Knowledge Commons of Institute of Automation,CAS
Lane change decision-making through deep reinforcement learning with rule-based constraints | |
Wang JJ(王俊杰)1,2; Zhang QC(张启超)1,2; Zhao DB(赵冬斌)1,2; Chen YR(陈亚冉)1,2 | |
2019-03 | |
会议名称 | International Joint Conference on Neural Networks |
会议日期 | 2019-7 |
会议地点 | Budapest, Hungary |
摘要 | Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level lateral decision-making and low-level rule-based trajectory modification, a safe and efficient lane change behavior can be achieved. With the setting of our state representation and reward function, the trained agent is able to take appropriate actions in a real-world-like simulator. The generated policy is evaluated on the simulator for 10 times, and the results demonstrate that the proposed rule-based DQN method outperforms the rule-based approach and the DQN method. |
关键词 | Lane Change Decision-making Deep Reinforcement Learning Deep Q-Network |
学科门类 | 工学 ; 工学::控制科学与工程 |
七大方向——子方向分类 | 强化与进化学习 |
国重实验室规划方向分类 | 智能计算与学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51720 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang JJ,Zhang QC,Zhao DB,et al. Lane change decision-making through deep reinforcement learning with rule-based constraints[C],2019. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Lane_Change_Decision(295KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论