Discriminative and adaptive imitation in uni-manual and bi-manual tasks

被引:122
作者
Billard, Aude G. [1 ]
Calinon, Sylvain [1 ]
Guenter, Florent [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Sch Engn, Ecole Polytech Fed Lausanne, LASA Lab,STI 12S, CH-1015 Lausanne, Switzerland
关键词
discriminative imitation; learning; humanoid robots; kinesthetic teaching; HMM; Lagrange optimization;
D O I
10.1016/j.robot.2006.01.007
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper addresses the problems of what to imitate and how to imitate in simple uni and bi-manual manipulatory tasks. To solve the what to imitate issue, we use a probabilistic method, based on Hidden Markov Models (HMM), to extract the relative importance of reproducing either the gesture or the specific hand path in a given task. This allows us to determine a metric of imitation performance. To solve the how to imitate issue, we compute the trajectory that optimizes the metric given the constraints of the robot's body. We validate the methods using a series of experiments where a human demonstrator uses kinesthetics in order to teach a robot how to manipulate simple objects. (c) 2006 Elsevier B.V. All rights reserved.
引用
收藏
页码:370 / 384
页数:15
相关论文
共 27 条
[1]   Imitation with ALICE: Learning to imitate corresponding actions across dissimilar embodiments [J].
Alissandrakis, A ;
Nehaniv, CL ;
Dautenhahn, K .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2002, 32 (04) :482-496
[2]  
Alissandrakis A, 2004, INTERACTION STUDIES, V5, P3
[3]  
[Anonymous], P IEEE INT C FIELD S
[4]  
[Anonymous], 1996, AISB96 WORKSH LEARN
[5]  
[Anonymous], P INT S IM AN ART
[6]  
ASFOUR T, 2003, IEEE RSJ INT C INT R
[7]  
BELPAEME T, 2006, IN PRESS IMITATION S
[8]   Discovering optimal imitation strategies [J].
Billard, A ;
Epars, Y ;
Calinon, S ;
Schaal, S ;
Cheng, G .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2004, 47 (2-3) :69-77
[9]  
CALINON S, 2005, P INT C ROB AUT BARC
[10]  
CALINON S, 2004, P IEEE RSJ INT C INT