mlsanityData to 14 Oct 2026

LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation

arXiv 2510.24118 ↗First posted 28 Oct 2025cs.RO cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 40 of its 43 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

40 of 43 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  6. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  7. 2023Segment Everything Everywhere All at Oncecited by 548
  8. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  9. 2023Gaussian Splatting SLAMcited by 415
  10. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  11. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  12. 2022Visual Language Maps for Robot Navigationcited by 365
28 more
  1. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  2. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  3. 2024A Survey on 3D Gaussian Splattingcited by 224
  4. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 208
  5. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 205
  6. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 196
  7. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  8. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  9. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  10. 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 145
  11. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 117
  12. 2022Navigating to Objects in the Real Worldcited by 106
  13. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 94
  14. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 93
  15. 2023GOAT: GO to Any Thingcited by 89
  16. 2024VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Modelcited by 57
  17. 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigationcited by 57
  18. 2022Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instancescited by 55
  19. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  20. 2023SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real Worldcited by 48
  21. 2022Retrospectives on the Embodied AI Workshopcited by 46
  22. 2022Topological Semantic Graph Memory for Image-Goal Navigationcited by 45
  23. 2022Stubborn: A Strong Baseline for Indoor Object Navigationcited by 32
  24. 2024Prioritized Semantic Learning for Zero-shot Instance Navigationcited by 31
  25. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  26. 2024One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigationcited by 13
  27. 2025IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigationcited by 11
  28. 2025Online Language Splattingcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Memory Over Maps: 3D Object Localization Without Reconstructioncited by 1
  2. 2026Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worldscited by 0