Safe Mission Planning under Dynamical Uncertainties

TL;DR

This paper introduces a probabilistic framework and Monte Carlo method for safe robot mission planning in uncertain dynamical environments, enhancing safety and computational efficiency.

Contribution

It develops a novel probabilistic model for dynamical uncertainties and a Monte Carlo-based planning approach to generate safe paths efficiently.

Findings

The approach effectively maximizes safety in complex missions.

Monte Carlo method improves computational efficiency.

Performance validated through multiple case studies.

Abstract

This paper considers safe robot mission planning in uncertain dynamical environments. This problem arises in applications such as surveillance, emergency rescue, and autonomous driving. It is a challenging problem due to modeling and integrating dynamical uncertainties into a safe planning framework, and finding a solution in a computationally tractable way. In this work, we first develop a probabilistic model for dynamical uncertainties. Then, we provide a framework to generate a path that maximizes safety for complex missions by incorporating the uncertainty model. We also devise a Monte Carlo method to obtain a safe path efficiently. Finally, we evaluate the performance of our approach and compare it to potential alternatives in several case studies.