Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion | |
Peng Hao; Tao Lu; Shaowei Cui; Junhang Wei; YInghao Cai; Shuo Wang | |
刊名 | IEEE Robotics and Automation Letters |
2022 | |
卷号 | 7期号:7页码:3656-3663 |
关键词 | meta-learning residual learning |
英文摘要 | Adapting the mastered manipulation skill to novel objects is still challenging for robots. Recent works have attempted to endow the robot with the ability to adapt to unseen tasks by leveraging meta-learning. However, these methods are data-hungry in the training phase, which limits their application in the real world. In this paper, we propose Meta-Residual Policy Learning (MRPL) to reduce the cost of policy learning and adaptation. During meta-training, MRPL accelerates the learning process by focusing on the residual task shared knowledge that is hard to be formulated as physical models. During testing, MRPL achieves fast adaptation on similar unseen tasks through fusing task-specific knowledge in the demonstration with task-shared knowledge in the learned policy. We conduct a series of simulated and real-world peg-in hole tasks to evaluate the proposed method. The experimental results demonstrate that MRPL outperforms prior methods in robot skill adaptation. Code for this work is available at https://github.com/Bartopt/code4MRPL |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/47500] |
专题 | 智能机器人系统研究 |
通讯作者 | Shuo Wang |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Peng Hao,Tao Lu,Shaowei Cui,et al. Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion[J]. IEEE Robotics and Automation Letters,2022,7(7):3656-3663. |
APA | Peng Hao,Tao Lu,Shaowei Cui,Junhang Wei,YInghao Cai,&Shuo Wang.(2022).Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion.IEEE Robotics and Automation Letters,7(7),3656-3663. |
MLA | Peng Hao,et al."Meta-Residual Policy Learning: Zero-Trial Robot Skill Adaptation via Knowledge Fusion".IEEE Robotics and Automation Letters 7.7(2022):3656-3663. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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