Towards Machine Learning of Motor Skills

13 years 10 months ago

Download www-clmc.usc.edu

Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artiﬁcial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artiﬁcial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulﬁll. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulﬁll this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one st...

Jan Peters, Stefan Schaal, Bernhard Schölkopf

Real-time Traffic