Saved in:
Bibliographic Details
Main Authors: Zhou, Haotian, Wang, Xiaole, Li, He, Qi, Zhuo, Yin, Jinrun, Kong, Haiyu, Xu, Jianghuan, Zhao, Huijing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24118
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911494794379264
author Zhou, Haotian
Wang, Xiaole
Li, He
Qi, Zhuo
Yin, Jinrun
Kong, Haiyu
Xu, Jianghuan
Zhao, Huijing
author_facet Zhou, Haotian
Wang, Xiaole
Li, He
Qi, Zhuo
Yin, Jinrun
Kong, Haiyu
Xu, Jianghuan
Zhao, Huijing
contents Navigating to a designated goal using visual information is a fundamental capability for intelligent robots. To address the practical demands of multi-modal, open-vocabulary goal queries and multi-goal visual navigation, we propose LagMemo, a navigation system that leverages a language 3D Gaussian Splatting memory. During a one-time exploration, LagMemo constructs a unified 3D language memory with robust spatial-semantic correlations. With incoming task goals, the system efficiently queries the memory, predicts candidate goal locations, and integrates a local perception-based verification mechanism to dynamically match and validate goals. For fair and rigorous evaluation, we curate GOAT-Core, a high-quality core split distilled from GOAT-Bench. Experimental results show that LagMemo's memory module enables effective multi-modal open-vocabulary localization, and significantly outperforms state-of-the-art methods in multi-goal visual navigation. Project page: https://weekgoodday.github.io/lagmemo
format Preprint
id arxiv_https___arxiv_org_abs_2510_24118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation
Zhou, Haotian
Wang, Xiaole
Li, He
Qi, Zhuo
Yin, Jinrun
Kong, Haiyu
Xu, Jianghuan
Zhao, Huijing
Robotics
Artificial Intelligence
Navigating to a designated goal using visual information is a fundamental capability for intelligent robots. To address the practical demands of multi-modal, open-vocabulary goal queries and multi-goal visual navigation, we propose LagMemo, a navigation system that leverages a language 3D Gaussian Splatting memory. During a one-time exploration, LagMemo constructs a unified 3D language memory with robust spatial-semantic correlations. With incoming task goals, the system efficiently queries the memory, predicts candidate goal locations, and integrates a local perception-based verification mechanism to dynamically match and validate goals. For fair and rigorous evaluation, we curate GOAT-Core, a high-quality core split distilled from GOAT-Bench. Experimental results show that LagMemo's memory module enables effective multi-modal open-vocabulary localization, and significantly outperforms state-of-the-art methods in multi-goal visual navigation. Project page: https://weekgoodday.github.io/lagmemo
title LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2510.24118