Redundant robot control with learning from expert demonstrations

被引：0

作者：

Ramirez, Jorge ^{[1
]}

Yu, Wen ^{[2
]}

机构：

[1] Natl Polytech Inst, Dept Control Automat, IPN, CINVESTAV, Mexico City, DF, Mexico

[2] IPN, Dept Control Automat, CINVESTAV, Mexico City, DF, Mexico

来源：

2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) | 2022年

关键词：

reinforcement learning; learning from expert demonstration; redundant robot control;

D O I：

10.1109/SSCI51031.2022.10022138

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes a biased exploration based reinforcement learning, which uses expert experiences to avoid the exploration of all states. The method is applied to control redundant robots with expert experiences. A 7-degree-of-freedom robot manipulator is used in experiments. The results show that expert demonstrations based robot control works well.

引用

页码：715 / 720

页数：6

共 50 条

[21] Learning From Imperfect Demonstrations From Agents With Varying Dynamics
Cao, Zhangjie
Sadigh, Dorsa
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03) : 5231 - 5238
[22] Integrating Reinforcement Learning and Learning From Demonstrations to Learn Nonprehensile Manipulation
Sun, Xilong
Li, Jiqing
Kovalenko, Anna Vladimirovna
Feng, Wei
Ou, Yongsheng
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2023, 20 (03) : 1735 - 1744
[23] Poster Abstract: Learning from Demonstrations with Temporal Logics
Puranic, Aniruddh G.
Deshmukh, Jyotirmoy, V
Nikolaidis, Stefanos
HSCC 2022: PROCEEDINGS OF THE 25TH ACM INTERNATIONAL CONFERENCE ON HYBRID SYSTEMS: COMPUTATION AND CONTROL (PART OF CPS-IOT WEEK 2022), 2022,
[24] Toward learning to control robot behaviors
Müller, JP
Faihe, Y
INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2000, 6 (03) : 205 - 213
[25] Adversarial Imitation Learning from State-only Demonstrations
Torabi, Faraz
Warnell, Garrett
Stone, Peter
AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 2229 - 2231
[26] Adaptive cooperative exploration for reinforcement learning from imperfect demonstrations *
Huang, Fuxian
Ji, Naye
Ni, Huajian
Li, Shijian
Li, Xi
PATTERN RECOGNITION LETTERS, 2023, 165 : 176 - 182
[27] Reinforcement learning from suboptimal demonstrations based on Reward Relabeling
Peng, Yong
Zeng, Junjie
Hu, Yue
Fang, Qi
Yin, Quanjun
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 255
[28] Redundant robot manipulator control with obstacles avoidance using self-motion approach
Benzaoui, M.
Chekireb, H.
PROCEEDINGS OF THE 13TH IASTED INTERNATIONAL CONFERENCE ON ROBOTICS AND APPLICATIONS/PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON TELEMATICS, 2007, : 21 - 26
[29] Learning Skills From Demonstrations: A Trend From Motion Primitives to Experience Abstraction
Tavassoli, Mehrdad
Katyara, Sunny
Pozzi, Maria
Deshpande, Nikhil
Caldwell, Darwin G.
Prattichizzo, Domenico
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2024, 16 (01) : 57 - 74
[30] Constructing Action Set from Basis Functions for Reinforcement Learning of Robot Control
Yamaguchi, Akihiko
Takamatsu, Jun
Ogasawara, Tsukasa
ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7, 2009, : 4173 - 4180

← 1 2 3 4 5 →