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.

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.

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.

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).

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.

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.