Reachability-based Trajectory Design with Neural Implicit Safety Constraints

Abstract

Generating safe motion plans in real-time is a key requirement for deploying robot manipulators to assist humans in collaborative settings.In particular, robots must satisfy strict safety requirements to avoid self-damage or harming nearby humans.Satisfying these requirements is particularly challenging if the robot must also operate in real-time to adjust to changes in its environment.This paper addresses these challenges by proposing Reachability-based Signed Distance Functions (RDFs) as a neural implicit representation for robot safety.RDF, which can be constructed using supervised learning in a tractable fashion, accurately predicts the distance between the swept volume of a robot arm and an obstacle.RDF's inference and gradient computations are fast and scale linearly with the dimension of the system; these features enable its use within a novel real-time trajectory planning framework as a continuoustime collision-avoidance constraint.The planning method using RDF is compared to a variety of state-of-the-art techniques and is demonstrated to successfully solve challenging motion planning tasks for high-dimensional systems faster and more reliably than all tested methods.Code, data, and video demonstrations can be found at https://roahmlab.github.