Institutional Repository of Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China
Deep Reinforcement Learning of Robotic Precision Insertion Skill Accelerated by Demonstrations | |
Wu, Xiapeng1,2; Zhang, Dapeng2; Qin, Fangbo2; Xu, De2 | |
2019-08 | |
会议名称 | CASE 2019: IEEE Conference on Automation Science and Engineering |
会议日期 | 2019-08-22 |
会议地点 | Vancouver, British Columbia, Canada |
出版者 | CASE会议主办方 |
摘要 | Abstract—Automatic high precision assembly of millimeter sized objects is a challenging task. Traditional methods for precision assembly rely on explicit programming with real robot system, and require complex parameter-tuning work. In this paper, we realize deep reinforcement learning of precision insertion skill learning, based on prioritized dueling deep Q-network (DQN). The Q-function is represented by the long short term memory (LSTM) neural network, whose input and output are the raw 6D force-torque feedback and the Q-value,respectively. According to the Q values conditioned on the current state, the skill model selects a 6 degree-of-freedom action from the predefined action set. To accelerate the learning process, the data from demonstrations is used to pre-train the model before the DQN starts. In order to improve the insertion efficiency and safety, insertion step length is modulated based on the instant reward. Our proposed method is validated with the peg-in-hole insertion experiments on a precision assembly robot. The reusability of the skill model is also investigated with different types of insertion tasks. |
语种 | 英语 |
七大方向——子方向分类 | 人工智能+制造 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39078 |
专题 | 精密感知与控制研究中心_精密感知与控制 |
作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
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 | Wu, Xiapeng,Zhang, Dapeng,Qin, Fangbo,et al. Deep Reinforcement Learning of Robotic Precision Insertion Skill Accelerated by Demonstrations[C]:CASE会议主办方,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 | ||
Deep Reinforcement L(1748KB) | 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