Knowledge Commons of Institute of Automation,CAS
Modeling Socially Normative Navigation Behaviors from Demonstrations with Inverse Reinforcement Learning | |
Xingyuan Gao1,2; Xiaoguang Zhao1; Min Tan1 | |
2019-09 | |
会议名称 | IEEE International Conference on Automation Science and Engineering |
会议日期 | 2019-08-22至2019-08-26 |
会议地点 | Vancouver, British Columbia, Canada |
摘要 | Navigation in an efficient and socially normative manner is essential for the robot to operate in human populated environments. Traditional methods treat the pedestrians as dynamic obstacles and design a manual cost function for collision avoidance, but neglect social norms in navigation and do not generalize well to new environments. In this paper, we propose a mixture model to capture the human navigation behaviors in terms of the features of the continuous trajectories and discrete navigation decisions, such as passing on the left or right. The lower level of the model aims to generate socially normative trajectories. To this end, we extend inverse reinforcement learning (IRL) framework to a motion planner called Timed Elastic Band to learn from demonstrations. The upper level comprises a discrete distribution over the homotopy classes of the trajectories. IRL algorithm is employed to find the parameters of distribution that match demonstrations best. Experiments demonstrate that our learning algorithm has the capacity to recover the human navigation behaviors that respect social norms, which makes our approach outperform state-of-the-art methods in social navigation scenarios. |
语种 | 英语 |
七大方向——子方向分类 | 机器人感知与决策 |
国重实验室规划方向分类 | 实体人工智能系统决策-控制 |
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/173211/57461 |
专题 | 多模态人工智能系统全国重点实验室_智能机器人系统研究 |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
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 | Xingyuan Gao,Xiaoguang Zhao,Min Tan. Modeling Socially Normative Navigation Behaviors from Demonstrations with Inverse Reinforcement Learning[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 | ||
Modeling_Socially_No(1500KB) | 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