mlsanityData to 14 Oct 2026

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

arXiv 2603.15370 ↗First posted 16 Mar 2026cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and poor robustness to execution perturbations. We present NavGRPO, a reinforcement learning framework that learns goal-directed navigation policies through Group Relative Policy Optimization. By exploring diverse trajectories and optimizing via within-group performance comparisons, our method enables agents to distinguish effective strategies beyond expert paths without requiring additional value networks. Built on ScaleVLN, NavGRPO achieves superior robustness on R2R and REVERIE benchmarks with +3.0% and +1.71% SPL improvements in unseen environments. Under extreme early-stage perturbations, we demonstrate +14.89% SPL gain over the baseline, confirming that goal-directed RL training builds substantially more robust navigation policies. Code and models will be released.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 94 of its 107 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

94 of 107 references.

References · 94

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  3. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  4. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  6. 2025Group Sequence Policy Optimizationcited by 835
  7. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  8. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  9. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
  10. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  11. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  12. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 302
38 more
  1. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  2. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  3. 2019Learning to Navigate Unseen Environments: Back Translation with Environmental Dropoutcited by 244
  4. 2020Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingcited by 231
  5. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  6. 2019Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Taskscited by 179
  7. 2020Improving Vision-and-Language Navigation with Image-Text Pairs from the Webcited by 177
  8. 2019Self-Monitoring Navigation Agent via Auxiliary Progress Estimationcited by 176
  9. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  10. 2023Towards Learning a Generalist Model for Embodied Navigationcited by 138
  11. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  12. 2019Stay on the Path: Instruction Fidelity in Vision-and-Language Navigationcited by 130
  13. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 130
  14. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 124
  15. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  16. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  17. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 117
  18. 2020Topological Planning with Transformers for Vision-and-Language Navigationcited by 116
  19. 2025Geometric-Mean Policy Optimizationcited by 111
  20. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussionscited by 110
  21. 2020Language and Visual Entity Relationship Graph for Agent Navigationcited by 100
  22. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  23. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  24. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  25. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 86
  26. 2018Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigationcited by 84
  27. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  28. 2019Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigationcited by 81
  29. 2019Robust Navigation with Language Pretraining and Stochastic Samplingcited by 77
  30. 2020Object-and-Action Aware Model for Visual Language Navigationcited by 77
  31. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  32. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 72
  33. 2020Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigationcited by 71
  34. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
  35. 2022HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigationcited by 70
  36. 2020Sub-Instruction Aware Vision-and-Language Navigationcited by 66
  37. 2021Less is More: Generating Grounded Navigation Instructions from Landmarkscited by 64
  38. 2024Volumetric Environment Representation for Vision-Language Navigationcited by 63

50 most cited of 94 All 94 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMscited by 2
  2. 2026Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPOcited by 1
  3. 2026Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigationcited by 1
  4. 2026DataClaw0: Agentic Tailoring Multimodal Data from Raw Streamscited by 0
  5. 2026BPG: Balancing Plasticity and Generalization for Domain Incremental Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation
  2. 2024Scaling Vision-and-Language Navigation With Offline RL
  3. 2025TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
  4. 2025SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization
  5. 2026Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments
  6. 2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
  7. 2024Vision-Language Navigation with Energy-Based Policy
  8. 2026Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation