Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning

TL;DR

This paper presents a hierarchical contingency planning approach for autonomous vehicles to adapt quickly to sudden changes in environment beliefs, ensuring safety in stochastic, partially observable settings.

Contribution

The paper introduces an end-to-end method for learning and integrating contingency plans with hierarchical planning for robust autonomous navigation.

Findings

Achieves robust, safe behavior in stochastic, partially observable environments.

Generalizes well to unseen environment dynamics.

Enhances autonomous vehicle safety through contingency planning.

Abstract

When learning to act in a stochastic, partially observable environment, an intelligent agent should be prepared to anticipate a change in its belief of the environment state, and be capable of adapting its actions on-the-fly to changing conditions. As humans, we are able to form contingency plans when learning a task with the explicit aim of being able to correct errors in the initial control, and hence prove useful if ever there is a sudden change in our perception of the environment which requires immediate corrective action. This is especially the case for autonomous vehicles (AVs) navigating real-world situations where safety is paramount, and a strong ability to react to a changing belief about the environment is truly needed. In this paper we explore an end-to-end approach, from training to execution, for learning robust contingency plans and combining them with a hierarchical planner to obtain a robust agent policy in an autonomous navigation task where other vehicles' behaviours are unknown, and the agent's belief about these behaviours is subject to sudden, last-second change. We show that our approach results in robust, safe behaviour in a partially observable, stochastic environment, generalizing well over environment dynamics not seen during training.