Knowing What to Imitate and Knowing When You Succeed
Brian Scassellati
- Year
- 2007
- Citations
- 17
Abstract
If we are to build robots that can imitate the actions of a human instructor, the robotics community must address a variety of issues. In this paper, we examine two of these issues. First, how does the robot know which things it should imitate? Second, how does the robot know when its actions are an adequate imitation of the original? We further describe an on-going research effort to implement systems for a humanoid robot that address these issues. 1 Introduction Humans (and other animals) acquire new skills from social interactions with others through direct tutelage, observational conditioning, goal emulation, imitation, and other methods (Galef 1988). These social learning skills provide a powerful mechanism for children to acquire skills and knowledge from their parents, other adults, and other children. In particular, imitation is an extremely powerful mechanism for social learning which has received a great deal of interest from researchers in the fields of animal behavior...
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991