Formation Control with Collision Avoidance through Deep Reinforcement Learning | |
Sui Zezhi1,2; Pu Zhiqiang1,2; Yi Jianqiang1,2; Xiong Tianyi1,2 | |
2019-07 | |
会议名称 | 2019 International Joint Conference on Neural Networks (IJCNN) |
会议日期 | July 14-19, 2019 |
会议地点 | Budapest, Hungary, Hungary |
出版者 | Institute of Electrical and Electronics Engineers Inc |
摘要 | Generating collision free, time efficient paths for followers is a challenging problem in formation control with collision avoidance. Specifically, the followers have to consider both formation maintenance and collision avoidance at the same time. Recent works have shown the potentialities of deep reinforcement learning (DRL) to learn collision avoidance policies. However, only the collision factor was considered in the previous works. In this paper, we extend the learning-based policy to the area of formation control by learning a comprehensive task. In particular, a two-stage training scheme is adopted including imitation learning and reinforcement learning. A fusion reward function is proposed to lead the training. Besides, a formation-oriented network architecture is presented for environment perception and long short-term memory (LSTM) is applied to perceive the information of an arbitrary number of obstacles. Various simulations are carried out and the results show the proposed algorithm is able to anticipate the dynamic information of the environment and outperforms traditional methods. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39697 |
专题 | 综合信息系统研究中心 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences Beijing, 100190, China 2.University of Chinese Academy of Sciences Beijing, 100049, China |
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 | Sui Zezhi,Pu Zhiqiang,Yi Jianqiang,et al. Formation Control with Collision Avoidance through Deep Reinforcement Learning[C]:Institute of Electrical and Electronics Engineers Inc,2019. |
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 | ||
IJCNN2019.pdf(2431KB) | 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