The invention relates to an automatic driving decision-making method based on deep reinforcement learning. The method comprises the following steps: S1, constructing a Markov decision-making process suitable for a car following decision-making and lane changing decision-making training environment in automatic driving; and S2, respectively training a car following decision and a lane changing decision of a specific agent through a deep Q network and an aggregation algorithm of a deep deterministic strategy gradient. According to the invention, the traffic efficiency is improved, the traffic safety is enhanced, and the driving comfort is improved.
本发明涉及一种基于深度强化学习的自动驾驶决策方法,包括如下步骤:S1、构造适合自动驾驶中跟驰决策和换道决策训练环境的马尔可夫决策过程;S2、通过深度Q网络和深度确定性策略梯度的聚合算法分别训练特定智能体的跟驰决策和换道决策。本发明有利于提高交通效率、增强交通安全性以及改善行驶的舒适性。
Automatic driving decision-making method based on deep reinforcement learning
基于深度强化学习的自动驾驶决策方法
2024-03-08
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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Automatic driving behavior decision-making method based on deep reinforcement learning
Europäisches Patentamt | 2020
|Automatic driving vehicle overtaking decision-making method based on deep reinforcement learning
Europäisches Patentamt | 2022
|Automatic driving decision-making system based on deep reinforcement learning
Europäisches Patentamt | 2024
|Automatic driving behavior decision-making method based on deep reinforcement learning
Europäisches Patentamt | 2024
|Automatic driving behavior integrated decision-making method based on deep reinforcement learning
Europäisches Patentamt | 2022
|