Learning and communication via imitation: An autonomous robot perspective

被引:73
作者
Andry, P [1 ]
Gaussier, P
Moga, S
Banquet, JP
Nadel, J
机构
[1] Univ Cergy Pontoise, ETIS,Grad Sch Elect & Elect Engn, ENSEA,Signal & Image Proc Lab, Neurocybernet Team, Cergy, France
[2] INSERM, French Inst Hlth & Med Res, Paris, France
[3] Hop La Pitie Salpetriere, UMR CNRS 7593, Equipe Dev & Psychopathol, Paris, France
来源
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS | 2001年 / 31卷 / 05期
关键词
autonomous learning; imitation; implicit reinforcement; interaction; neural network; synchronization;
D O I
10.1109/3468.952717
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes a neural network architecture designed to exhibit learning and communication capabilities via imitation. Our architecture allows a "protoimitation" behavior using the "perception ambiguity" inherent in real environments. In the perspective of turntaking and gestural communication between two agents, new experiments on movement synchronization in an interaction game are presented. Synchronization is obtained as a global attractor depending on the coupling between agents' dynamic. We also discuss the nonsupervised context of the imitation process and we present new experiments in which the same architecture is able to learn perception-action associations without any explicit reinforcement. The learning is based on the ability to detect novelty or irregularities in the communication rhythm.
引用
收藏
页码:431 / 442
页数:12
相关论文
共 32 条
  • [1] ANDRY P, 2000, P 6 INT C SIM AD BEH, P353
  • [2] [Anonymous], 1960, DESIGN BRAIN
  • [3] [Anonymous], PSYCHOL MODELING CON
  • [4] BANQUET JP, 1998, COMPUT NEUR, P77
  • [5] BANQUET JP, 1997, COGNITIVE SCI PERSPE, P123
  • [6] BILLARD A, 1997, P 7 INT C ART NEUR N, P763
  • [7] BILLARD A, 1997, P 6 EUR WORKSH LEARN
  • [8] Billard A., 1998, P SOC SIT INT WORKSH
  • [9] Butterworth G., 1999, IMITATION INFANCY, P63
  • [10] Cheng G., 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065), P2235, DOI 10.1109/ROBOT.2000.846360