Abstract
Infants imitate behaviour flexibly. Depending on the circumstances, they copy both actions and their effects or only reproduce the demonstrator’s intended goals. In view of this selective imitation, infants have been called rational imitators. The ability to selectively and adaptively imitate behaviour would be a beneficial capacity for robots. Indeed, selecting what to imitate is an outstanding unsolved problem in the field of robotic imitation. In this paper, we first present a formalized model of rational imitation suited for robotic applications. Next, we test and demonstrate it using two humanoid robots.
Highlights
Imitation is a very important form of social learning in humans and has been suggested to underlie human cumulative culture (Legare and Nielsen, 2015; Tomasello, 2009)
The selective and rational imitation shown by children would be a beneficial capacity for robots (Gergely, 2003)
The Cost Difference Model (CDM) can be considered as a formalized version of the teleological reasoning hypothesis, which is underspecified (See Zmyj and Buttelmann, 2014, for references)
Summary
Imitation is a very important form of social learning in humans and has been suggested to underlie human cumulative culture (Legare and Nielsen, 2015; Tomasello, 2009). Having outlined a functional account of rational imitation, we proceed to describe the computations we assume to underlie the selection of action policies for imitation We propose this proceeds in three steps: (1) parsing the continuous stream of sensory input, (2) solving the correspondence problem, (3) comparing the costs of the existing and the demonstrated action policies. O s = { o 0 , o T }) < τE , the imitator will plan an action sequence to attain the final state demonstrated – no imitation of any intermediate goal will take place In this case, the imitator assumes that the observed behaviour ~. This would imply that infants are less good at copying motor behavior at 12 months than at 9 months
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
