Cross-Modal Navigation with Multi-Agent Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shuo, Li, Xinzichen, Amato, Christopher
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911658336583680
author Liu, Shuo
Li, Xinzichen
Amato, Christopher
author_facet Liu, Shuo
Li, Xinzichen
Amato, Christopher
contents Robust embodied navigation relies on complementary sensory cues. However, high-quality and well-aligned multi-modal data is often difficult to obtain in practice. Training a monolithic model is also challenging as rich multi-modal inputs induce complex representations and substantially enlarge the policy space. Cross-modal collaboration among lightweight modality-specialized agents offers a scalable paradigm. It enables flexible deployment and parallel execution, while preserving the strength of each modality. In this paper, we propose \textbf{CRONA}, a Multi-Agent Reinforcement Learning (MARL) framework for \textbf{Cro}ss-Modal \textbf{Na}vigation. CRONA improves collaboration by leveraging control-relevant auxiliary beliefs and a centralized multi-modal critic with global state. Experiments on visual-acoustic navigation tasks show that multi-agent methods significantly improve performance and efficiency over single-agent baselines. We find that homogeneous collaboration with limited modalities is sufficient for short-range navigation under salient cues; heterogeneous collaboration among agents with complementary modalities is generally efficient and effective; and navigation in large, complex environments requires both richer multi-modal perception and increased model capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06595
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Modal Navigation with Multi-Agent Reinforcement Learning
Liu, Shuo
Li, Xinzichen
Amato, Christopher
Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
Robust embodied navigation relies on complementary sensory cues. However, high-quality and well-aligned multi-modal data is often difficult to obtain in practice. Training a monolithic model is also challenging as rich multi-modal inputs induce complex representations and substantially enlarge the policy space. Cross-modal collaboration among lightweight modality-specialized agents offers a scalable paradigm. It enables flexible deployment and parallel execution, while preserving the strength of each modality. In this paper, we propose \textbf{CRONA}, a Multi-Agent Reinforcement Learning (MARL) framework for \textbf{Cro}ss-Modal \textbf{Na}vigation. CRONA improves collaboration by leveraging control-relevant auxiliary beliefs and a centralized multi-modal critic with global state. Experiments on visual-acoustic navigation tasks show that multi-agent methods significantly improve performance and efficiency over single-agent baselines. We find that homogeneous collaboration with limited modalities is sufficient for short-range navigation under salient cues; heterogeneous collaboration among agents with complementary modalities is generally efficient and effective; and navigation in large, complex environments requires both richer multi-modal perception and increased model capacity.
title Cross-Modal Navigation with Multi-Agent Reinforcement Learning
topic Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2605.06595