Enforcing safety for vision-based controllers via Control Barrier Functions and Neural Radiance Fields

TL;DR

This paper introduces a novel approach combining neural radiance fields with control barrier functions to ensure safety in vision-based robotic control, enabling real-time safety guarantees from high-dimensional visual data.

Contribution

It proposes integrating NeRFs with CBFs to provide visual foresight, addressing the challenge of ensuring safety using high-dimensional image feedback.

Findings

Successfully prevents robots from unsafe actions in real-time simulations

Enables safety certification directly from visual inputs

Demonstrates real-time applicability in complex environments

Abstract

To navigate complex environments, robots must increasingly use high-dimensional visual feedback (e.g. images) for control. However, relying on high-dimensional image data to make control decisions raises important questions; particularly, how might we prove the safety of a visual-feedback controller? Control barrier functions (CBFs) are powerful tools for certifying the safety of feedback controllers in the state-feedback setting, but CBFs have traditionally been poorly-suited to visual feedback control due to the need to predict future observations in order to evaluate the barrier function. In this work, we solve this issue by leveraging recent advances in neural radiance fields (NeRFs), which learn implicit representations of 3D scenes and can render images from previously-unseen camera perspectives, to provide single-step visual foresight for a CBF-based controller. This novel combination is able to filter out unsafe actions and intervene to preserve safety. We demonstrate the effect of our controller in real-time simulation experiments where it successfully prevents the robot from taking dangerous actions.