Experience-Based Heuristic Search: Robust Motion Planning with Deep Q-Learning

TL;DR

This paper introduces an experience-based heuristic search method that integrates Deep Q-Network experiences into heuristic search for robust, efficient motion planning in autonomous driving, addressing the statistical limitations of pure reinforcement learning.

Contribution

It presents a novel algorithm combining deep reinforcement learning with heuristic search to improve robustness and computational efficiency in autonomous vehicle path planning.

Findings

Demonstrates improved robustness over pure deep RL methods

Shows computational speedup in semi-structured parking scenarios

Provides accurate heuristic estimates for path planning

Abstract

Interaction-aware planning for autonomous driving requires an exploration of a combinatorial solution space when using conventional search- or optimization-based motion planners. With Deep Reinforcement Learning, optimal driving strategies for such problems can be derived also for higher-dimensional problems. However, these methods guarantee optimality of the resulting policy only in a statistical sense, which impedes their usage in safety critical systems, such as autonomous vehicles. Thus, we propose the Experience-Based-Heuristic-Search algorithm, which overcomes the statistical failure rate of a Deep-reinforcement-learning-based planner and still benefits computationally from the pre-learned optimal policy. Specifically, we show how experiences in the form of a Deep Q-Network can be integrated as heuristic into a heuristic search algorithm. We benchmark our algorithm in the field of path planning in semi-structured valet parking scenarios. There, we analyze the accuracy of such estimates and demonstrate the computational advantages and robustness of our method. Our method may encourage further investigation of the applicability of reinforcement-learning-based planning in the field of self-driving vehicles.