Safe and Efficient Path Planning under Uncertainty via Deep Collision Probability Fields
This addresses safety in autonomous driving and robotics by providing a less conservative and computationally efficient method for collision probability estimation, though it appears incremental as it builds on existing planning frameworks.
The paper tackles the problem of estimating collision probabilities for safe robot path planning under uncertainty by introducing Deep Collision Probability Fields, which uses neural networks to compute probabilities efficiently, achieving reasonably accurate results up to 10^{-3} in experiments.
Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning. This is an important building block of modern planning algorithms in many application scenarios such as autonomous driving, where noisy sensors perceive obstacles. While many approaches exist, they either provide too conservative estimates of the collision probabilities or are computationally intensive due to their sampling-based nature. To deal with these issues, we introduce Deep Collision Probability Fields, a neural-based approach for computing collision probabilities of arbitrary objects with arbitrary unimodal uncertainty distributions. Our approach relegates the computationally intensive estimation of collision probabilities via sampling at the training step, allowing for fast neural network inference of the constraints during planning. In extensive experiments, we show that Deep Collision Probability Fields can produce reasonably accurate collision probabilities (up to 10^{-3}) for planning and that our approach can be easily plugged into standard path planning approaches to plan safe paths on 2-D maps containing uncertain static and dynamic obstacles. Additional material, code, and videos are available at https://sites.google.com/view/ral-dcpf.