Evaluating Trajectory Collision Probability through Adaptive Importance Sampling for Safe Motion Planning
This addresses the need for reliable safety assessment in motion planning for robots, though it appears incremental as it builds on existing Monte Carlo methods.
The paper tackles the problem of evaluating the safety of robot trajectories under uncertainty by developing an adaptive importance sampling Monte Carlo framework that provides a certificate of accuracy for probabilistic collision avoidance constraints, with effectiveness demonstrated through numerical experiments.
This paper presents a tool for addressing a key component in many algorithms for planning robot trajectories under uncertainty: evaluation of the safety of a robot whose actions are governed by a closed-loop feedback policy near a nominal planned trajectory. We describe an adaptive importance sampling Monte Carlo framework that enables the evaluation of a given control policy for satisfaction of a probabilistic collision avoidance constraint which also provides an associated certificate of accuracy (in the form of a confidence interval). In particular this adaptive technique is well-suited to addressing the complexities of rigid-body collision checking applied to non-linear robot dynamics. As a Monte Carlo method it is amenable to parallelization for computational tractability, and is generally applicable to a wide gamut of simulatable systems, including alternative noise models. Numerical experiments demonstrating the effectiveness of the adaptive importance sampling procedure are presented and discussed.