Challenges in Perception and Decision Making for Intelligent Automotive Vehicles: A Case Study

This paper overviews challenges in perception and decision making for intelligent, or highly automated, automotive vehicles. We illustrate our development of a complete perception and decision making system which addresses various challenges and propose an action planning method for highly automated vehicles which can merge into a roundabout. We use learning from demonstration to construct a classifier for high-level decision making, and develop a novel set of formulations that is suited to this challenging situation: multiple agents in a highly dynamic environment with interdependencies between agents, partial observability, and a limited amount of training data. Having limited amount of labeled training data is highly constraining, but a very real issue in real-world applications. We believe that our formulations are also well suited to other automated driving scenarios.