LLM-Assisted Planning with Distributed Onboard Behaviour Tree Execution for Multi-AUV Missions
LLM-Assisted Planning with Distributed Onboard Behaviour Tree Execution for Multi-AUV Missions
This research presents a hierarchical framework that integrates Large Language Models (LLMs) with Mixed-Integer Linear Programming (MILP) and distributed Behavior Tree execution to coordinate autonomous underwater vehicles. The system translates natural-language mission instructions into feasible assignments while maintaining autonomous operation under limited communication. Evaluation in a ROS-based AUV simulator compares Qwen-3-8B and Llama-3.1-8B models on constraint extraction accuracy and recovery from sensor degradation and vehicle faults, with results supporting the feasibility of combining language-based specification with structured allocation.
The study evaluates a hierarchical framework combining LLMs with MILP and distributed behavior trees for multi-AUV missions, demonstrating constraint extraction accuracy and fault recovery in simulation using Qwen-3-8B and Llama-3.1-8B.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- Control
- Reported autonomousOpen source S2
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ased 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
Open source S4
arXiv:2611.04518v1 Announce Type: new 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 Beh
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org