The invention discloses an improved PID (Proportion Integration Differentiation) transverse tracking control method for an automatic driving vehicle based on reinforcement learning, which comprises the following steps of: respectively establishing a longitudinal PID control method and a transverse PID control method based on a transverse and longitudinal decoupling control strategy by analyzing vehicle characteristics and transverse and longitudinal decoupling requirements; establishing a vehicle kinetic equation, and obtaining a vehicle state equation based on the transverse position error and the course angle error; establishing a state space and an action space of reinforcement learning by using the vehicle state information and the vehicle state equation, and constructing an Actor-Critic network based on the state space and the action space; designing a reward function, updating the Actor network by using a depth deterministic strategy gradient algorithm, and updating transverse PID control parameters in real time; the method comprises the following steps: setting parameters of a horizontal and longitudinal PID controller, designing a training map to carry out reinforcement learning training, designing a test map to test a trained model, and evaluating a tracking control effect of the model in a real scene. According to the method, the adaptive capacity of the controller to the uncertain environment and the tracking control precision are remarkably improved.
本发明公开了一种基于强化学习的自动驾驶汽车改进PID横向跟踪控制方法,通过分析车辆特性和横纵解耦需求,基于横纵解耦控制策略分别建立纵向PID控制方法和横向PID控制方法;建立车辆动力学方程,获取基于横向位置误差和航向角误差的车辆状态方程;利用车辆状态信息和车辆状态方程建立强化学习的状态空间和动作空间,基于状态空间和动作空间构建Actor‑Critic网络;设计奖励函数,利用深度确定性策略梯度算法对Actor网络进行更新,实时更新横向PID控制参数;整定横纵向PID控制器参数,设计训练地图进行强化学习的训练,设计测试地图对训练好的模型进行测试,评估其在真实场景下的跟踪控制效果。该方法显著提高了控制器对不确定环境的自适应能力和跟踪控制的精度。
Improved PID (Proportion Integration Differentiation) transverse tracking control method for self-driving automobile based on reinforcement learning
基于强化学习的自动驾驶汽车改进PID横向跟踪控制方法
2024-07-09
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G05B Steuer- oder Regelsysteme allgemein , CONTROL OR REGULATING SYSTEMS IN GENERAL / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
European Patent Office | 2022
|European Patent Office | 2022
|European Patent Office | 2023
|Control method of self-driving automobile and self-driving automobile
European Patent Office | 2024
|European Patent Office | 2015
|