Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions
This work addresses the need for adaptable and reliable robot control in domestic or industrial settings by improving BT generation, though it is incremental as it builds on existing BT methods with new integration of LLMs and optimal planning.
The paper tackles the problem of generating Behavior Trees (BTs) from human instructions for robots by proposing a two-stage framework that uses large language models (LLMs) for intent understanding and an optimal planning algorithm (OBTEA) for BT construction, resulting in validated proficiency in goal interpretation and demonstrated superiority over baselines in metrics like efficiency and deployability.
Robots executing tasks following human instructions in domestic or industrial environments essentially require both adaptability and reliability. Behavior Tree (BT) emerges as an appropriate control architecture for these scenarios due to its modularity and reactivity. Existing BT generation methods, however, either do not involve interpreting natural language or cannot theoretically guarantee the BTs' success. This paper proposes a two-stage framework for BT generation, which first employs large language models (LLMs) to interpret goals from high-level instructions, then constructs an efficient goal-specific BT through the Optimal Behavior Tree Expansion Algorithm (OBTEA). We represent goals as well-formed formulas in first-order logic, effectively bridging intent understanding and optimal behavior planning. Experiments in the service robot validate the proficiency of LLMs in producing grammatically correct and accurately interpreted goals, demonstrate OBTEA's superiority over the baseline BT Expansion algorithm in various metrics, and finally confirm the practical deployability of our framework. The project website is https://dids-ei.github.io/Project/LLM-OBTEA/.