CoChat
Sign Up
Cited by 56Reinforcement Learning in RoboticsMultimodal Machine Learning ApplicationsSpatial Cognition and Navigation

Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments

Open access
Krantz, Jacob, Lee, Stefan·2022·Lecture Notes in Computer Science
DOI 10.1007/978-3-031-19842-7_34
Open this paper in CoChat — free accountOpen PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-031-19842-7_34

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Navigation agents trained with rendered views perform significantly worse than agents trained with high-quality images.

    “Previous work has shown that navigation agents trained with rendered views will perform significantly worse than agents trained with high-quality images [43].”

    From Scaling Data Generation in Vision-and-Language Navigation (2023) · cites this paper as [43]

    Section 5.2 (pp. 8–9) reports that performance drops when an agent trained on high-quality MP3D panoramas is evaluated on Habitat renders. That is a change in evaluation images, not a finding that training on renders performs worse. The paper instead says that training on Habitat renders almost entirely eliminates the gap. (LLM, conf=0.91)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

  • The process toward large-scale training involves key sub-problems such as building navigation graphs, recovering corrupted rendered images, and generating navigational instructions, which significantly influence the quality of collected data.

    “the process towards such large-scale training involves solving a series of key sub-problems such as how to build navigation graphs [10, 30, 37], how to recover corrupted rendered images [8, 43], and how to generate navigational instructions [23, 25, 78, 83], which significantly influence the quality of collected data”

    From Scaling Data Generation in Vision-and-Language Navigation (2023) · cites this paper as [43]

    Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 20

  1. [1]1. Anderson, P., Chang, A., Chaplot, D.S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., Savva, M., et al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018) · arXiv
  2. [2]2. Anderson, P., Shrivastava, A., Truong, J., Majumdar, A., Parikh, D., Batra, D., Lee, S.: Sim-to-real transfer for vision-and-language navigation. In: CoRL (2020)
  3. [3]3. Anderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sünderhauf, N., Reid, I., Gould, S., van den Hengel, A.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)
  4. [4]4. Blukis, V., Terme, Y., Niklasson, E., Knepper, R.A., Artzi, Y.: Learning to map natural language instructions to physical quadcopter control using simulated flight. In: CoRL (2020)
  5. [6]6. Chaplot, D.S., Gandhi, D., Gupta, S., Gupta, A., Salakhutdinov, R.: Learning to explore using active neural slam. In: ICLR (2020)
  6. [7]7. Chen, K., Chen, J.K., Chuang, J., Vázquez, M., Savarese, S.: Topological planning with transformers for vision-and-language navigation. In: CVPR (2021)
  7. [8]8. Chen, S., Guhur, P.L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. In: NeurIPS (2021)
  8. [9]9. Cuturi, M.: Sinkhorn distances: Lightspeed computation of optimal transport. NeurIPS (2013)
  9. [13]13. Hahn, M., Chaplot, D.S., Tulsiani, S., Mukadam, M., Rehg, J.M., Gupta, A.: No rl, no simulation: learning to navigate without navigating. In: NeurIPS (2021)
  10. [14]14. Hao, W., Li, C., Li, X., Carin, L., Gao, J.: Towards learning a generic agent for vision-and-language navigation via pre-training. In: CVPR (2020)
  11. [17]17. Irshad, M.Z., Mithun, N.C., Seymour, Z., Chiu, H.P., Samarasekera, S., Kumar, R.: Sasra: semantically-aware spatio-temporal reasoning agent for vision-and-language navigation in continuous environments. arXiv preprint arXiv:2108.11945 (2021) · arXiv
  12. [18]18. Kadian, A., Truong, J., Gokaslan, A., Clegg, A., Wijmans, E., Lee, S., Savva, M., Chernova, S., Batra, D.: Are we making real progress in simulated environments? measuring the sim2real gap in embodied visual navigation. In: IROS (2020)
  13. [19]19. Krantz, J., Gokaslan, A., Batra, D., Lee, S., Maksymets, O.: Waypoint models for instruction-guided navigation in continuous environments. In: ICCV (2021)
  14. [20]20. Krantz, J., Wijmans, E., Majumdar, A., Batra, D., Lee, S.: Beyond the nav-graph: vision-and-language navigation in continuous environments. In: ECCV (2020)
  15. [21]21. Majumdar, A., Shrivastava, A., Lee, S., Anderson, P., Parikh, D., Batra, D.: Improving vision-and-language navigation with image-text pairs from the web. In: ECCV (2020)
  16. [22]22. Manolis Savva*, Abhishek Kadian*, Oleksandr Maksymets*, Zhao, Y., Wijmans, E., Jain, B., Straub, J., Liu, J., Koltun, V., Malik, J., Parikh, D., Batra, D.: Habitat: a platform for embodied ai research. In: ICCV (2019)
  17. [23]23. Quigley, M., Conley, K., Gerkey, B.P., Faust, J., Foote, T., Leibs, J., Wheeler, R., Ng, A.Y.: Ros: an open-source robot operating system. In: ICRA Workshop on Open Source Software (2009)
  18. [24]24. Raychaudhuri, S., Wani, S., Patel, S., Jain, U., Chang, A.X.: Language-aligned waypoint (law) supervision for vision-and-language navigation in continuous environments. In: EMNLP (2021)
  19. [26]26. Wang, X., Huang, Q., Celikyilmaz, A., Gao, J., Shen, D., Wang, Y.F., Wang, W.Y., Zhang, L.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: CVPR (2019)
  20. [27]27. Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: A 10 million image database for scene recognition. TPAMI (2017)

Cited by

Sorted by citations

Authors
Krantz, J., & Lee, S.
Affiliations
Oregon State University (US)
Corresponding author
Krantz, Jacob
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer Nature Switzerland
Published
2022
Pages
588-603
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-031-19842-7_34
OpenAlex
W4312996039
Cited by
56
References
8
Citations by year
2026: 19 · 2025: 22 · 2024: 9 · 2023: 6
FWCI
4.81
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Defense Advanced Research Projects Agency
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Engineering › Automotive Engineering › Spatial Cognition and Navigation
Keywords
vision-and-language navigation, performance degradation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review