A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation
Biomimetics · 16.06.2023 · 8 (2) · 264
DOI: 10.3390/biomimetics8020264 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 16.06.2023. Verfasst von Jianhua Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical Engineering, Beijing University of Science and Technology, Beijing 100083, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Joint Fund of National Natural Science Foundation of China with Shenzhen City, the Key Research and Development Program of Zhejiang, the Natural Science Foundation of Zhejiang.
Abstract (Originalsprache)
Robotic hands have the potential to perform complex tasks in unstructured environments owing to their bionic design, inspired by the most agile biological hand. However, the modeling, planning and control of dexterous hands remain unresolved, open challenges, resulting in the simple movements and relatively clumsy motions of current robotic end effectors. This paper proposed a dynamic model based on generative adversarial architecture to learn the state mode of the dexterous hand, reducing the model’s prediction error in long spans. An adaptive trajectory planning kernel was also developed to generate High-Value Area Trajectory (HVAT) data according to the control task and dynamic model, with adaptive trajectory adjustment achieved by changing the Levenberg–Marquardt (LM) coefficient and the linear searching coefficient. Furthermore, an improved Soft Actor–Critic (SAC) algorithm is designed by combining maximum entropy value iteration and HVAT value iteration. An experimental platform and simulation program were built to verify the proposed method with two manipulating tasks. The experimental results indicate that the proposed dexterous hand reinforcement learning algorithm has better training efficiency and requires fewer training samples to achieve quite satisfactory learning and control performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Mechanical Engineering, Beijing University of Science and Technology, Beijing 100083, China.
- College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310023, China.
- Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
ORCID-Profile: Guoyuan Liang, Guanjun Bao
Förderung
- Joint Fund of National Natural Science Foundation of China with Shenzhen City
- the Key Research and Development Program of Zhejiang
- the Natural Science Foundation of Zhejiang
- Joint Fund of the National Natural Science Foundation of China with Shenzhen City
- Key Research and Development Program of Zhejiang
- Natural Science Foundation of Zhejiang
Zitieren
APA
Zhang, J., Zhou, X., Zhou, J., Qiu, S., Liang, G., Cai, S., & Bao, G. (2023). A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation. Biomimetics, 8(2), 264. https://doi.org/10.3390/biomimetics8020264
Vancouver
Zhang J, Zhou X, Zhou J, Qiu S, Liang G, Cai S, et al. A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation. Biomimetics. 2023;8(2):264. doi:10.3390/biomimetics8020264
BibTeX
@article{Zhang2023,
author = {Zhang, Jianhua and Zhou, Xuanyi and Zhou, Jinyu and Qiu, Shiming and Liang, Guoyuan and Cai, Shibo and Bao, Guanjun},
title = {A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation},
journal = {Biomimetics},
year = {2023},
volume = {8},
number = {2},
pages = {264},
doi = {10.3390/biomimetics8020264}
}
EUVIMED