Decentralized Intent-Based Multi-Robot Task Planner with LLM Oracles on Hyperledger Fabric

2026-02-09

AI Summary

This work addresses the safety, privacy, and preference bias concerns arising from reliance on a single large language model (LLM) in multi-robot task planning, as well as the limitation of existing LLM aggregation approaches that neglect temporal task structure. To overcome these challenges, we propose a decentralized multi-robot collaboration framework built upon Hyperledger Fabric, featuring an Oracle mechanism composed of LLMs from multiple vendors. This architecture decomposes natural language intents into temporally consistent subtasks and enables cross-vendor robot coordination through fine-grained access control. We further introduce a novel LLM output aggregation method tailored for task planning that explicitly enforces temporal constraints and release the SkillChain-RTD benchmark dataset. Experimental results demonstrate that our approach significantly outperforms existing methods in task planning accuracy.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Safety and Robustness

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• 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

Abstract

Large language models (LLMs) have opened new opportunities for transforming natural language user intents into executable actions. This capability enables embodied AI agents to perform complex tasks, without involvement of an expert, making human-robot interaction (HRI) more convenient. However these developments raise significant security and privacy challenges such as self-preferencing, where a single LLM service provider dominates the market and uses this power to promote their own preferences. LLM oracles have been recently proposed as a mechanism to decentralize LLMs by executing multiple LLMs from different vendors and aggregating their outputs to obtain a more reliable and trustworthy final result. However, the accuracy of these approaches highly depends on the aggregation method. The current aggregation methods mostly use semantic similarity between various LLM outputs, not suitable for robotic task planning, where the temporal order of tasks is important. To fill the gap, we propose an LLM oracle with a new aggregation method for robotic task planning. In addition, we propose a decentralized multi-robot infrastructure based on Hyperledger Fabric that can host the proposed oracle. The proposed infrastructure enables users to express their natural language intent to the system, which then can be decomposed into subtasks. These subtasks require coordinating different robots from different vendors, while enforcing fine-grained access control management on the data. To evaluate our methodology, we created the SkillChain-RTD benchmark made it publicly available. Our experimental results demonstrate the feasibility of the proposed architecture, and the proposed aggregation method outperforms other aggregation methods currently in use.

Problem

• LLM oracle
• multi-robot task planning
• decentralization
• temporal ordering
• access control

Innovation

• LLM Oracle
• Decentralized Multi-Robot Planning
• Hyperledger Fabric
• Temporal-Aware Aggregation
• Intent-Based Task Decomposition