Knowledge Commons of Institute of Automation,CAS
Improving the Ability of Robots to Navigate Through Crowded Environments Safely using Deep Reinforcement Learning | |
Shan QF(单钦锋)1,2,3![]() ![]() ![]() | |
2022-11-29 | |
会议名称 | 2022 7th IEEE International Conference on Advanced Robotics and Mechatronics |
会议日期 | 2022-7-9 |
会议地点 | 中国桂林 |
摘要 | Autonomous robot navigation in unpredictable and crowded environments requires a guarantee of safety and a stronger ability to pass through a narrow passage. However, it’s challenging to plan safe, dynamically-feasible trajectories in real-time. Previous approaches, such as Reachability-based Trajectory Design (RTD), focus on safety guarantee, but the lack of online strategy always makes the robot fail to pass through a narrow passage. This paper proposes to learn a policy that guides the robot to make successful plans using deep Reinforcement Learning (RL). We train a deep network based on the RTD method to create cost functions in realtime. The created cost function is expected to help the online planner optimize the robot’s feasible trajectory, satisfying its kino-dynamics model and collision avoidance constraints. In crowded simulated environments, our approach substantially improves the planning success rate compared to RTD and some other methods. |
关键词 | Deep learning Mechatronics Navigation Reinforcement learning Cost function Real-time systems Trajectory |
学科门类 | 工学::控制科学与工程 |
DOI | 10.1109/ICARM54641.2022.9959459 |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 智能机器人 |
国重实验室规划方向分类 | 高通过性仿生机器人 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51898 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Jia LH(贾立好) |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 3.中国科学院香港创新研究院人工智能与机器人创新中心 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Shan QF,Wang WJ,Guo DF,et al. Improving the Ability of Robots to Navigate Through Crowded Environments Safely using Deep Reinforcement Learning[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Improving_the_Abilit(494KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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