POMDPs for Safe Visibility Reasoning in Autonomous Vehicles

Abstract

We present solutions for autonomous vehicles in limited visibility scenarios, such as traversing T-intersections, as well as detail how these scenarios can be handled simultaneously. The approach models each problem separately as a partially observable Markov decision process (POMDP). We propose an approach for integrating limited visibility within a POMDPs and implementing them on a physical robot. In order to address scalability challenges, we use a framework for multiple online decision-components with interacting actions (MODIA). We present the novel necessary architectural details to deploy MODIA on an actual robot. The entire approach is demonstrated on a fully operational autonomous vehicle prototype acting in the real world at two different T-intersections.