mlsanityData to 7 Oct 2026

Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification

arXiv 2604.16993 ↗First posted 18 Apr 2026cs.AI cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. However, current agents suffer from a "goal-driven trap", prioritizing physical geometry ("can I go?") over semantic rules ("may I go?"), frequently overlooking subtle regulatory constraints. To bridge this gap, we establish Rule-VLN, the first large-scale urban benchmark for rule-compliant navigation. Spanning a massive 29k-node environment, it injects 177 diverse regulatory categories into 8k constrained nodes across four curriculum levels, challenging agents with fine-grained visual and behavioral constraints. We further propose the Semantic Navigation Rectification Module (SNRM), a universal, zero-shot module designed to equip pre-trained agents with safety awareness. SNRM integrates a coarse-to-fine visual perception VLM framework with an epistemic mental map for dynamic detour planning. Experiments demonstrate that while Rule-VLN challenges state-of-the-art models, SNRM significantly restores navigation capabilities, reducing CVR by 19.26% and boosting TC by 5.97%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 63 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

51 of 63 references.

References · 51

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2025Qwen3-VL Technical Reportcited by 2,534
  4. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  6. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  7. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 655
  8. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  9. 2018On Evaluation of Embodied Navigation Agentscited by 526
  10. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 411
  11. 2023T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generationcited by 253
  12. 2018Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environmentscited by 238
38 more
  1. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  2. 2023SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Modelscited by 174
  3. 2024Pixtral 12Bcited by 174
  4. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  5. 2023Towards Learning a Generalist Model for Embodied Navigationcited by 135
  6. 2022Benchmarking Spatial Relationships in Text-to-Image Generationcited by 96
  7. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 96
  8. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 85
  9. 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street Viewcited by 67
  10. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  11. 2024Visual Prompting in Multimodal Large Language Models: A Surveycited by 52
  12. 2024Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environmentscited by 49
  13. 2024FLAIR: VLM with Fine-grained Language-informed Image Representationscited by 47
  14. 2024VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Modelscited by 46
  15. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  16. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 26
  17. 2022Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areascited by 24
  18. 2023Counting Guidance for High Fidelity Text-to-Image Synthesiscited by 24
  19. 2020Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problemcited by 22
  20. 2023Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environmentscited by 22
  21. 2020Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigationcited by 20
  22. 2024FLAME: Learning to Navigate with Multimodal LLM in Urban Environmentscited by 19
  23. 2025Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Drivingcited by 19
  24. 2024NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigationcited by 18
  25. 2024VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigationcited by 14
  26. 2025Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directionscited by 12
  27. 2024Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigationcited by 11
  28. 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Biascited by 11
  29. 2024Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systemscited by 10
  30. 20243D Question Answering for City Scene Understandingcited by 10
  31. 2024Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environmentscited by 10
  32. 2025GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigationcited by 10
  33. 2025Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigationcited by 8
  34. 2024How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?cited by 7
  35. 2025STRICT: Stress Test of Rendering Images Containing Textcited by 7
  36. 2025HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactionscited by 6
  37. 2024Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environmentcited by 4
  38. 2025CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimationcited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentVLN: Towards Agentic Vision-and-Language Navigation
  2. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
  3. 2026What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
  4. 2026AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
  5. 2026ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
  6. 2025Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
  7. 2026Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models
  8. 2026How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace