Header logo is am

Is imitation learning the route to humanoid robots?




This review will focus on two recent developments in artificial intelligence and neural computation: learning from imitation and the development of humanoid robots. It will be postulated that the study of imitation learning offers a promising route to gain new insights into mechanisms of perceptual motor control that could ultimately lead to the creation of autonomous humanoid robots. This hope is justified because imitation learning channels research efforts towards three important issues: efficient motor learning, the connection between action and perception, and modular motor control in form of movement primitives. In order to make these points, first, a brief review of imitation learning will be given from the view of psychology and neuroscience. In these fields, representations and functional connections between action and perception have been explored that contribute to the understanding of motor acts of other beings. The recent discovery that some areas in the primate brain are active during both movement perception and execution provided a first idea of the possible neural basis of imitation. Secondly, computational approaches to imitation learning will be described, initially from the perspective of traditional AI and robotics, and then with a focus on neural network models and statistical learning research. Parallels and differences between biological and computational approaches to imitation will be highlighted. The review will end with an overview of current projects that actually employ imitation learning for humanoid robots.

Author(s): Schaal, S.
Book Title: Trends in Cognitive Sciences
Volume: 3
Number (issue): 6
Pages: 233-242
Year: 1999

Department(s): Autonomous Motion
Bibtex Type: Article (article)

Cross Ref: p1246
Note: clmc
URL: http://www-clmc.usc.edu/publications/S/schaal-TICS1999.pdf; http://www-clmc.usc.edu/publications/S/schaal-TICS1999-rep.pdf


  title = {Is imitation learning the route to humanoid robots?},
  author = {Schaal, S.},
  booktitle = {Trends in Cognitive Sciences},
  volume = {3},
  number = {6},
  pages = {233-242},
  year = {1999},
  note = {clmc},
  crossref = {p1246},
  url = {http://www-clmc.usc.edu/publications/S/schaal-TICS1999.pdf; http://www-clmc.usc.edu/publications/S/schaal-TICS1999-rep.pdf}