LLM-HBT: Dynamic Behavior Tree Construction for Adaptive Coordination in Heterogeneous Robots

2025-10-10

AI Summary

Traditional robots exhibit limited adaptability and robustness in dynamic environments and struggle to autonomously reconfigure collaborative strategies. To address this, we propose a large language model (LLM)-enhanced framework for dynamic behavior tree construction in heterogeneous multi-robot systems. Our method employs a four-module closed-loop architecture that integrates the LLM’s high-level reasoning with the modularity and interpretability of behavior trees, and introduces a virtual coordinator—“Alex”—to enable cross-robot task reallocation and behavioral synchronization. We validate the approach across three simulation scenarios and a real-world café environment, completing 60 tasks. Results demonstrate significant improvements over baseline methods in task success rate, robustness under environmental disturbances, and system scalability. The core contribution is the first deep integration of LLMs into both behavior tree generation and runtime reconfiguration within a closed loop, enabling long-term, adaptive collaborative execution.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

We introduce a novel framework for automatic behavior tree (BT) construction in heterogeneous multi-robot systems, designed to address the challenges of adaptability and robustness in dynamic environments. Traditional robots are limited by fixed functional attributes and cannot efficiently reconfigure their strategies in response to task failures or environmental changes. To overcome this limitation, we leverage large language models (LLMs) to generate and extend BTs dynamically, combining the reasoning and generalization power of LLMs with the modularity and recovery capability of BTs. The proposed framework consists of four interconnected modules task initialization, task assignment, BT update, and failure node detection which operate in a closed loop. Robots tick their BTs during execution, and upon encountering a failure node, they can either extend the tree locally or invoke a centralized virtual coordinator (Alex) to reassign subtasks and synchronize BTs across peers. This design enables long-term cooperative execution in heterogeneous teams. We validate the framework on 60 tasks across three simulated scenarios and in a real-world cafe environment with a robotic arm and a wheeled-legged robot. Results show that our method consistently outperforms baseline approaches in task success rate, robustness, and scalability, demonstrating its effectiveness for multi-robot collaboration in complex scenarios.

Problem

• Dynamic behavior tree construction for adaptive robot coordination
• Overcoming fixed robot limitations in dynamic environments
• Enabling long-term cooperation in heterogeneous multi-robot systems

Innovation

• LLMs dynamically generate behavior trees for robots
• Closed-loop modules enable adaptive task coordination
• Centralized coordinator synchronizes heterogeneous robot behaviors