In order for a mobile robot to accurately interpret its sensations and predict the effects of its actions, it must have accurate models of its sensors and actuators. These models are typically tuned manually, a brittle and laborious process. Autonomous model learning is a promising alternative to manual calibration, but previous work has assumed the presence of an accurate action or sensor model in order to train the other model. This paper presents an adaptation of the Expectation-Maximization (EM) algorithm to enable a mobile robot to learn both its action and sensor model functions, starting without an accurate version of either. The resulting algorithm is validated experimentally both on a Sony Aibo ERS-7 robot and in simulation.
In IEEE International Conference on Robotics and Automation, May 2008.

Peter Stone Faculty pstone [at] cs utexas edu
Daniel Stronger Ph.D. Alumni dan stronger [at] gmail com