Stochastic Implicit Neural Signed Distance Functions for Safe Motion Planning under Sensing Uncertainty

Carlos Quintero-Pena, Wil Thomason, Zachary Kingston, Anastasios Kyrillidis, Lydia E Kavraki

Keywords: Motion Planning, Sensing Uncertainty, Neural Implicit Representations, Chance-Constrained Planning

TL;DR: We propose a method that directly models sensor-specific aleatoric uncertainty to find safe motions for high-dimensional systems in complex environments, without exact knowledge of environment geometry

Abstract: Motion planning under sensing uncertainty is critical for robots in unstructured environments, to guarantee safety for both the robot and any nearby humans. Most work on planning under uncertainty does not scale to high-dimensional robots such as manipulators, assumes simplified geometry of the robot or environment, or requires per-object knowledge of noise. Instead, we propose a method that models sensor-specific aleatoric uncertainty to find safe motions for high-dimensional systems in complex environments, without exact knowledge of environment geometry. We combine a novel implicit neural model of stochastic signed distance functions with a hierarchical optimization-based motion planner to plan low-risk motions without sacrificing path quality. Our method also explicitly bounds the risk of the path, offering trustworthiness. We empirically validate that our method produces safe motions and accurate risk bounds and is safer than baseline approaches. A version of this paper has been accepted to be published at ICRA 2024.

Submission Number: 16