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.”
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1514 · Cited by 2,319 · cited 7×
“In the pre-training stage, we initialize the model with pre-trained LXMERT on the R2R-CE dataset and pre-trained RoBerta [92] for the multilingual RxR-CE dataset.”
InfluentialUsing occupancy grids for mobile robot perception and navigation
Elfes, A. (1989) · Computer · doi:10.1109/2.30720 · Cited by 2,213 · 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].”
DTAM: Dense tracking and mapping in real-time
Newcombe, R. A., Lovegrove, S. J., & Davison, A. J. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126513 · Cited by 2,078 · 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 Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Ross, S., Gordon, G. J., & Bagnell, J. A. (2018) · Carnegie Mellon University · doi:10.1184/r1/6550949 · Cited by 1,941
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
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621 · cited 1×
“We leverage scheduled sampling [87] to train the model, shifting from teacher-forcing to studentforcing with a decay frequency of per 3000 iterations and decay ratio of 0.”
Monte Carlo localization for mobile robots
Dellaert, F., Fox, D., Burgard, W., & Thrun, S. (2003) · Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C) · doi:10.1109/robot.1999.772544 · Cited by 1,620 · 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].”
Habitat: A Platform for Embodied AI Research
Savva, M., Kadian, A., Maksymets, O., Zhao, Y., Wijmans, E., Jain, B., Straub, J., Liu, J., Koltun, V., Malik, J., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00943 · Cited by 1,237 · cited 6×
“We conduct experiments on R2R-CE and RxR-CE datasets, which are created by converting discrete paths of R2R [1] and RxR [19] datasets into continuous environments through the Habitat Simulator [55].”
InfluentialAnderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sunderhauf, N., Reid, I., Gould, S., & van den Hengel, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00387 · Cited by 1,187
Multimodal learning with transformers: A survey
Xu, P., Zhu, X., & Clifton, D. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275156 · Cited by 1,072 · cited 1×
“Lastly, we conclude this work in § 5.”
A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations
Kuipers, B., & Byun, Y.-T. (1991) · Robotics and Autonomous Systems · doi:10.1016/0921-8890(91)90014-c · Cited by 707 · cited 1×
“Thus, nonmetric topological representations have also been considered in classical literature [70], [71], and researchers have investigated the use of semantic topo maps for high-level navigation tasks [72], [73].”
Choset, H., & Nagatani, K. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.928558 · Cited by 624 · cited 1×
“Thus, nonmetric topological representations have also been considered in classical literature [70], [71], and researchers have investigated the use of semantic topo maps for high-level navigation tasks [72], [73].”
On evaluation of embodied navigation agents
Anderson, P., Chang, A., Chaplot, D. S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., Savva, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1807.06757 · Cited by 622 · cited 1×
“As in [1], [79], [80], we adopt the following navigation metrics.”
Wang, X., Huang, Q., Celikyilmaz, A., Gao, J., Shen, D., Wang, Y.-F., Wang, W. Y., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00679 · Cited by 522 · cited 3×
“This task has been well-studied over the past few years [2], [3], [4], [5], however, the majority of works focus on the discrete VLN setting.”
Self-citationHistory Aware Multimodal Transformer for Vision-and-Language NavigationPreprint
Chen, S., Guhur, P.-L., Schmid, C., & Laptev, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13309 · Cited by 422 · cited 4×
“The same as [5], [9], [77], we set the layers’ number of the panorama encoder, the text encoder, and the cross-modal graph encoder as 2, 9, 4, respectively.”
InfluentialTOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
Chen, H., Suhr, A., Misra, D., Snavely, N., & Artzi, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01282 · Cited by 343 · cited 2×
“R2R [1] and RxR [22] datasets introduce low-level human language instructions and photo-realistic environments for indoor navigation, while Touchdown [23] further extends this task in an outdoor navigation context.”
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
Qi, Y., Wu, Q., Anderson, P., Wang, X., Wang, W. Y., Shen, C., & van den Hengel, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01000 · Cited by 331 · cited 2×
“Following these works, dialogue-based navigation such as CVDN [21] and HANNA [22], and navigation for remote object-finding such as REVERIE [23] and SOON [24] have been proposed for further research.”
Self-citationObject Goal Navigation using Goal-Oriented Semantic Exploration
Chaplot, D. S., Gandhi, D., Gupta, A., & Salakhutdinov, R. (2020) · arXiv · doi:10.48550/arxiv.2007.00643 · Cited by 321 · cited 1×
“Modern literature has begun to integrate spatial representations with semantics, yielding promising results in various tasks, such as object-goal navigation [64], [65], vision-language navigation [15], [57], [66], and active perception [67], [68].”
Learning to explore using active neural SLAM
Chaplot, D. S., Gandhi, D., Gupta, S., Gupta, A., & Salakhutdinov, R. (2020) · arXiv · doi:10.48550/arxiv.2004.05155 · Cited by 318 · cited 1×
“Modern literature has begun to integrate spatial representations with semantics, yielding promising results in various tasks, such as object-goal navigation [64], [65], vision-language navigation [15], [57], [66], and active perception [67], [68].”
Udin, S. B., & Fawcett, J. W. (1988) · Annual Review of Neuroscience · doi:10.1146/annurev.ne.11.030188.001445 · Cited by 300 · cited 1×
“Topo maps, partially inspired by cognitive science [13], typically depict environments as low-dimensional graph representations with nodes for places and edges for reachability.”
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 · cited 2×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [31], [35], [36], [37], [38] or synthesis new instructions [25], [39], [40], [41], [42].”
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 · cited 2×
“Early VLN methods use sequence-to-sequence LSTMs to predict low-level actions [1] or high-level actions from panoramas [28].”
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
Ku, A., Anderson, P., Patel, R., Ie, E., & Baldridge, J. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.356 · Cited by 274
Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
Krantz, J., Wijmans, E., Majumdar, A., Batra, D., & Lee, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58604-1_7 · Cited by 266
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training
Hao, W., Li, C., Li, X., Carin, L., & Gao, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01315 · Cited by 264
VLN↻BERT: A Recurrent Vision-and-Language BERT for Navigation
Hong, Y., Wu, Q., Qi, Y., Rodriguez-Opazo, C., & Gould, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00169 · Cited by 264 · cited 3×
“This task has been well-studied over the past few years [2], [3], [4], [5], however, the majority of works focus on the discrete VLN setting.”
Neural Topological SLAM for Visual Navigation
Singh Chaplot, D., Salakhutdinov, R., Gupta, A., & Gupta, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01289 · Cited by 241 · cited 2×
“This map shares a similar structure with [78], which abstracts the visited or observed locations along the traversed path as a graph representation, denoted as G t = ⟨ N t , E t ⟩ at step t .”
Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
Majumdar, A., Shrivastava, A., Lee, S., Anderson, P., Parikh, D., & Batra, D. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_16 · Cited by 201
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 · cited 1×
“Various attention mechanisms [26], [27], [28], [29] are proposed to improve the learning of visualtextual correspondence.”
Wang, X., Xiong, W., Wang, H., & Wang, W. Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_3 · Cited by 186 · cited 1×
“Reinforcement learning is also explored to improve policy learning [2], [30], [31], [32].”
Self-citationThink Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
Chen, S., Guhur, P.-L., Tapaswi, M., Schmid, C., & Laptev, I. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01604 · Cited by 180 · cited 6×
“In VLN, several works have employed topo maps and demonstrated superior performance [3], [16], [17], [54].”
InfluentialThomason, J., Murray, M., Cakmak, M., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1907.04957 · Cited by 173 · cited 1×
“Following these works, dialogue-based navigation such as CVDN [24] and HANNA [25], and navigation for remote object-finding such as REVERIE [26] and SOON [27] have been proposed for further research.”
Weakly-Supervised Multi-Granularity Map Learning for Vision-And-Language Navigation
Chen, P., Ji, D., Lin, K., Zeng, R., Lin, K., Tan, M., & Gan, C. (2022) · neural information processing systems · doi:10.52202/068431-2764 · Cited by 160
MapNet: An Allocentric Spatial Memory for Mapping Environments
Henriques, J. F., & Vedaldi, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00884 · Cited by 146 · 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].”
Airbert: In-domain Pretraining for Vision-and-Language Navigation
Guhur, P.-L., Tapaswi, M., Chen, S., Laptev, I., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00166 · Cited by 139 · cited 1×
“Recently, transformer-based models have shown superior performance thanks to their powerful ability to learn generic multi-modal representations [43], [44], [45].”
Language and Visual Entity Relationship Graph for Agent NavigationPreprint
Hong, Y., Rodríguez-Opazo, C., Qi, Y., Wu, Q., & Gould, S. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09304 · Cited by 137 · cited 1×
“Various attention mechanisms [26], [27], [28], [29] are proposed to improve the learning of visualtextual correspondence.”
SOON: Scenario Oriented Object Navigation with Graph-based Exploration
Zhu, F., Liang, X., Zhu, Y., Yu, Q., Chang, X., & Liang, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01250 · Cited by 130 · cited 2×
“Following these works, dialogue-based navigation such as CVDN [21] and HANNA [22], and navigation for remote object-finding such as REVERIE [23] and SOON [24] have been proposed for further research.”
Navigating to objects in the real world
Gervet, T., Chintala, S., Batra, D., Malik, J., & Chaplot, D. S. (2023) · Science Robotics · doi:10.1126/scirobotics.adf6991 · Cited by 125
Dreamwalker: Mental Planning for Continuous Vision-Language Navigation
Wang, H., Liang, W. G., Gool, L. V., & Wang, W. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00998 · Cited by 125 · cited 1×
“Recognizing the navigation graph assumption cannot reflect the challenges a deployed system would experience in a real environment, Krantz et al. [6] introduce VLN in continuous environments (VLN-CE) - requiring the agent to navigate”
Self-citationStructured Scene Memory for Vision-Language Navigation
Wang, H., Wang, W., Liang, W., Xiong, C., & Shen, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00835 · Cited by 123 · cited 5×
“This task has been well-studied over the past few years [2], [3], [4], [5], however, the majority of works focus on the discrete VLN setting.”
InfluentialSelf-citationNguyen, K., & Daumé III, H. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1063 · Cited by 115 · cited 1×
“Following these works, dialogue-based navigation such as CVDN [24] and HANNA [25], and navigation for remote object-finding such as REVERIE [26] and SOON [27] have been proposed for further research.”
Topological Planning with Transformers for Vision-and-Language Navigation
Chen, K., Chen, J. K., Chuang, J., Vazquez, M., & Savarese, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01112 · Cited by 113 · cited 3×
“Notably, this scheme is greatly distinct from previous VLN literature regarding topo mapping, which requires either predefined graphs [3], [14], [15] or environment pre-exploration [16].”
Sim-to-Real Transfer for Vision-and-Language NavigationPreprint
Anderson, P., Shrivastava, A., Truong, J., Majumdar, A., Parikh, D., Batra, D., & Lee, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03807 · Cited by 110
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language NavigationPreprint
Deng, Z., Narasimhan, K., & Russakovsky, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05655 · Cited by 107 · cited 4×
“In VLN, several works have employed topo maps and demonstrated superior performance [3], [14], [15], [50].”
InfluentialObject-and-action aware model for visual language navigation
Qi, Y., Pan, Z., Zhang, S., van den Hengel, A., & Wu, Q. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58607-2_18 · Cited by 100
Waypoint Models for Instruction-guided Navigation in Continuous Environments
Krantz, J., Gokaslan, A., Batra, D., Lee, S., & Maksymets, O. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01488 · Cited by 94
Hong, Y., Wang, Z., Wu, Q., & Gould, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01500 · Cited by 94 · cited 10×
“The predictor is pre-trained on the MP3D graph dataset [9], and its parameters are fixed.”
InfluentialSelf-citationSOAT: A Scene- and Object-Aware Transformer for Vision-and-Language NavigationPreprint
Moudgil, A., Majumdar, A., Agrawal, H., Lee, S., & Batra, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14143 · Cited by 91 · cited 1×
“This scheme is further extended by recurrent agent state [4], [46], [47], episodic memory [5], [48], [49], graph memory [15], [50], [51] and prompt learning [52], [53] that significantly improves sequential action prediction.”
Envedit: Environment Editing for Vision-and-Language Navigation
Li, J., Tan, H., & Bansal, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01497 · Cited by 87 · cited 1×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [31], [35], [36], [37], [38] or synthesis new instructions [25], [39], [40], [41], [42].”
LANA: A Language-Capable Navigator for Instruction Following and Generation
Wang, X., Wang, W., Shao, J., & Yang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01826 · Cited by 85
Self-citationFILM: Following Instructions in Language with Modular Methods
Min, S. Y., Chaplot, D. S., Ravikumar, P., Bisk, Y., & Salakhutdinov, R. (2021) · arXiv · doi:10.48550/arxiv.2110.07342 · Cited by 81 · cited 1×
“Modern literature has begun to integrate spatial representations with semantics, yielding promising results in various tasks, such as object-goal navigation [64], [65], vision-language navigation [15], [57], [66], and active perception [67], [68].”
Vision-Language Navigation with Random Environmental Mixup
Liu, C., Zhu, F., Chang, X., Liang, X., Ge, Z., & Shen, Y.-D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00167 · Cited by 80 · cited 1×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [34], [38], [39], [40], [41] or synthesis new instructions [28], [42], [43], [44], [45], [46].”
Qi, Y., Pan, Z., Hong, Y., Yang, M.-H., van den Hengel, A., & Wu, Q. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00168 · Cited by 80 · cited 1×
“This scheme is further extended by recurrent agent state [4], [46], [47], episodic memory [5], [48], [49], graph memory [15], [50], [51] and prompt learning [52], [53] that significantly improves sequential action prediction.”
Cross-modal Map Learning for Vision and Language Navigation
Georgakis, G., Schmeckpeper, K., Wanchoo, K., Dan, S., Miltsakaki, E., Roth, D., & Daniilidis, K. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01502 · Cited by 79 · cited 3×
“This idea is further extended with semantic maps for better perception of environments [57], [58], finding increased performance but still far below VLN.”
Visual Graph Memory with Unsupervised Representation for Visual Navigation
Kwon, O., Kim, N., Choi, Y., Yoo, H., Park, J., & Oh, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01559 · Cited by 77 · cited 1×
“Thus, nonmetric topological representations have also been considered in classical literature [70], [71], and researchers have investigated the use of semantic topo maps for high-level navigation tasks [72], [73].”
Retrospectives on the Embodied AI WorkshopPreprint
Deitke, M., Batra, D., Bisk, Y., Campari, T., Chang, A. X., Chaplot, D. S., Chen, C., Pérez-D’Arpino, C., Ehsani, K., Farhadi, A., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.06849 · Cited by 77 · cited 1×
“Based on the algorithm described in this paper, we won the CVPR 2022 RxR-Habitat Challenge [11], [18].”
Active visual information gathering for vision-language navigation
Wang, H., Wang, W., Shu, T., Liang, W., & Shen, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58542-6_19 · Cited by 74
Self-citationNeighbor-view Enhanced Model for Vision and Language Navigation
An, D., Qi, Y., Huang, Y., Wu, Q., Wang, L., & Tan, T. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475282 · Cited by 74 · cited 1×
“Various attention mechanisms [29], [30], [31], [32] are proposed to improve the learning of visual-textual correspondence.”
Self-citationNo RL, No Simulation: Learning to Navigate without NavigatingPreprint
Hahn, M., Chaplot, D. S., Tulsiani, S., Mukadam, M., Rehg, J. M., & Gupta, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09470 · Cited by 72 · cited 1×
“Thus, Krantz et al. [8] propose to decouple the navigation process as subgoal planning and low-level control, where the model predicts a language-conditioned waypoint as subgoal at each step, and then reaches the subgoal with a rotate-then-forward control flow.”
Bird’s-Eye-View Scene Graph for Vision-Language Navigation
Liu, R., Wang, X., Wang, W., & Yang, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01007 · Cited by 65 · cited 1×
“This scheme is further extended by recurrent agent state [4], [50], [51], episodic memory [5], [52], [53], graph memory [17], [54], [55], [56], [57] and prompt learning [58], [59] that significantly improves sequential action prediction.”
Self-citationCounterfactual Vision-and-Language Navigation: Unravelling the Unseen
Parvaneh, A., Abbasnejad, E., Teney, D., Shi, Q., & van den Hengel, A. (2020) · neural information processing systems · Cited by 63
Raychaudhuri, S., Wani, S., Patel, S., Jain, U., & Chang, A. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.328 · Cited by 60 · cited 3×
“…has been shown far more difficult than VLN, with a few published works revealing episode success rates less than half of those reported in VLN. Early efforts for VLN-CE are end-to-end trained systems to directly predict low-level actions (or waypoints) from language and observations [6], [7], [8].”
InfluentialSoft Expert Reward Learning for Vision-and-Language Navigation
Wang, H., Wu, Q., & Shen, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58545-7_8 · Cited by 57
Self-citationSim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments
Krantz, J., & Lee, S. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19842-7_34 · Cited by 56
Wang, H., Liang, W., Shen, J., Van Gool, L., & Wang, W. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01503 · Cited by 55 · cited 1×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [34], [38], [39], [40], [41] or synthesis new instructions [28], [42], [43], [44], [45], [46].”
Self-citationTarget-Driven Structured Transformer Planner for Vision-Language Navigation
Zhao, Y., Chen, J., Gao, C., Wang, W., Yang, L., Ren, H., Xia, H., & Liu, S. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548281 · Cited by 54 · cited 2×
“In VLN, several works have employed topo maps and demonstrated superior performance [3], [16], [17], [54].”
Self-citationMultimodal Transformer with Variable-Length Memory for Vision-and-Language Navigation
Lin, C., Jiang, Y., Cai, J., Qu, L., Haffari, G., & Yuan, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20059-5_22 · Cited by 50
ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Lin, B., Zhu, Y., Chen, Z., Liang, X., Liu, J., & Liang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01496 · Cited by 49 · cited 1×
“This scheme is further extended by recurrent agent state [4], [46], [47], episodic memory [5], [48], [49], graph memory [15], [50], [51] and prompt learning [52], [53] that significantly improves sequential action prediction.”
HOP+: History-Enhanced and Order-Aware Pre-Training for Vision-and-Language Navigation
Qiao, Y., Qi, Y., Hong, Y., Yu, Z., Wang, P., & Wu, Q. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3234243 · Cited by 49 · cited 1×
“This scheme is further extended by recurrent agent state [4], [50], [51], episodic memory [5], [52], [53], graph memory [17], [54], [55], [56], [57] and prompt learning [58], [59] that significantly improves sequential action prediction.”
Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
Liang, X., Zhu, F., Lingling, L., Xu, H., & Liang, X. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.332 · Cited by 46
Less is More: Generating Grounded Navigation Instructions from Landmarks
Wang, S., Montgomery, C., Orbay, J., Birodkar, V., Faust, A., Gur, I., Jaques, N., Waters, A., Baldridge, J., & Anderson, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01499 · Cited by 45 · cited 5×
“We leverage the discrete paths in the R2R and RxR datasets for pre-training purposes and augment the data using synthetic instructions from Prevalent [43] and RxR-Markey [40].”
InfluentialThe Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
Zhao, X., Agrawal, H., Batra, D., & Schwing, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01582 · Cited by 41
Irshad, M. Z., Chowdhury Mithun, N., Seymour, Z., Chiu, H.-P., Samarasekera, S., & Kumar, R. (2022) · 2022 26th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr56361.2022.9956561 · Cited by 39 · cited 1×
“Initial methods for VLN-CE are end-to-end trained systems to directly predict low-level actions from language and observations [6], [7], [56], but demonstrate a huge performance gap to VLN.”
Kamath, A., Anderson, P., Wang, S., Koh, J. Y., Ku, A., Waters, A., Yang, Y., Baldridge, J., & Parekh, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01041 · Cited by 39 · cited 1×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [34], [38], [39], [40], [41] or synthesis new instructions [28], [42], [43], [44], [45], [46].”
On the Evaluation of Vision-and-Language Navigation Instructions
Zhao, M., Anderson, P., Jain, V., Wang, S., Ku, A., Baldridge, J., & Ie, E. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.111 · Cited by 35
Active Perception for Visual-Language Navigation
Wang, H., Wang, W., Liang, W., Hoi, S. C. H., Shen, J., & Gool, L. V. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01721-6 · Cited by 32 · cited 1×
“Different strategies are also investigated to form a more robust navigation policy, such as environment pre-exploration [2], active perception [33], [34], and planning with graph memory [3], [14].”
Self-citationOmnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation
Chen, J., Wang, W., Liu, S., Li, H., & Yang, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01009 · Cited by 28 · cited 7×
“During fine-tuning, the agent interacts with the environments online through the Habitat Simulator [61] and is supervised by the teacher node generated by the demonstrator ∗ .”
InfluentialSelf-citationHwang, M., Jeong, J., Kim, M., Oh, Y., & Oh, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00646 · Cited by 26 · cited 1×
“This scheme is further extended by recurrent agent state [4], [46], [47], episodic memory [5], [48], [49], graph memory [15], [50], [51] and prompt learning [52], [53] that significantly improves sequential action prediction.”
Learning to Follow and Generate Instructions for Language-Capable Navigation
Wang, X., Wang, W., Shao, J., & Yang, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3341828 · Cited by 23 · cited 1×
“To enhance an agent’s generalization ability to novel environments, various data augmentation strategies are studied to mimic new environments [34], [38], [39], [40], [41] or synthesis new instructions [28], [42], [43], [44], [45], [46].”
Self-citationBEVBert: Multimodal Map Pre-training for Language-guided Navigation
An, D., Qi, Y., Li, Y., Huang, Y., Wang, L., Tan, T., & Shao, J. (2022) · arXiv · doi:10.48550/arxiv.2212.04385 · Cited by 20 · cited 1×
“This scheme is further extended by recurrent agent state [4], [50], [51], episodic memory [5], [52], [53], graph memory [17], [54], [55], [56], [57] and prompt learning [58], [59] that significantly improves sequential action prediction.”
Self-citation1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)
An, D., Wang, Z., Li, Y., Wang, Y., Hong, Y., Huang, Y., Wang, L., & Shao, J. (2022) · arXiv · doi:10.48550/arxiv.2206.11610 · Cited by 6 · cited 11×
“Moreover, our model also generalizes well on the test unseen split, as it outperforms Sim2Sim [10] by 11% on SR and 11% on SPL. Reborn [11] serves as the initial version for the 2022 RxRHabitat Challenge.”
BackgroundMethodInfluentialSelf-citationGeneral Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping
Ilharco, G., Jain, V., Ku, A., Ie, E., & Baldridge, J. (2019) · arXiv · doi:10.48550/arxiv.1907.05446 · cited 1×
“As in [1], [79], [80], we adopt the following navigation metrics.”
Research works printed but not linked: 4
- Wijmans, DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames
- Chaplot, SEAL: Self-supervised embodied active learning using exploration and 3D consistency, 34, 13086
- Luo, Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 3287
- 10.5555/3454287.3455008 · doi:10.5555/3454287.3455008
Cited by
Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI
Liu, Y., Chen, W., Bai, Y., Liang, X., Li, G., Gao, W., & Lin, L. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3574943 · Cited by 527
“BGBL [129] and ETPNav [132] used a similar method to design a waypoint predictor that can predict movable path points in a continuous environment based on the observation of the current navigation graph node.”
Scaling 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) · arXiv · doi:10.48550/arxiv.2307.15644 · Cited by 64
“Similar to prior work [4, 5, 81], our HAMT agent in R2R-CE leverages a candidate waypoint predictor [30] which predicts navigable locations to support agent’s high-level decision-making process.”
ResultSelf-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
“Similar to prior work [4, 5, 81], our HAMT agent in R2R-CE leverages a candidate waypoint predictor [30] which predicts navigable locations to support agent’s high-level decision-making process.”
ResultSelf-citationDreamwalker: Mental Planning for Continuous Vision-Language Navigation
Wang, H., Liang, W. G., Gool, L. V., & Wang, W. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00998 · Cited by 125
“Later approaches attempt to reproduce the success of the abstract VLN in the continuous counterpart, by building a high-level action space based on online prediction of waypoints [70, 30, 45, 83, 4].”
BackgroundSelf-citationVolumetric Environment Representation for Vision-Language Navigation
Liu, R., Wang, W., & Yang, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01544 · Cited by 126
“Existing VLN models introduce various representations for environment modeling, including topological graphs [2, 11, 16, 19, 32, 81], and semantic spatial representations [1, 4, 12, 26, 34, 38, 56, 74, 93].”
BackgroundSelf-citation
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.