Collision Probability Distribution Estimation via Temporal Difference Learning
This work addresses the need for explainable AI in safety-critical robotics applications like autonomous driving, though it appears incremental as it adapts existing temporal difference learning methods to this specific domain.
The authors tackled the problem of estimating cumulative collision probability distributions for safety-aware agents in robotics, particularly autonomous driving, by introducing CollisionPro, a framework using temporal difference learning that demonstrated high sample efficiency and reliable prediction for unseen collision events in simulator tests.
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.