mlsanityData to 13 Oct 2026

Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation

arXiv 2009.13112 ↗First posted 28 Sep 2020cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Vision-and-Language Navigation (VLN) is a natural language grounding task where an agent learns to follow language instructions and navigate to specified destinations in real-world environments. A key challenge is to recognize and stop at the correct location, especially for complicated outdoor environments. Existing methods treat the STOP action equally as other actions, which results in undesirable behaviors that the agent often fails to stop at the destination even though it might be on the right path. Therefore, we propose Learning to Stop (L2Stop), a simple yet effective policy module that differentiates STOP and other actions. Our approach achieves the new state of the art on a challenging urban VLN dataset Touchdown, outperforming the baseline by 6.89% (absolute improvement) on Success weighted by Edit Distance (SED).

Key facts. Cited by 20 papers in the map (data through 13 Oct 2026). First posted on arXiv 28 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 2; 2024: 3; 2025: 2; 2026: 3.

20 papers.

Sort:

By area:

  1. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 124
  2. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 116
  3. 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street Viewcited by 67
  4. 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
  5. 2021Vision-Language Navigation: A Survey and Taxonomycited by 33
  6. 2021Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Informationcited by 31
  7. 2022One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestonescited by 26
  8. 2022Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areascited by 24
  9. 2022Ground then Navigate: Language-guided Navigation in Dynamic Scenescited by 20
  10. 2024VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigationcited by 14
  11. 2021SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmarkcited by 11
  12. 2024Vision-Language Navigation with Embodied Intelligence: A Surveycited by 9
8 more
  1. 2022FedVLN: Privacy-preserving Federated Vision-and-Language Navigationcited by 8
  2. 2022A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cuescited by 5
  3. 2025City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learningcited by 2
  4. 2026VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructionscited by 2
  5. 2025GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regionscited by 1
  6. 2026DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigationcited by 1
  7. 2024Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigationcited by 0
  8. 2026Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectificationcited by 0