The invention relates to the technical field of automatic driving control, and discloses an automatic driving vehicle lane changing decision system and method based on deep reinforcement learning, and the system comprises a processor module, and a data collection module, a data analysis module and a lane changing strategy module which are connected with the processor module. Operation data of interference vehicles near the target vehicle are collected and analyzed, a safe automatic lane changing strategy of the current target vehicle is obtained, and lane changing is completed rapidly and safely. The method has the advantages that the accuracy of the automatic lane changing strategy of the automatic driving vehicle is improved, the safety of the vehicle in the lane changing process is guaranteed, and the road congestion condition and collision accidents are reduced.
本发明涉及自动驾驶控制技术领域,公开了一种基于深度强化学习的自动驾驶车辆换道决策系统及方法,包括处理器模块,以及分别与处理器模块连接的数据采集模块、数据分析模块和换道策略模块,利用对采集到的目标车辆的数据信息,以及采集目标车辆附近的干扰车辆的运行数据进行分析,得到当前目标车辆的安全自动换道策略,实现快速安全地完成车道变更。本发明具有提高自动驾驶车辆自动换道策略的准确性,保证车辆在换道过程中的安全性,减少道路拥挤情况和碰撞事故的发生的有益效果。
Automatic driving vehicle lane changing decision system and method based on deep reinforcement learning
基于深度强化学习的自动驾驶车辆换道决策系统及方法
2022-07-29
Patent
Elektronische Ressource
Chinesisch
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 vehicle lane changing method based on double-layer deep reinforcement learning
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2024
|Automatic driving lane changing decision control method based on rule fusion reinforcement learning
Europäisches Patentamt | 2022
|Automatic driving lane changing decision making method and device and vehicle
Europäisches Patentamt | 2021
|Harmonious Lane Changing via Deep Reinforcement Learning
IEEE | 2022
|