A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator
Abstract
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.
Cite
@article{arxiv.2109.05795,
title = {A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator},
author = {Peijin Li and Gaotian Wang and Hao Jiang and Yusong Jin and Yinghao Gan and Xiaoping Chen and Jianmin Ji},
journal= {arXiv preprint arXiv:2109.05795},
year = {2024}
}
Comments
This work has been submitted to the IEEE ROBIO 2021 for possible publication