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

TL;DR

This paper introduces a novel neural approach to motion planning that explicitly models sensor uncertainty, enabling safe, high-quality paths for complex robots without detailed environment knowledge.

Contribution

It presents a stochastic implicit neural signed distance function model combined with hierarchical planning, explicitly bounding path risk in uncertain environments.

Findings

Produces safe motions with accurate risk bounds

Outperforms baseline approaches in safety metrics

Effective for high-dimensional robots in complex environments

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 directly 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.