AlphaAdj uses a VLM to dynamically adjust Control Barrier Function parameters in real-time for safe and efficient robotic navigation.
March 24, 2026
Original Paper
Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation
arXiv · 2603.21142
The Takeaway
It bridges high-level semantic risk perception with low-level control theory. This allows robots to be aggressive in safe areas and cautious in hazardous ones, improving navigation efficiency by 18.5% while maintaining strict safety guarantees.
From the 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