Real-time robot learning with locally weighted statistical learning

S. Schaal, C.G. Atkeson, S. Vijayakumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Locally weighted learning (LWL) is a class of statistical learning techniques that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional beliefs that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested in up to 50 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing of a humanoid robot arm, and inverse-dynamics learning for a seven degree of-freedom robot.
Original languageEnglish
Title of host publicationRobotics and Automation, 2000. Proceedings. ICRA'00. IEEE International Conference on
Number of pages6
Publication statusPublished - 2000


Dive into the research topics of 'Real-time robot learning with locally weighted statistical learning'. Together they form a unique fingerprint.

Cite this