Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation
Open accessAbstract
Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. Although learning to navigate in continuous spaces is closer to the real-world, training such an agent is significantly more difficult than training an agent in discrete spaces. However, recent advances in discrete VLN are challenging to translate to continuous VLN due to the domain gap. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environment…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
The augmented data helps boost VLN performance in continuous environments (R2R-CE) by 5% SR.
“it helps boost VLN performance in continuous environments (R2R-CE) [5, 30, 44], a much more realistic but difficult scenario, by 5% SR.”
From Scaling Data Generation in Vision-and-Language Navigation (2023) · cites this paper as [30]
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 [30]
Our augmented ScaleVLN data can benefit the agent's performance in continuous environments with the support of the candidate waypoint predictor.
“Although our augmented ScaleVLN data only contains discrete instruction-trajectory pairs, it can benefit the agent's performance in continuous environments with the support of the candidate waypoint predictor [30] (Table 11).”
From Scaling Data Generation in Vision-and-Language Navigation (2023) · cites this paper as [30]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
Matterport3D: Learning from RGB-D Data in Indoor Environments
Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00081 · Cited by 1,858 · see citing works
AI2-THOR: An Interactive 3D Environment for Visual AI
Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., Weihs, L., Herrasti, A., Deitke, M., Ehsani, K., Gordon, D., Zhu, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.05474 · Cited by 578 · see citing works
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
Tan, H., Yu, L., & Bansal, M. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1268 · Cited by 293 · see citing works
Speaker-Follower Models for Vision-and-Language Navigation
Fried, D., Hu, R., Cirik, V., Rohrbach, A., Andreas, J., Morency, L.-P., Berg-Kirkpatrick, T., Saenko, K., Klein, D., & Darrell, T. (2018) · arXiv · doi:10.48550/arxiv.1806.02724 · Cited by 291 · see citing works
SoundSpaces: Audio-Visual Navigation in 3D Environments
Chen, C., Jain, U., Schissler, C., Gari, S. V. A., Al-Halah, Z., Ithapu, V. K., Robinson, P., & Grauman, K. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_2 · Cited by 202 · see citing works
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Ma, C.-Y., Lu, J., Wu, Z., AlRegib, G., Kira, Z., Socher, R., & Xiong, C. (2019) · arXiv · doi:10.48550/arxiv.1901.03035 · Cited by 200 · see citing works
Learning to Set Waypoints for Audio-Visual Navigation
Chen, C., Majumder, S., Al-Halah, Z., Gao, R., Ramakrishnan, S. K., & Grauman, K. (2020) · arXiv · doi:10.48550/arxiv.2008.09622 · Cited by 53 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Visual Language Maps for Robot Navigation
Huang, C., Mees, O., Zeng, A., & Burgard, W. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160969 · Cited by 376 · see citing works
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
An, D., Wang, H., Wang, W., Wang, Z., Huang, Y., He, K., & Wang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3386695 · Cited by 103 · see citing works
Self-citationGridMM: Grid Memory Map for Vision-and-Language Navigation
Wang, Z., Li, X., Yang, J., Liu, Y., & Jiang, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01432 · Cited by 93 · see citing works
Self-citationScaling Data Generation in Vision-and-Language Navigation
Wang, Z., Li, J., Hong, Y., Wang, Y., Wu, Q., Bansal, M., Gould, S., Tan, H., & Qiao, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01103 · Cited by 64 · see citing works
“Note that in this section, we only present our method to generate instruction-path pairs in R2R-style, which will be shared to address downstream R2R [10], CVDN [75] and R2R-CE [44] tasks.”
BackgroundMethodResultInfluentialSelf-citationEmbodied navigation with multi-modal information: A survey from tasks to methodology
Wu, Y., Zhang, P., Gu, M., Zheng, J., & Bai, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102532 · Cited by 34 · see citing works
- Authors
- Hong, Y., Wang, Z., Wu, Q., & Gould, S.
- Affiliations
- Australian National University (AU)
- The University of Adelaide (AU)
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 15418-15428
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312253995
- Cited by
- 94
- References
- 9
- Citations by year
- 2026: 30 · 2025: 34 · 2024: 15 · 2023: 13 · 2022: 2
- FWCI
- 5.66
- Type
- conference paper
- Language
- en
- Open access
- green
- zenodo.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Automotive Engineering › Spatial Cognition and Navigation
- Keywords
- vision-and-language navigation, waypoint prediction, Matterport3D, imitation learning, cross-modal matching, generalization across environments
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
