Feasibility Study of Fully Automated Vehicles Using Decision-theoretic Control
J. M. Forbes, Nikunj C. Oza, R. Parr, Stuart Russell · PATH research report · 1997
This project studied the feasibility of constructing an autonomous vehicle controller based on probabilistic inference and utility maximization. Several theoretical and algorithmic advances were required in order to create an inference system capable of handling vehicle monitoring in a real-time fashion. New methods were also developed for learning probabilistic models from data, and for learning control policies given reward/penalty feedback.