Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation

TL;DR

This paper introduces AlphaAdj, a real-time navigation framework that uses vision-language models to adapt control barrier function parameters, balancing safety and efficiency in dynamic environments.

Contribution

It presents a novel method to dynamically adjust safety constraints in robot navigation using vision-language models and real-time risk estimation.

Findings

Maintains collision-free navigation in dynamic environments.

Improves efficiency by up to 18.5% over fixed parameters.

Enhances robustness and success rate compared to uncapped baselines.

Abstract

Robots operating in dynamic, unstructured environments must balance safety and efficiency under potentially limited sensing. While control barrier functions (CBFs) provide principled collision avoidance via safety filtering, their behavior is often governed by fixed parameters that can be overly conservative in benign scenes or overly permissive near hazards. We present AlphaAdj, a vision-to-control navigation framework that uses egocentric RGB input to adapt the conservativeness of a CBF safety filter in real time. A vision-language model(VLM) produces a bounded scalar risk estimate from the current camera view, which we map to dynamically update a CBF parameter that modulates how strongly safety constraints are enforced. To address asynchronous inference and non-trivial VLM latency in practice, we combine a geometric, speed-aware dynamic cap and a staleness-gated fusion policy with lightweight implementation choices that reduce end-to-end inference overhead. We evaluate AlphaAdj across multiple static and dynamic obstacle scenarios in a variety of environments, comparing against fixed-parameter and uncapped ablations. Results show that AlphaAdj maintains collision-free navigation while improving efficiency (in terms of path length and time to goal) by up to 18.5% relative to fixed settings and improving robustness and success rate relative to an uncapped baseline.