Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing

TL;DR

This paper introduces CoDiG, a diffusion guidance framework that incorporates barrier functions to enable real-time, constraint-aware obstacle avoidance in autonomous racing robots, demonstrating safety and efficiency.

Contribution

The paper presents a novel, data-efficient method integrating barrier functions into diffusion models for constraint-aware robotic control, especially in dynamic environments.

Findings

CoDiG achieves real-time obstacle avoidance in autonomous racing.

The framework ensures safety constraints are satisfied during operation.

Experimental results confirm its effectiveness in dynamic, real-world scenarios.

Abstract

Diffusion models hold great potential in robotics due to their ability to capture complex, high-dimensional data distributions. However, their lack of constraint-awareness limits their deployment in safety-critical applications. We propose Constraint-Aware Diffusion Guidance (CoDiG), a data-efficient and general-purpose framework that integrates barrier functions into the denoising process, guiding diffusion sampling toward constraint-satisfying outputs. CoDiG enables constraint satisfaction even with limited training data and generalizes across tasks. We evaluate our framework in the challenging setting of miniature autonomous racing, where real-time obstacle avoidance is essential. Real-world experiments show that CoDiG generates safe outputs efficiently under dynamic conditions, highlighting its potential for broader robotic applications. A demonstration video is available at https://youtu.be/KNYsTdtdxOU.