arXiv 2510.239882025-10-28cs.RO

基于3D高斯泼溅的协作SLAM综述

A Survey on Collaborative SLAM with 3D Gaussian Splatting

Institute of System Integration, Le Quy Don Technical University, Hanoi, 10000, Vietnam（越南吕文技术大学系统整合研究所）；Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology（日本先进科学技术研究院先进科学技术研究生院）；University of Engineering and Technology, Vietnam National University, Hanoi, 10000, Vietnam（越南国家大学工程技术大学）

Phuc Nguyen Xuan, Thanh Nguyen Canh, Huu-Hung Nguyen, Nak Young Chong, Xiem HoangVan

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该综述系统梳理了基于3DGS的多机器人协作SLAM领域，按架构分类分析核心技术，总结了数据集与评估指标，指出了开放挑战与未来研究方向。

摘要：

本综述全面回顾了利用3D高斯泼溅（3D Gaussian Splatting, 3DGS）的多机器人协作同步定位与地图构建（Simultaneous Localization and Mapping, SLAM）这一不断发展的领域。作为一种显式场景表示方法，3DGS实现了前所未有的实时高保真渲染，非常适用于机器人领域。然而，将其应用于多机器人系统时，在维持全局一致性、管理通信以及融合多源异构数据方面带来了重大挑战。我们按架构（集中式、分布式）对相关方法进行了系统分类，并分析了多智能体一致性与对齐、通信高效的高斯表示、语义蒸馏、融合与位姿优化、实时可扩展性等核心组件。此外，本文还总结了关键数据集和评估指标，为性能评估提供背景。最后，我们指出了关键的开放性挑战，并规划了未来研究方向，包括终身建图、语义关联与建图、提升鲁棒性的多模型方法以及缩小Sim2Real差距。

英文摘要：

This survey comprehensively reviews the evolving field of multi-robot collaborative Simultaneous Localization and Mapping (SLAM) using 3D Gaussian Splatting (3DGS). As an explicit scene representation, 3DGS has enabled unprecedented real-time, high-fidelity rendering, ideal for robotics. However, its use in multi-robot systems introduces significant challenges in maintaining global consistency, managing communication, and fusing data from heterogeneous sources. We systematically categorize approaches by their architecture -- centralized, distributed -- and analyze core components like multi-agent consistency and alignment, communication-efficient, Gaussian representation, semantic distillation, fusion and pose optimization, and real-time scalability. In addition, a summary of critical datasets and evaluation metrics is provided to contextualize performance. Finally, we identify key open challenges and chart future research directions, including lifelong mapping, semantic association and mapping, multi-model for robustness, and bridging the Sim2Real gap.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。