We introduce CollisionPro, a pioneering framework designed to estimate cumulative collision probability distributions using temporal difference learning, specifically tailored to applications in robotics, with a particular emphasis on autonomous driving. This approach addresses the demand for explainable artificial intelligence (XAI) and seeks to overcome limitations imposed by model-based approaches and conservative constraints. We formulate our framework within the context of reinforcement learning to pave the way for safety-aware agents. Nevertheless, we assert that our approach could prove beneficial in various contexts, including a safety alert system or analytical purposes. A comprehensive examination of our framework is conducted using a realistic autonomous driving simulator, illustrating its high sample efficiency and reliable prediction capabilities for previously unseen collision events. The source code is publicly available.
@article{arxiv.2407.20000,
title = {Collision Probability Distribution Estimation via Temporal Difference Learning},
author = {Thomas Steinecker and Thorsten Luettel and Mirko Maehlisch},
journal= {arXiv preprint arXiv:2407.20000},
year = {2024}
}