Utility Decomposition for Planning under Uncertainty for Autonomous Driving

The objective of this research is to provide scalable decision making algorithms for autonomously navigating urban environments. The vehicle must plan in a stochastic environment with many entities to avoid, rapid changes in driver behavior, and partial observability. Partially observable Markov decision processes (POMDP) offer a theoretically grounded framework to model such problems. We aim at developing a scalable POMDP formulation that takes into account dynamic occlusions, interaction between entities, and can generalize to a variety of different scenarios. This work demonstrates utility fusion and deep reinforcement learning methods to efficiently find optimal policies to navigate occluded urban environments.