Regularized Deep Signed Distance Fields for Reactive Motion Generation

TL;DR

This paper introduces ReDSDF, a neural implicit function that efficiently computes smooth, high-resolution signed distance fields for dynamic obstacle avoidance and human-robot interaction, enabling safer and more responsive robotic behaviors.

Contribution

The paper presents ReDSDF, a novel neural implicit approach for real-time, scalable distance field computation applicable to articulated bodies and dynamic environments.

Findings

ReDSDF achieves smooth distance field computation at any scale.

It performs effectively in simulated whole-body control and HRI tasks.

Proof of concept demonstrated in real-world robot handover scenario.

Abstract

Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting both humans and their hardware. However, different applications require different distance resolutions, leading to various heuristic approaches for measuring distance fields w.r.t. obstacles, which are computationally expensive and hinder their application in dynamic obstacle avoidance use-cases. We propose Regularized Deep Signed Distance Fields (ReDSDF), a single neural implicit function that can compute smooth distance fields at any scale, with fine-grained resolution over high-dimensional manifolds and articulated bodies like humans, thanks to our effective data generation and a simple inductive bias during training. We demonstrate the effectiveness of our approach in representative simulated tasks for whole-body control (WBC) and safe Human-Robot Interaction (HRI) in shared workspaces. Finally, we provide proof of concept of a real-world application in a HRI handover task with a mobile manipulator robot.