Anomaly Management in Multi-Robot Coordination: Detection and Handling Framework for Self-Driving Laboratories

Abstract

This study introduces an innovative framework for anomaly detection and handling in multi-robot collaboration within scientific laboratories, addressing challenges posed by complex procedures and precision equipment. We propose a hierarchical approach utilizing large language models (LLMs) for task planning, action decomposition, and dynamic adjustments. A key innovation is the development of a cross-behavior tree (BT) extension algorithm triggered by anomaly nodes, enabling efficient localization and management of anomalies. Additionally, we present a spatiotemporal coupling strategy to suppress anomaly propagation, minimizing the need for task re-planning. To validate our approach, we constructed a high-fidelity simulation environment and conducted extensive experiments, demonstrating the algorithm’s effectiveness across various scenarios. Experimental results confirm that our method reduces BT node expansion by up to 17.7% and task duration by up to 18.9%, with strong stability and operational efficiency even under high anomaly probabilities. Real-world testing further affirms the system’s flexibility and fault tolerance, underscoring significant advancements in laboratory automation. This work lays the groundwork for pioneering automated anomaly handling mechanisms in future intelligent laboratories. Note to Practitioners—Labs with multiple robots often face disruptions that interrupt runs and consume operator time, such as missing molds or complete material depletion (hybrid anomalies), overturned reagent bottles (spatial issues), and failed retrievals or delayed operations (temporal issues). Our approach detects these issues early and handles them on the spot, allowing the workflow to continue without full re-planning. We adjust timing to avoid knock-on delays and restrict recovery actions to the affected area, which limits propagation and speeds up recovery. This results in fewer manual interventions, shorter downtime, and steadier throughput. We validated the approach in simulation and on physical robots. For deployment, note two limitations: sufficient training data is required for anomaly perception, and standardized workflow cues are needed to guide recovery. With these prerequisites, the method is transferable to chemistry and biology labs and can be extended to industrial settings with additional integration.