ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
Open accessThe DOI matches its Crossref record; 92 of the 92 references it cites were found in a registry or an index.
Abstract
Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. It becomes increasingly crucial in the field of embodied AI, with potential applications in autonomous navigation, search and rescue, and human-robot interaction. In this paper, we propose to address a more practical yet challenging counterpart setting - vision-language navigation in continuous environments (VLN-CE). To develop a robust VLN-CE agent, we propose a new navigation framework, ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments. ETPNav performs online topological mapping of environments by self-organizing predicted waypoints along a traversed path, without prior environmental experience. It privileges the agent to break down the navigation procedure into high-level planning and low-level control. Concurrently, ETPNav utilizes a transformer-based cross-modal planner to generate navigation plans based on topological maps and instructions. The plan is then performed through an obstacle-avoiding controller that leverages a trial-and-error heuristic to prevent navigation from getting stuck in obstacles. Experimental results demonstrate the effectiveness of the proposed method. ETPNav yields more than 10% and 20% improvements over prior state-of-the-art on R2R-CE and RxR-CE datasets, respectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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 cited source says what the claim attributes to it.
In the citing paper
“More recently, GridMM30 builds a top-down dense grid memory map that aggregates fine-grained visual features via cross-modal attention (essentially modeling localized route knowledge), whereas ETPNav32 dynamically evolves sparse topological nodes in continuous environments (leaning towards a reasoning-capable landmark representation).”
From Brain-inspired spatial intelligence for embodied agents (2026) · cites this paper as [32]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
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 · cited 2×
“For visual encoding, we use ViT-B/32 [89] pre-trained in CLIP [90] to encode RGB images as [11], and ResNet-50 [91] pre-trained in point-goal navigation [13] to encode depth images following [6].”
Self-citationVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 2×
“For node encoding, the standard self-attention layer [17] only considers visual similarity among nodes, which may overlook nearby nodes which are more relevant than distant nodes.”
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 5×
“Each word embedding wi is added a positional embedding [76] corresponding to the position of the word in the sentence and a type embedding for text [77].”
InfluentialAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472 · cited 1×
“For visual encoding, we use ViTB/32 [81] pre-trained in CLIP [82] to encode RGB images as [11], and ResNet-50 [83] pre-trained in point-goal navigation [12] to encode depth images following [6].”
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“Our experiments were performed using the PyTorch framework [85] and executed on two NVIDIA RTX 3090 GPUs.”
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 3×
“Specifically, RecBERT [9], HAMT [5] and DUET [17] are transferred into VLN-CE where we align their controllers and model configurations with ETPNav’s ( e.g. , the CLIP-ViT-B/32 [90] visual encoder, depth-only waypoint and topological map).”
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 1×
“Researchers have investigated explicit metric spatial representations [59], and examined the construction of these representations using various sensors [60], [61], as well as how to locate agents with such representations [62], [63].”
A fast marching level set method for monotonically advancing fronts.
Sethian, J. A. (1996) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.93.4.1591 · Cited by 3,221 · cited 2×
“Lastly, we conclude this work in § 5.”
Research works printed but not linked: 6
- [13] E. Wijmans, A. Kadian, A. Morcos, S. Lee, I. Essa, D. Parikh, M. Savva, and D. Batra, 'Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames,' in International Conference on Learning Representations , 2019. -
- [24] J. Thomason, M. Murray, M. Cakmak, and L. Zettlemoyer, 'Visionand-dialog navigation,' in Conference on Robot Learning . PMLR, 2020, pp. 394-406. -
- [28] D. Fried, R. Hu, V. Cirik, A. Rohrbach, J. Andreas, L.-P. Morency, T. Berg-Kirkpatrick, K. Saenko, D. Klein, and T. Darrell, 'Speakerfollower models for vision-and-language navigation,' Advances in Neural Information Processing Systems , vol. 31, pp. 3318-3329, 2018. -
- [70] D. S. Chaplot, M. Dalal, S. Gupta, J. Malik, and R. R. Salakhutdinov, 'Seal: Self-supervised embodied active learning using exploration and 3d consistency,' Advances in Neural Information Processing Systems , vol. 34, pp. 13 086-13 098, 2021. -
- [85] H. Luo, A. Yue, Z.-W. Hong, and P. Agrawal, 'Stubborn: A strong baseline for indoor object navigation,' in IEEE/RSJ International Conference on Intelligent Robots and Systems . IEEE, 2022, pp. 32873293. -
- [92] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, 'Roberta: A robustly optimized bert pretraining approach,' arXiv preprint arXiv:1907.11692 , 2019. - · arXiv
Cited by
Items 101–104 of 104
Seeing Space in RGB: Spatially Enhanced Zero-Shot Vision-and-Language Navigation
Hu, H., Li, S., & Liu, J. (2026) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1109/ccris71163.2026.11721606
“Another line of work introduces waypoint-based planning, where candidate subgoals guide local movement [12], [13].”
Li, L., Huang, C., Zhang, R., Ren, X., & Shen, Y. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3746085
“Such waypoint predictors have become a key component of many VLN-CE models [4], [10], [11].”
EdgeCurator: Efficient Cross-Modal Grounding for Real-Time Language-Guided UAV Navigation
Peng, S., & Wang, R. (2026) · doi:10.1145/3840749.3841574
EBM-Nav: energy-based model for zero-shot visual navigation via implicit scene representation
Tang, M., Wan, J., & Dang, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01323-z
Metadata
- Authors
- An, D., Wang, H., Wang, W., Wang, Z., Huang, Y., He, K., & Wang, L.
- Affiliations
- University of Chinese Academy of Sciences (CN)
- Beijing Institute of Technology (CN)
- Zhejiang University (CN)
- Australian National University (AU)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2025-07
- Volume
- 47
- Issue
- 7
- Pages
- 5130-5145
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4394627367
- Cited by
- 103
- References
- 92
- Citations by year
- 2026: 42 · 2025: 40
- FWCI
- 13.79
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Key R&D Program of China (2022ZD0117900)
- National Natural Science Foundation of China (62236010, 62276261, 62322607, 62372405)
- CCF-Tencent Open Fund
- 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 › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Keywords
- vision-and-language navigation, continuous environments, topological mapping, waypoint generation, obstacle avoidance, embodied AI
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.