing action distribution discrepancies. Furthermore, it constructs an unbiased estimation reward considering action constraints by sampling action confidence intervals, filtering out distorted actions, thus balancing efficiency and fidelity. DGRL was trained using the highD dataset, demonstrating robust acceleration performance, with interquartile range ($IQR$) of 3.1 and first quartile ($Q_{1}$) of 75.6 in the acceleration ratio distribution, representing the bandwidth and baseline, respectively. The model also achieved high fidelity, with scenario discrepancies compared to natural scenarios reduced by 85.4% ($Q_{1}$) and 46.5% ($IQR$) relative to GAIL, which considers the rationality of driving behavior. Here,$Q_{1}$represents the baseline of scenario discrepancy, and$IQR$denotes the distribution bandwidth of scenario discrepancy. Additionally, there was 69.7% reduction in the upper limit of the 95% confidence interval, indicating a significant decrease in maximum scenario discrepancy. Deployment on an intelligent connected hardware-in-the-loop testing platform validated DGRL’s effectiveness and applicability in real-world.

The energy management system (EMS) of fuel cell electric buses (FCEBs) significantly affects their operational costs, and its performance is closely related to driving speed. Passenger numbers impact the stop time between stations, providing foresight for speed planning. Additionally, maintaining a stable driving speed helps reduce overall energy consumption and power fluctuations, thus extending the lifespan of the fuel cell. Therefore, this paper proposes a learning-based EMS for FCEBs, which integrates speed planning that accounts for passenger flow prediction and speed stability, improving overall vehicle performance through optimized weight coefficients. The study consists of three main parts: 1) predicting passenger flow based on weather, temperature, time, and holidays, and estimating stop times; 2) planning speed with a focus on punctuality and passenger comfort, while minimizing red light waiting time to reduce frequent stop-start cycles; 3) performing multi-objective optimization weight learning, considering passenger flow prediction and speed planning. The planned speed curve is categorized into three driving modes: acceleration, steady-state, and deceleration. The weight coefficients are learned based on the power requirements in these modes, improving the overall system performance. Finally, simulations validate the effectiveness and advantages of the proposed algorithm in passenger flow prediction, punctuality, and EMS performance optimization. This approach significantly enhances passenger trust in public transportation while reducing bus operation costs.

A game-based cooperative steering control (GCSC) approach is introduced to facilitate effective collaboration between human drivers and automation, incorporating the neuromuscular delay inherent in human responses. In this framework, a dynamic coordination between driver and automation goals is achieved through the establishment of a game equilibrium in instances of driver and automation conflict. In response to the challenges posed by frequent modifications in driving weights and their subsequent burden on human drivers, this article proposes a strategy that integrates fixed initial weights with dynamic adjustments to driver–automation driving weights. Moreover, a comprehensive evaluation method including subjective and objective evaluation indexes is proposed. Different drivers are invited to perform virtual driving experiments, and the experimental results are analyzed by the proposed evaluation method. It is concluded that the driver’s driving weight should be kept at a high level during cooperative steering control when the driver’s intention cannot be perfectly obtained, and the determination of the driving weight should also consider the driver’s driving skills.

In order to improve the environmental adaptation and safety of autonomous vehicles trajectory planning process in a complex driving environment, a novel trajectory planning method which meets the requirement of multidriving tasks and adapts to various driving conditions is proposed in this article. In the trajectory planning method, the optimal control problem considering multiple driving tasks is established based on the constructed performance function and constraint analysis of different driving tasks to ensure the accurate realization of driving tasks. Besides, the neural network empirical model, precollision detection model, and trajectory evaluation model are designed by the consideration of selecting the optimal planning parameters in different driving conditions to enhance the adaptability to traffic environment. The advantage of the proposed method is that it not only meets the requirements of a variety of driving tasks, but also able to select the optimal planning parameters according to different traffic conditions while existing methods usually only meet single planning task, such as lane change, and has the fixed and rigid parameter selection. Four different typical scenarios are given to verify the effectiveness of the proposed method and the results show that the proposed trajectory planning method is able to ensure the safety of the vehicle and adapt to different traffic environments flexibly.

Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction. Our code is available on our project website: https://xiaomiaozhang.github.io/Co-MTP/

Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario generation and selection methods often lack adaptivity and semantic relevance, limiting their impact on performance improvement. In this paper, we propose SERA, an LLM-powered framework that enables autonomous driving systems to self-evolve by repairing failure cases through targeted scenario recommendation. By analyzing performance logs, SERA identifies failure patterns and dynamically retrieves semantically aligned scenarios from a structured bank. An LLM-based reflection mechanism further refines these recommendations to maximize relevance and diversity. The selected scenarios are used for few-shot fine-tuning, enabling targeted adaptation with minimal data. Experiments on the benchmark show that SERA consistently improves key metrics across multiple autonomous driving baselines, demonstrating its effectiveness and generalizability under safety-critical conditions.

Jiawei Liu, Yanjiao Liu, Xun Gong, Tingting Wang, Hong Chen, Yunfeng Hu. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Ensuring the side-by-side configuration of the automated surface vessels under the effect of the uncertainties of the environment attracted continued efforts on this challenging issue. This paper investigates the learning-based safety-enhanced adaptive side-by-side control algorithm that suitably defines and uses the modified adaptive control barrier functions to tackle the constrained control satisfied under the uncertainty environment by ensuring the control barriers on state-variables constraints. In addition to the inherent adaptivity of the adaptive control barrier functions, the finite-time auxiliary system is enabled to modify the adaptive control barrier functions, which considers the unknown part of the nominal model to ensure the satisfaction of system constraints, especially under uncertain situations. For the formulated quadratic programs with adaptive control barrier functions and control Lyapunov functions, the operator splitting quadratic program is employed in problem-solving, which effectively enlarges the robustness of problem-solving, making it particularly efficient and reliable for real-time applications. The effectiveness of the proposed method is demonstrated via comparative simulations under uncertain cases to show the superior adaptive ability under the model uncertainties, which can be employed in marine industry applications, e.g., carbon emissions estimation modeling and optimization.Note to Practitioners—This paper was motivated by enlarging the adaptive ability of optimization-based safe operation for safety-critical automated surface vessels control under the side-by-side configuration under the effect of the uncertainty of the environment. The proposed learning-based safety-enhanced adaptive side-by-side control algorithm promotes adaptivity and control performance with the usage of the finite-time auxiliary system to the refined adaptive control barrier functions in the optimization problem formulation. The problem-solving is accelerated with the usage of the operator-splitting quadratic program. These implements effectively enlarge the robustness of the proposed method, making it particularly efficient and reliable for industrial real-time applications. The proposed method employed a complicated system design with the outcome of a simple algorithm implemented with promoted adaptivity and robustness, which can be employed in industrial applications in future research to promote current control system performance.

Decoupling control of the air supply system is crucial for enhancing the performance and prolonging the service life of proton exchange membrane (PEM) fuel cells. However, the strong coupling and nonlinearity inherent in the system pose significant challenges. Current decoupling techniques typically rely on model knowledge and commonly overlook the avoidance of compressor surge, which motivates our work with a twofold contribution. We first design a data-driven feedforward (DDF) and propose a feasible domain constraint (FDC) to avoid surge. Subsequently, an adaptive generalized supertwisting algorithm (AGSTA) is presented that eliminates the residual tracking errors of the DDF. Furthermore, its gradient descent principle and stability are demonstrated. The proposed method has been validated on an air supply system test bench and a hardware-in-the-loop (HiL) platform carrying a fuel cell electric vehicle (FCEV) model. The results indicate that our approach is more advantageous in terms of tracking accuracy, response speed, overshoot suppression and computational cost.

Manipulability optimization plays a crucial role in the motion control of omni-directional mobile redundant manipulator (OMRM), since it can reduce the risk of the OMRM to enter into singular postures. However, manipulability is a nonlinear nonconvex function with respect to the joint variables, and thus its efficient optimization is a challenge. In addition, existing manipulability optimization methods rarely consider obstacle avoidance. To solve these limitations, a time-varying quadratic programming problem-based manipulability-optimized obstacle avoidance scheme is proposed, which no longer approximates obstacles as a single point and avoids singularity in the motion control process. To address the problem that the traditional neural network with fixed convergence parameters is not accurate enough for system disturbance or external noise, this article proposes an antinoise disturbance fuzzy neural dynamics (AND-FND) model. The model adapts the fuzzy parameters and convergence rate based on error fluctuations, enhancing both robustness and adaptability. Notably, the AND-FND model utilizes membership functions and rules to describe controller parameter variations due to external disturbances and operational complexity. Theoretical analysis demonstrates that the AND-FND model possesses global convergence and strong robustness. Numerical results and physical experiments demonstrate the practicability and advantages of the proposed method compared to the existing techniques.

This article develops a distributed economic model predictive control (DEMPC) method to address the load frequency control (LFC) issue in multi-area interconnected power systems, which are subject to control input constraints. The proposed method is designed to enhance economic performance, while ensuring the desired control performance in power systems. To overcome the challenges posed by disturbances and dynamic couplings in interconnected power systems, robustness constraints are incorporated into the framework of DEMPC. In addition, to optimize overall operational economics, the stage cost function encompasses costs associated with load frequency regulation, fuel consumption and wind power generation. Since the stage cost function is typically nonconvex and not positive definite, a positive definite function at the economically optimal equilibrium point is defined. Subsequently, the optimal value function of this function is utilized to establish an adjustable stability constraint for each optimization problem. The closed-loop stability is ensured through the combination of terminal constrained sets, terminal penalty functions, local controllers, and the appropriate sampling interval. Comprehensive analysis and simulation results, conducted on a multiarea interconnected power system, demonstrate possible improvements in computation performance, economic performance, and robustness, while respecting control input constraints.

The embedding of high-level traffic semantics has elevated the precision of vehicle trajectory prediction tasks to a new level. However, owing to the absence of feature-level integration, the information from high-definition maps is underutilized. To this end, a map search-based vehicle trajectory prediction method conditioned on lane segments is proposed in this article. The map is discretized into a graph, where nodes represent lane centerline segments. On this basis, the agent-to-agent, agent-to-map, and map-to-map modules are designed to depict heterogeneous interaction patterns involving vehicles and pedestrians. In addition, a goal node querying mechanism is introduced, which integrates vehicle motion, interaction, and traffic flow states and serves as prior information for trajectory prediction. Finally, a feasible path selection strategy is proposed, generating traffic rule-related prediction trajectories point by point, fully utilizing map information. The experimental results on the nuScenes dataset indicate that the proposed method achieves state-of-the-art prediction accuracy compared with advanced methods.

Reliable remaining useful life (RUL) prediction provides a reference for the secure operation of solid-state batteries (SSBs). However, the intricate potential relations of degradation mechanism and limited degradation data in SSBs bring tremendous challenge. Thus, a novel RUL prediction method named cured memory strategic term moments network with attention of degradation information combined progressive-topologia fusion health indicators (IDPHIs-CMSTM) is proposed for SSBs. It is designed to obtain the implicit relations from Euclidean space and non-Euclidean space and increase the predicted precision on limited degradation data while interpretability is guaranteed. Specifically, in IDPHIs, layer-by-layer progressive fusion method with back-connections assisted by learnable dot product attention mechanism is proposed to gain deep fusion degradation health indicators (HIs) in Euclidean space. It mitigates the risk on information loss during the deep fusion HIs construction process for SSBs. Besides, the topological relations of degradation HIs are presented by graph attention network with two-layers (GAT). The IDPHIs are fed into the developed novel CMSTM to realize RUL prediction. The motivation for CMSTM comes from the early phases of the Ebbinghaus forgetting process, in which recent historical information is utilized to mitigate the forgetting rate of recent degradation information while exploring implicit relations of different degradation information in limited samples. Experiment results on real SSBs dataset show that the IDPHIs-CMSTM achieves higher than 95% predicted precision with well interpretability.

Various discrete-time zeroing neural network (DTZNN) models have been developed for solving dynamic constrained quadratic programming. However, two challenges persist within the DTZNN framework: first, the theoretical analysis of robustness in disturbance suppression remains insufficient; second, to the best of authors' knowledge, existing DTZNN models have yet to provide a theoretical proof of finite-step convergence. Inspired by the inherent robustness and finite-step convergence of discrete sliding-mode control based on the reaching-law, this article is the first work to integrate reaching-law theory into the DTZNN framework to address the aforementioned challenges, ensuring that the resulting DTZNN exhibits both robustness and finite-step convergence. In addition, a novel hyperbolic type reaching law (HTRL) is designed, which offers advantages in reducing the width of the quasi-sliding-mode region and suppressing chattering. The zeroing neural network (ZNN) based on this HTRL (HTRL-ZNN) is rigorously proven to exhibit effective disturbance suppression robustness and finite-step convergence, with an explicit expression provided for the convergence step length. Finally, the effectiveness and advantages of HTRL-ZNN in solving dynamic constrained quadratic programming are validated through both a numerical example and an application-oriented case.

In order to prevent the overheating of motors and enhance vehicle stability, a centralized fault prevention control method based on model predictive control that incorporates a motor thermal model is proposed. The motor thermal model is separated into heat generation and heat dissipation components, precisely capturing the impact of motor torque on temperature variations. By dynamically adjusting motor torque distribution, it effectively regulates motor temperature, extends motors lifespan, and addresses the research gap in the coupling of motor thermal management and vehicle motion control. Besides, it coordinates the control of motor torques, steering angles, and active suspension forces within a unified centralized architecture, thereby avoiding response delays and performance conflicts that may arise from distributed control framework, achieving a balance between vehicle dynamics and thermal protection. Finally, the effectiveness of the proposed method in preventing motor overheating and controlling vehicle stability while maintaining ride comfort is validated through hardware-in-the-loop testing.

Safe trajectory planning in uncertain environments is critical for autonomous driving. However, keeping the safety of vehicles under uncertainty is an open and challenging problem. The key challenges are how to predict and quantify the trajectory uncertainty of other traffic participants, and perform high-quality real-time trajectory planning in dynamic and complex environments. To address these challenges, this paper presents an uncertainty-aware safe trajectory planner based on model predictive control, which considers the uncertain trajectory of the target vehicle and enhances the system safety. To predict the trajectory uncertainty of the target vehicle, a trajectory prediction method combining kinematics and reachable set is proposed, which can reduce the conservatism compared to robust invariant set. To ensure vehicle safety in uncertain environments, an uncertainty-aware safe trajectory planner is established, which extend the control barrier function to uncertain system, and the control barrier function safety constraints are constructed based on the probabilistic n-step reachable set of the target vehicle trajectory. In addition, safety constraints including safe distance from the target vehicle, vehicle handling stability, road boundary, actuator saturation constraints are taken into account. Finally, simulation results show that the proposed planner can improve the system safety and feasibility in uncertain environments compared with other baseline methods. Additionally, its robustness is validated by analyzing the impact of different levels of uncertainty in complex scenarios. Moreover, the real-time performance is verified by the hardware-in-the-loop experiment, which proves that the planner can be applied in real-world autonomous vehicle systems.

Various artificial intelligence (AI) algorithms have been developed for autonomous vehicles (AVs) to support environmental perception, decision making and automated driving in real-world scenarios. Existing AI methods, such as deep learning and deep reinforcement learning, have been criticized due to their black box nature. Explainable AI technologies are important for assisting users in understanding vehicle behaviors to ensure that users trust, accept, and rely on AI devices. In this paper, an explainable$Q$-learning method for AV longitudinal control is proposed. First, AI control of AVs is realized by constructing a deep$Q$-network (DQN) with an intelligent driver model, with the control objective maximizing vehicle speed while preventing collisions. Then, a deep explainer for humans is developed via a Shapley additive explanation (SHAP), and a novel positive SHAP method that defines new base values is proposed to explain how individual state features contribute to decisions. Finally, statistical analyses and intuitive explanations are quantified based on SHAP tools to improve clarity. Elaborate numerical simulations are conducted to demonstrate the effectiveness of the proposed algorithm. The code is available at https://github.com/limeng-1234/Pos$\_$Shap.

In high-temperature environments, integrating dynamic traffic information with an efficient thermal management optimization strategy has proven effective in rapidly reducing battery temperature, keeping it within the optimal operational range. This approach ensures electric vehicles (EVs) maintain optimal power output and range performance. However, due to the prolonged battery heat accumulation, effective optimization requires a long predictive horizon. The real-time implementation of centralized model predictive control (MPC) faces challenges in computational complexity. To address this, the proposed bipartite integration optimization strategy combines two levels for cabin and battery thermal management, enhancing computational efficiency through a segmented, hierarchical optimization approach. A comprehensive thermal model for the cooling system is developed, employing a combination of liquid cooling and active air cooling. In the upper level, vehicle-to-cloud (V2C) communication is utilized to obtain the average vehicle velocity over a long horizon, enabling more accurate forecasts of power demand and thermal load, thereby optimizing the thermal trajectory. In the lower level, the extreme learning machine (ELM) method is used to predict future vehicle velocity over a short horizon, facilitating precise temperature tracking and minimizing variations for optimal control. Simulation results under real driving conditions indicate that the proposed strategy reduces energy consumption by 18.90%, improves computational efficiency by 83.53%, and results in a 0.055% improvement in battery state of health (SOH) over extended cycles, without compromising the cooling requirements of the passenger cabin.

This paper proposes an online co-optimization strategy for velocity planning and powertrain control in autonomous vehicles (AVs), aiming to improve energy efficiency and travel time in urban driving. A hierarchical eco-driving framework is designed to incorporate both long-horizon traffic signal information and short-horizon traffic dynamics. In the upper layer, velocity planning is formulated as a mixed-integer optimal control problem (MIOCP) in the distance domain. Binary variables are introduced using the big-M method to model disjunctive constraints associated with signalized intersection crossing decisions. The lower layer ensures velocity eco-tracking and car-following safety in the time domain while co-optimizing gearshift, traction, and braking torque, also resulting in an MIOCP. To address the real-time computation challenge, a two-stage optimization method is introduced. First, a neural network (NN) is trained offline via supervised learning to predict feasible integer strategies based on MIOCP parameters. Then, the predicted integers are fixed online, and the resulting problem is solved as a nonlinear programming (NLP) problem. The effectiveness of the proposed method is thoroughly validated through extensive simulation studies under various urban scenarios, including multiple signalized intersections, varying road speed limits, and diverse preceding vehicle (PV) behaviors. The results demonstrate that the proposed approach enables safe and adaptive eco-driving, obtaining a 5.97% average improvement in energy efficiency over the intelligent driver model, while accelerating computation speed by 1–2 orders of magnitude compared to Bonmin and achieving millisecond-level computational time.

Due to the input of high-dimensional data in end-to-end autonomous driving, if the feature extraction network is trained online from scratch, it will lead to difficulties in learning and decision-making. To solve this challenging problem, this paper proposes a predefined multi-modal image method to improve decision-making accuracy and a shared framework to quickly train all networks. The inputs are composed of various observations including bird’s-eye view, state, and front view, rather than traditional sensor raw data. They can be filtered out ineffectual features based on human prior knowledge to avoid over-exploration with invalid changes, such as light, trees, mountains, etc. Combined with the processed representations, predefined images are formed by embedding the trajectory, forbidden line, etc. The method can assist agents to capture the coupling relationship between the actions and states, allowing networks to positively adjust weights to quickly obtain expected rewards. Considering that embedding a feature extraction network into reinforcement learning networks will lead to repeated cumulative calculations, a shared framework is proposed to independently compress features while jointly participates in online training to reduce computing costs. This module dynamically combines the policy and critic to update its weights, which overcomes decision-making problems caused by inaccurate the latent feature sequence during pre-training and fine-tuning methods. Finally, the interactive environment is constructed on a realistic driving simulator CARLA, and the fusion of different modal states is explored. The results showed that the multi-modal fusion can explore to earn maximum rewards, and the proposed methods are effective for the training.

The integration of look-ahead information into Model Predictive Control (MPC) frameworks has shown promise for intelligent transportation systems. However, transitioning Predictive Cruise Control (PCC) system research into practical application poses challenges due to numerous weighting parameters and increased computational demands in complex driving environments. Although the Weighted Sum Method is commonly used in PCC system research to balance fuel consumption and trip time objectives, it requires time-consuming weight tuning and often results in suboptimal performance due to fixed weighting parameters. To address this, this paper proposes a Utopia-tracking Model Predictive Control (UTM-MPC) controller, where the cost function is reformulated as the sum of the distances between the objectives and the average Utopia point over the prediction horizon. By analyzing the Pareto front of the PCC optimization problem under varying slope profiles extracted from digital map data, we demonstrate that the proposed UTM-MPC effectively leverages the geometric characteristics of the Pareto front to identify preferred trade-off solutions. The adaptive weighting mechanism—derived from the online-calculated Utopia point—enhances the robustness of the PCC system under complex and dynamic driving conditions. To mitigate the computational burden associated with integrating UTM-MPC into the MPC framework, we introduce a tailored neighboring extremal-based solving algorithm. Leveraging the receding horizon nature of MPC, this method requires only minimal updates to efficiently identify an optimal solution near the nominal trajectory from the previous sampling instance. Simulation results show that the UTM-MPC controller, with its adaptive weighting strategy, consistently outperforms the traditional Weighted Sum Method in terms of both fuel efficiency and trip time.

Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment. Take advantage of trial and error mechanism, reinforcement learning is able to self evolve by learning the optimal policy, and it is particularly well suitable for solving decision-making problems. However, reinforcement learning suffers from safety issues and low learning efficiency, especially in the continuous action space. Therefore, the motivation of this paper is to address the above problem by proposing a hybrid Mechanism-Experience-Learning augmented approach. Specifically, to realize the efficient self-evolution, the driving tendency by analogy with human driving experience is proposed to reduce the search space of the autonomous driving problem, while the constrained optimization problem based on a mechanistic model is designed to ensure safety during the self-evolving process. Experimental results show that the proposed method is capable of generating safe and reasonable actions in various complex scenarios, improving the performance of the autonomous driving system. Compared to conventional reinforcement learning, the safety and efficiency of the proposed algorithm are greatly improved. The training process is collision-free, and the training time is equivalent to less than 10 minutes in the real world.

As artificial intelligence (AI) has already seen numerous successful applications, the upcoming challenge lies in how to realize artificial general intelligence (AGI). Self-learning algorithms can autonomously acquire knowledge and adapt to new, demanding applications, recognized as one of the most effective techniques to overcome this challenge. Although many related studies have been conducted, there is still no comprehensive and systematic review available, nor well-founded recommendations for the application of autonomous intelligent systems, especially autonomous driving. As a result, this article comprehensively analyzes and classifies self-learning algorithms into three categories: broad self-learning, narrow self-learning, and limited self-learning. These categories are used to describe the popular usage, the most promising techniques, and the current status of hybridization with self-supervised learning. Then, the narrow self-learning is divided into three parts based on the self-learning realization path: sample self-learning, model self-learning, and self-learning architecture. For each method, this article discusses in detail its self-learning capacity, challenges, and applications to autonomous driving. Finally, the future research directions of self-learning algorithms are pointed out. It is expected that this study has the potential to eventually contribute to revolutionizing autonomous driving technology.

The performance and safety of the battery are affected by temperature. To maintain the battery temperature within a suitable range, the battery thermal management (BTM) system in electric vehicles (EVs) consumes considerable energy, which significantly reduces the driving range of EVs. Due to the slow dynamics of the thermal system, a long prediction horizon is required to prevent overheating of the battery and achieve low energy consumption. However, the large uncertainties associated with long-term velocity prediction significantly affect performance and robustness. This article proposes an approximate scenario-based model predictive control (ASCMPC) framework to improve the battery temperature control robustness under long-term preview uncertainty and reduce energy consumption while decreasing computation time. The scenario-based model predictive control (SCMPC) determines the control law by optimizing multiple previous velocity examples on the same route, which reduces energy consumption and satisfies battery temperature constraint in the presence of preview uncertainties. But SCMPC inevitably increases the number of optimization problem; thus, a trained deep neural network (DNN) is adopted to obtain an approximate SCMPC control law for easy online implementation. The effectiveness of the approximate controller is verified using Hoeffding’s inequality. Co-simulation results show that the proposed ASCMPC enhances the enforcement of battery temperature constraints and reduces energy consumption by 2.18%–2.76% compared to nondeterministic MPC under the uncertainty of preview information and different ambient temperatures, which also has less computation time.

Battery capacity and safety are closely related to the battery temperature. The battery thermal management (BTM) system consumes considerable energy to maintain the temperature of the battery in the safe range. This energy consumption significantly decreases the driving range of the electric vehicle (EV). This article investigates the optimal control strategy of the BTM system based on model predictive control (MPC) for the connected and automated EV (CAEV), which minimizes energy consumption of the BTM system under the constraint of power and thermal at the same time. The slow thermodynamics of the battery requires a long prediction horizon to achieve optimal temperature and energy consumption of the BTM system. However, long preview information, such as vehicle speed, has large uncertainties, which significantly affects the energy efficiency performance and constraint enforcement robustness. In this study, the effects of the different prediction horizon lengths and the information within the prediction horizon on the MPC performance are first analyzed. Then, the MPC optimization strategy based on adaptive optimization horizon and multitimescale (AOH-MT) is proposed to reduce the temperature constraint violations and computation time. Finally, to improve the robustness under the real driving condition where there are large uncertainties in the speed preview information, a chance-constrained stochastic MPC (C-SMPC) is proposed and the AOH-MT framework is integrated into its prediction horizon to reduce time cost. The simulation results under real-world traffic data show that the proposed approach reduces the constraint violation by 84.88% and the energy cost by 2.44%, which improves robustness against uncertainty in the speed preview information.

This article proposes a novel data-driven iterative learning decoupling controller aimed at addressing the precise tracking issues in discrete-time nonlinear multi-input–multioutput (MIMO) repetitive systems, caused by difficult-to-characterize nonlinearity, multivariate coupling, and data noise pollution. First, a dynamic linearized data model (DLDM) is established, where the estimation of the pseudo-Jacobian matrix (PJM) in prior methods neglects noise suppression. To overcome this gap, a PJM adaptive robust estimation method using a noise-tolerant zeroing neural network (NN) is designed, guaranteeing residual-free convergence and enhancing robustness against data noise. Furthermore, an iterative sliding mode observer is developed to estimate the coupling between multiple variables, aiming to obtain a decoupled DLDM for synthesizing controllers. Next, the iterative learning controller (ILC) utilizing wavelet NNs is designed, and its convergence characteristics are analyzed theoretically. Integrating ILC with decoupling strategies simplifies controller design and provides new perspectives for analyzing the convergence of the MIMO system. Finally, the developed scheme’s performance are validated through case studies. Real-time feasibility is assessed using the dSPACE rapid prototyping system.

This paper proposed a timescale graph-parallel (GP) computation method to solve the real-time optimization problem of nonlinear predictive energy-saving control, thus to realize the implementation of MPC on vehicle on-board controllers. The proposed scheme consists of two parts: forward prediction of the objective function and backpropagation of the partial differential function, both of which can be calculated in parallel. Thus, compared with traditional serial solution method for optimization problems, the timescale graph-parallel computation method can utilize the computing resources of the controller fully. In this paper, firstly, based on the characteristics of commercial vehicles, a mixed integral optimal control problem (MIOCP) was constructed. Then, a detailed timescale graph-parallel computation algorithm was derived for the MIOCP. Finally, GP and Pontryagin’s Minimum Principle (PMP) algorithms were applied on the predefined road for the simulation of the prediction of energy-saving control for commercial vehicles. The simulation results showed that compared with PMP, the maximum iteration number, average iteration number, single longest solution time, and single average solution time of the proposed GP decreased by 60%, 64.28%, 89.53%, and 93.56%, respectively. In addition, GP can also improve fuel efficiency by 1.55% without sacrificing much power performance.

Due to the limitations of network communication conditions for online calling GPT, the onboard deployment of Large Language Models for autonomous driving is in need. In this paper, we propose Drive as Veteran, a fine-tuned LLaMA-7B model with driving tasks. A training set consisting of instructions, scenario descriptions and human-annotated driving tasks is established. Through LoRA fine-tuning, the capability of generating correct driving tasks of our model is demonstrated through a numerical experiment and the comparison to GPT-3.5 is presented. We show that smaller-sized Large Language Models could be deployed onboard with fast generation speed and high accuracy, which could serve as a core component for decision-making in autonomous driving.

Advanced control and safety systems are crucial for electric vehicles, and the accurate estimation of the tire-road friction coefficient (TRFC) is crucial for developing effective safety control strategies. The hybrid data-mechanism model (HDMM), introduced in this paper, addresses the performance challenges posed by the inaccuracies of physical models and the limited interpretability of data-driven models in tire force estimation for TRFC estimation. Tire dynamics often exhibit transient responses, while mechanism-based models(MBM) typically reflect steady-state characteristics. Neglecting transient characteristics leads to a decrease in model accuracy. A neural network is used to learn the transient response characteristics of tire dynamics. These characteristics are then integrated with the steady-state tire forces from MBM to estimate the lateral and vertical forces acting on the wheel. The estimated tire forces serve as virtual measurements to calibrate parameters in the TRFC estimator, based on the Unscented Kalman Filter (UKF). During real-world vehicle tests, the proposed method reduced the Mean Error (ME) in lateral and vertical forces by 1271.85 N and 996.7 N, respectively, compared to the estimated tire forces from MBM. Additionally, the estimated TRFC converged to the reference value approximately 40ms earlier than the result from the MBM, with an estimated deviation within 0.1.

High-performance learning-based control for the typical safety-critical autonomous vehicles invariably requires that the full-state variables are constrained within the safety region even during the learning process. To solve this technically critical and challenging problem, this work proposes an adaptive safe reinforcement learning (RL) algorithm that invokes innovative safety-related RL methods with the consideration of constraining the full-state variables within the safety region with adaptation. These are developed toward assuring the attainment of the specified requirements on the full-state variables with two notable aspects. First, thus, an appropriately optimized backstepping technique and the asymmetric barrier Lyapunov function (BLF) methodology are used to establish the safe learning framework to ensure system full-state constraints requirements. More specifically, each subsystem's control and partial derivative of the value function are decomposed with asymmetric BLF-related items and an independent learning part. Then, the independent learning part is updated to solve the Hamilton-Jacobi-Bellman equation through an adaptive learning implementation to attain the desired performance in system control. Second, with further Lyapunov-based analysis, it is demonstrated that safety performance is effectively doubly assured via a methodology of a constrained adaptation algorithm during optimization (which incorporates the projection operator and can deal with the conflict between safety and optimization). Therefore, this algorithm optimizes system control and ensures that the full set of state variables involved is always constrained within the safety region during the whole learning process. Comparison simulations and ablation studies are carried out on motion control problems for autonomous vehicles, which have verified superior performance with smaller variance and better convergence performance under uncertain circumstances. The effectiveness of the safe performance of overall system control with the proposed method accordingly has been verified.

The coupling of multivariate repeated systems and the nonlinearity that is difficult to characterize through mechanisms, along with actuator constraints and data noise pollution, pose challenges in achieving precise tracking tasks. To address these issues, a novel data-driven robust iterative learning predictive control (ILPC) scheme is proposed. The contribution lies in its ability to achieve multivariable tracking without requiring any prior model information, all while effectively suppressing noise pollution and actively addressing actuator constraints. Specifically, a dynamic linearization data predictive model (DLDPM) is first obtained for system dynamic behavior prediction and controller synthesis. The estimation of the unknown pseudoJacobian matrix (PJM) in DLDPM was previously overlooked in terms of data noise suppression mechanisms. In this study, we utilize a noise-tolerant zeroing neural network (NT-ZNN) for its estimation. Theoretical analysis confirms that the PJM adaptive estimation law can achieve residue-free convergence and its robustness in noise suppression. Then, a constrained ILPC scheme is proposed, which transforms the multivariable tracking problem with actuator constraints into an iteration-varying quadratic programming problem with both inequality and equality constraints, which is solved using NT-ZNN. Theoretical proofs substantiate that a constrained ILPC scheme can achieve asymptotic convergence along the iterative axis. Finally, the proposed scheme is validated in a thermal management system for a proton exchange membrane fuel cell, showcasing the effectiveness in tracking tasks and handling actuator constraints in the presence of noise pollution.

Cooperative perception techniques empower connected and automated vehicles (CAVs) perception capabilities through Vehicle-to-Everything (V2X) communication. However, this advancement introduces a significant influx of information within CAVs, posing a new challenge in managing potentially intricate aspects of asynchrony and correlation in this information landscape. In this context, this paper proposes a cooperative perception algorithm that considers localization uncertainty and information correlation and asynchrony. Specifically, a hierarchical split covariance intersection (SCI) approach is proposed to efficiently fuse the information from local sensors and connected devices. To bridge the reference disparities of information among CAVs, we incorporate localization uncertainty into the connected information fusion through a coordinate transformation approach based on the cubature rule, which unifies the references. Then, the covariance boundedness of the whole proposed algorithm is theoretically analyzed, demonstrating to some extent the safety guaranteed by our algorithm in practical applications. Finally, we build a high-fidelity driving simulator and collected real trajectory data from 80 drivers. The simulation and driver data testing results show the effectiveness and superiority of the proposed algorithm.

In this paper, a hierarchical control strategy of vehicle platoons is presented, in which the longitudinal and lateral coupling property of vehicles is taken into account. A three-degree-of-freedom dynamic model of vehicles is approximated to a “global” linear model by the Koopman operator theory. A synchronous distributed predictive control scheme of vehicle platoons is proposed as an upper-level controller, where both the linear vehicle model and a linear parametric-varying lane-keeping model are adopted to predict the dynamic of vehicles, and keep vehicles in the designated lane. Thus, it can avoid the solution of nonlinear optimization problems and reduce the computational burden accordingly. A lower-level controller is designed, where the desired longitudinal control force determined by the upper-level controller is transformed into the desired throttle angle and brake pressure through an inverse longitudinal dynamics model of vehicles. The joint simulation results by PreScan, CarSim and MATLAB/Simulink show that when the leader vehicle accelerates or decelerates, the following vehicles in the platoon can keep the same velocity as the leader vehicle, and maintain the desired safety distance between the front and rear vehicles. In addition, joint simulation in the curved road scenario show that the performance of lane keeping can be guaranteed for vehicle platoons with the proposed control strategy.

For personalized human-machine cooperative (HMC) control, traditional model-driven approaches, which rely on predefined driver-vehicle-road (DVR) models, often struggle to adapt to individual driver differences. To address this, a data-learning shared control strategy based on game output regulation and adaptive dynamic programming (ADP) is presented. Firstly, considering the differences in driver’s characteristics, vehicle-road dynamics and human-machine interaction, an uncertain DVR system is established. Subsequently, robust output regulation (ROR) is utilized to handle road curvature perturbations and ensure closed-loop system stability. Subsequently, a dynamic game framework between the front-wheel steering system (AFS) and the active rear-wheel steering system (ARS) is further developed to ensure both vehicle stability and path-tracking accuracy in complex environments. Finally, the AFS-ARS optimal control strategies are iteratively learned and updated by ADP, using online DVR system data, without requiring prior knowledge of specific drivers or vehicles. Through driver-in-the-loop experiments, it is demonstrated that the presented method exhibits good adaptability to different drivers.

Due to the inherently coupled dynamics of vehicle and powertrain levels, this paper proposes an energy management strategy that co-optimizes the power split and operating mode selection for hybrid electric vehicles. A mixed integer nonlinear model predictive control (MPC) problem is formulated to guarantee the sub-optimality and robustness of the strategy. The optimization objectives are to achieve minimal fuel consumption, battery degradation inhibition and state-of-charge maintenance within the system physical constraints. However, the existence of logic events and continuous variables poses a significant challenge to solve the optimal control problem. A Pontryagin’s Minimum Principle (PMP)-Dynamic Programming (DP) based solution method is presented, avoiding segmented linear approximation to the powertrain model and relaxation approach to the problem. The PMP calculates the optimal control sequence and cost for each mode, then determines the optimal operating mode based on DP. Moreover, the Gaussian process regression (GPR) model is developed for vehicle speed prediction to deal with the stochastic uncertainties of driving conditions. Experimental results are demonstrated that the proposed algorithm offers about 2% to 10% cost reduction compared to the conventional MPC, while still keeping relatively close to the result of DP.

Game theory-based decision-making model provides an effective means to enable intelligent and human-like Mandatory Lane Change (MLC), which is closely linked to driving safety and efficiency. However, current relevant models have limitations, such as imperfect game structure and incomplete information considered in payoff definitions, with the root cause of ignoring differences in driving styles between interacting vehicles, which are directly related to the acceptable safety thresholds of drivers. To address this issue, this study presents a novel game theory-based decision-making strategy, considering diverse driving styles, achieved by constructing a game with a variable structure according to the Relative Driving Style (RDS) between vehicles. Validation of the Next Generation SIMulation (NGSIM) dataset shows that the proposed decision-making strategy achieves an average accuracy of 98%, which is superior to that of existing single-type game theory-based algorithms.

Autonomous vehicles are expected to achieve self-evolution in the real-world environment to gradually cover more complex and changing scenarios. Reinforcement learning focuses on how agents act in the environment to maximize the cumulative reward, with a great potential to achieve self-evolution ability. However, most of reinforcement learning algorithms suffer from a low sample efficiency, which greatly limits their application in autonomous driving. This paper presents an efficient self-evolution method for any given algorithm based on the combination of Soft Actor Critic (SAC) and Behavioral Cloning(BC). First, the states of the sample trajectory in the replay buffer are separated and input into the given algorithm (algorithm with fundamental performance) to get the output label of actions such that the SAC algorithm can be guided using BC to achieve fast iteration in the direction of optimization with existing basic performance. Then, the value iteration algorithm is combined to achieve the proportion allocation of mixed gradient feedback, in order to trade off exploitation and exploration. In addition, the proposed methodology is evaluated in simulation environment taking automated speed control as an example. Experiment results show that compared with SAC algorithm, the proposed method can realize more than three times of convergence efficiency improvement, while without destroying the exploration enhancement advantage of reinforcement learning algorithm, that is, the performance is improved by 20% compared with the given algorithm (Intelligent Driver Model, IDM). The proposed method can easily extended to improve any given model no matter it is model-based or learning-based algorithm.

The explainability of complex machine-learning models is becoming increasingly significant in safety-critical domains such as autonomous driving. In this context, counterfactual explanation (CE), as an effective explainability method in explainable artificial intelligence, plays an important role. It aims to identify minimal alterations to input that can change the model’s output, thereby revealing key factors influencing model decisions. However, generating counterfactual samples might involve manually selecting input features, potentially leading to suboptimal and biased explanations. This study introduces a feature contribution guided CE generation framework to address this issue. Our method utilizes feature contributions based on Shapley values to guide the model’s focus on the most influential features. This enables end-users to quickly pinpoint the search direction in generating CEs (e.g., prioritizing the most critical features) and producing representative CEs. To comprehensively evaluate our method, we conducted experimental validation on two representative machine learning models: autonomous driving decision-making using Deep Q-Network and lane-changing prediction using deep learning. In addition, we conducted a user-centered study to evaluate the practical applicability of the SVCE in autonomous driving scenarios, which serves as a crucial validation of the presented SVCE. The results show that SVCE can help users understand and diagnose the model.

This paper introduces a novel nonlinear game-based driver-automation cooperative steering control method to mitigate collision caused by the driver’s limited experience on low adhesion road conditions. First, we utilize a model predictive control (MPC) driver model to capture the characteristics of driver experience deficit in low adhesion road conditions, considering the driver’s neuromuscular delay as the system time lag. Then, a dynamic driving weighting strategy is proposed to adjust the driving weights, taking into account both driver-automation handling conflicts and road risks. Next, in order to account for the nonlinear tire dynamics encountered on low adhesion road surfaces, the problem of driver-automation cooperative steering control is mathematically framed as a nonlinear game. The utilization of the piecewise affine(PWA) theory enables the linearization of the nonlinear game optimization problem, facilitating the derivation of an optimal control strategy for ensuring vehicle stability on low adhesion road conditions. Finally, the proposed method is rigorously validated through simulations and driver-in-the-loop tests, comparing its performance against an existing driver-automation cooperative steering control approach. The experimental results substantiate the effectiveness of the proposed method in mitigating the driver’s steering workload and leveraging tire forces optimally to enhance vehicle stability.

Motion prediction of surrounding vehicles in complex environments is essential for autonomous vehicle trajectory planning. Accurate motion prediction requires accurately estimating the state information of the surrounding vehicles. For this purpose, a moving horizon estimation with interacting multiple model (IMM-MHE) algorithm is first proposed here. The algorithm can match multiple vehicle maneuvers, but also fully utilizes the historical information obtained during the driving process, achieving a high estimation accuracy. Second, a moving horizon estimation with variable structure interacting multiple model (VSIMM-MHE) framework is designed. Time-domain adaptation is proposed to solve the problem that the fixed time domain of some models cannot be filled due to model activation and elimination. A new interaction method is proposed to solve the problem that models cannot interact because the starting timesteps of their time domains are different. The proposed framework reduces not only the computational burden, but also the final estimation error caused by the model not matching the current maneuver. Third, based on a model set consisting of different kinds of intention models, a VSIMM-MHE algorithm is proposed. This algorithm introduces residual information into the model classification method, reducing the dependence on the accuracy of the model probabilities. It can not only accurately estimate the state information of surrounding vehicles in a complex environment, but also identify the model that best matches the current maneuver and effectively predict the motion trajectories of surrounding vehicles through model probabilities. Finally, joint simulation with SCANeR studio, Carsim and Simulink and hardware-in-the-loop experiment demonstrate the effectiveness of not only the two proposed estimation algorithms but also the motion prediction of surrounding vehicles using the model probabilities in the VSIMM-MHE algorithm.

Accurately estimating the remaining useful life (RUL) of lithium-ion batteries is crucial for the safe and reliable operation of batteries in electric vehicles. Due to the slow aging process and complex chemical reactions of batteries, it is challenging to obtain the complete battery lifecycle data to predict the RUL. To embrace these challenges, we propose an intelligent Transformer network with the improved self-attention mechanism based on data of the key interval area. Firstly, the knee-point and knee-onset in the capacity decay curve of the battery are identified by the Bacon-Watts model. The feature data that does not meet the minimum aging period between the knee-point and knee-onset in the aging curve is eliminated to ensure the accuracy and quickness of the prediction. Secondly, the denoising autoencoder (DAE) is used to mine the correlation between the aging characteristics in this interval and the low-dimensional hidden feature of battery aging is reconstructed. Finally, the Transformer network with improved multi-head self-attention mechanism is taken to capture the dependencies between features at different positions. A feed-forward neural network is employed to determine the weights of the features at the different sample time, which are then used in conjunction with fully connected layers and a prediction layer to estimate the remaining lifespan of lithium batteries. The proposed method is validated using the CALCE battery dataset. Simulation results show that the method achieves accurate and fast health prognosis with an average error of 0.0091 for the accuracy metric RE when only key feature interval data are used. There is also a significant advantage in computation time compared to other state-of-the-art algorithms, and our method can provide more accurate and faster health prognosis of batteries.

The performance of the battery decreases dramatically in the low temperature, and the heating system of the battery in the cold environment consumes considerable energy, which leads to reduced range and increased safety hazards of electric vehicle. This article focuses on an optimal control strategy of battery thermal management system (BTMS) with waste heat recovery for connected electric vehicle (CEV), which improves heating efficiency and minimizes energy consumption. Firstly, to compensate the insufficient heating capacity of heat pump system in low temperature, the battery pack heating system integrated with heat pump air conditioning system (HPACS), waste heat recovery and electric heater is designed. Secondly, to address the problems of the battery slow thermodynamic response and the increased system complexity due to waste heat recovery, a multi-layer nonlinear model predictive control (ML-NMPC) strategy is developed, which utilizes intelligent transportation system (ITS) information to optimize the energy consumption of the integrated system. The upper layer and lower layer controllers coordinate with each other using the long and short speed prediction respectively to solve the problems of multi-layer control, fast implementation and reference trajectory tracking. The simulation results show that the waste heat recovery system can improve the performance of the HPACS, which increases the coefficient of performance (COP) from 1.79 to 2.54. Compared to centralized NMPC, ML-NMPC reduces energy consumption by 10.2% and 13.7% in the insulation stage under NEDC and real driving condition with higher state of health and less computation time, which demonstrates the superior thermal management capability.

Vehicle carbon emission models are essential for monitoring and managing transportation emissions. Considering the numerous vehicle types and diverse driving conditions, modeling each vehicle individually is not possible. A generalized carbon emission module (GCEM) is proposed to realize fast model transfer across both light-duty gasoline and heavy-duty diesel vehicles. It has five main components: normalized torque function, category-specified fuel consumption rate function, denormalized function, emission-standard correction, and fuel-specified conversion. GCEM estimates carbon emissions based on the engine bench results of a reference vehicle, avoiding time-consuming and costly experiments. By normalizing engine torque, the significant power disparities within the same vehicle category can be effectively addressed. Integrating GCEM within the parallel transportation system is a feasible solution for monitoring complex traffic emissions. Through comprehensive comparisons, GCEM demonstrates a superior generalized ability in this data-limited scenario than three baseline models, both for various test vehicles and diverse driving conditions. As real-world traffic is a typical data-limited scenario, GCEM is a promising and practical transfer method for estimating vehicle carbon emissions.

Connectivity technologies in intelligent transportation systems offer unprecedented opportunities to enhance mobility, fuel economy, and safety for automotive systems. However, the uncertain driving behavior of surrounding vehicles in real-world traffic scenarios can significantly undermine these benefits. To tackle this challenge, this article develops a stochastic predictive-adaptive cruise control (P-ACC) system that effectively addresses uncertainties and automatically adapts to various driving scenarios. The proposed system employs a Gaussian process (GP)-based velocity predictor as its foundation, accurately capturing the driving dynamics of the preceding vehicle while accounting for prediction uncertainty using variances. The real-time feasibility is assessed in a dSPACE rapid prototyping system. In addition, the developed stochastic-model predictive control (S-MPC) approach incorporates the predicted velocity variance into the probabilistic chance constraints, conservatively narrowing the optimization space of the velocity planning domain, thereby enabling more reliable control. To further enhance the system’s performance in adapting to different driving conditions, a scenario-based parameter self-learning (PSL) technique is introduced in the S-MPC controller, utilizing Bayesian optimization (BO). Finally, the performance of the proposed controller is comprehensively evaluated by leveraging a high-fidelity simulator and on-board actual vehicle testing data. Simulation results demonstrate that the proposed method achieved a boost in tracking performance and driving comfort while maintaining fuel-saving benefits.

Recently, thanks to the introduction of human feedback, Chat Generative Pre-trained Transformer (ChatGPT) has achieved remarkable success in the language processing field. Analogically, human drivers are expected to have great potential in improving the performance of autonomous driving under real-world traffic. Therefore, this study proposes a novel framework for evolutionary decision-making and planning by developing a hybrid augmented intelligence (HAI) method to introduce human feedback into the learning process. In the framework, a decision-making scheme based on interactive reinforcement learning (Int-RL) is first developed. Specifically, a human driver evaluates the learning level of the ego vehicle in real-time and intervenes to assist the learning of the vehicle with a conditional sampling mechanism, which encourages the vehicle to pursue human preferences and punishes the bad experience of conflicts with the human. Then, the longitudinal and lateral motion planning tasks are performed utilizing model predictive control (MPC), respectively. The multiple constraints from the vehicle’s physical limitation and driving task requirements are elaborated. Finally, a safety guarantee mechanism is proposed to ensure the safety of the HAI system. Specifically, a safe driving envelope is established, and a safe exploration/exploitation logic based on the trial-and-error on the desired decision is designed. Simulation with a high-fidelity vehicle model is conducted, and results show the proposed framework can realize an efficient, reliable, and safe evolution to pursue higher traffic efficiency of the ego vehicle in both multi-lane and congested ramp scenarios.

Guaranteed safety and performance under various circumstances remain technically critical and practically challenging for the wide deployment of autonomous vehicles. Safety-critical systems in general, require safe performance even during the reinforcement learning (RL) period. To address this issue, a Barrier Lyapunov Function-based safe RL (BLF-SRL) algorithm is proposed here for the formulated nonlinear system in strict-feedback form. This approach appropriately arranges and incorporates the BLF items into the optimized backstepping control method to constrain the state-variables in the designed safety region during learning. Wherein, thus, the optimal virtual/actual control in every backstepping subsystem is decomposed with BLF items and also with an adaptive uncertain item to be learned, which achieves safe exploration during the learning process. Then, the principle of Bellman optimality of continuous-time Hamilton-Jacobi-Bellman equation in every backstepping subsystem is satisfied with independently approximated actor and critic under the framework of actor-critic through the designed iterative updating. Eventually, the overall system control is optimized with the proposed BLF-SRL method. It is furthermore noteworthy that the variance of the attained control performance under uncertainty is also reduced with the proposed method. The effectiveness of the proposed method is verified with two motion control problems for autonomous vehicles through appropriate comparison simulations.

Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV.

This paper proposes an integrated planning and control method for autonomous ground vehicles in dynamic environments. This method takes the dynamic characteristics of large vehicles in consider and is able to autonomously avoid obstacle vehicles during global path tracking without the need for additional planning modules. Firstly, we establish a vehicle dynamics model and tire model to describe the complex dynamic response characteristics of the vehicle. Then, the planning and control problem is formulated as a multiple-constraint model predictive control (MPC) problem to achieve optimal decisions within the predictive horizon. A control barrier function (CBF) is designed as a constraint for the optimization problem to achieve safety-critical obstacle avoidance. Additionally, for dynamic traffic scenarios, an adaptive rule for control barrier function is designed to reduce the impact on surrounding vehicles. Finally, the effectiveness of this method is verified in multiple simulation scenarios.

To achieve rapid and high-precision servo control of an electronic throttle, an adaptive control scheme is proposed based on the extremum seeking (ES), which consists of a variable-gain adaptive proportional-integral (ES-API) controller and an adaptive compensator (ES-ACP). The two gains (${K_{p}}$,${K_{i}}$) of the ES-API controller are designed as maps with respect to the tracking error, and the parameters of these maps are learned by ES. Additionally, the ES-ACP is applied to compensate for the strong nonlinearity inherent in an electronic throttle control (ETC) system, whose parameters are also learned by ES. During parameter learning, an objective function is utilized to quantify the tracking error of the opening angle of the electronic throttle plate, and then the parameters are learned using a step reference signal and a ramp reference signal. ES optimizes the above parameters by reducing the objective function to achieve a more favorable tracking response. Five reference signals are used to evaluate the learned controller after the parameter learning process is completed. Experiments were performed on a test bench equipped with an electronic throttle, and the experimental results show that the control scheme is capable of tracking multiple reference trajectories quickly and accurately.

Cooperative perception techniques incorporating Vehicle-to-Everything (V2X) information offer new possibilities for enhancing the perception capability of automated vehicles (AVs), but also present a new challenge of how to maximize the benefits of connected information with limited communication burden. In this context, this paper proposes a novel cooperative perception solution based on consensus theory to improve the accuracy and consistency for the detection and tracking of non-connected targets by combining V2X information. Given the common multi-sensor configurations of AVs, we design a consensus-based distributed cooperative perception (DCP) algorithm in the framework of multi-layer information fusion for local sensors and connected nodes, and give a nonlinear form based on cubature rules to include more accurate nonlinear system models and nonlinear sensors. Considering the high maneuverability of vehicle targets, we then extend the DCP algorithm to a multi-model form (DMMCP) to improve the model uncertainty of maneuvering targets via combining the prior knowledge of multiple models, which also gives a calculation method for model probability and its average consensus in the context of multiple local sensors. Besides, a new consensus information weight strategy and the properties from different consensus information weights are discussed. The simulation results demonstrate the superiority of both our algorithms over the traditional algorithms in accuracy and consistency, moreover, the DMMCP algorithm, which takes into account model uncertainty, shows better performance than DCP in complex conditions.

Benefiting from the advancement of intelligent transportation systems (ITSs), intelligent connected vehicles (ICVs) are ushering in a once-in-a-generation development opportunity. Considering the widespread presence of heterogeneous vehicles with disturbances and uncertain dynamics in actual platoon scenarios as well as the multimodel switching produced by unavoidable interruptions in the communication process, this paper proposes a data–mechanism adaptive switched predictive (DASP) control strategy. The characteristics of the mechanism model are mapped based on state data to more accurately describe the system’s dynamic characteristics and improve the interpretability of variables. The introduction of Givens rotations and switching criteria enables online adaptive switching of the controller. A robustness analysis of heterogeneous platoon switching control under bounded disturbance is presented, and sufficient conditions for$\mathcal {L}_{2}$string stability are provided. Finally, CarSim simulations and real-time bench experiments are reported to demonstrate the effectiveness of the DASP algorithm for heterogeneous multivehicle regulation with communication interruptions.

In order to resolve the driving conflict and improve the safety and efficiency of autonomous vehicles at unsignalized intersections, a new decision-making method based on game theory with personalized driving preferences considered is proposed in this paper. In the decision-making method, the alterable game mode is constructed by combing the designed game entrying mechanism and replanning of game sequential order under different intersection conditions to ensure the adaptiveness and effectiveness of the decision-making algorithm. Besides, four payoff indicators and personalized payoff function are designed with the consideration of driving efficiency, safety and comfort requirement. The advantage of proposed method is that it not only reduces the complexity of game mode and improves the effectiveness at the same time, but also fully considers the personalized driving preferences to realize human-like driving and personalized decision while the existing methods usually neglect the difference among the drivers and its influence. Five different typical scenarios at the unsignalized intersection are given under co-simulation environment of Matlab and Prescan. The results show that the proposed decision-making method is able to resolve the driving conflict and ensure the safe passage of autonomous vehicles at unsignalized intersections, which verifies the effectiveness of the proposed method.

Under extreme conditions, such as low friction surfaces, violent steering and urgent acceleration/deceleration, vehicle states change rapidly and are influenced by nonlinear and coupled vehicle dynamics. To improve vehicle stability under extreme conditions, a hierarchical control strategy is proposed for DDEVs. In the upper layer controller, a combined-slip tire model is adopted to improve the model accuracy under extreme conditions. A nonlinear model predictive control based controller is then designed to generate the desired tire slip ratios with the main objectives of tracking the desired yaw rate and suppressing the lateral velocity and tire slip ratios. In the lower layer controller, the disturbance on the driver’s torque requirement, which is disregarded by existing studies, is taken into account. Next, a linear predictive controller is designed to track the desired tire slip ratios by adjusting the motor torques. To improve the computational efficiency of the nonlinear predictive controller, a PMP-based, fast solving algorithm is proposed. The effectiveness of the proposed solving algorithm is checked by comparing the control performance with IPOPT. The proposed control strategy is evaluated by a series of HIL experiments. The HIL results show better performance in overall stability improvement and minimize the disturbance on the driver’s torque requirement.

In ice and snow-rutted conditions, it is challenging to design a vehicle stability controller to simultaneously resolve the conflict between the accuracy of the system model and the easy implementation of the controller. To this end, the application of a data-driven control method for vehicle stability control represents a novel, feasible opportunity. This article introduces Givens rotation and forgetting factors to efficiently update the subspace prediction equation with online data. An online data-driven predictive control (ODPC) method is proposed on this basis. To address the problem that persistently excited (PE) condition will cause fluctuations in the steady-state response of ODPC, a data-driven switched predictive control strategy (DSPCS) employing attenuated excitation (AE) signals and hysteresis comparisons based on posterior prediction errors is proposed. In addition, an implementation method involving the Laguerre function (LF) parameterization of the control input is proposed to improve the computational efficiency further. Numerical simulation results show that both the ODPC method and the DSPCS can effectively track given yaw rate and sideslip angle reference under the influence of ruts. Furthermore, the DSPCS can effectively reduce steady-state response fluctuations. In addition, the LF parameterization is superior regarding computational time.

As a critical component of the Internet of Things, connected automated vehicles (CAVs) are progressively gaining attention for their benefits in terms of increased safety and reduced traffic congestion. In this article, a novel distributed data-driven model-predictive control (DDMPC) approach including feedforward for disturbance is proposed for cruise control of a hybrid platoon with a combination of human-operated and autonomous vehicles. By employing a predictor constructed from input/output data, predictive controllers are obtained without depending on the characteristic information of the system. A robustness analysis is performed with a combination of the input-to-state stability (ISS) theory with the sampled-data systems theory, and the$\mathcal {L}_{2}$-norm string stability is ensured by strict mathematical proof. In addition, we also discuss the asymptotic stability when the controller switches. CarSim simulation and bench experiment results verify that the DDMPC for connected vehicles can be robust to velocity disturbances and achieve satisfactory performance in ensuring string stability.

To reduce the impact of human–machine conflict on vehicle safety, this study proposes a novel human–machine cooperative steering control approach from the perspective of driver trust in the machine. The relationship between driver trust in the machine and driving skill is analyzed by the chi-square test method, and an online cooperative algorithm is designed using fuzzy control for different conditions, which assigns control authority based on driver trust under safe conditions and gives most of the authority to the machine to ensure safety under dangerous conditions. The machine is designed using model predictive control as an alternative controller parallel to the driver. To implement the proposed approach, a simulation platform that includes drivers and a test vehicle is established. Based on the driving data of human drivers collected in field tests, a two-point visual driver model is established to simulate steering behaviors and reflect physical workload. The parameters of the driver model are identified by a particle swarm optimization method to represent different drivers. The effectiveness of the approach, such as guaranteeing vehicle safety and reducing physical workload and human–machine conflict, is verified by simulations under typical conditions and obstacle avoidance conditions based on veDYNA vehicle dynamics software.

The rapid development of connected vehicles (CVs) has offered novel opportunities for eco-driving control. Considering inherent spatial and temporal constraints from the preceding vehicle, multiple signalized intersections, and queues, this paper proposes a hierarchical energy-efficient control strategy (HCS) in different domains to reduce fuel consumption and travel time. Considering both traffic lights and queue information, the concept of virtual traffic lights is proposed based on queue estimation. In the higher-level controller, a distance-based energy-economy velocity optimization problem is formulated to treat spatial constraints from virtual traffic lights and queues. The optimal velocity profile is solved by the direct multiple shooting algorithm in a model predictive control (MPC) framework, which is used as a reference by the lower-level controller. To treat temporal constraints of safe inter-vehicular time, a predictive cruise control (PCC) in the time domain is introduced in the lower-level controller to ensure safe inter-vehicle distances and improve fuel efficiency while tracking the reference speed. Comparative simulation results show that the proposed strategy can significantly reduce fuel consumption and travel time.

Under extreme conditions, vehicle states change rapidly between stable and unstable, resulting in dynamic requirements for the vehicle’s overall safety stability. Simultaneously, the coupled nonlinear characteristics of vehicle dynamics cannot be ignored in controller design. To address the above problems and improve vehicle longitudinal and lateral stability integrally, an envelope-based model predictive control (MPC) strategy with dynamic objectives is proposed for four-wheel independent motor-drive electric vehicles (4WIMD EVs). First, according to the current driving behavior and the collected road information, the envelope control regions concerning vehicle side-slip angle and yaw rate are obtained online, and divided into stable, critically stable, and instable regions with different safety requirements. Then, the safety dynamic requirements are constructed in the designed MPC-based control structure. A nonlinear vehicle dynamics model with a combined-slip tire model, which integrates the longitudinal and lateral dynamics, is utilized to predict vehicle states. The switching of requirements is reflected in the variation of weighting factors and constraint values. Finally, CarSim and Matlab/Simulink co-simulation, and hardware-in-the-loop simulation test results show better satisfactory performance in improving overall vehicle stability under extreme driving conditions.

In order to improve the efficiency and safety of autonomous vehicles’ decision-making process in complex urban scenarios, a decision-making method for hierarchical processing of static traffic law information and dynamic traffic participant information is proposed in this paper. In the decision-making method, the candidate behavior set is constructed by extracting the element of traffic laws and fully considering the traffic laws constraints to ensure the legality and effectiveness of the decision-making algorithm. Besides, four evaluation indicators and two-level entry threshold are designed to select the optimal driving behavior with the consideration of driving efficiency, ride safety and macro path requirement. The advantage of proposed method is that it avoids the problem of poor adaptability to traffic laws and regulations as the existing methods usually make decisions under the condition of mixed traffic laws and traffic participant information. A complete driving task simulation and analysis, including six typical urban traffic scenarios, is given under Matlab environment. The results show that the proposed decision-making method is able to make reasonable and feasible decisions and highly consistent with the actual driver’s decision-making behavior in complex urban scenarios, which verifies the effectiveness of the proposed method.

Existing hierarchical planning and control architectures can cause the upper-level target trajectory passed to the lower-level tracking controller to be too conservative or impossible to track on slippery roads. To solve this problem, this paper proposes a new simultaneous planning and control scheme that determines the control inputs without explicit path planning and requires only information about the control objectives and safety constraints. First, we establish the vehicle stability boundary and the safety distance constraints to ensure that the vehicle avoids drifting and collisions on slippery roads. Moreover, real-time adaptive model predictive control (MPC) with online model linearization is designed to approximate the nonlinear programming as a quadratic program (QP), which allows the use of fast convex optimization tools. The steering angle and longitudinal acceleration are thus obtained. Finally, we design the controller to convert the longitudinal acceleration into an actuatable drive torque to avoid tire skidding on slippery surfaces. The simulation results show that under the conditions of low adhesion road and$\mu $-split roads, the proposed algorithm makes the sideslip angle of the vehicle within 1 degree. In contrast, the sideslip angle of the hierarchical algorithm reaches 6 degrees, and the vehicle has a noticeable drift. The proposed algorithm dramatically improves stability and driving comfort.

Robust model predictive control (MPC) is a well-known control technique for model-based control with constraints and uncertainties. In classic robust tube-based MPC approaches, an open-loop control sequence is computed via periodically solving an online nominal MPC problem, which requires prior model information and frequent access to onboard computational resources. In this article, we propose an efficient robust MPC solution based on receding horizon reinforcement learning, called r-LPC, for unknown nonlinear systems with state constraints and disturbances. The proposed r-LPC utilizes a Koopman operator-based prediction model obtained offline from precollected input–output datasets. Unlike classic tube-based MPC, in each prediction time interval of r-LPC, we use an actor–critic structure to learn a near-optimal feedback control policy rather than a control sequence. The resulting closed-loop control policy can be learned offline and deployed online or learned online in an asynchronous way. In the latter case, online learning can be activated whenever necessary; for instance, the safety constraint is violated with the deployed policy. The closed-loop recursive feasibility, robustness, and asymptotic stability are proven under function approximation errors of the actor–critic networks. Simulation and experimental results on two nonlinear systems with unknown dynamics and disturbances have demonstrated that our approach has better or comparable performance when compared with tube-based MPC and linear quadratic regulator, and outperforms a recently developed actor–critic learning approach.

In this article, a systematic assessment of cyber-physical security on the energy management system for connected and automated electric vehicles is proposed, which, to our knowledge, has not been attempted before. The generalized methodology of impact analysis of cyber attacks is developed, including novel evaluation metrics from the perspectives of steady state and transient performance of the energy management system and innovative index-based resilience and security criteria. Specifically, we propose a security criterion in terms of dynamic performance, comfortability, and energy, which are the most critical metrics to evaluate the performance of an electronic control unit (ECU). If an attack does not impact these metrics, it perhaps can be negligible. Based on the statistical results and the proposed evaluation metrics, the impact of cyber attacks on ECU is analyzed comprehensively. The conclusions can serve as guidelines for attack detection, diagnosis, and countermeasures.

This study aims to develop an optimal cruise controller that can automatically adapt to individual car-following style. First, the adaptive cruise control (ACC) problem is formulated as a linear quadratic optimal control, and an optimal control law containing the longitudinal acceleration of the target vehicle is derived. Then, a certain number of individual car-following styles are predefined on the basis of the proposed optimal cruise controller. Thereafter, a car-following style learning algorithm is proposed to quantify the closeness of the predefined individual car-following style to the specific driver, and a proper style is thus determined for the specific driver by using this learning algorithm. On the basis of the learned car-following style, the proposed optimal cruise controller can adapt itself to individual car-following style. Finally, the proposed self-learning optimal cruise controller is evaluated through simulation and experimental tests. Results show that the control behavior of the proposed self-learning optimal controller is closer to that of the human driver than that of a factory-installed ACC.

The roundabout is a typical changeable, interactive scenario in which automated vehicles should make adaptive and safe decisions. In this article, an optimization embedded reinforcement learning (OERL) is proposed to achieve adaptive decision-making under the roundabout. The promotion is the modified actor of the Actor-Critic framework, which embeds the model-based optimization method in reinforcement learning to explore continuous behaviors in action space directly. Therefore, the proposed method can determine the macroscale behavior (change lane or not) and medium-scale behaviors of desired acceleration and action time simultaneously with high sample efficiency. When scenarios change, medium-scale behaviors can be adjusted timely by the embedded direct search method, promoting the adaptability of decision-making. More notably, the modified actor matches human drivers' behaviors, macroscale behavior captures the human mind's jump, and medium-scale behaviors are preferentially adjusted through driving skills. To enable the agent adapts to different types of the roundabout, task representation is designed to restructure the policy network. In experiments, the algorithm efficiency and the learned driving strategy are compared with decision-making containing macroscale behavior and constant medium-scale behaviors of the desired acceleration and action time. To investigate the adaptability, the performance under an untrained type of roundabout and two more dangerous situations are simulated to verify that the proposed method changes the decisions with changeable scenarios accordingly. The results show that the proposed method has high algorithm efficiency and better system performance.

Non-orthogonal multiple access (NOMA) is regarded as a promising technology to provide high spectral efficiency and support massive connectivity in 5G systems. Traditionally, NOMA user grouping is non-overlapping, leading to a waste of power resources within each NOMA group. Motivated by this, in this paper we propose a novel generalized user grouping (GuG) concept for NOMA from an overlapping perspective, which allows each user to participate in multiple user groups but subject to individual maximum power constraint. In order to achieve effective GuG and maximize the system sum rate, we formulate a joint power control and GuG optimization problem. Then we further provide a machine learning-based GuG scheme to obtain the optimized feasible GuG and the optimal power control solutions efficiently, in which the established machine learning-based model is exploited to explore the relative relationships of channel gains of users and obtain several fixed grouping patterns via Merge operation. Simulation results verify the efficiency of GuG in NOMA systems and indicate that compared with traditional NOMA user grouping schemes, our proposed GuG scheme achieves significant performance gains in terms of system sum rate.

Connected automated vehicle (CAV) platoon control is becoming increasingly prevalent because of its unique advantages in reducing fuel consumption and improving traffic efficiency. A novel control framework for CAV platoon control is designed in this article. First, a model predictive control (MPC)-based method is proposed to obtain the optimal velocity of the whole platoon, in which both reducing fuel consumption and improving transport efficiency are taken into account in the optimization process. Then, a distributed adaptive triple-step nonlinear control strategy is investigated from the perspective of multiagent system control. The adaptive performance of the control strategy can guarantee the string stability of the CAV platoon under the premise of the existence of dynamic uncertainties. Various simulation conditions with heterogeneous dynamic disturbances are designed to validate the proposed control strategy, and the results show that the proposed control strategy can be robust to dynamic disturbances while ensuring the string stability of the CAV platoon.

The rapid development of active safety control systems has paved the way for the discussion of lateral stability in critical running conditions. To improve the lateral stability of a vehicle in critical running conditions, a nonlinear model predictive control (NMPC) strategy that integrates active front steering and additional yaw moment is proposed in this manuscript. The reference yaw rate in critical running conditions is obtained by employing Lyapunov's second method. In addition, this method adopts a varied sideslip angle to describe a stability region using a phase plane approach, which is used as the vehicle stability constraints. To verify the effectiveness of the presented lateral NMPC stability controller, off-line simulations under various running conditions are carried out using the high-precision vehicle simulation veDYNA software. It is shown that the N-MPC controller presents a feasible performance enhancement in tracking the reference yaw rate and keeping the vehicle stable in critical running conditions.

This paper proposes a predictive cruise control based on eco-driving for a passage car that uses the information of upcoming traffic limits and the preceding vehicle to realize better fuel economy. To fully exploit the inherent potential of the powertrain system to reduce fuel consumption, the velocity is obtained by optimizing the engine torque, the brake force, and the gearshift while ensuring safe distance separation and traffic speed limits. The problem is described as a nonlinear mixed-integer problem and solved by the concept of combining Pontryagin’s minimum principle and bisection method. The simulation results show a significant improvement in computational efficiency compared with traditional numerical methods, and the simulation results also show that the computational time increases linearly with prediction horizon. It is shown that an improvement of 8% in fuel is achieved in a realistic scenario compared with a basic vehicle using a standard adaptive cruise control.

Velocity profile optimization of on-road vehicles is one of the main eco-driving techniques, which has great potential to extend the capability of powertrain and automatic longitudinal control by minimizing the energy consumption. Due to the multi factors affecting the driving trajectory and longer prediction horizon comparing with other traditional control, the calculation of a velocity profile optimization often requires a large number of computations. In this paper, a hierarchical control (HC) strategy of velocity optimization is proposed to reduce computation burden with little accuracy loss. In the HC strategy, a specific driving task is divided into several operation of modes as acceleration (A), constant speed (C), deceleration (D), and braking (B). The shift timing of the driving modes are optimized by formulating a nonlinear programming problem in a master controller. Then, engine torque, gear position, and brake force are optimized in each driving mode. Results indicate that the computation time of velocity profile optimization using the proposed HC strategy is reduced by 90% of the ones using the basic centralized optimal controller while the resulting velocities are similar. It is also shown that an improvement of 30% in fuel economy is achieved compared with the real-life human-driven velocity profiles.

The rapid development of intelligent vehicles has paved the way for active chassis lateral stability, which is a novel issue and critical to vehicle stability and handling performance. To obtain active chassis lateral stability for intelligent vehicles, a nonlinear model predictive control (NMPC) method integrating active front steering and an additional yaw moment is proposed. It adopts the tire sideslip angle to express vehicle lateral stability, and addresses the actuator and security constraints and the nonlinear properties of the tire-road force effectively. Moreover, the hardware implementation, based on the field programmable gate array (FPGA), is presented to satisfy miniaturization and to discuss the computational efficiency of the proposed NMPC method. To verify the effectiveness of the presented NMPC method, offline simulations comparing the NMPC method with the direct yaw moment control (DYC) method under various running conditions and a real-time implementation experiment are carried out. The results indicate that the proposed NMPC method controls better than the DYC-based method. In addition, the presented NMPC method exhibits good robustness when the longitudinal velocity and tire-road friction coefficient vary within a suitable range. Moreover, the computational time of the proposed NMPC controller, implemented using the FPGA, is only 4.994 ms during one sampling period, which can satisfy the real-time requirement of active chassis lateral stability control.

This paper proposes an extensive overview of the tire-road interaction estimation issue as it relates to automated driving from the prospectives of sensor configuration, tire modeling, and estimation approaches. The tire-road interactions needed for estimation are first determined and classified. Then, the sensor configuration schemes of different types of tire-road interactions are presented and analyzed. The following introduces various types of tire models and provides the limitations and advantages of different estimation approaches based on categorizing and summarizing those techniques. Moreover, some interesting perspectives for future research are listed based on the extensive experience of the authors.

Eliminating the influence of cogging torque and model uncertainty on the tracking control of a dc motor when its speed varies nonperiodically is a challenge. In this paper, an adaptive robust triple-step control method is proposed for compensating cogging torque and model uncertainty. First, a new presentation of the cogging torque and a simplified model of the friction torque are presented to facilitate the online estimation of the unknown model parameters. The load torque, motor disturbance, and model errors are considered as model uncertainty. Based on these considerations, a control-oriented model that contains unknown parameters and model uncertainty is obtained. Second, benefitting from the new presentation, an adaptive algorithm is employed to identify the unknown parameters online. The model uncertainty is estimated by an extended state observer. Third, the model-based triple-step nonlinear method is extended to a system with both parameter uncertainty and model uncertainty, and an adaptive robust triple-step nonlinear controller is derived. The robust stability of the closed-loop system is proven in the framework of Lyapunov theory. Finally, the effectiveness and the satisfactory control performance of this controller are evaluated through comparative experiments on a J60LYS05 motor.

The driving model switched between an intelligent vehicle and a human driver is a hot discussing issue for intelligent driving system, and it relates to the safety of the intelligent vehicle and traffic efficiency of transportation system. It presents a hazard-evaluation-based driver-automation switched shared steering control approach for intelligent vehicles in this manuscript. The switched operation between human driver and autopilot system is carried out when the hazard situation is tested by the autopilot controller. The driver's operation and the deviation from the road center line are employed to carry out the hazard evaluation. The autopilot controller is designed using the constrained model predictive control (MPC) approach to keep the intelligent vehicle run in the safe area that is between the road boundary. In order to verify the control performance of the proposed algorithm, simulation verification under hazard situation of the proposed approach are carried out and compared with the non-switching method. The results show that the intelligent vehicle can keep safe in the hazard situation.

As a typical example of cyber-physical systems, intelligent vehicles are receiving increasing attention, and the obstacle avoidance problem for such vehicles has become a hot topic of discussion. This paper presents a simultaneous trajectory planning and tracking controller for use under cruise conditions based on a model predictive control (MPC) approach to address obstacle avoidance for an intelligent vehicle. The reference trajectory is parameterized as a cubic function in time and is determined by the lateral position and velocity of the intelligent vehicle and the velocity and yaw angle of the obstacle vehicle at the start point of the lane change maneuver. Then, the control sequence for the vehicle is incorporated into the expression for the reference trajectory that is used in the MPC optimization problem by treating the lateral velocity of the intelligent vehicle at the end point of the lane change as an intermediate variable. In this way, trajectory planning and tracking are both captured in a single MPC optimization problem. To evaluate the effectiveness of the proposed simultaneous trajectory planning and tracking approach, joint veDYNA-Simulink simulations were conducted in the unconstrained and constrained cases under leftward and rightward lane change conditions. The results illustrate that the proposed MPC-based simultaneous trajectory planning and tracking approach achieves acceptable obstacle avoidance performance for an intelligent vehicle.

In this paper, a learning-based predictive control (LPC) scheme is proposed for adaptive optimal control of discrete-time nonlinear systems under stochastic disturbances. The proposed LPC scheme is different from conventional model predictive control (MPC), which uses open-loop optimization or simplified closed-loop optimal control techniques in each horizon. In LPC, the control task in each horizon is formulated as a closed-loop nonlinear optimal control problem and a finite-horizon iterative reinforcement learning (RL) algorithm is developed to obtain the closed-loop optimal/suboptimal solutions. Therefore, in LPC, RL and adaptive dynamic programming (ADP) are used as a new class of closed-loop learning-based optimization techniques for nonlinear predictive control with stochastic disturbances. Moreover, LPC also decomposes the infinite-horizon optimal control problem in previous RL and ADP methods into a series of finite horizon problems, so that the computational costs are reduced and the learning efficiency can be improved. Convergence of the finite-horizon iterative RL algorithm in each prediction horizon and the Lyapunov stability of the closed-loop control system are proved. Moreover, by using successive policy updates between adjoint time horizons, LPC also has lower computational costs than conventional MPC which has independent optimization procedures between two different prediction horizons. Simulation results illustrate that compared with conventional nonlinear MPC as well as ADP, the proposed LPC scheme can obtain a better performance both in terms of policy optimality and computational efficiency.

The accurate information of vehicle states that could not be obtained directly by onboard sensors is virtual important for vehicle active safety systems. This paper presents the nonlinear full-order observer which is used to estimate the longitudinal velocity, lateral velocity and road grade estimation with autonomous driving. Firstly, this paper established a simplified vehicle dynamics model for the Hongqi HQ430 which could characterize the performance of autonomous driving vehicle on highway, and the estimator was designed. Secondly, in order to verify the effectiveness of the proposed nonlinear full-order observer, we do some simulation experiments, simulation experiments were carried out under different running conditions, the simulation results showed that the estimation method have certain validity and accuracy.

Wide usage of vehicle's onboard navigation system offers vehicles better terms to improve energy efficiency. In this paper, a computationally effective energy management strategy using model predictive control (MPC) is proposed to find the energy optimal torque split, gear shift, and velocity control of a parallel hybrid electric vehicle (HEV). We consider the vehicles in urban driving, where the vehicle trajectory is constrained by the infrastructure (road signs) and other vehicles (traffic). Restricted by the discrete gear ratio, nonlinear dynamics of the vehicles, and especially different time scales between velocity trajectory and torque split optimization, finding these control variables in one optimal problem is quite challenging. Thus, this paper uses bi-level methodology to reduce computational time and simplify the hybrid optimal problem by decoupling its components into two subproblems. In the outer loop, the optimal velocity trajectory is obtained by solving a nonlinear time-varying optimal problem using a Krylov subspace method to improve computational efficiency. In the second subproblem, we provide an explicit solution of the optimal torque split ratio and gear shift schedule by combining Pontryagin's minimum principle and numerical methods in the framework of MPC. Simulation results on an AMESim model of an HEV with seven-speed automated manual transmission over multiple driving cycles are presented. The results indicate that both energy efficiency and computational speed are improved.

Trajectory tracking control of wheeled mobile robots (WMRs) has been an important research topic in control theory and robotics. Although various tracking control methods with stability have been developed for WMRs, it is still difficult to design optimal or near-optimal tracking controller under uncertainties and disturbances. In this paper, a near-optimal tracking control method is presented for WMRs based on receding-horizon dual heuristic programming (RHDHP). In the proposed method, a backstepping kinematic controller is designed to generate desired velocity profiles and the receding horizon strategy is used to decompose the infinite-horizon optimal control problem into a series of finite-horizon optimal control problems. In each horizon, a closed-loop tracking control policy is successively updated using a class of approximate dynamic programming algorithms called finite-horizon dual heuristic programming (DHP). The convergence property of the proposed method is analyzed and it is shown that the tracking control system based on RHDHP is asymptotically stable by using the Lyapunov approach. Simulation results on three tracking control problems demonstrate that the proposed method has improved control performance when compared with conventional model predictive control (MPC) and DHP. It is also illustrated that the proposed method has lower computational burden than conventional MPC, which is very beneficial for real-time tracking control.

Path tracking issues of autonomous ground vehicles (AGVs) have attracted more attention in recent years with the intelligent and electrified development of vehicles. In order to make AGVs path tracking problem more flexible, regional path tracking problem is discussed in this manuscript based on model predictive control (MPC) method, where the front wheel steering angle is regarded as the control variable. The feasible region for AGVs running is determined first according to the detected road boundaries. In the following, AGVs running in this region is considered using kinematic model. Then, in order to make the actual trajectory of AGVs keep in the region and satisfy the safety requirements, MPC method is employed to design path tracking controller considering the vehicle dynamics, the actuator and state constraints. In order to verify the effectiveness of the proposed algorithm, simulations under various test conditions are carried out using a high fidelity vehicle simulator veDYNA, where the Hongqi vehicle HQ430 parameters are matched. The results obtained from the simulation illustrate that the proposed algorithm obtains good performance in dealing with the regional path tracking problem.

Great advances in simulation-based vehicle system design and development of various driver assistance systems have enhanced the research on improved modeling of driver steering skills. However, little effort has been made on developing driver steering skill models while capturing the uncertainties or statistical properties of the vehicle-road system. In this paper, a stochastic model predictive control (SMPC) approach is proposed to model the driver steering skill, which effectively incorporates the random variations in the road friction and roughness, a multipoint preview approach, and a piecewise affine (PWA) model structure that are developed to mimic the driver's perception of the desired path and the nonlinear internal vehicle dynamics. The SMPC method is then used to generate a steering command by minimization of a cost function, including the lateral path error and ease of driver control. In the analyses, first, the experimental data of Hongqi HQ430 are used to validate the driver steering skill controller. Then, the parametric studies of control performance during a nonlinear steering maneuver are provided. Finally, further discussions about the driver's adaption and the indication on vehicle dynamics tuning are given. The proposed switching-based SMPC driver steering control framework offers a new approach for driver behavior modeling.

Simulation-based vehicle system design and development of various active chassis control systems necessitate an enhanced understanding of driver-vehicle systems, in particular improved modeling of driver driving control characteristics. A number of research efforts have been made in developing driver models in the past few decades. However, little effort has been attempted in modeling driver steering control behavior capturing vehicle-road system parameter uncertainties. In this paper, a novel driver steering control model based on stochastic model predictive control (SMPC) is proposed to effectively incorporate the variations in the vehicle-road system parameters. The proposed SMPC-based driver steering control framework consists of three modules, namely perception, decision and execution, where a multi-point driver preview approach is employed. An internal vehicle dynamics model with the parameter uncertainty in road friction coefficient is formulated to represent the driver's knowledge and adaptation about the variations in road conditions. The SMPC method is then used to minimize a cost function that is a weighted combination of lateral path error and ease of driver control. Simulation analysis about the variant parameters and comparison with an MPC-based driver model demonstrate the effectiveness and robustness of the proposed SMPC-based driver steering control model.

In this paper, a data-driven predictive controller is designed for the start-up process of vehicles with automated manual transmissions (AMTs). It is obtained directly from the input-output data of a driveline simulation model constructed by the commercial software AMESim. In order to obtain offset-free control for the reference input, the predictor equation is gained with incremental inputs and outputs. Because of the physical characteristics, the input and output constraints are considered explicitly in the problem formulation. The contradictory requirements of less friction losses and less driveline shock are included in the objective function. The designed controller is tested under nominal conditions and changed conditions. The simulation results show that, during the start-up process, the AMT clutch with the proposed controller works very well, and the process meets the control objectives: fast clutch lockup time, small friction losses, and the preservation of driver comfort, i.e., smooth acceleration of the vehicle. At the same time, the closed-loop system has the ability to reject uncertainties, such as the vehicle mass and road grade.

Integral input-to-state stability (iISS) of a class of nonlinear systems is investigated via satisficing decision theory in this paper. In particular, based on a new concept of control Lyapunov function (ilSS-CLF), a satisficing complete parameterization design of integral input-to-state stabilizing control laws that achieve iISS disturbance attenuation is discussed. A large family of the designed control laws has certain robustness to input disturbances and under some assumption can solve an inverse optimal gain assignment problem. The same method can also apply to the problem of integral input-output-to-state stabilization.