The invention relates to a parking path planning method based on reinforcement learning. Traditional planning needs a large amount of iteration, the calculated amount is large, the time is long, and complexity is higher and higher along with the increase of the data volume. The parking path planning method comprises steps that 1, a state model of the parking space environment is established; 2, asingle-line model of a vehicle is established; 3, a state reward value function and an action value function is defined to obtain a Bellman equation of the state and behavior functions; 4, a reward function in the Bellman equation is determined; 5, an equation from a certain current state to a target state is determined in combination with rewards; 6, Q value vectors of all actions are outputted in combination with a deep Q learning network; 7, an optimal path from an initial state to the target state is determined; and 8, a path curve is generated and sent to a tracking control module of thevehicle, and path data is provided. The method is advantaged in that the parking path can be rapidly obtained, an implementation method is simple and efficient, and the effect of good path tracking control continuity can be guaranteed.
传统规划需要大量迭代,计算量较大,时间长;而智能规划算法随着数据量的增大,复杂度越来越大。本申请提供了一种基于强化学习的泊车路径规划方法,包括1:建立车位环境的状态模型;2:建立车辆的单线模型;3:定义状态奖励值函数和动作值函数,得到状态和行为函数的贝尔曼方程;4:确定贝尔曼方程中的奖励函数;5:结合奖励确定从某一个当前状态到目标状态的方程;6:结合深度Q学习网络,输出所有动作的Q值向量;7:确定起始状态到目标状态的最优路径;8:生成路径曲线,发送到车辆的跟踪控制模块中,提供路径数据。能快速获得泊车路径,实现方法简单高效,同时能保证路径跟踪控制连续性好的效果。
Parking path planning method based on reinforcement learning
一种基于强化学习的泊车路径规划方法
2020-05-05
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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Reinforcement learning parking path planning method and system for non-structural scene
European Patent Office | 2023
|OBSTACLE AVOIDANCE METHOD IN AUTOMATIC PARKING PATH PLANNING AND PARKING PATH PLANNING SYSTEM
European Patent Office | 2021
|Obstacle avoidance method for automatic parking path planning and parking path planning system
European Patent Office | 2020
|Intention-driven reinforcement learning-based path planning method
European Patent Office | 2024
|