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

[1] Reinforcement learning from expert demonstrations with application to redundant robot control
Ramirez, Jorge
Yu, Wen
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 119
[2] Learning Control Barrier Functions from Expert Demonstrations
Robey, Alexander
Hu, Haimin
Lindemann, Lars
Zhang, Hanwen
Dimarogonas, Dimos, V
Tu, Stephen
Matni, Nikolai
2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 3717 - 3724
[3] Robot Learning to Paint from Demonstrations
Park, Younghyo
Jeon, Seunghun
Lee, Taeyoon
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 3053 - 3060
[4] Robot Learning from Failed Demonstrations
Grollman, Daniel H.
Billard, Aude G.
INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS, 2012, 4 (04) : 331 - 342
[5] Robot Learning from Failed Demonstrations
Daniel H. Grollman
Aude G. Billard
International Journal of Social Robotics, 2012, 4 : 331 - 342
[6] ConBaT: Control Barrier Transformer for Safe Robot Learning from Demonstrations
Meng, Yue
Vemprela, Sai
Bonatti, Rogerio
Fan, Chuchu
Kapoor, Ashish
2024 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2024), 2024, : 12857 - 12864
[7] Learning Robust Output Control Barrier Functions From Safe Expert Demonstrations
Lindemann, Lars
Robey, Alexander
Jiang, Lejun
Das, Satyajeet
Tu, Stephen
Matni, Nikolai
IEEE OPEN JOURNAL OF CONTROL SYSTEMS, 2024, 3 : 158 - 172
[8] Watch and Learn: Learning to control feedback linearizable systems from expert demonstrations
Sultangazin, Alimzhan
Pannocchi, Luigi
Fraile, Lucas
Tabuada, Paulo
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 8577 - 8583
[9] Introducing CARESSER: A framework for in situ learning robot social assistance from expert knowledge and demonstrations
Andriella, Antonio
Torras, Carme
Abdelnour, Carla
Alenya, Guillem
USER MODELING AND USER-ADAPTED INTERACTION, 2023, 33 (02) : 441 - 496
[10] Introducing CARESSER: A framework for in situ learning robot social assistance from expert knowledge and demonstrations
Antonio Andriella
Carme Torras
Carla Abdelnour
Guillem Alenyà
User Modeling and User-Adapted Interaction, 2023, 33 : 441 - 496

← 1 2 3 4 5 →