基于机理 + 数据补偿模型的车辆轨迹跟踪控制

Vehicle Trajectory Tracking Control Based on Mechanism + Data Compensation Model

针对无人驾驶车辆在制造和装配过程中的精度限制导致车辆的实际物理参数和设计值不一致性的问题。本文提出了一种机理与数据驱动补偿模型的线性二次调节器(LQR)控制策略。通过线性回归误差补偿对观光车机理模型进行优化,提高了模型的准确性和稳定性。基于补偿后的模型,设计了LQR路径跟踪控制器,通过优化二次型性能指标确定系统最优控制序列。仿真结果证实,与未补偿模型相比,该策略有效提高路径跟踪精度和维持系统稳定性,展示了机理与数据驱动补偿的LQR控制策略在无人驾驶车辆路径跟踪控制中的有效性和优越性。Aiming at the problem of inconsistencies between actual physical parameters and design values caused by precision limitations in the manufacturing and assembly process of unmanned vehicles. In this paper, a linear quadratic regulator (LQR) control strategy combining mechanism model and data-driven compensation is proposed. Through linear regression error compensation, the sightseeing vehicle mechanism model is optimized, and the accuracy and stability of the model are improved. Based on the compensated model, the LQR path tracking controller is designed, and the optimal control sequence is determined by optimizing the quadratic performance index. Simulation results confirm that compared with the uncompensated model, the proposed strategy effectively improves the path tracking accuracy and maintains the system stability, demonstrating the effectiveness and superiority of the LQR control strategy based on the fusion mechanism and data-driven compensation in the path tracking control of unmanned vehicles.