Maximum likelihood estimation of sensor and action model functions on a mobile robot

Abstract

Abstract-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.

Dynamic collision risk modeling under uncertainty

“…The coordinates of the outmost points p i1 and p i2 are deduced in a similar way. Their covariance matrices are characterized by systems similar to system (24). The uncertainties in these positions allow to deduce the conflict region.…”

“…The Gaussian distribution assumption for sensing measurement is a reasonable one and has been used by many authors. [22][23][24] The suggested method uses dynamic models that take uncertainties in motion and geometry into account. Two approaches are discussed: the virtual configuration space (VCS), and the rate of change of visibility angles.…”