2015 IEEE Intelligent Vehicles Symposium (IV2015) is being held on June 28 ~ July 1, 2015 at COEX in Seoul, Korea.
The following oral presentation will be delivered.

6/29(Mon.) 17:00-18:20 E1/E2/E3
Regular Session MoOrPT1: Vehicle Environment Perception

17:20-17:40, Paper MoOrPT1.2
Predicting Driving Behavior Using Inverse Reinforcement Learning with Multiple Reward Functions towards Environmental Diversity
Masamichi Shimosaka, Kentaro Nishi, Junichi Sato and Hirokatsu Kataoka

In this research, we propose a mixtured IRL framework where multiple reward functions deal with environmental diversity. Specifically, the model employs Dirichlet process mixtures as a flexible and powerful Bayesian model to divide the environment into clusters and learns the parameters in each cluster simultaneously. Experimental result shows that our model provides superior performance over the IRL model with single reward function.

— Conference information —
IV2015 Home http://www.iv2015.org/
IV2015 Program https://its.papercept.net/conferences/scripts/rtf/IV2015_ProgramAtAGlanceWeb.html