mlsanityData to 7 Oct 2026

Navi-Agent: Unlocalized Monocular Navigation Agent

arXiv 2609.20388 ↗First posted 17 Sep 2026cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to execute long-horizon instructions in unknown environments. Existing zero-shot VLN-CE systems typically maintain spatial states through geometric localization or coordinate-based representations. Recent geometry-constrained navigation removes depth and globally consistent coordinates, but maintaining persistent spatial awareness for place confirmation, progress verification, and recovery remains challenging. We present Navi-Agent, a zero-shot VLN-CE agent that constructs a coordinate-free spatial state from visual observations and executed motion histories. Navi-Agent organizes this state as a navigation topology, where nodes represent visual places and edges represent motion transitions. This representation enables observation-based approximate self-localization, task progress verification, and visual revisitation-based recovery. Navi-Agent performs closed-loop navigation by decomposing instructions into sub-goals, executing local visual navigation, and verifying visited places through the constructed spatial state. Experiments on zero-shot VLN-CE benchmark and real-world robot platforms show that Navi-Agent achieves state-of-the-art performance among geometry-constrained methods while remaining competitive with approaches relying on geometric localization.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

31 of 40 references.

References · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Segment Anythingcited by 8,158
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  6. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  7. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  8. 2025OpenAI GPT-5 System Cardcited by 910
  9. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  10. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  11. 2022Visual Language Maps for Robot Navigationcited by 362
  12. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 357
19 more
  1. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 274
  2. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 268
  3. 2023ViNT: A Foundation Model for Visual Navigationcited by 210
  4. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 201
  5. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  6. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 150
  7. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 127
  8. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 125
  9. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 117
  10. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussionscited by 108
  11. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 85
  12. 2024Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMscited by 60
  13. 2024Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environmentscited by 49
  14. 2025SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigationcited by 29
  15. 2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigationcited by 15
  16. 2025GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigationcited by 10
  17. 2025Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigationcited by 6
  18. 2026LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMscited by 1
  19. 2026MVP-Nav: Multi-layer Value Map Planner Navigatorcited by 1

Built on by

Not cited yet.