Safe learning-based optimal motion planning for automated driving

TL;DR

This paper introduces a machine learning-based heuristic for optimal motion planning in automated driving that accounts for dynamic obstacles, improving search efficiency and enabling more consistent real-time performance.

Contribution

It proposes a novel ML-based heuristic that considers dynamic obstacles, enhancing search efficiency in urban autonomous driving scenarios.

Findings

ML heuristic improves search efficiency

Enhanced performance consistency in dynamic environments

Potential for real-time implementation

Abstract

This paper presents preliminary work on learning the search heuristic for the optimal motion planning for automated driving in urban traffic. Previous work considered search-based optimal motion planning framework (SBOMP) that utilized numerical or model-based heuristics that did not consider dynamic obstacles. Optimal solution was still guaranteed since dynamic obstacles can only increase the cost. However, significant variations in the search efficiency are observed depending whether dynamic obstacles are present or not. This paper introduces machine learning (ML) based heuristic that takes into account dynamic obstacles, thus adding to the performance consistency for achieving real-time implementation.