The invention discloses an automatic driving behavior decision-making method and system based on reinforcement learning, and the method comprises the steps: obtaining the description of the environment around a vehicle; and a reinforcement learning model is constructed, an intelligent agent of the model is set as the vehicle, a state space of the model is set as environment description around the vehicle, and an action space of the model is set as executable actions of the vehicle. And training the reinforcement learning model by adopting a self-adaptive dominant strategy function and a momentum value function algorithm to obtain a trained reinforcement learning model. And inputting the description of the environment around the vehicle into the trained reinforcement learning model, and outputting a behavior decision of the intelligent agent as an automatic driving behavior decision of the vehicle. Compared with the prior art, the method has the advantages that the reinforcement learning model is optimized, so that the computing resource demand during the calculation of the automatic driving behavior decision is reduced, and the model training speed and the model stability are improved.
本发明公开了一种基于强化学习的自动驾驶行为决策方法及系统,获取车辆周围的环境描述。构建强化学习模型,其中将模型的智能体设置为车辆,将模型的状态空间设置为车辆周围的环境描述,将模型的动作空间设置为车辆的可执行动作。采用自适应优势策略函数和动量值函数算法对强化学习模型进行训练,得到训练后的强化学习模型。将车辆周围的环境描述输入至训练后的强化学习模型,输出智能体的行为决策作为车辆的自动驾驶行为决策。本申请与传统技术相比,通过对强化学习模型进行优化,降低在计算自动驾驶行为决策时的计算资源需求,提高了模型训练速度和模型稳定性。
Automatic driving behavior decision-making method and system based on reinforcement learning
一种基于强化学习的自动驾驶行为决策方法及系统
2024-10-15
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 |
Automatic driving behavior decision-making method based on deep reinforcement learning
European Patent Office | 2020
|Automatic driving behavior decision-making method based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving decision-making method based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving decision-making system based on deep reinforcement learning
European Patent Office | 2024
|Automatic driving vehicle microscopic decision-making method based on reinforcement learning
European Patent Office | 2020
|