MA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLN

TL;DR

MA-CoNav introduces a hierarchical multi-agent framework with dual-level reflection for improved long-horizon vision-language navigation, effectively distributing perception, planning, and memory functions to enhance performance in complex environments.

Contribution

The paper proposes a novel Master-Slave multi-agent architecture with a dual-stage reflection mechanism, enabling better distribution of tasks and dynamic optimization in VLN tasks.

Findings

Outperforms existing VLN methods on real-world indoor datasets

No scene-specific fine-tuning required for the models

Demonstrates significant improvements across multiple evaluation metrics

Abstract

Vision-Language Navigation (VLN) aims to empower robots with the ability to perform long-horizon navigation in unfamiliar environments based on complex linguistic instructions. Its success critically hinges on establishing an efficient ``language-understanding -- visual-perception -- embodied-execution'' closed loop. Existing methods often suffer from perceptual distortion and decision drift in complex, long-distance tasks due to the cognitive overload of a single agent. Inspired by distributed cognition theory, this paper proposes MA-CoNav, a Multi-Agent Collaborative Navigation framework. This framework adopts a ``Master-Slave'' hierarchical agent collaboration architecture, decoupling and distributing the perception, planning, execution, and memory functions required for navigation tasks to specialized agents. Specifically, the Master Agent is responsible for global orchestration, while the Subordinate Agent group collaborates through a clear division of labor: an Observation Agent generates environment descriptions, a Planning Agent performs task decomposition and dynamic verification, an Execution Agent handles simultaneous mapping and action, and a Memory Agent manages structured experiences. Furthermore, the framework introduces a ``Local-Global'' dual-stage reflection mechanism to dynamically optimize the entire navigation pipeline. Empirical experiments were conducted using a real-world indoor dataset collected by a Limo Pro robot, with no scene-specific fine-tuning performed on the models throughout the process. The results demonstrate that MA-CoNav comprehensively outperforms existing mainstream VLN methods across multiple metrics.