cs.RONov 3, 2026

LLM-Assisted Planning with Distributed Onboard Behaviour Tree Execution for Multi-AUV Missions

Authors: Ehsan Khorrambakht, Cristiano Caissutti, Andrea Munafo, Andrea Caiti

Organizations: Department of Information Engineering, University of Pisa Pisa, Italy

Abstract

Coordinating autonomous underwater vehicles requires translating operator intent into feasible assignments while preserving autonomous execution when communication is limited. We present a hierarchical framework that couples Large Language Model (LLM) interpretation of natural-language mission instructions with Mixed-Integer Linear Programming (MILP) and distributed Behaviour Tree (BT) execution. The LLM extracts assignment and ordering constraints, which the MILP optimizer combines with vehicle capabilities and temporal requirements. A BT-LLM Bridge distributes the resulting allocations to onboard BT Mission Managers. Per-vehicle Robotic Agents assess local faults and request selective replanning, allowing unaffected vehicles to continue their assigned tasks. Evaluation in a ROS-based AUV simulator compares Qwen-3-8B and Llama-3.1-8B on constraint extraction and tests recovery from sensor degradation and critical vehicle faults. Qwen-3-8B provides more accurate constraint extraction, and all tasks are completed in the tested failure scenarios. These simulation results support the feasibility of combining language-based mission specification with structured allocation and distributed execution.

Figures & tables

Explore similar work

CardsList
  1. A Cognitive Architecture for Shared Autonomy in AUV Operations

    Aug 29, 2026Niamh Ellis, Thi Tran, Ignacio Carlucho +1Shared AutonomyCognitive Architectures for AI Agents

  2. A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies

    Sep 17, 2026Khalid Halba, Kylie Cooper, James G. BellinghamLanguage Model-Based ControlRobot Failure Recovery

  3. MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning

    Jun 30, 2026Sheng Zhang, Qinglin Li, Yuechao Zang +3Aerial RoboticsLarge Language Model-Based Robot Planning