We present an information theoretic approach to stochastic optimal control problems that can be used to derive general sampling based optimization schemes. This new mathematical method is used to develop a sampling based model predictive control algorithm. We apply this information theoretic model predictive control (IT-MPC) scheme to the task of aggressive autonomous driving around a dirt test track, and compare its performance to a model predictive control version of the cross-entropy method.
@article{arxiv.1707.02342,
title = {Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving},
author = {Grady Williams and Paul Drews and Brian Goldfain and James M. Rehg and Evangelos A. Theodorou},
journal= {arXiv preprint arXiv:1707.02342},
year = {2017}
}
Comments
20 pages, 12 figures, submitted to Transactions on Robotics (T-RO)