Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

TL;DR

This paper introduces Code-as-Monitor (CaM), a vision-language model-based framework for real-time, constraint-aware failure detection in robotic systems, capable of both reactive and proactive monitoring in complex environments.

Contribution

It presents a unified approach using VLM-generated code for simultaneous reactive and proactive failure detection, with geometric constraint elements for improved accuracy and efficiency.

Findings

Achieves 28.7% higher success rate in failure detection.

Reduces execution time by 31.8% under severe disturbances.

Enables long-horizon tasks in cluttered, dynamic scenes.

Abstract

Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively after they occur and prevent foreseeable ones proactively. To this end, we propose Code-as-Monitor (CaM), a novel paradigm leveraging the vision-language model (VLM) for both open-set reactive and proactive failure detection. The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitoring. To enhance the accuracy and efficiency of monitoring, we further introduce constraint elements that abstract constraint-related entities or their parts into compact geometric elements. This approach offers greater generality, simplifies tracking, and facilitates constraint-aware visual programming by leveraging these elements as visual prompts. Experiments show that CaM achieves a 28.7% higher success rate and reduces execution time by 31.8% under severe disturbances compared to baselines across three simulators and a real-world setting. Moreover, CaM can be integrated with open-loop control policies to form closed-loop systems, enabling long-horizon tasks in cluttered scenes with dynamic environments.