Home /Research /LEARNING TO ACT FROM OBSERVATION AND PRACTICE
LEARNING

LEARNING TO ACT FROM OBSERVATION AND PRACTICE

Darrin C. Bentivegna, Christopher G. Atkeson, Aleš Ude, Gordon Cheng

Year
2004
Citations
53

Abstract

We present a method for humanoid robots to quickly learn new dynamic tasks from observing others and from practice. Ways in which the robot can adapt to initial and also changing conditions are described. Agents are given domain knowledge in the form of task primitives. A key element of our approach is to break learning problems up into as many simple learning problems as possible. We present a case study of a humanoid robot learning to play air hockey.

Keywords

Computer scienceHumanoid robotTask (project management)RobotKey (lock)Human–computer interactionArtificial intelligenceSimple (philosophy)Robot learningDomain (mathematical analysis)

Related papers

Browse all LEARNING papers