OSDAG: Online Scheduling for Efficient Multi-Robot Collaboration

2026-06-13

AI Summary

This work addresses the high latency and resource underutilization in existing large language model (LLM)-based heterogeneous multi-robot coordination approaches, which stem from redundant reasoning and offline scheduling. The authors propose a novel framework that integrates one-shot LLM-based task decomposition with directed acyclic graph (DAG) modeling: a single LLM invocation generates a task graph encoding inter-task dependencies, and a lightweight online scheduler dynamically assigns ready tasks to idle robots in real time. This approach is the first to unify LLM inference with DAG-constrained online parallel scheduling, enabling efficient coordination under both resource and sequencing constraints. Experiments across five benchmark scenarios demonstrate 5–15× faster inference compared to conversational methods, up to 38% reduction in task completion time, higher success rates, and validated efficacy in both simulated and real-world dual-arm manipulation tasks.

Abstract

Coordinating heterogeneous multi-robot systems (MRS) for complex, long-horizon tasks requires both flexible high-level reasoning and efficient low-level scheduling. Existing LLM-based approaches address the reasoning side but introduce two critical bottlenecks: (1) repeated LLM inference during execution, which inflates latency with agent count, and (2) offline, pre-committed scheduling, which forces robots to idle while waiting for sequentially ordered predecessors even when independent work is available. This paper presents OSDAG, a novel framework that integrates LLM-based task reasoning with Directed Acyclic Graph (DAG) representation and constraint-aware online scheduling. The LLM is invoked once to decompose a natural-language instruction into a dependency-annotated task graph, and a lightweight online scheduler then allocates ready tasks to idle agents in real time. The DAG representation encodes both precedence and resource constraints, ensuring correctness while exposing all available parallelism. Experiments across five benchmark scenarios demonstrate that OSDAG achieves 5-15x faster reasoning time compared to dialogue-based methods, reduces makespan by up to 38% over sequential baselines, and maintains competitive success rates. Both simulation and real-world experiments on dual-arm manipulation tasks validate the effectiveness and practicality of the proposed approach for efficient multi-robot coordination. The website and resources are available at http://thanhnguyencanh.github.io/LLM_DAG4MultiRobot

Problem

• multi-robot coordination
• online scheduling
• task parallelism
• LLM-based reasoning
• makespan reduction

Innovation

• Online Scheduling
• Directed Acyclic Graph (DAG)
• LLM-based Task Planning
• Multi-Robot Coordination
• Constraint-aware Scheduling