A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912086160834560 |
|---|---|
| author | Li, Peijin Wang, Gaotian Jiang, Hao Jin, Yusong Gan, Yinghao Chen, Xiaoping Ji, Jianmin |
| author_facet | Li, Peijin Wang, Gaotian Jiang, Hao Jin, Yusong Gan, Yinghao Chen, Xiaoping Ji, Jianmin |
| contents | It is challenging to control a soft robot, where reinforcement learning methods have been applied with promising results. However, due to the poor sample efficiency, reinforcement learning methods require a large collection of training data, which limits their applications. In this paper, we propose a Q-learning controller for a physical soft robot, in which pre-trained models using data from a rough simulator are applied to improve the performance of the controller. We implement the method on our soft robot, i.e., Honeycomb Pneumatic Network (HPN) arm. The experiments show that the usage of pre-trained models can not only reduce the amount of the real-world training data, but also greatly improve its accuracy and convergence rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2109_05795 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator Li, Peijin Wang, Gaotian Jiang, Hao Jin, Yusong Gan, Yinghao Chen, Xiaoping Ji, Jianmin Robotics It is challenging to control a soft robot, where reinforcement learning methods have been applied with promising results. However, due to the poor sample efficiency, reinforcement learning methods require a large collection of training data, which limits their applications. In this paper, we propose a Q-learning controller for a physical soft robot, in which pre-trained models using data from a rough simulator are applied to improve the performance of the controller. We implement the method on our soft robot, i.e., Honeycomb Pneumatic Network (HPN) arm. The experiments show that the usage of pre-trained models can not only reduce the amount of the real-world training data, but also greatly improve its accuracy and convergence rate. |
| title | A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator |
| topic | Robotics |
| url | https://arxiv.org/abs/2109.05795 |