📊 研究方向
- 🤖 大语言模型与应用
- 🎮 强化学习与决策优化
- 📈 模型预测控制 (MPC)
📚 学术论文
这里记录我发表的学术论文和研究工作。
📖 已发表论文
第一作者发表
Close-range docking control for reconfigurable ground vehicles: Model-guided reinforcement learning with robust predictive safety filter
Xu Yang, Jun Ni, Hangjie Cen, Tiezhen Wang and Yuxuan Zhang
📖 期刊：Engineering Applications of Artificial Intelligence
🔗 PDF | 论文主页
摘要：Reconfigurable ground vehicles (RGVs) equipped with all-wheel independent steering (AWIS) provide enhanced mission adaptability but present challenges for achieving high-precision autonomous docking, particularly during the close-range capture stage (CCS). This paper presents a novel control strategy for close-range docking control based on the twin delayed deep deterministic policy gradient (TD3) and robust predictive safety filter (RPSF). The key artificial intelligence (AI) contribution lies in a model-guided reinforcement learning (MGRL) training framework that leverages prior optimal control solutions derived from the generalized RGV dynamic model to accelerate the TD3 learning process. This strategy employs theoretical steering radius angle and sideslip angle as generalized control inputs, dynamically adjusting the instantaneous center of rotation (ICR) to fully leverage AWIS’s capabilities for precise position and orientation control. The engineering application focuses on the integration of a RPSF with the trained reinforcement learning (RL) agent for enhanced CCS docking control of the RGV. The RPSF incorporates feedback compensation to mitigate model-plant mismatch and employs online optimization to ensure strict compliance with state and control constraints throughout the docking process. Simulation results validate the proposed method, demonstrating millimeter-level docking accuracy in CCS while effectively utilizing AWIS agility and guaranteeing safety constraint satisfaction.
Modeling and Control of AWOISV: A Filtered Tube-Based MPC Approach for Simultaneous Tracking of Lateral Position and Heading Angle (二审中)
Xu Yang, Jun Ni, Hengyang Feng, Feiyu Wang and Tiezhen Wang
📖 期刊：Vehicle System Dynamics
🔗 PDF | 论文主页
摘要：An all-wheel omni-directional independent steering vehicle (AWOISV) is a specialized all-wheel independent steering vehicle with each wheel capable of steering up to ±90°, enabling unique maneuvers like yaw and diagonal movement. This paper introduces a theoretical steering radius angle and sideslip angle () representation, based on the position of the instantaneous center of rotation relative to the wheel rotation center, defining the motion modes and switching criteria for AWOISVs. A generalized dynamic model is developed with forward velocity v, sideslip angle β, and yaw rate r as states, and θR and βR as control inputs. This model decouples longitudinal and lateral motions into forward and rotational motions, allowing seamless transitions across all motion modes under specific conditions. A filtered tube-based linear time-varying MPC (FT-LTVMPC) strategy is proposed, achieving simultaneous tracking of lateral position and arbitrary heading angles, with robustness to model inaccuracies and parameter uncertainties. Co-simulation and hardware-in-loop (HIL) experiments confirm that FT-LTVMPC enables high-precision control of both position and heading while ensuring excellent real-time performance.
The energy management strategy of the multi-source parallel power system for the self-reconfigurable ground vehicle
Xu Yang and Jun Ni
📖 期刊：Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
🔗 PDF | 论文主页
摘要：The self-reconfigurable ground vehicle (SRGV) has the ability of self-assembly and self-disassembly, which is a disruptive innovation to the traditional fixed configuration ground vehicle. The basic component of the SRGV is defined as a cell unit (CU), which is a complete system capable of working independently and has the basic function of the ground vehicle. The reconfiguration of the SRGV is not only the connection of the mechanical systems but also the integration between the power sources of different CUs. To this end, this paper proposes a novel multi-source parallel power system (MSPPS) for the SRGV, whose key characteristics are multi-branch and co-bus. The MSPPS can extend any number of power sources, which greatly improves the power level of SRGV. In this paper, the MSPPS with battery power source is discussed. The disassembly and assembly of the SRGV could lead to some inconsistencies such as SoC between the battery packs of each CU. To prolong the lifetime of the battery packs and working time of the SRGV, a hierarchical proportional control (HPC) strategy and a filtered model predictive control (FMPC) strategy are proposed. Both energy management strategies can reasonably allocate the output energy between different battery packs to meet the power demand and reduce battery inconsistencies. To verify and compare the effectiveness of the proposed two strategies, numerous simulations are carried out. The simulation results show that the FMPC strategy has faster convergence speed and lower power fluctuations in the energy management process. A SRGV prototype consisting of three CUs is developed, and the experimental platform for the power system of the SRGV is successfully established. The feasibility of the proposed MSPPS architecture is validated. The proposed HPC strategy is deployed in the rapid ECU. The experiment results are similar to the simulations and effectively demonstrate the real-time performance.
A cloud-edge combined control system with MPC parameter optimization for path tracking of unmanned ground vehicle
Xu Yang and Jun Ni
📖 期刊：Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
🔗 PDF | 论文主页
摘要：As a new carrier to carry out intelligent task, the unmanned ground vehicle (UGV) is an important component of the intelligent transportation system (ITS) in the future. Most of traditional UGV path tracking control methods are deployed in the edge-side (on-board computing platform) with restricted data, which severely limits the improvement of UGVs’ path tracking performance. Therefore, this paper proposes a novel cloud-edge combined control system with MPC parameter optimization based on cloud brain control center (CBCC) applied in future ITS, which consists of edge-side control module and cloud-side optimization module. The proposed control system can optimize control parameters iteratively in CBCC by making the utmost of big data generated by UGVs to markedly enhance the control effectiveness. In CBCC, the path tracking performance is quantitatively evaluated from the aspects of path tracking accuracy, vehicle stability, and control stability. Also, an optimization algorithm is established by using SVR theory. Based on this, the cloud-side optimization module optimizes the control parameters of the edge-side control module by collecting and processing the big data generated by UGVs while driving. Besides, the designed edge-side control module is based on MPC algorithm and innovatively introduces a compensator which obviously reduces the error caused by the inaccuracy of the prediction model. To verify the effectiveness of the proposed cloud-edge combined control system, numerous simulation experiments are carried out. The results shows that the proposed cloud-edge combined control system can improve UGV’s path tracking performance and have strong robustness at different speeds.
全轮全向独立转向车辆动力学建模及分析
杨续 等
🔗 PDF
摘要：随着线控底盘技术高速发展，以自行式模块运输车、重型平板运输车、军用地面无人平台等为典型的代表的全轮全向独立转向（All Wheel Omnidirectional Independent Steering, AWOIS）车辆已逐渐应用于各行各业。AWOIS车辆每个车轮转向范围均能达到±90°，能够实现原地转向驾驶、横向/斜向驾驶、前轴转向驾驶等特殊运动模式。传统车辆动力学模型将不再适用于AWOIS车辆，而针对AWOIS车辆的研究，大多采用离散模式切换形式，并且各模式运动模式间的切换条件尚不明晰，导致AWOIS车辆动力学性能无法全部发挥。有鉴于此，本文以转向中心在车身坐标系中的位置为切入点，提出半径角-侧偏角表示方法，以描述AWOIS车辆控制输入及运动模式；共划分纵向直驶、斜向直驶、横向直驶、纵向转向、横向转向、原地转向6种运动模式，并给出各模式间的切换条件；建立AWOIS车辆通用动力学模型，以描述任意轴数AWOIS车辆动力学行为。基于所建立的通用动力学模型，本文对AWOIS车辆运动模式切换性能及运动过程动力学特性进行了详细分析。
通讯作者发表
Game theory-based MPC control strategy for path following of reconfigurable unmanned ground vehicle: A multi-agent control method
Tiezhen Wang, Xu Yang, Minghao Ma, Hangjie Cen and Zhangzhen Deng
📖 期刊：Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
🔗 论文主页
Optimal docking path planning and tracking method for reconfigurable unmanned shuttle with a six-DoF parallel docking mechanism
Wencheng Lv, Xu Yang, Tiezhen Wang, Hangjie Cen and Minghao Ma
📖 期刊：Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
🔗 论文主页
📧 学术合作：欢迎通过 邮箱 联系