The invention relates to a security constraint behavior decision-making system considering social preference of a vehicle behind a target lane, and the system comprises the steps: adding reward or punishment setting according to the social preference of the vehicle behind the target lane in a behavior decision-making algorithm of PP0-DQN hierarchical reinforcement learning based on the social preference attribute of a vehicle closest to the vehicle behind the target lane, and carrying out the decision-making of the vehicle behind the target lane. And for a target (goal), a profit social preference of a vehicle behind a target lane is formulated to carry out a safety constraint of lane changing return so as to adapt to uncertainty in a mixed scene, so that the efficiency of finding an optimal behavior decision strategy by an automatic driving vehicle in a dynamic environment is facilitated, and the safety of the automatic driving vehicle in a multi-lane dynamic complex environment is improved.
本案涉及一种考虑目标车道后车社会偏好的安全约束行为决策系统,基于目标车道后车最近车的社会偏好属性,在PP0‑DQN的分层强化学习的行为决策算法中,加入根据目标车道后车社会偏好的奖励或惩罚设置,并针对目标(goal)制定目标车道后车利己性社会偏好进行换道返回的安全约束,以适应混合场景下的不确定性,有助于自动驾驶车辆在动态环境中发现最优行为决策策略效率,提高自动驾驶车辆在多车道动态复杂环境下的安全。
Security constraint behavior decision-making system considering social preferences of vehicles behind target lane
考虑目标车道后车社会偏好的安全约束行为决策系统
2024-11-22
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 |
European Patent Office | 2024
|European Patent Office | 2024
|Game Theory-Based Lane Change Decision-Making Considering Vehicle’s Social Value Orientation
SAE Technical Papers | 2023
|European Patent Office | 2023
|