author = {Olivier Pietquin and Fabio Tango and Raghav Aras},
title = {Batch Reinforcement Learning for Optimizing Longitudinal Driving Assistance Strategies},
year = {2011},
booktitle = {Proceedings of the IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (CIVTS 2011)},
pages = {73 - 79},
month = {April},
address = {Paris (France)},
url = {http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/CIVTS_2011_OPRAFT.pdf},
doi = {10.1109/CIVTS.2011.5949533},
abstract = {Partially Autonomous Driver's Assistance Systems (PADAS) are systems aiming at providing a safer driving experience to people. Especially, one application of such systems is to assist the drivers in reacting optimally so as to prevent collisions with a leading vehicle. Several means can be used by a PADAS to reach this goal. For instance, warning signals can be sent to the driver or the PADAS can actually modify the speed of the car by braking automatically. An optimal combination of different warning signals together with assistive braking is expected to reduce the probability of collision. How to associate the right combination of PADAS actions to a given situation so as to achieve this aim remains an open problem. In this paper, the use of a statistical machine learning method, namely the reinforcement learning paradigm, is proposed to automatically derive an optimal PADAS action selection strategy from a database of driving experiments. Experimental results conducted on actual car simulators with human drivers show that this method achieves a significant reduction of the risk of collision.}