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.

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.

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.

This article aims to address the problem of trajectory tracking and obstacle avoidance for omnidirectional mobile manipulator in the actual working condition. To this end, a model predictive control-based trajectory tracking and obstacle avoidance scheme is proposed, which achieves the coordinated execution of trajectory tracking tasks and obstacle avoidance in a simple and efficient manner. In practice, noise disturbances pose challenges to the normal operation of the system. Thus, a noise suppression iterative neural dynamics (NSIND) model is proposed to improve the system of anti-interference performance against noise. Then, the convergence and robustness of the NSIND model are proven through rigorous theoretical analysis. Numerical simulation and physical experimental results further verify the effectiveness and superiority of the proposed method in handling trajectory tracking and obstacle avoidance under noisy environment. Compared to existing technologies, the proposed method exhibits significantly greater practical utility.

Precise position and posture control of an omnidirectional mobile redundant manipulator (OMRM) with unknown structural information is challenging. This article develops a data-driven orthogonal repetitive motion-posture control (DDORMPC) scheme that leverages online learning to regulate repetitive motions in both position and end-effector quaternion orientation. Then, a dynamic neural network with nonconvex mappings (NCMDNN) is introduced by integrating structure learning with OMRM control to solve the DDORMPC problem. It employs a velocity-compensated gradient-descent update for accurate online estimation of the system Jacobian, theoretically driving the tracking error to zero. Theoretical analysis demonstrates that both the learning and control modules exhibit favorable convergence properties under necessary noise conditions. Numerical simulations, comparative experiments, and platform validation collectively verify the innovation, effectiveness, and practical value of both the proposed DDORMPC scheme and the NCMDNN model.

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.

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.

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.

The joint drift problem may result in the omnidirectional mobile manipulator (OMM) failing to perform its tasks or even causing damage in practical applications. However, the coefficients for eliminating joint drift are coupled with the equation constraints in Cartesian space under the existing scheme, which theoretically results in a paradox between zero joint drift and zero positional error in Cartesian space. To address the joint drift, a joint drift-free repetitive motion programme with position error feedback (JDF-RMPPEF) is presented and analyzed. The JDF-RMPPEF scheme decouples the joint error and position error, which enables the OMM to accurately perform the trajectory tracking and repetitive motion tasks. In addition, to suppress the disturbances and solve the JDF-RMPPEF problem accurately, an allowed nonconvex noise-resistant neural network (ANNRNN) model is proposed, which allows for a nonconvex activation function with noise suppression properties. Theoretical analysis demonstrates that the ANNRNN model exhibits global convergence and strong robustness in the presence of interference. Through examples and comparisons, the effectiveness and superiority of the JDF-RMPPEF scheme synthesized by the ANNRNN model are validated.

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.

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.

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.

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.

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.

Traffic sign recognition is crucial for enhancing the safety and efficiency of intelligent transportation systems (ITS). This paper proposes a hybrid structure named DK-former, a lightweight and robust deep kernel Gaussian process transformer network, aiming to tackle non-linear small samples, high model parameters, and environmental variations, providing a distinctive solution that enhances robustness and adaptability in intelligent transportation systems. The whole structure is trained end-to-end based on the Bayesian framework. First, introducing convolutional random Fourier features facilitates effective non-linear sample feature mapping, capturing complex patterns inherent in traffic signs and enhancing computational efficiency. Second, the transformer model refines feature representations with its powerful self-attention mechanism to capture the global relationship between traffic sign pixels. Furthermore, the hybrid structure enhances the generalization capability of the model, allowing it to adapt to diverse scenarios, such as varying lighting conditions and weather fluctuations commonly encountered in real-world traffic environments. Extensive experiments have been conducted to validate the effectiveness of the proposed DK-former for traffic sign recognition. The model has achieved an outstanding recognition accuracy of 99.09% on the German Traffic Sign Recognition Benchmark (GTSRB) dataset, superior to current state-of-the-art deep kernel learning traffic sign models with only 8.3 million parameters. Experiments on Indian and Chinese datasets comprehensively demonstrate the generalization of the model across different geographies and environments. The code is publicly available at:https://github.com/w-tingting/DK-former.

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.

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.

This article investigates the event-triggered fuzzy filtering issue for vehicle sideslip angle estimation with consideration of data quantization and dropouts. First, an uncertain Takagi–Sugeno fuzzy model is developed to describe vehicle nonlinear dynamics resulted from nonlinear tire dynamics, varying velocity, uncertain mass, and yaw moment inertia. Then, an adaptive event-triggered scheme is introduced between the sensor and the filter for the decision of releasing sampled data to economize limited network resource. Moreover, the network-induced constraints, such as delay, data quantization, and dropouts, are taken into account to improve the robustness of the filtering method. Based on the Lyapunov stability theory, a new event-triggered asynchronous fuzzy filtering method is proposed by establishing an augmented Lyapunov–Krasovskii functional candidate and applying integral inequalities in the derivation. Finally, simulation results are presented to verify the advantages of the proposed method in comparison with the existing results.

This paper is concerned with the human-machine shared control issue for vehicle lane keeping systems via a new fuzzy observer-based event-triggered method. In order to capture system nonlinear and uncertain characteristics such as nonlinear tire dynamics, varying velocity and driver behavioral uncertainties, Takagi-Sugeno fuzzy approach is employed to model the global driver-vehicle-road system. After system modeling, the fuzzy observer-based control structure is considered because a full states information is not available in practical driving environment. Then, most existing human-machine shared control methods are based on the periodic sampling communication mechanism. However, since the network bandwidth is limited, the above mechanism may cause oversampling and communication congestion. Thus, an adaptive event-triggered mechanism is introduced between the observer and the controller to mitigate the communication burden and improve the bandwidth utilization. Based on Lyapunov functional theory, a set of sufficient conditions are given to calculate desired human-machine shared controllers. Finally, simulation tests are implemented on Matlab/Simulink-CarSim platform and simulation results illustrate that the proposed method can achieve a favorable improvement in the lane keeping capability, the driver handling comfort and the network bandwidth utilization.

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.

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.