What Makes a Good Demonstration for Robot Learning Generalization?

被引:2
作者
Sakr, Maram [1 ]
Van der Loos, H. F. Machiel [1 ]
Kulic, Dana [2 ]
Croft, Elizabeth [2 ]
机构
[1] Univ British Columbia, Vancouver, BC, Canada
[2] Monash Univ, Clayton, Vic, Australia
来源
HRI '21: COMPANION OF THE 2021 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION | 2021年
关键词
Learning from Demonstration; Inverse Optimal Control;
D O I
10.1145/3434074.3446362
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Robot learning from demonstration (LfD) is a common approach that allows robots to perform tasks after observing teacher's demonstrations. Thus, users without a robotics background could use LfD to teach robots. However, such users may provide low quality demonstrations. Besides, demonstration quality plays a crucial role in robot learning and generalization. Hence, it is important to ensure quality demonstrations before using them for robot learning. This abstract proposes an approach for quantifying demonstration quality which in turn enhances robot learning and generalization.
引用
收藏
页码:607 / 609
页数:3
相关论文
共 19 条
[1]   A survey of robot learning from demonstration [J].
Argall, Brenna D. ;
Chernova, Sonia ;
Veloso, Manuela ;
Browning, Brett .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2009, 57 (05) :469-483
[2]   Eliciting good teaching from humans for machine learners [J].
Cakmak, Maya ;
Thomaz, Andrea L. .
ARTIFICIAL INTELLIGENCE, 2014, 217 :198-215
[3]   A tutorial on task-parameterized movement learning and retrieval [J].
Calinon, Sylvain .
INTELLIGENT SERVICE ROBOTICS, 2016, 9 (01) :1-29
[4]   Programing by demonstration: Coping with suboptimal teaching actions [J].
Chen, J ;
Zelinsky, A .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2003, 22 (05) :299-319
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]  
Fischer K, 2016, ACMIEEE INT CONF HUM, P213, DOI 10.1109/HRI.2016.7451754
[7]  
Flacco F, 2012, IEEE INT C INT ROBOT, P3970, DOI 10.1109/IROS.2012.6385619
[8]   THE COORDINATION OF ARM MOVEMENTS - AN EXPERIMENTALLY CONFIRMED MATHEMATICAL-MODEL [J].
FLASH, T ;
HOGAN, N .
JOURNAL OF NEUROSCIENCE, 1985, 5 (07) :1688-1703
[9]  
Grollman Daniel H., 2011, 2011 IEEE International Conference on Robotics and Automation, P3804
[10]   Geometry-aware manipulability learning, tracking, and transfer [J].
Jaquier, Noemie ;
Rozo, Leonel ;
Caldwell, Darwin G. ;
Calinon, Sylvain .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2021, 40 (2-3) :624-650