.png){kind=icon}
返回
An Efficient Robot Precision Assembly Skill Learning Framework Based on Several Demonstrations
.png){kind=icon}
PRE
AI
DOI：10.1109/TASE.2022.3144282.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes an efficient robot assembly skill learning framework based on only a few demonstrations. The assembly skill learning process consists of two phases, e.g., the pre-training phase and the self-learning phase. In pre-training phase, the assembly networks are initialized from demonstration data. A novel data augmentation model based on state transition model is designed, which only requires several human demonstrations to learn the parameters of the model and reduces the cost of demonstration data collection in pre-training. In self-learning phase, the pre-trained assembly networks are further optimized by a hybrid exploration strategy in assembly environment, which explores both parameter space and action space to increase exploration efficiency. On par with the learning framework, a fuzzy reward function balancing the efficiency and compliance of assembly is elaborately designed to evaluate action's performance in assembly skill self-learning process. Series of physical experiments were well conducted on a sophisticated assembly platform to verify the effectiveness of the proposed efficient robot assembly skill learning framework. Experimental results demonstrate that the learning efficiency of the proposed framework is at least three times as efficient as the state-of-art methods, while the skill performance outperforms the state-of-art by more than 50%.
Keyword:
Robots
Reinforcement learning
Data models
Task analysis
Learning systems
Trajectory
Training
Efficient robot skill learning
demonstration learning
robot assembly
robot and automation
期刊
IF:
6.4
论文数:
5.0K
被引数:
1.6W
机构
引用论文
Multiple Targets for Suppression of RNA Interference by Tomato Aspermy Virus Protein 2B.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏
Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation柔性两连杆机械手的强化学习控制: 实验研究
PREAI
分享收藏Efficient Insertion Control for Precision Assembly Based on Demonstration Learning and Reinforcement Learning基于演示学习和强化学习的精密装配高效插入控制
PREAI
分享收藏Formation Control With Collision Avoidance Through Deep Reinforcement Learning Using Model-Guided Demonstration使用模型引导演示通过深度强化学习进行防撞的编队控制
PREAI
分享收藏
查看更多内容