Multi-Robot Motion Planning (MRMP) involves generating collision-free trajectories for multiple robots operating in a shared continuous workspace. While discrete multi-agent path finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization severely limits trajectory quality. In contrast, continuous optimization-based planners offer higher-quality paths but suffer from the curse of dimensionality, resulting in poor scalability with respect to the number of robots. This paper tackles the limitations of these two approaches by introducing a novel framework that integrates discrete MAPF solvers with constrained generative diffusion models. The resulting framework, called Discrete-Guided Diffusion (DGD), has three key characteristics: (1) it decomposes the original nonconvex MRMP problem into tractable subproblems with convex configuration spaces, (2) it combines discrete MAPF solutions with constrained optimization techniques to guide diffusion models capture complex spatiotemporal dependencies among robots, and (3) it incorporates a lightweight constraint repair mechanism to ensure trajectory feasibility. The proposed method sets a new state-of-the-art performance in large-scale, complex environments, scaling to 100 robots while achieving planning efficiency and high success rates.

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.

Understanding vehicle-to-vehicle interactions is critical for safe and efficient autonomous driving in complex traffic scenarios. However, most existing behavior prediction and planning models implicitly account for interactions through soft weighting or metrics based on distance and risk, without a clear or quantitative definition of vehicle interaction. This paper proposes a metric called Vehicle Interaction Level (VIL) to quantify the degree to which a vehicle’s behavior is constrained by another vehicle. By applying a VIL threshold, strong-interaction vehicles are distinguished from weak ones. Then, the Feature Difference Level (FDL) is proposed to analyze feature-level behavioral differences across interaction categories, which is quantified using the Random Forest (RF) and the Gini Index (GI). Based on real-world vehicle trajectory pairs, an optimal VIL threshold of 0.2 is determined by maximizing FDL to identify strong-interaction vehicles, providing a more discriminative and broadly applicable interaction characterization than distance-based and risk-based metrics. Furthermore, the application of this strong-interaction vehicle identification method to trajectory prediction achieves consistently better performance than the baseline across multiple evaluation metrics, demonstrating its practical value for downstream autonomous driving tasks. Owing to its lightweight and model-agnostic formulation, the VIL-based method can be integrated into existing autonomous driving systems operating in highly interactive traffic scenarios.

It is recognized that the control of mixed-autonomy platoons comprising connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) can enhance traffic flow. Among existing methods, Multi-Agent Reinforcement Learning (MARL) appears to be a promising control strategy because it can manage complex scenarios in real time. However, current research on MARL-based mixed-autonomy platoon control suffers from several limitations. First, existing MARL approaches address safety by penalizing safety violations in the reward function, thus lacking theoretical safety guarantees due to the limited interpretability of RL. Second, few studies have explored the cooperative safety of multi-CAV platoons, where CAVs can be coordinated to further enhance the system-level safety involving the safety of both CAVs and HDVs. Third, existing work tends to make an unrealistic assumption that the behavior of HDVs and CAVs is publicly known and rational. To bridge the research gaps, we propose a safe MARL framework for mixed-autonomy platoons. Specifically, this framework 1) characterizes cooperative safety by designing a cooperative Control Barrier Function (CBF), enabling CAVs to collaboratively improve the safety of the entire platoon, 2) provides a safety guarantee to the MARL-based controller by integrating the CBF-based safety constraints into MARL through a differentiable quadratic programming (QP) layer, and 3) incorporates a conformal prediction module that enables each CAV to estimate the unknown behaviors of the surrounding vehicles with uncertainty qualification. Simulation results show that our proposed control strategy can effectively enhance the system-level safety through CAV cooperation of a mixed-autonomy platoon with a minimal impact on control performance.

Recent advances in diffusion models hold significant potential in robotics, enabling the generation of diverse and smooth trajectories directly from raw representations of the environment. Despite this promise, applying diffusion models to motion planning remains challenging due to their difficulty in enforcing critical constraints, such as collision avoidance and kinematic feasibility. These limitations become even more pronounced in Multi-Robot Motion Planning (MRMP), where multiple robots must coordinate in shared spaces. To address these challenges, this work proposes **S**imultaneous **M**RMP **D**iffusion (SMD), a novel approach integrating constrained optimization into the diffusion sampling process to produce collision-free, kinematically feasible trajectories. Additionally, the paper introduces a comprehensive MRMP benchmark to evaluate trajectory planning algorithms across scenarios with varying robot densities, obstacle complexities, and motion constraints. Experimental results show SMD consistently outperforms classical and other learning-based motion planners, achieving higher success rates and efficiency in complex multi-robot environments. The code and implementation are available at https://github.com/RAISELab-atUVA/Diffusion-MRMP.

This paper addresses the issue of obstacles encountered by intelligent vehicles during their movement in agricultural fields. The traditional artificial potential field (APF) method for obstacle avoidance often results in problems such as unreachable target points and the vehicle getting trapped in local minima, preventing it from moving. To overcome these issues, we propose dynamically adjusting the size of the potential field by incorporating the relative distance between the vehicle s real-time position and the target point as a criterion. Additionally, we apply the simulated annealing (SA) method, which uses its inherent search probability to escape local minima. Finally, path smoothing is performed to compensate for the shortcomings of the traditional APF algorithm. MATLAB simulations of the improved APF-based obstacle avoidance path planning confirm the feasibility of the proposed method.

The Automatic Emergency Braking (AEB) system is capable of assessing driving risks, alerting the driver to potential collision hazards, and, in the absence of driver response to the collision risk, autonomously activating braking to mitigate the occurrence of collision accidents. Most existing Automatic Emergency Braking (AEB) systems rely on Time to Collision (TTC) for risk assessment and decision-making. However, TTC fails to account for the impact of absolute velocity on driving safety when assessing risk, leading to inaccurate risk descriptions, particularly in high-speed scenarios with minor speed differences. The Safety Margin (SM) takes into account key factors affecting driving risk, such as relative velocity and distance, and is capable of accurately quantifying driving risks. Based on the SM, this study proposes a full-speed range single-threshold Automatic Emergency Braking (AEB) model. The model comprises two components: traffic environment risk quantification and road surface friction coefficient estimation. It is applicable to automatic emergency braking tasks under varying speeds and road surface conditions. Simulation experiments were conducted by constructing three typical scenarios: stationary lead vehicle, slow-moving lead vehicle, and braking lead vehicle, to determine the braking threshold as 0.2. The safety performance of the proposed safety margin-based AEB model is evaluated by comparing it with the traditional TTC-based AEB model across the specified scenarios. The results demonstrate that the safety margin-based AEB model proposed in this study achieves 100% safe braking in all scenarios, successfully performing emergency braking and outperforming the TTC-based AEB model.

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.

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.

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.

Connected and automated vehicles (CAVs) can be beneficial for improving the operation of highway bottlenecks such as weaving sections. This paper proposes a bi-level control approach based on an upper-level deep reinforcement learning controller and a lower-level model predictive controller to coordinate the lane-changings of a mixed fleet of CAVs and human-driven vehicles (HVs) in weaving sections. The upper level represents a roadside controller that collects vehicular information from the entire weaving section and determines the control weights used in the lower-level controller. The lower level is implemented within each CAV, which takes the control weights from the upper-level controller and generates the acceleration and steering angle for individual CAVs based on the local situation. The lower-level controller further incorporates an HV trajectory predictor, which is capable of handling the dynamic topology of vehicles in weaving scenarios with intensive mandatory lane changes. The case study inspired by a real weaving section in Basel, Switzerland, shows that our method consistently outperforms state-of-the-art benchmarks.

The paper concerns the contemporary approaches of Distributed Drive Electric Vehicles (DDEVs) to the development process and their problems. It starts with describing the complete independent control of a vehicle's throttling and braking forces through in-wheel motors. The study then goes further down the line and addresses vehicle reaction rate, eco-friendliness, and road-controlling precision. The paper uses the model of complete vehicle dynamics to develop a controller that would collect the specified characteristics of the given vehicle. It will make it more stable and safe on the road and explain the controller design and optimization procedure in this way. Furthermore, simulation methods are used to model the performance of different control strategies and algorithms and how they react to specific driving situations. The research findings, imply that DDEVs enable the exploitation of different kinds of torque management values, loss of unstopped energy, and stability enhancement, which are crucial in the effort toward shedding the negative emission detriments from our transportation systems.

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.

This research proposes a coordination method for multi-connected and automated vehicles (CAVs) and traffic signal. It aims at reducing stop-and-go maneuvers of CAVs and enhancing traffic efficiency. The proposed method has the following highlights: i) Adaptive to actual CAV and humandriven vehicle (HV) mixed traffic; ii) Jointly optimization of both vehicle trajectory and signal timing via formulating in the spatial domain; iii) Parallel distributed computing. Simulation test results demonstrate that the proposed coordinated control significantly outperforms the benchmark method. The proposed method reduces the average travel delay by 29.56%, enhances fuel efficiency by 18.87%, and reduces stop count by 87.10%. The proposed parallel distributed computing algorithm ensures a computation time basically within 10 milliseconds. It indicates that the proposed method is ready for real-time large-scale implementation.

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.

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.

EMG based hand gesture recognition on convolutional neural networks (CNNs) has been widely learned, which gains high accuracy. However, CNN based systems are computationally complex and power consuming, thus hard to be deployed at edge. Biologically inspired, a new neuromorphic learning and computing approach for electromyogram (EMG) based hand gesture recognition tasks is proposed in this work. This approach designs an activate and inhibit joint processing spiking neural network (AIPS-SNN) which reaches an accuracy of 85.6% on Nina Pro dataset. Furthermore, the AIPS-SNN is deployed on the proposed memristor based computation in-memory (CIM) system, the power efficiency and area efficiency of which reach 10.146 TOPS/W and 35.399 GOPS/mm2, respectively. The experimental results indicate that the proposed neuromorphic CIM engine is promising for edge deployment.

This paper presents an encoded smart floor for multiple human localization, include binary sensor designing, space encoding and decoding scheme. This system can localize a group of people, as well as recognize associated scenarios, with high sensing efficiency and low computational complexity. The novelty of this work includes: (1) a set of code design for binary sensor deployment; (2) a Bayesian inference based decoding scheme in the context of activity and scenario recognition. The proposed scheme has been tested with pressure sensors, and the experiment results have demonstrated the superior performance of our design.