Motion Planning for Autonomous Vehicles in the Presence of Uncertainty Using Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning approach for autonomous vehicle motion planning under sensing uncertainty, optimizing for worst-case outcomes to improve safety and performance in occluded and limited-view scenarios.

Contribution

It presents a novel distributional RL method that focuses on worst-case outcomes, enhancing safety in autonomous driving under uncertainty, and demonstrates its effectiveness with two RL algorithms in simulation.

Findings

Outperforms traditional RL in uncertain scenarios

Behaves comparably to human drivers in tests

Improves safety and robustness in motion planning

Abstract

Motion planning under uncertainty is one of the main challenges in developing autonomous driving vehicles. In this work, we focus on the uncertainty in sensing and perception, resulted from a limited field of view, occlusions, and sensing range. This problem is often tackled by considering hypothetical hidden objects in occluded areas or beyond the sensing range to guarantee passive safety. However, this may result in conservative planning and expensive computation, particularly when numerous hypothetical objects need to be considered. We propose a reinforcement learning (RL) based solution to manage uncertainty by optimizing for the worst case outcome. This approach is in contrast to traditional RL, where the agents try to maximize the average expected reward. The proposed approach is built on top of the Distributional RL with its policy optimization maximizing the stochastic outcomes' lower bound. This modification can be applied to a range of RL algorithms. As a proof-of-concept, the approach is applied to two different RL algorithms, Soft Actor-Critic and DQN. The approach is evaluated against two challenging scenarios of pedestrians crossing with occlusion and curved roads with a limited field of view. The algorithm is trained and evaluated using the SUMO traffic simulator. The proposed approach yields much better motion planning behavior compared to conventional RL algorithms and behaves comparably to humans driving style.