The modular chassis architecture of distributed drive electric vehicles (DDEVs) provides flexibility for integrating more electrical control units. To address the challenge of enhancing longitudinal dynamics while guaranteeing ride comfort, especially under frequent urban acceleration and deceleration conditions, this paper proposes a multi-agent system (MAS)-based framework to integrate the torque vectoring system (TVS) and the active suspension system (ASS), aiming to achieve better vehicle dynamics performance. First, a half-vehicle dynamics model is constructed to describe the coupling between longitudinal and vertical motions. The polytope technique is employed to address tire nonlinearity and time-varying system states. Then, cooperative control between the TVS and ASS is developed using the MAS system, where interaction behavior is modeled based on distributed model predictive control (DMPC) optimization results, and game theory is applied to find the optimal solution. This design effectively addresses the need for modularity and scalability in integrated chassis control systems. Furthermore, terminal constraints are introduced to ensure system stability performance. Finally, the experimental tests are performed to verify the performance of the proposed MAS framework. The results demonstrate the effectiveness in enhancing vehicle longitudinal driving performance while ensuring driving comfort.

The integration of motion planning and control within a unified architecture based on reachability theory provides an effective approach to extending the autonomous motion capability boundaries of distributed drive electric vehicles (DDEVs). This architecture is further enhanced by embedding forward set propagation methods into the dynamics analysis of DDEVs. The analytical expression of forward reachable sets (FRSs), the real-time processing of reachability constraints, and the design of integrated planning-control frameworks remain challenging. To address these challenges, this paper proposes a reachability-constrained motion planning and control integration framework (RC-MPCI) for DDEVs. The proposed RC-MPCI features strong interpretability, rigorous safety guarantees, and computational efficiency. First, a maneuver-oriented vehicle motion model is established to construct the closed-loop system dynamics. Subsequently, an FRS computation method based on sum-of-squares programming (SOSP) is proposed. It formulates an analytical expression of dynamic reachable boundaries that accounts for multi-actuator coordination, and tracking error models are introduced to ensure the reachability of the closed- loop system. Then, a constraint optimization strategy based on collision-free tunnels (CFTs) is designed, within which online motion planning and control methods are developed under a receding horizon optimization framework. Finally, the effectiveness and robustness of the proposed RC-MPCI are confirmed through virtual simulations and hardware-in-the-loop (HIL) tests. This framework, based on reachability theory, provides both theoretical and technical foundations that enable safe and efficient autonomous motion of DDEVs in highly dynamic environments.

This paper develops a fuzzy game-theoretic tube model predictive control (MPC) framework for coordinated vehicle lateral motion control using active front steering (AFS) and direct yaw moment control (DYC). The vehicle dynamics are represented by a discrete-time Takagi-Sugeno fuzzy model to capture operating-condition dependence and parametric uncertainty, while a common-feedback tube MPC structure is employed to guarantee robust constraint satisfaction through an offline-designed invariant tube and terminal set. On this basis, the nominal control problem is formulated as a two-player finite-horizon Nash game, allowing AFS and DYC to optimize individual performance objectives under shared state dynamics and constraints. To enable real-time implementation, two fixedcomplexity online Nash solvers are considered: a best-response (BR) iteration scheme and a variational inequality (VI) formulation solved by an extragradient method. The closed-loop analysis establishes recursive feasibility under bounded disturbances and finite-iteration online equilibrium computation. In addition, a practical input-to-state stability result is derived, in which the effect of inexact online Nash solutions is explicitly captured through a practical-descent framework. Compared with the BR solver, the VI-based solver provides a more direct residual-based interpretation of equilibrium approximation accuracy and its relation to closed-loop stability margins. Hardware-in-the-loop experiments under multiple driving maneuvers verify that the proposed framework is computationally tractable and effective in real time, while achieving robust tracking performance, constraint satisfaction, and coordinated actuator usage.

Shared control provides a human-centered development direction for intelligent driving. However, existing shared control methodologies address the risk factors related to both the driver and the traffic environment inadequately. To this end, a shared steering control strategy is proposed based on the driver-vehicle-road (DVR) system risk assessment result. Firstly, the driver’s steering behavior is described through a two-point preview driver model. The key parameters are identified using real driving data. Meanwhile, the deep deterministic policy gradient (DDPG) algorithm is applied to train a reinforcement learning (RL) agent considering tracking accuracy, steering smoothness and vehicle stability as the autonomous driving controller. Afterwards, three time-varying risk factors are designed to evaluate the DVR system risk level, which represent driver risk, road risk and lane departure risk, respectively. Based on the system risk level, the control authority is initially calculated by a fuzzy inference method. Then, considering the smoothness of authority transition, a model prediction control (MPC) method is applied to optimize the initial authority level in real-time. Finally, simulation and the driver-in-the-loop (DIL) experiments are performed to validate the proposed strategy. The results demonstrate that the proposed shared control strategy could reduce driving burden and demonstrates distinct superiority in terms of human-machine collaboration, driving comfort and personalized support.

The existing research on intelligent driving vehicles mainly focuses on improving the performance of safety, economy, and control accuracy, ignoring the personalized manipulation pReferences of different driving groups. The differences in driving styles and preferences of different passengers require that the driving behavior of intelligent driving systems in different traffic situations should conform to the habits of self-vehicle passengers, that is, to achieve personalized driving considering human factors. This paper provides a comprehensive and systematic review of the research status in the field of personalized driving. Firstly, it clarifies the necessity of personalized driving. Secondly, the existing decision-making and planning methods for personalized driving of single-vehicle are summarized from two aspects: machine learning-based methods and driver characteristic characterization-based methods. On this basis, the interactive decision-making and planning method of multi-vehicle games considering personalized preference in intelligent networking and mixed driving environments is summarized. Finally, the problems faced by the research of personalized intelligent driving systems and the future development trend are analyzed and prospected.

While large Transformer models have exhibited outstanding performance on multimodal tasks, the underlying massive parameters land up with memory-wall issues. To address this bottleneck, SRAM-based compute-in-memory (CiM) is a promising technique. However, frequent off-chip weight loading due to limited on-chip capacity could severely limit the systemlevel energy efficiency. Recently, a high-density CiM structure at 16.4Mb/mm2, YOLoC, has shown the potential of complete on-chip deployment of a large detection model using transistor-based read-only-memory (ROM). However, it is still challenging to deploy even larger Transformer models. With opportunities provided by LoRA for finetuning large pretrained models on ROM-CiM with very light SRAM-CiMs, this work achieves ultra-high density up to 165.6Mb/mm2 by eliminating the use of transistors for ROM-CiM with a proposed 3D-METRO and a 3D stacking array on the mature CMOS process. Unlike the usual belief that parasitics have negative impacts, this work observes that parasitics can be utilized for data storage. Furthermore, a local recovering unit (LRU) is proposed for addressing the interference due to the transistor-less structure. 3D-METRO achieves ultra-high density improvement over the previous YOLoC, which is hundreds of times higher than that of SRAM-CiM, enabling the opportunity for large language model (LLM) deployment on a single chip with 28x energy efficiency improvement.

Owing to mature fabrication support and high flexibility, static random-access memory (SRAM) has become a very promising candidate for compute-in-memory (CiM) in accelerating deep neural networks (DNNs). However, SRAM-based CiM has low memory density and thus very limited total on-chip capacity, resulting in frequent weights reloading and additional power consumption during end-to-end inference tasks. Analog ROM CiM increases memory density but suffers from low computing density caused by A/D converter (ADC) limitation. To address these challenges, for the first time, a fully digital compute-in-read-only-memory (DCiROM) design approach is proposed in this paper. DCiROM introduces a novel ROM-logic fusion CiM that successfully reduces CiM area by 51% while maintaining high memory density and computing performance. By reusing multiply-and-accumulation (MAC) resources, DCiROM further achieves flexibility with a minimal area cost. We have implemented a DCiROM chip loaded 3024Kb ResNet-56 parameters using 65nm CMOS technology. This macro achieves 10.2x-55.7x higher normalized FoM (memory density x computing density) than the state-of-the-art CiM works. It also reduces 2.9x-9.9x energy consumption per image inference than SRAM CiM works when considering off-chip access.

Global climate change has emerged as a pressing global challenge, underscoring the imperative for governments and urban traffic management authorities to prioritize carbon emission reduction in the transportation sector. In mixed traffic environments, where internal combustion engine vehicles and electric vehicles coexist, the disparity in carbon emissions between these vehicle types poses a significant challenge for the formulation of effective transportation coordination policies. Consensus-based speed advisory systems (CSAS) have been extensively employed to enhance fleet energy efficiency and mitigate emissions. This paper develops a novel vehicle speed advisory framework for mixed traffic environments, termed the MP-CSAS, where M stands for Mixed Traffic and P for Privacy-preserving, which leverages blockchain technology, privacy-preserving mechanisms, and secure car-following strategies. By incorporating a coordination factor, the framework enables policymakers to dynamically optimize carbon emission reduction strategies while safeguarding vehicle user data privacy and ensuring operational safety. Simulation results demonstrate that the MP-CSAS framework effectively minimizes fleet carbon emissions while preserving data confidentiality and ensuring system security. This study contributes a forward-looking decision-making paradigm for road infrastructure providers and policymakers, equipping them with scientifically grounded and adaptive strategies to achieve sustainable and safe transportation objectives.

Accurate vehicle trajectory prediction process depends on seamless data sharing within the Internet of Vehicles. However, such interconnected data exchange introduces significant security risks. Specifically, network attacks can compromise data integrity, thereby degrading prediction accuracy. Concurrently, the need to protect sensitive vehicle data, such as driving trajectories and user account information, results in data silos that hinder the free flow of information essential for effective prediction. Existing studies have largely addressed either privacy preservation or attack mitigation in isolation, lacking a unified solution that simultaneously tackles both challenges. To address this gap, we propose Fed-SecTP, an integrated dual-module secure federated learning framework. The first module employs a Temporal Convolutional Network (TCN) with multi-head attention to detect and filter network attacks in real-time. The second module combines TCN with a Bidirectional Long Short-Term Memory (Bi-LSTM) network for trajectory prediction and leverages FedProx for federated learning, thereby enabling privacy-preserving model training without sharing raw data. Experimental results demonstrate that Fed-SecTP achieves high prediction accuracy and robustness even when up to 50% of the data is compromised by attacks, while ensuring secure data processing. This framework offers a reliable and comprehensive solution for autonomous vehicle trajectory prediction.

Smoke detection is essential for fire prevention, yet it is significantly hampered by the visual similarities between smoke and fog. To address this challenge, a split top-k attention transformer framework (STKformer) is proposed. The STKformer incorporates split top-k attention (STKA), which partitions the attention map for top-k selection to retain informative self-attention values while capturing long-range dependencies. This approach effectively filters out irrelevant attention scores, preventing information loss. Furthermore, the adaptive dark-channel-prior guidance network (ADGN) is designed to enhance smoke recognition under foggy conditions. ADGN employs pooling operations instead of minimum value filtering, allowing for efficient dark channel extraction with learnable parameters and adaptively reducing the impact of fog. The extracted prior information subsequently guides feature extraction through a priorformer block, improving model robustness. Additionally, a cross-stage fusion module (CSFM) is introduced to aggregate features from different stages efficiently, enabling flexible adaptation to smoke features at various scales and enhancing detection accuracy. Comprehensive experiments demonstrate that the proposed method achieves state-of-the-art performance across multiple datasets, with an accuracy of 89.68% on dataset for smoke detection in fog, 99.76% on CCTV images of smoke, and 99.76% on UAV images of wildfire. The method maintains high speed and lightweight characteristics, validated with an inference speed of 211.46 FPS on an NVIDIA Jetson AGX Orin after TensorRT acceleration, confirming its effectiveness and efficiency for real-world applications. The source code is available athttps://github.com/Jiongze-Yu/STKformerhttps://github.com/Jiongze-Yu/STKformer.

Modular distributed electric drive heavy-duty vehicles (MDED-HDV) integrate advanced technologies such as all-wheel steering (AWS) and distributed drive, achieving complete decoupling of the chassis’ motion degrees of freedom (DoFs). This architecture is considered a promising solution for enhancing the stability of heavy-duty vehicles (HDV). However, the impact mechanism of multi-axle steering configurations on stability remains inadequately understood, and the redundancy in control DoFs results in multiple feasible steering configurations. To address these challenges, this paper proposes a hierarchical control framework featuring steering mode switching based on stability region constraints. First, a dynamics model of MDED-HDV is established using rational polynomials. Subsequently, the sum-of-squares programming (SOSP) is employed to estimate the stability region, providing the first analysis of the effects of multi-axle steering on the stability region from the perspective of nonlinear system dynamics. Based on this analysis, a stability region-based steering mode switching strategy is developed. It incorporates vehicle states and road conditions to enable autonomous transitions among anti-phase, front-wheel, and in-phase steering modes. Finally, a hierarchical control framework is implemented. The upper layer selects the steering mode based on the estimated stability region. The lower layer executes a trajectory tracking controller with stability region constraints. The framework addresses the issue of multiple solutions caused by redundant DoFs. Experimental results demonstrate that the proposed steering mode switching strategy improves the tracking accuracy, while the stability region-based controller ensures maneuver stability.

This paper proposes an event-triggered control method for the CAN-network delayed human-machine shared steering system. The uncertain model parameter of vehicle speed is handled by the polytypic technology, and then represented by a new state with fewer vertices. Thus, a driver-vehicle path-tracking model is built. After that, the communication model of the shared control scheme considering the CAN network delays is redefined by the event-triggered system (ETS). Instead of employing the periodic communication from the sensor to the controller, it only occurs when the triggered condition of ETS is satisfied. Such a design can reduce the communication load and improve the usage of network resources. Finally, a robust state-feedback controller with the parallel distribution method is adopted to guarantee vehicle path-tracking accuracy, while reducing driver steering efforts. Through constructing a Lyapunov-Krasovskii function, the asymptotic stability of the system is proved. Some essential conditions are derived to obtain the controller and triggered parameters. The hardware-in-the-loop (HIL) tests by Carsim/ Matlab joint platform are further used to validate the proposed shared assistance control strategy. The results illustrate the effectiveness to ensure the prescribed system performance while using fewer CAN network resources.Note to Practitioners—The driver assistance steering system plays an important role to enhance driving performance. Almost all road vehicles have been equipped with the Electrical Power Steering (EPS) function. Based on the information feedback from the onboard sensors, it can generate an extra steering input to assist the driver in real time. The advanced steering control technology, such as Servolectric of ZF and ESTEERTM of Delphi, can significantly reduce traffic accidents and improve the driving experience. Recently, the Original Equipment Manufacturers (OEMs) bring various advanced driver assistance systems to further guarantee the vehicle safety. This is usually accompanied by the communication load of the in-vehicle network CAN (Controller Area Network). Meanwhile, the x-by-wire technique can also induce the possibility of CAN delays. It would deteriorate the control performance. Hence, this paper introduces the event-triggered system to develop the steering assistance controller. The CAN network delays are also integrated into the human-machine shared steering model. The communication only occurs when the triggered condition of ETS is satisfied. A robust control method is further presented to ensure the system prescribed performance. This technology aims to be a paradigm to design active safety control units. Note that some poor driver states, such as fatigued driving and distracted driving have not been considered in this study for the design of the assistance controller. Future research will focus on developing a shared controller to accommodate time-varying driver characteristics.

Human-like decision-making and planning are crucial for advancing the decision-making level of autonomous driving and increasing acceptance in the autonomous vehicle market, as well as for achieving data closed loop for autonomous driving. However, human-like decision-making and planning methods still face challenges in safety and interpretability, particularly in multi-vehicle interaction scenarios. In light of this, this paper proposes an interpretable human-like decision-making and planning method with Transformer-based deep inverse reinforcement learning. The proposed method employs a Transformer encoder to extract features from the scenario and determine the attention assigned by the ego vehicle to each traffic vehicle, thereby improving the interpretability of planning outcomes. Furthermore, for improved safety in planning, the model is trained on both positive and negative expert demonstrations. The experimental results show that the proposed method enhances model safety while maintaining imitation levels compared to conventional methods. Additionally, the attention allocation results closely align with those of human drivers, indicating the model’s ability to elucidate the importance of each traffic vehicle for decision-making and planning, thereby improving interpretability. Therefore, the proposed method not only ensures high levels of imitation and safety but also enhances interpretability by providing accurate attention allocation results for decision-making and planning. Note to Practitioners—This paper presents a method for enhancing the planning of autonomous vehicles by making it more interpretable and safer. Using Transformer-based deep reinforcement learning, the approach improves clarity by showing how the vehicle prioritizes other traffic participants and learning from both positive and negative examples. This not only enhances safety and decision accuracy but also provides insights into the vehicle’s reasoning process, which is crucial for debugging and increasing user trust. Future work could focus on adapting this method for even more complex driving scenarios.

The stability region is an important criterion in the active safety system of vehicle. Extensive literatures have developed various stability regions for the centralized driving vehicle (CDV). However, seldom of them make a thorough analysis of the stability for distributed driving electric vehicle (DDEV). Especially when the direct yaw moment control (DYC) intervenes, the stability region of DDEV shows a huge difference compared with CDV. So far, most researches on the stability control of DDEV are still based on the traditional CDV stability region, which leads to the conservation of controller design. To this end, a dynamic and analytical stability region of DDEV is firstly developed in this paper. By employing sum of square programming (SOSP) algorithm, we choose a high-order Lyapunov function to make a precise estimation of the stability region. A novel DC shape function is proposed to reduce the conservation of estimation when DYC involves. To ensure the real-time performance for control application, Long Short Term Memory (LSTM) neural network is employed to fit the coefficients of Lyapunov function, as well as enable the dynamic shifting with driving conditions. Based on the aforementioned stability region, we develop a MPC controller to ensure the stability and tracking performance during handling limit. Both simulations and road tests demonstrate that the developed stability region could effectively restraint the vehicle states from diverging, which enhances vehicle maneuverability while ensuring vehicle stability.Note to Practitioners—Handling stability is a crucial factor which concerns the safety of vehicle. Almost all vehicles should be equipped with active safety system, such as Electronic Stability Program (ESP) of Bosch and Electronic Stability Controller (ESC) of GM. They collect the real-time vehicle states by the Built-in sensors. Meanwhile, they calculate the current stability margin according to the driver’s control input and analyze the deviation of the vehicle states to decide whether the active control is needed to maintain the stability of vehicle. This system is established well in CDV. However, for DDEV, it has another input of DYC in addition to wheel steering angle, which changes the dynamic characteristic of vehicle. This means that the stability margin of traditional ESP is inaccurate when the DYC intervenes, which will lead to the misjudgment of instability or the unsafety of vehicle. This paper develops an analytic stability region of DDEV and describes the stability margin with different values of DYC, which could adapt to varying conditions. This technology fills the gap of the stability determination of DDEV and has a good application prospect in the active safety system of DDEV.

Benefited from the advantage of four-wheel independent driving, Distributed Driving Electric Vehicle (DDEV) can precisely generate direct yaw moment (DYC) to influence lateral motion. In coordination with Active Front Steering (AFS), this allows for decoupled control under normal driving condition. However, DYC is fundamentally generated through the longitudinal forces of the tires, so its impact on dynamic stability under handling limit cannot be ignored. Particularly, the intervention of DYC changes the vehicle’s safety boundary, a factor seldom addressed in existing research. Extension literatures use the safety boundaries of traditional Centralized Driving Vehicle (CDV) to design stability controller for DDEV, resulting in conservative or aggressive performance. To this end, we propose a hierarchical safety-critical controller for DDEV during handling limit. A feedback control law based on high-order polynomials is constructed, and the closed-loop stability boundary is expanded using the Sum of Square Programming (SOSP) algorithm. Additionally, DYC is included in the stability margin assessment, and a safety envelope boundary suitable for DDEV is reconstructed. This safety boundary is used as a state constraint to design a safety-critical controller based on ODCBF. Simulation and experiments show that the proposed algorithm can widen the stable yaw rate boundary by 15% under high-speed continuous steering condition, enhancing the vehicle’s maneuverability while ensuring safety.

Multispectral object detection has gained significant attention for its ability to enhance detection performance by integrating complementary information from both visible and infrared images. This approach has proven particularly beneficial across a wide range of industrial applications. However, the large number of parameters in existing network models and the dynamically changing features between dual modalities often result in inefficiencies, consuming excessive computational resources, and hindering effective fusion of the complementary data. This study introduces RetinexDet, a lightweight and efficient detection method designed specifically for infrared and visible image modalities. RetinexDet simultaneously addresses these two critical challenges by leveraging the Retinex state space duality block, which efficiently extracts and refines fine-grained features from both image types while emphasizing salient regions of interest. Furthermore, the Wavelet-Based Frequency Adaptive Fusion module is proposed, a novel method that adaptively fuses multilevel semantic and intensity information from the infrared and visible images in the frequency domain. Extensive experimental evaluations on multiple public datasets demonstrate the superior performance of RetinexDet. Specifically, on the Low-Light Visible and Infrared Paired dataset, RetinexDet reduces the model parameters by 98.8% compared to CrossFormer while achieving a higher mean average precision (mAP). When compared to GAFF, a method with a similar parameter count, RetinexDet outperforms with a 26.7% increase in mAP.

Despite remarkable achievements have been obtained for the connected and automated vehicles (CAVs) in last decades, various of realistic problems still exist, which exactly block the large-scale application of CAVs. Against this backdrop, this paper proposes a novel stochastic cooperative adaptive cruise control (CACC) strategy to realize the stable control of nonhomogeneous vehicle platoon system with simultaneously suffering from the on-board sensor data distortion, random wind disturbance, and communication delay. First, the dynamics model of the nonhomogeneous platoon with variant vehicle masses and lengths is built based on the predecessor-leader following (PLF) communication topology. Then, the simplified characteristic of sensor data distortion resulting from the limited sensing range is depicted in line with the variation of headway spacing. Thereafter, the random wind velocity is treated as the Gaussian white noise and incorporated into the platoon system via employing the Ito stochastic differential. The varying road slope and communication delay are also accommodated in unison. Next, the distributed robustH∞ controller is generated via the stochastic Lyapunov-Krasovskii functional approach. Moreover, the condition for string stability is derived with the defined stochastic L2stability criterion. Finally, numerical simulations and real-time hardware in loop (HiL) experiment demonstrate the feasibility of the proposed approach.

A critical aspect of safe and efficient motion planning for autonomous vehicles (AVs) is to handle the complex and uncertain behavior of surrounding human-driven vehicles (HDVs). Despite intensive research on driver behavior prediction, existing approaches often overlook the interactions between AVs and HDVs, assuming that HDV trajectories are not influenced by AV actions. To address this gap, we present a transformer-transfer learning-based interaction-aware trajectory predictor for safe motion planning in autonomous driving, focusing on a vehicle-to-vehicle (V2V) interaction scenario involving an AV and an HDV. Specifically, we construct a transformer-based interaction-aware trajectory predictor using widely available datasets of HDV trajectory data and further transfer the learned predictor using a small set of AV-HDV interaction data. Then, to better incorporate the proposed trajectory predictor into the motion planning module of AVs, we introduce an uncertainty quantification method to characterize the predictor’s errors, which are integrated into the path-planning process. Our experimental results demonstrate the value of explicitly considering interactions and handling uncertainties.

High-speed cruising scenarios with mixed traffic greatly challenge the road safety of autonomous vehicles (AVs). Unlike existing works that only look at fundamental modules in isolation, this work enhances AV safety in mixed-traffic high-speed cruising scenarios by proposing an integrated framework that synthesizes three fundamental modules, i.e., behavioral decision-making, path-planning, and motion-control modules. Considering that the integrated framework would increase the system complexity, a bootstrapped deep Q-Network (DQN) is employed to enhance the deep exploration of the reinforcement learning method and achieve adaptive decision making of AVs. Moreover, to make AV behavior understandable by surrounding HDVs to prevent unexpected operations caused by misinterpretations, we derive an inverse reinforcement learning (IRL) approach to learn the reward function of skilled drivers for the path planning of lane-changing maneuvers. Such a design enables AVs to achieve a human-like tradeoff between multi-performance requirements. Simulations demonstrate that the proposed integrated framework can guide AVs to take safe actions while guaranteeing high-speed cruising performance.

Accurately obtaining motion states of surrounding vehicles (SVs) plays a pivotal role in achieving the safety and closed-loop optimality of intelligent vehicles (IVs) for motion control, where the connected environment serves as the hardware foundation. To mitigate data collisions and alleviate communication burdens, this paper introduces a novel protocol-based fusion estimator (PBFE) for estimating the motion states of SVs. Based on the time-varying nonlinear system models, RRP-based cubature Kalman filter (CKF) and WTODP-based CKF are designed, which embed communication protocols, i.e., round-robin protocol (RRP) and weighted try-once-discard protocol (WTODP), into the variable-structure CKF framework. Then, mathematical definitions and descriptions of RRP and WTODP are provided, which are utilized to adjust the data transmission mechanism from sensors to estimators, leading to the establishment of a novel protocol-based measurement model. Subsequently, to preemptively quantify the performance impact of communication protocols on PBFE from a theoretical perspective, the boundedness analysis of the estimation error is rigorously derived. Conclusively, virtual simulations (VSs) based on high-fidelity models from CarSim and Matlab/Simulink, covering diverse real-world driving scenarios, are conducted to compare the protocol-based CKF method with the protocol-based unscented Kalman filter (UKF) method. Furthermore, the robustness and stability of the proposed approach are verified through practical on-road tests (ORTs).

In this paper, a safety-oriented hierarchical personalized driving system is proposed, which aims to mitigate the preference conflict between the passengers and the intelligent vehicle control system. Firstly, experiments on driving simulator are designed to analyze both the general and individual characteristics of different drivers, and a driving risk field (DRF) model for various driving events, such as free-driving, car-following, and lane-changing, is constructed. Secondly, the HighD natural dataset is clustered to explore the real preferences of different driving styles, and the DRF is calibrated to describe the driver’s subjective risk feeling more realistically. Thirdly, a driving decision-making mechanism with consideration of safety, efficiency, and personalized tolerance on the current lane is designed to select optimal driving events. Then, multi-point visual preview longitudinal speed adjustment and lateral lane-changing trajectory planning methods based on the spatial-temporal DRF under different driving events are proposed. Finally, human-in-the-loop experiments show that the proposed real-time system can generate personalized trajectories for different passengers in changing environments.

Trajectory prediction (TP) of surrounding vehicles (SVs) is crucial for autonomous vehicles (AVs) to understand traffic situations and achieve safe-efficient decision-making and motion planning. However, different drivers’ personalized driving preferences will bring uncertainties for long-term TP in the mixed traffic environment. To this end, this paper proposes a TP model with interaction awareness and driving style awareness for long-term TP of heterogeneous SVs. Firstly, the driving conditions in the highD dataset are distinguished, and three different driving styles of the vehicle in the car-following condition are obtained based on an unsupervised clustering algorithm. Then, an encoder-decoder architecture based on novel lane attention and multi-head attention mechanisms is proposed, where the encoder analyzes historical trajectory patterns and the decoder generates future trajectory sequences. The lane attention mechanism enhances the spatial perception capability of vehicles towards the target lane, and the multi-head attention mechanism extracts high-dimensional global interaction information about the heterogeneous vehicle group (HVG) surrounding the target vehicle (TV). Experimental results show that the proposed model outperforms state-of-the-art models in root-mean-square-error (RMSE) for long-term TP and exhibits excellent adaptability to diverse driving tasks. Moreover, this paper verifies that the driving style topology within the HVG has multiple impacts on the TP accuracy of the TV.

As a specific articulated vehicle, lateral stability of car-trailer combination deserves special attention because this vehicle shows catastrophic dynamic instability occasionally at high speeds. This is known as sway or flutter and might poses a serious threat to traffic safety on the highway. The problem can be attribute to complex dynamics coupling between the towing car and the trailer. This paper proposes a phase portrait-based sliding mode control method via differential braking at the towing car and the trailer simultaneously to realize the direct yaw moment control and improve dynamic stability. In this process, a nonlinear single-track model with 3 degrees of freedom is established and integrated into the controller design. The stability region of the towing car and the trailer is analyzed based on the sideslip angle – yaw rate phase portraits under different speeds. And the sliding mode surface of controller is designed based on the stability region. The Matlab/Simulink and TruckSim co-simulation is established to verify the performance of controller. The steering wheel input of simulation is designed in accordance with ISO9815 and the dynamic critical speed is determined based on the yaw damping ratio of car-trailer combination. Compared with the model predictive control-based method, the simulation results demonstrate that the phase portrait-based sliding mode control method has realized yaw damping ratio of 0.81 both in the towing car and the trailer at dynamic critical speed. The proposed method has superior performance in enhancing the dynamic stability of car-trailer combination.

This research article considers the subject of finite-time control for a set of uncertain high-order stochastic nonlinear systems (HOSNSs) with unknown time-varying control coefficients. The growth conditions for the uncertain nonlinearities are more inclusive compared to those found in most previous studies. The exponents of high-order systems can take arbitrary rational numbers, which can be represented by two positive odd integers, and they are not all exactly larger than 1. Based on the conventional backstepping idea, the method ofadding a power integratoris adopted to design an adaptive controller that renders the closed-loop system stochastically finite-time stable (SFTS). Due to the general nonlinearities, high-order exponents, and stochastic characteristics, the design process requires more effort, so domination instead of cancellation techniques is used. A simulation example demonstrates the correctness of the theoretical results.

Deploying a lightweight quantized model in compute-in-memory (CIM) might result in significant accuracy degradation due to reduced signal-noise rate (SNR). To address this issue, this paper presents ZEBRA, a zero-bit robust-accumulation CIM approach, which utilizes bitwise zero patterns to compress computation with ultra-high resilience against noise due to circuit non-idealities, etc. First, ZEBRA provides a cross-level design that successfully exploits value-adaptive zero-bit patterns to improve the performance in robust 8-bit quantization dramatically. Second, ZEBRA presents a multi-level local computing unit circuit design to implement the bitwise sparsity pattern, which boosts the area/energy efficiency by 2x-4x compared with existing CIM works. Experiments demonstrate that ZEBRA can achieve10% accuracy loss. Such robustness leads to much more stable accuracy for high-parallelism inference on large models in practice.

This paper proposed a set of steering control strategies for commercial vehicles based on Electro-Hydraulic Coupling Steering (EHCS) system, including power assistance control and active front wheel steering control. Firstly, the dynamic model of EHCS was established. Then, steering assistance control strategy and active front wheel steering control strategy were respectively designed based on the torque mode and angle mode of the power steering motor, and validated in the Simulink simulation environment. Finally, real-road tests were conducted on a test vehicle equipped with EHCS, and the smoothness and agility of EHCS control strategies were verified through subjective evaluation by test drivers combined with whole vehicle tests.

Human-driven vehicles (HDVs) and autonomous vehicles will coexist for a long time. The time-varying charac-teristics of human-driven vehicles need to be considered when designing cruise strategies for autonomous vehicles. In this paper, the variable forgetting factor recursive least squares (VFFRLS) is proposed to identify the characteristic parameters of HDV. Based on the obtained characteristic parameters, the influence of the HDV on the stability of the vehicle platoon is analyzed, and the optimal time headway of the following autonomous vehicle is selected. Then, the time-varying cooperative adaptive cruise control method is designed to reduce the acceleration perturbation caused by HDV. Based on the data collected by the driving simulator, it is verified that the parameter identifi-cation method proposed in this paper can effectively extract the driving characteristics of HDV. Finally, the numerical simulation results demonstrate that the control strategy enhances vehicle platoon stability and improves traffic efficiency in mixed traffic environments.

Distributed drive electric vehicles (DDEV) utilize differential torque to generate direct yaw moment (DYM) to improve vehicle safety and controllability, making the DYM control an active safety research hotspot. However, the generation of DYM relies on additional longitudinal tire forces, which may exceed the feasible tire force region, leading to vehicle drift. In addition, the DYM and traction force are highly coupled and can come into conflict under extreme handling operations. Thus, a novel concept of maneuverable stability region is proposed to describe the feasible safety boundaries of DYM and traction force. According to the different maneuverable stability region, four modes of vehicle operation are defined. Subsequently, the multi-modes judgment criterion is formulated using linear matrix inequality (LMI) to determine the boundaries of each mode and identify the current vehicle mode. Finally, a multi-mode torque distribution strategy (MTDS) is developed to meet the control requirements of the different modes, taking into account both energy saving and mechanical fatigue of the motors. Simulation and experimental results demonstrate that the multi-mode torque distribution strategy outperforms both the distributed torque distribution strategy and the single-mode torque distribution strategy. This strategy effectively mitigates the trade-off between mobility and stability, while maintaining vehicle safety, controllability, and energy saving at extreme handling limits.

Multi-modal fused images can provide reliable perceptual information for intelligent vehicles in various weather and lighting conditions. However, most existing fusion algorithms neglect the information interactions among different modalities, leading to a loss of essential information in transportation systems characterized by strong information correlations. To enhance the quality of multi-modal semantic information fusion perception in intelligent vehicles, we propose the Cross Rubik Cube Attention Fusion Network (RCAFusion). Inspired by the shape and recovery process of a Rubik’s Cube, RCAFusion establishes an information interaction pathway among different modalities, and it achieves a more comprehensive information crossover through the simultaneous spatial attention, channel attention, and self-attention mechanisms, which enhance the feature extraction effect in the fusion architecture. Experimental results demonstrate that RCAFusion outperforms mainstream fusion algorithms in several metrics and obtains the highest score in the objective fused image metric Qabf. Moreover, the fused images output by RCAFusion have good results in the image object detection task and can achieve 95.4% mAP using the yolov8m model in the MSRS open source datasets. Pre-trained model and code are available at https://github.com/vehicle-AngLi/RCAFusion.

Object detection in 3-D space is a fundamental technology in the autonomous driving system. Among the published 3-D object detection methods, the single-modal methods based on point clouds have been widely studied. One problem exposed by these methods is that point clouds lack color and texture features. The limitation in conveying semantic information often leads to failures in detection. In contrast, the multimodal methods based on the image and point clouds fusion may solve this problem, but relevant research is not sufficient. In this work, a single-stage multiview multimodal 3-D object detector (MVMM) is proposed, which can naturally and efficiently extract semantic and geometric information from the image and point clouds. Specifically, the data-level fusion approach of point clouds coloring is used for combining information from the camera and LIDAR. Next, an encoder–decoder backbone is devised to extract features from colored points in the range view. Then, colored points are concatenated with the range view features, voxelized, and fed into the point view bridge for down-sampling. Finally, the down-sampled feature map is used by the bird's eye view backbone and the detection head for generating 3-D results based on predefined anchors. According to extensive experiments on the KITTI dataset, MVMM achieves competitive performance while runs at 27 FPS on the 1080 Ti GPU. Particularly, MVMM performs extremely well in difficult scenes (e.g., heavy occlusion and truncation) due to the understanding of fused information.

Fatigue and distraction are the most common long-term poor state and short-term abnormal behavior of drivers, significantly increasing the driving risk of vehicles equipped with the advanced driver assistance system (ADAS). To provide a more reliable decision-making basis for ADAS and improve driving safety, this paper proposes a driving risk assessment framework considering the driver’s long-term poor state and short-term abnormal behavior. Firstly, based on the self-built fatigue dataset and transfer learning method, an adaptive fatigue detection model with strong generalization capability is established to enable multi-view driver fatigue detection. Then, the idea of multi-clustering and adding offset parameters is introduced into the classical contrast loss function, and the D-InfoNCE loss function is designed to realize the accurate identification of the driver’s specific distraction behavior under open set detection. Subsequently, a driving risk assessment system is developed to quantify driving risk based on the vehicle driving risk factors when fatigued or distracted driving occurs. Finally, the proposed driving risk assessment system is validated by the datasets and driver-in-the-loop test bench. The results show that the proposed framework can accurately detect the driver’s fatigue state and distraction behavior and give ADAS the corresponding driving risk levels to enhance driving safety.

Preceding vehicles typically dominate the movement of following vehicles in traffic systems, thereby significantly influencing the efficacy of eco-driving control that concentrates on vehicle speed optimization. To potentially mitigate the negative effect of preceding vehicles on eco-driving control at the signalized intersection, this study proposes an overtaking-enabled eco-approach control (OEAC) strategy. It combines driving lane planning and speed optimization for connected and automated vehicles to relax the first-in-first-out queuing policy at the signalized intersection, minimizing the host vehicle’s energy consumption and travel delay. The OEAC adopts a two-stage receding horizon control framework to derive optimal driving trajectories for adapting to dynamic traffic conditions. In the first stage, the driving lane optimization problem is formulated as a Markov decision process and solved using dynamic programming, which takes into account the uncertain disturbance from preceding vehicles. In the second stage, the vehicle’s speed trajectory with the minimal driving cost is optimized rapidly using Pontryagin’s minimum principle to obtain the closed-form analytical optimal solution. Extensive simulations are conducted to evaluate the effectiveness of the OEAC. The results show that the OEAC is excellent in driving cost reduction over constant speed and regular eco-approach and departure strategies in various traffic scenarios, with an average improvement of 20.91% and 5.62%, respectively.

Fatigue driving has been regarded as one of the most important factors that cause traffic accidents. This paper proposes a robust human-machine shared control strategy to improve the vehicle performance for different driver fatigue states. Firstly, the time-varying driver steering model is proposed to address the model mismatch caused by fatigue driving. And the driver fatigue evaluation system is established based on facial features to quantify driver fatigue levels. Based on the quantified fatigue levels, a novel strategy for allocating authorities of the driver and controller is developed for building the driver-vehicle interaction system. Then, to weaken the influence of parameter perturbations caused by the time-varying driver states, we design a fatigue-based shared controller through state feedback. The actuator saturation and system constraints are considered in the controller design through the robust set-invariance property to improve vehicle safety and driving comfort. The driver-in-the-loop platform is conducted to validate the effectiveness of the proposed shared steering controller. The experimental results show that the proposed strategy can adaptively optimize the human-machine authorities according to fatigue states and comprehensively improve vehicle performance.

Parking semi-trailer train in extremely narrow environments pose challenges due to high nonholonomic constraints, unstable reversing dynamics, and non-convex obstacle avoidance constraints. This paper presents the APTEN (Autonomous Parking of semi-Trailer train in Extremely Narrow environments) with a three-layer framework to address these challenges. In the first layer, we employ a linearized gain scheduling method to create a stable Cl-RRT planner tailored for simplifying unstable reverse dynamics. This planner is adept at promptly warm starting the following homotopy problems. In the second layer, we introduce a novel “dynamics–full dimensional obstacle avoidance” progressive constraint approach. Modifying the constraints of nonlinear programming in separate homotopy problems not only protects the solver from falling into unfeasible local optima but also significantly enhances computational efficiency. In the third layer, a differentiable approach based on convex set separation is employed to establish full-dimensional obstacle avoidance constraints for semi-trailer train. Leveraging the warm start solutions obtained from the previous two layers, the algorithm identifies the optimal solution that strictly adheres to the obstacle avoidance constraints in an extremely narrow environment. The simulation results demonstrate that APTEN excels in parking motion planning within extremely narrow environments, exhibiting the shortest solution time, the highest trajectory quality, and exceptional adaptability to diverse working conditions.

This article aims to address the realistic path tracking control problem toward high-system performance for commercial autonomous ground vehicles (AGVs) with simultaneously guaranteeing the tracking accuracy, yaw and roll stability under limited vehicle network resources in global position system temporarily unavailable environments. In such conditions, the vehicle full state information and road topography might not be accessible in real time. To this end, this article proposes an effective adaptive event-trigger (AET)-based robust path tracking control strategy with introducing the reliable Takagi–Sugeno (T–S) fuzzy state observer for practical implementation. First, the vehicle yaw and roll coupled dynamics is incorporated into the vehicle-road system model, with modeling the tire cornering stiffness uncertainty by the T–S fuzzy technique and resolving the system disturbances as unknown inputs. Then, the fuzzy observer structure is established with unmeasurable premise variables which are handled by norm-bound method. Next, a well-designed AET control framework is constructed to reduce the real-time network occupation rate and economize the communication bandwidth resources. Besides, the input constraint and rollover prevention are handled using the robust set invariance. After that, the parallel distributed compensation (PDC) controller and observer are co-designed through solving the effective linear matrix inequalities (LMIs). In addition, the close-loop stability and$H\infty$performance are ensured by means of the delay dependent Lyapunov–Krasovski method. Finally, the validity and superiority of the proposed control strategy have been verified by Carsim-Simulink co-simulations in different dynamic scenarios with high-fidelity full vehicle model.

This article proposes an actuator fault detection and isolation (FDI) scheme for quadrotor unmanned aerial vehicle (UAV) with a cable-suspended load. First, a linear parameter-varying (LPV) model of quadrotor UAV is established, in which the effects of cable-suspended load are considered. Then, a state boundary-based FDI design is systemically presented. A bank of interval observers is constructed to build the preliminary upper and lower boundaries of system states under healthy conditions, where$H_{-}/H_{\infty }$performance is applied to enhance its robustness against disturbances and sensitivity to faults. Furthermore, a novel updating strategy is further proposed to periodically adjust state boundaries to cope with the effects of varying wind disturbances. Finally, based on the QDrone platform, experimental tests under random faults are carried out to verify the effectiveness and performance of the proposed scheme.

Performing data-intensive tasks in the von Neumann architecture is challenging to achieve both high performance and energy efficiency due to the memory wall bottleneck. Compute-in-memory (CiM) is a promising mitigation approach by enabling parallel and in-situ multiply-accumulate (MAC) operations within the memory array. Thanks to the good matching of capacitors, SRAM-based charge-domain CiM (Q-CiM) has shown its potential for higher row-wise parallelism. However, the peripheral circuits of Q-CiM, such as the input drivers and analog-digital converters (ADCs), limit further improvement of throughput and area efficiency. This paper proposes a single-ADC multi-bit accumulation CiM macro architecture SAMBA, which can perform multi-bit MAC operation with ReLU of two vectors in one CiM cycle by only a single A/D conversion to mitigate the ADC overhead. In addition, post-correction methods are proposed to compensate the non-linearity of sensitive circuit modules in SAMBA to recover the accuracy drop due to the capacitor mismatch. A proof-of-concept macro is fabricated in a 65nm process and achieves 51.2GOPS throughput and 10.3TOPS/W energy efficiency, while showing 88.6% accuracy on CIFAR-10 and 64.8% accuracy on the CIFAR-100 with VGG-8 model.

This paper presents a robust finite frequency${H} _{\infty }$control strategy for improving vibration performance and ride comfort of electric vehicles through in-wheel motor-active suspension system(IWM-ASS). Since the human body is much sensitive to the vertical vibration of 4 -8 Hz, the main objective is dedicated to deal with the vibration challenge that matches the characteristics of the human body by applying the finite-frequency technique. Firstly, the uncertain quarter-vehicle active suspension model with dynamic damping in-wheel motor driven system is established, in which in-wheel motor is suspended as dynamic vibration absorber(DVA) to isolate the force transmitted to motor bearing in IWM-ASS. Based on the framework of generalized Kalman–Yakubovich–Popov lemma and stability theory, then the performance index of${H} _{\infty }$norm from external disturbance to controlled output for IWM-ASS is attenuated within the concerned frequency range while other system requirements such as parameter uncertainty, suspension deflection constraint and actuator saturation are also guaranteed in controller design. The resulting robust finite frequency state feedback${H} _{\infty }$controller is finally designed utilizing two new theorems, and solved via a set of linear matrix inequalities. Simulations for frequency-domain and time-domain responses are implemented and compared with the entire frequency control method to evaluate the effectiveness of the proposed strategy. It can be concluded from the results that the developed control strategy can effectively attenuate the negative vibration and enhance ride comfort and road-holding ability for electric vehicles of IWM-ASS.

Distributed drive electric vehicles (DDEVs) eliminate the complex drivetrain. The independently driven in- wheel motors also endow the vehicle with more ability for improving maneuverability. To this end, this paper proposes an integrated control framework of torque vectoring (TV) and active front-wheel steering system (AFS) to ensure the vehicle lateral motion stability performance. First, the polytope method with finite vertices is employed to deal with the system uncertainties and simplify the modeling structure, based on which a distributed model predictive control is adopted to construct a dynamic interactive model between agents. Then, through introducing the game theory, a distributed parallel control scheme is developed to obtain the cooperative strategy of agents. Such a design can also satisfy the modular and scalable requirement for integrated chassis control. To ensure the system asymptotic stability, the terminal input combined with the terminal cost function are treated as the constraints in the game paradigm and then transformed as the linear matrix inequalities. Furthermore, a robust$\text{H}\infty $compensation method is used to suppress the system disturbance. Finally, the hardware-in-the-loop (HIL) tests are conducted to assess the control performance. The results verify the proposed integrated control scheme is effective to enhance the vehicle handling stability.

Cooperative on-ramp merging control for connected and automated vehicles (CAVs) can effectively improve traffic throughput and vehicle fuel efficiency at highway on-ramp merging bottlenecks. However, in the mixed traffic scenario where CAVs and human-driven vehicles (HDVs) coexist, the uncertain maneuvers of human drivers pose a major challenge to merging control in terms of safety and flexibility. To this end, this paper proposes a hierarchical cooperative on-ramp merging control strategy for CAVs to optimize flexible trajectories with safety guarantees in mixed traffic. First, the on-ramp merging control problem for CAVs is considered in the case of a three-vehicle coordination, resulting in an optimal control problem (OCP) coordinating on-ramp and main-lane CAVs for efficient operation while satisfying multiple safety-critical constraints. Second, a two-level hierarchical control architecture is developed to solve the OCP with mixed state-control constraints. The upper-level planner solves an unconstrained OCP with Pontryagin’s Minimum Principle to calculate an expected merging position, which is embedded in the variable time headway of safe merging constraints in the lower-level controller. Then, the controller converts the nonlinear OCP with safety-critical constraints to a quadratic programing (QP) problem by exploiting Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). By solving the QP efficiently, the time and energy efficient trajectory for each CAV is obtained. In addition, a receding horizon control framework is employed, which enables CAVs to determine flexible merging opportunity and tackle the disturbances caused by HDVs. Finally, comprehensive simulation results show that the proposed cooperative on-ramp merging strategy has potential in enabling merging flexibility, improving traffic efficiency and energy economy in real time.

Aggressive driving behavior has greatly endangered vehicle safety and posed challenges to the design of advanced driver-assistance systems (ADASs). A novel driver–automation cooperative shared control system is proposed in this article to make steering assistance actions better cooperate with aggressive drivers. Based on investigating shared control modes, a driving activity parameter for drivers is introduced, which aims to modulate the shared control authority and mitigate the conflicts between aggressive drivers and ADAS. A polytope represented by finite vertices is employed to handle uncertain parameters, including driving activity and longitudinal velocity. Then, an H$\infty $robust output-feedback control method satisfying the regional pole assignment is presented to provide robustness and stability of the polytope space while simplifying the control structure through reducing vertices. The driver-in-the-loop simulator experiments are carried out to verify the proposed controller, in which the driver model parameters are identified. The results demonstrate that the developed assistance controller can effectively ensure path-tracking accuracy and simultaneously improve aggressive drivers’ comfort.

Computing-in-memory (CiM) is a promising technique to achieve high energy efficiency in data-intensive matrix-vector multiplication (MVM) by relieving the memory bottleneck. Unfortunately, due to the limited SRAM capacity, existing SRAM-based CiM needs to reload the weights from DRAM in large-scale networks. This undesired fact weakens the energy efficiency significantly. This work, for the first time, proposes the concept, design, and optimization of computing-in-ROM to achieve much higher on-chip memory capacity, and thus less DRAM access and lower energy consumption. Furthermore, to support different computing scenarios with varying weights, a weight fine-tune technique, namely Residual Branch (ReBranch), is also proposed. ReBranch combines ROM-CiM and assisting SRAM-CiM to achieve high versatility. YOLoC, a ReBranch-assisted ROM-CiM framework for object detection is presented and evaluated. With the same area in 28nm CMOS, YOLoC for several datasets has shown significant energy efficiency improvement by 14.8x for YOLO (DarkNet-19) and 4.8x for ResNet-18, with <8% latency overhead and almost no mean average precision (mAP) loss (−0.5% ~ +0.2%), compared with the fully SRAM-based CiM.

Motivated by reducing the data transfer activities in data-intensive neural network computing, SRAM-based compute-in-memory (CiM) has made significant progress. Unfortunately, SRAM has low density and limited on-chip capacity. This makes the deployment of large models inefficient due to the frequent DRAM access to update the weight in SRAM. Recently, a ROM-based CiM design, YOLoC, reveals the unique opportunity of deploying a large-scale neural network in CMOS by exploring the intriguing high density of ROM. However, even though assisting SRAM has been adopted in YOLoC for task transfer within the same domain, it is still a big challenge to overcome the read-only limitation in ROM and enable more flexibility. Therefore, it is of paramount significance to develop new ROM-based CiM architectures and provide broader task space and model expansion capability for more complex tasks.

The eco-driving strategy that targets driving speed optimization is recognized as a promising technique to improve vehicle energy efficiency. However, it is difficult to achieve real-time eco-driving control of hybrid electric vehicle (HEV) since the speed optimization and powertrain energy management should be resolved simultaneously. This paper proposes a hierarchical control architecture consisting of learning-based velocity planner and real-time energy management system. In the upper stage, Proximal Policy optimization (PPO) agent is trained to generate acceleration which meets multiple control objectives. The lower stage adopts Equivalent Consumption Minimization Strategy (ECMS) for real-time power split control considering powertrain dynamics. Finally, the eco-driving simulations of six signalized intersections in Nanjing are conducted. Compared with two different rule-based strategies, the proposed control architecture can achieve at least 7.39% of fuel economy saving and avoid a significant drop in the battery state of charge at the expense of higher than 5% of travel time. Simulation results also prove that the proposed strategy has an energy-saving potential in unseen scenarios.

Lane-changing is a critical issue for autonomous vehicles (AVs), especially in complex environments. In addition, different drivers have different handling preferences. How to provide personalized maneuvers for individual drivers to increase their trust is another issue for AVs. Therefore, a framework of human-like path planning is proposed in this paper, considering driver characteristics of visual-preview, subjective risk perception, and degree of aggressiveness. In the decision making module, a model is built to select the most suitable merging spot, with respect to safety factors and the driver’s degree of aggressiveness. And a novel environmental potential field (PF) suitable for arbitrary road structures is designed to describe the driver’s individual risk perception. In the trajectory planning module, a model predictive control (MPC) based path planner is designed according to the decisions in coincidence with the driver’s individual intentions of collision avoidance. Simulation results have demonstrated that the proposed path planner can provide with personalized trajectories for different combinations of driver preferences and steering characteristics, in scenarios of curved roads with different risks of collision.

The accurate information of sideslip angle (SA) and tire cornering stiffness (TCS) is essential for advanced chassis control systems. However, SA and TCS cannot be directly measured by in-vehicle sensors. Thus, it is a hot topic to estimate SA and TCS with only in-vehicle sensors by an effective estimation method. In this article, we propose a novel fuzzy adaptive robust cubature Kalman filter (FARCKF) to accurately estimate SA and TCS. The model parameters of the FARCKF are dynamically updated using recursive least squares. A Takagi–Sugeno fuzzy system is developed to dynamically adjust the process noise parameter in the FARCKF. Finally, the performance of FARCKF is demonstrated via both simulation and experimental tests. The test results indicate that the estimation accuracy of SA and TCS is higher than that of the existing methods. Specifically, the estimation accuracy of SA is at least improved by more than 48%, while the estimators of TCS are closer to the reference values.

As one type of associative memory, content-addressable memory (CAM) has become a critical component in several applications, including caches, routers, and pattern matching. Compared with the conventional CAM that could only deliver a “matched or not-matched” result, emerging multilevel CAM (ML-CAM) is capable of delivering “the degree of match” with multilevel distance calculation. This feature has been desired in applications that need beyond-Boolean matching results. However, existing ML-CAM designs are limited by the bit-cell device discharging current mismatch and vulnerability to the timing of sensing operations for distance calculation. This inherent constraint makes it difficult to further improve the accuracy and scalability toward higher accuracy and higher dimension matching. In this work, we propose CapCAM, a multilevel Capacitive Content Addressable Memory. It could be implemented based on either static random-access memory (SRAM) or emerging technologies, e.g., the ferroelectric field-effect transistor (FeFET). CapCAM could provide linear and stable voltage drop scaled by the match degree and need no strict timing for result sensing, which embraces the high-accuracy and high-scalability search. The inherent enabler of CapCAM is the charge-domain computing mechanism. This article will present the basic concept, operating mechanisms, detailed circuit designs, and circuit-level simulations of CapCAM. Besides, we apply CapCAM to few-shot learning applications and compare CapCAM with the current-domain TCAM designs. Results show 99.2% accuracy for a five-way five-shot classification task with our proposed CapCAM design while considering 1-fF capacitors, 20-domain FeFETs, and 256 columns. In contrast, the prior work based on discharging dynamics requires strict timing controls and suffers from accuracy degradation under the same configuration, which demonstrates CapCAM’s capability of low-power, accurate, and scalable multilevel CAM (ML-CAM) computing.

Content-addressable memory (CAM) has been a critical component in pattern matching and also machine-learning applications. Recently emerged CAM that is capable of delivering multi-level distance calculation is promising for applications that need matching results beyond Boolean results of ?matched" and ?not matched". However, existing multi-level CAM designs are constrained by the bit-cell device discharging current mismatch and the strict timing of sensing operations for distance calculation. This fact results in the challenge of further improving the accuracy and scalability towards higher-resolution and higher-dimension matching. This work presents a multi-level CAM design that is capable of delivering high-accuracy and high-scalability search, which is immune to the discharging device mismatch and needs no strict timing for result sensing. The inherent enabler is the charge-domain computing mechanism. This work will present the operating mechanisms, the circuit simulation, and content-matching evaluation results, showing the promise towards high reliability, high energy efficiency, and high scalability.

This article establishes a novel electroencephalograph (EEG)-based brain-computer interface (BCI) system for ground vehicle control with potential application of mobility assistance to the disabled. To enable an intuitive motor imagery (MI) paradigm of “left,” “right,” “push,” and “pull,” a driving simulator based EEG data recording and automatic labeling platform is built for dataset making. In the preprocessing stage, a wavelet and canonical correlation analysis (CCA) combined method is used for artifact removal and improving signal-to-noise ratio. An ensemble learning based training and testing framework is proposed for MI EEG data classification. The average classification accuracy of proposed framework is about 91.75%. This approach essentially takes advantage of the common spatial pattern (CSP) with ability of extracting the feature of event-related potentials and the convolutional neural networks (CNNs) with powerful capacity of feature learning and classification. To convert the classification results of EEG data segments into motion control signals of ground vehicle, shared control strategy is used to realize the control command of “left-steering,” “right-steering,” “acceleration,” and “stop” considering collision avoidance with obstacles detected by a single-line LIDAR. The online experimental results on a model vehicle platform validate the significant performance of the established BCI system and reveal the application potential of BCI on the vehicle control and automation.

Vehicle active suspension systems provide possibility to bring better ride comfort, handling stability and driving safety with proper control than passive suspension. This paper utilizes deep reinforcement learning method to develop active suspension systems due to its good generalization. The controller is based on a quarter-car active suspension model, and suspension dynamic characteristics are analyzed under the condition of bump disturbance. Simulation results show that the performance of active suspension tends to be stable after proper training. Compared with the passive suspension and the Skyhook-based suspension, the deep reinforcement learning-based active suspension can reduce the vehicle body acceleration more effectively and further improve the ride comfort without sacrificing the suspension deflection and dynamic tire load. Deep reinforcement learning-based active suspension can still maintain good performance after switching bump heights or vehicle speed which verifies good generalization of the controller.

Accurate knowledge of the vehicle states is the foundation of vehicle motion control. However, in real implementations, sensory signals are always corrupted by delays and noises. Network induced time-varying delays and measurement noises can be a hazard in the active safety of over-actuated electric vehicles (EVs). In this paper, a brain-inspired proprioceptive system based on state-of-the-art deep learning and data fusion technique is proposed to solve this problem in autonomous four-wheel actuated EVs. A deep recurrent neural network (RNN) is trained by the noisy and delayed measurement signals to make accurate predictions of the vehicle motion states. Then unscented Kalman predictor, which is the adaption of unscented Kalman filter in time-varying-delay situations, combines the predictions of the RNN and corrupted sensory signals to provide better perceptions of the locomotion. Simulations with a high-fidelity, CarSim, full-vehicle model are carried out to show the effectiveness of our RNN framework and the entire proprioceptive system.

The fuzzy full-order dynamic output-feedback steering assistance control is proposed in this paper to follow large-curvature path for the steer-by-wire (SBW) vehicle. The driver-vehicle-road (DVR) model to follow large-curvature path is built under the assumption that the near and far vision information ofthe road for guidance is considered by the human driver. Five parameters describing the driver's steering characteristics and behaviors are considered as uncertainties of the DVR models with different drivers. The Takagi-Sugeno (T-S) fuzzy model is applied to handle these uncertainties in designing the dynamic output-feedback parallel distributed compensator (DPDC). The compensator design is then reduced to solving several linear matrix inequalities (LMIs). Simulation results show that the proposed controller can provide different human drivers with individual steering assistance in following the large-curvature path, and can reduce the driver's physical and mental workloads.

This paper presents a robust fuzzy H∞control strategy for improving vehicle lateral stability and handling performance through integration of direct yaw moment control system (DYC) and active front steering. Since vehicle lateral dynamics possesses inherent nonlinearities, the main objective is dedicated to deal with the nonlinear challenge in vehicle lateral dynamics by applying Takagi-Sugeno (T-S) fuzzy modeling approach. First, the nonlinear Brush tire dynamics and the nonlinear functions of longitudinal velocity are represented via a T-S fuzzy modeling technique, and vehicle parametric uncertainties are handled by the norm-bounded uncertainties. An uncertain nonlinear vehicle lateral dynamic T-S fuzzy model is then obtained with multi-fuzzy-rules. The resulting robust fuzzy H∞state-feedback controller is designed with the parallel distributed compensation strategy and premise variables, and solved via a set of linear matrix inequalities derived from Lyapunov asymptotic stability and quadratic H∞performance. Simulations for two different maneuvers are implemented with a high-fidelity, CarSim®, full-vehicle model to verify the effectiveness of the developed approach. It is confirmed from the results that the proposed controller can effectively preserve vehicle lateral stability and enhance yaw handling performance.