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
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 534
“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 128
“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 129
“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-citationGraph neural networks in vision-language image understanding: a survey
Senior, H., Slabaugh, G., Yuan, S., & Rossi, L. (2024) · The Visual Computer · doi:10.1007/s00371-024-03343-0 · Cited by 57
Embodied 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
Yue, L., Zhou, D., Xie, L., Zhang, F., Yan, Y., & Yin, E. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3387171 · Cited by 55
“To avoid slow convergence brought by end-to-end baselines [10], Krantz et al. [8], Hong et al. [12], Wang et al. [13] and An et al. [14] adopted a hierarchical framework by training a waypoint predictor module to obtainlocal candidatewaypoints.”
BackgroundMethodInfluentialGaussNav: Gaussian Splatting for Visual Navigation
Lei, X., Wang, M., Zhou, W., & Li, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3538496 · Cited by 101
“E MBODIED visual navigation is an emerging computer vision problem where an agent uses visual sensing to actively interact with the world and perform navigation tasks [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12].”
Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Song, X., Chen, W., Liu, Y., Chen, W., Li, G., & Lin, L. (2025) · 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/cvpr52734.2025.01128 · Cited by 133
“The second category, waypoint prediction-based methods, includes models such as ETPNav [1] and MultiPLY [11], which optimize navigation through key-point prediction and environmental graph learning, thereby supporting improved generalization across discrete and continuous environments [10].”
Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction
Dong, Y., Wang, L., Zhou, S., Hua, G., & Sun, C. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3493966 · Cited by 29
“This task is crucial in various applications such as autonomous driving [2], [3], [4], visual recognition [5], [6], [7], navigation [8], [9], [10], and video surveillance [11], [12], [13].”
Self-citationConstraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments
Chen, K., An, D. U., Huang, Y., Xu, R., Su, Y., Ling, Y., Reid, I. D., & Wang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3594204 · Cited by 91
“to guide navigation [2], [3].”
InfluentialSelf-citationESceme: Vision-and-Language Navigation with Episodic Scene Memory
Zheng, Q., Liu, D., Wang, C., Zhang, J., Wang, D., & Tao, D. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02159-8 · Cited by 36
“AuxRN [62] fine-tunes the agent in unseen environments with auxiliary tasks.”
Wen, S., Zhang, Z., Sun, Y., & Wang, Z. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3540577 · Cited by 22
“In terms of action executors, both our method and the method in [15] use a point navigation strategy, which outperforms the FMM method in [14], but slightly trails behind the RF method in [5].”
InfluentialSelf-citationEmbodied AI: From LLMs to World Models [Feature]
Feng, T., Wang, X., Jiang, Y., & Zhu, W. (2025) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2025.3603693 · Cited by 75
“Recent progress in LLMs/MLLMs [23], [24] and WMs [25], [26], [27] have progressively shown promise in overcoming these challenges.”
Instruction-guided path planning with 3D semantic maps for vision-language navigation
Wang, Z., Li, M., Wu, M., Moens, M., & Tuytelaars, T. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129457 · Cited by 23
Self-citationEvaluation of Topological Mapping Methods in Indoor Environments
Muravyev, K., & Yakovlev, K. (2023) · IEEE Access · doi:10.1109/access.2023.3335818 · Cited by 17
“In the work [18], a topological map consisting of locations connected in case of direct visibility is built for solving the Visual-Language Navigation task.”
BackgroundMethodInfluentialNavigation Instruction Generation with BEV Perception and Large Language Models
Fan, S., Liu, R., Wang, W., & Yang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72670-5_21 · Cited by 40
Self-citationEnhancing Large Language Models with RAG for Visual Language Navigation in Continuous Environments
Bao, X., Lv, Z., & Wu, B. (2025) · Electronics · doi:10.3390/electronics14050909 · Cited by 16
“To achieve more precise navigation planning in continuous environments, researchers have proposed a series of methods that improve navigation from various perspectives [5–7 , 16– 18 ].”
SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation
Shi, X., Li, Z., Lyu, W., Xia, J., Dayoub, F., Qiao, Y., & Wu, Q. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246147 · Cited by 63
“Besides, BEVBert [38] and ETPNav [17] require the construction of pre-mapped real-world environments, making the comparison inequitable.”
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
“For long-range context modeling and effective multi-modal represetation learning, recent solutions were developed with environment map [42], [43], [44], [45], [46], [47], transformer architectures [48], [49], [50], [51], [52], and large-scale pre-training [53], [54], [55], [56].”
BackgroundSelf-citationg3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
Wang, Z., & Lee, G. H. (2025) · 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/cvpr52734.2025.01324 · Cited by 45
“Some works use a topological map [2, 10] or BEV map [1, 32, 55] to represent semantic relationships between waypoints, while some [56, 57] explore feature fields to predict waypoint representations of novel views and improve navigation planning.”
Self-citation3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation
Gao, J., Liu, R., & Wang, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00864 · Cited by 22
“Subsequent map-based meth-ods introduce more explicit scene modeling, such as topological graphs [2, 7, 13, 16, 69] and top-down semantic maps [1, 11, 31, 47, 77].”
Self-citationMind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation
Taioli, F., Rosa, S., Castellini, A., Natale, L., Bue, A. D., Farinelli, A., Cristani, M., & Wang, Y. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801822 · Cited by 23
“In this section, we first introduce VLN in Continuous Environments (VLN-CE); then, we define the types of instruction errors and finally formalize our novel task of Detection and Localization of Instruction Errors .”
InfluentialNavigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments
Hong, H., Wang, S., Huang, Z. H., Wu, Q., & Liu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681640 · Cited by 17
“In VLN, ETP-Nav [3] applies an obstacle-avoiding controller with a trial-and-error heuristic to explicitly escape from deadlocks.”
MethodResultMossVLN: Memory-Observation Synergistic System for Continuous Vision-Language Navigation
Yu, T., Wu, Y., Cui, Q., Huang, Q., & Yu, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3586105 · Cited by 24
“To tackle the challenges posed by VLN-CE, more recently methods [16], [17], [18], [19], [20], [21], [22], [23], [24], [25] have been developed to address the absence of predefined navigation maps and the challenges associated with the inability to utilize long trajectory learning, due to imprecise…”
InfluentialPart2Object: Hierarchical Unsupervised 3D Instance Segmentation
Shi, C., Zhang, Y., Yang, B., Tang, J., Ma, Y., & Yang, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72649-1_1 · Cited by 17
Controllable Navigation Instruction Generation with Chain of Thought Prompting
Kong, X., Chen, J., Wang, W., Su, H., Hu, X., Yang, Y., & Liu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73397-0_3 · Cited by 40
“…instructions, and the ability to manipulate landmarks within the instructions (§1). tasks is vision-and-language navigation (VLN) [5], which has garnered extensive research interest [26, 31, 44, 45, 48, 51, 54, 72] and developed fast in recent years [2,3,9,17–19,23,34,39,40,49,59–61,64,70].”
BackgroundSelf-citationMultiple Visual Features in Topological Map for Vision-and-Language Navigation
Liu, R., Kong, P., & Zhang, W. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10803061 · Cited by 10
“These candidate waypoints are then transformed into nodes within the topological map by a waypoint localization function [15].”
InfluentialSanyal, S., & Roy, K. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3592138 · Cited by 22
“Room2Room [23] enables teleoperated communication using augmented reality, and [24] introduces the ‘Tryout’ method to prevent collision-related navigational stalls.”
Bio-inspired cognitive navigation for robots
Hao, Z., Guo, B., Ding, Y., Li, L., Liu, S., Gao, T., Liu, S., & Yu, Z. (2026) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-026-00294-7 · Cited by 7
“For instance, reinforcement learning can generate a step-by-step plan to distant goals across diverse environments 97,98 .”
Multimodal Pretrained Knowledge for Real-world Object Navigation
Yuan, H. L., Huang, Y., Yu, N., Zhang, D., Du, Z., Liu, Z., & Zhang, K. (2025) · Machine Intelligence Research · doi:10.1007/s11633-024-1537-x · Cited by 10
Self-citationTransformer-Driven Semantic-Spatial Adaptive Fusion Representation for Object-Goal Navigation
Yang, N., Lu, F., Li, X., Tian, G., Li, Z., & Fu, T. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3593344 · Cited by 4
“To support navigation in continuous space, [51] abstracts visited or observed locations into a graph and proposes an online mapping approach via waypoint self-organization, enabling robust long-range planning.”
DOPE: Dual Object Perception-Enhancement Network for Vision-and-Language Navigation
Yu, Y., & Yang, D. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733315 · Cited by 20
Ground-Level Viewpoint Vision-and-Language Navigation in Continuous Environments
Li, Z., Zhou, G., Hong, H., Shao, Y., Lyu, W., Qiao, Y., & Wu, Q. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127275 · Cited by 17
“We propose to adaptively gather information from previous unobstructed angles along the trajectory from the previous SoTA method ETPNav [36] on VLN-CE.”
Learning and grounding visual multimodal adaptive graph for visual navigation
Zhou, K., Wang, J., Xu, W., Song, L., Ye, Z., Guo, C., & Li, C. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103009 · Cited by 8
Stable Trajectory Planning for Quadruped Robots Using Terrain Features at Feet End
Li, C., Lin, S., Qu, S. L., Liu, Z., Yang, Q.-J., Meng, M. Q. ‐., & Sun, Y. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3645657 · Cited by 3
“It reduces dimensionality, saving storage and computation time, making it suitable for large-scale environments [21].”
monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation
Lu, R., Zhou, Y., Cheng, H., Meng, J., & Zheng, W.-S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00884 · Cited by 9
“The depth images D t are used to predict the coordinates of nearby navigable waypoints[3, 21, 34], enabling the update of the topological map from M t − 1 to M t .”
InfluentialRobust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Qi, M., Lv, C., & Ma, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3627224 · Cited by 21
“Such reasoning remains a signifi-cant challenge for machine intelligence, yet it is essential for applications like robot navigation [3] and augmented or virtual Fig.”
Taioli, F., Zorzi, E., Franchi, G., Castellini, A., Farinelli, A., Cristani, M., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01745 · Cited by 25
“…in Large Language Models (LLMs) and Vision-Language Models (VLMs) have significantly reinvig-orated research on language-driven navigation tasks [1, 3, 19, 23, 56], where a human engages with embodied agents via natural language only, the most intuitive human-agent interaction among other forms…”
I2EDL: Interactive Instruction Error Detection and Localization
Taioli, F., Rosa, S., Castellini, A., Natale, L., Bue, A. D., Farinelli, A., Cristani, M., & Wang, Y. (2024) · IEEE RO-MAN · doi:10.1109/ro-man60168.2024.10731349 · Cited by 3
“We then define the instruction embedding as Υ i ∈ R W × D , i.e., the instruction I i is tokenized and padded up to W = 80 tokens, while D is the dimension of the latent space in which each token is projected, following [12], [13].”
BackgroundMethodKong, P., Liu, R., Xie, Z., & Pang, Z. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127961 · Cited by 5
“The experiments are conducted on the VLN-CE dataset [10] and results indicate that our approach outperforms state-of-the-art methods.”
InfluentialMobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots
Huang, T., Li, D., Yang, R., Zhang, Z., Yang, Z., & Tang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37196-6_19 · Cited by 17
Exploratory UAV Autonomous Visual Navigation With Spatiotemporal Cognition
Jia, H., He, H., Chao, E., & Zhang, B. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3647148 · Cited by 3
“[36] constructedVLN-CEintelligentagentsEvolvingTopological PlanningforVisionLanguageNavigation,decomposethenavi-gationprocessintotwolevels:high-levelplanningandlow-level control, generate detailed navigation plans based on topology diagrams and instructions, and finally generate precise execution…”
A comprehensive review of recent advancements in vision-and-language navigation
Khan, J. T., Aafaq, N., Ali, Q., & Mohsin, M. (2026) · Discover Computing · doi:10.1007/s10791-026-09977-z · Cited by 6
Spatial attention for human-centric visual understanding: An Information Bottleneck method
Lai, Q., Nie, Y., Li, Y., Sun, H., & Xu, Q. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104180 · Cited by 3
He, Z., Wang, N., Wang, L., Liu, C., & Chen, Q. (2024) · Pattern Analysis and Applications · doi:10.1007/s10044-024-01339-z · Cited by 4
“To address these challenges, researchers have proposed modular agents, including mapping-based methods [15, 21], waypoint methods [12, 22] and discrete-to-continuous waypoint methods [11, 13, 23–25].”
Self-citationAction-Aware Visual-Textual Alignment for Long-Instruction Vision-and-Language Navigation
Huang, B., Zheng, Y., Lan, C., Sui, D., Zhao, X., Zhang, X., Xiao, M., & Yu, D. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3748656 · Cited by 2
“ETPNav [3] conducts real-time topological mapping of environments by autonomously organizing predicted waypoints on a traveled route.”
Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments
Zhang, H., Yu, Y., Wang, L., Sun, F., & Zheng, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4097-6_34 · Cited by 16
Self-citationObservation-Graph Interaction and Key-Detail Guidance for Vision and Language Navigation
Xie, Y., Ou, B., Ma, F., & Liu, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247072 · Cited by 3
“However, existing methods [4], [8], [9], [35] merely integrate instruction information through cross-attention mechanisms [20], lacking fine-grained instructional guidance and containing redundant information, which impedes effective vision-language navigation planning for embodied agents.”
OCNav: Object-centric Navigation via Parallel Language Grounding on Semantic Topological Graphs
Park, J.-S., Lee, Y. J., Park, J.-C., Park, S.-G., Ahn, W. J., Woo, J.-J., & Lim, M. T. (2025) · International Journal of Control Automation and Systems · doi:10.1007/s12555-025-0531-6 · Cited by 3
Indoor Scene Recognition in Vision-and-Language Navigation
Zhang, H., Qi, Y., Zhao, M., & Liu, Y. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3645249 · Cited by 2
“The remarkable feature extraction capabilities of convolutional neural networks (CNNs) and self-attention mechanisms [19] have firmly established deep neural network-based algorithms as the leading methodology in indoor scene classification tasks [20].”
ThinkMatter: Panoramic-Aware Instructional Semantics for Monocular Vision-and-Language Navigation
Dai, G., Wang, S., Zhao, H., Zhu, B., Sun, Q., & Shu, X. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3652003 · Cited by 6
“3) Settings of the Training: We revise ETPNav [10] model as our baseline VLN model, where we only use the robot’s forward-facing view features, following the Sim2Real-FF [22].”
InfluentialFine-Grained Alignment Supervision Matters in Vision-and-Language Navigation
He, K., Huang, Y., Jing, Y., Wu, Q., & Wang, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3658949 · Cited by 8
“…the coarse-grained dataset Room-to-Room (R2R), significant progress has been made in this direction, ranging from the sequence-to-sequence models [4] combined with cross-modal grounding modules [5], [6], [7] to Transformer-based models [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18].”
Self-citationLi, H., Liu, R., Fan, H., & Yang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37211-6_27 · Cited by 6
Liu, T., Qi, X., Wang, L., Li, J., Lin, X., Zhu, M., Cui, Y., Liu, C. X., & Chen, Q. (2026) · Sensors · doi:10.3390/s26123698 · Cited by 2
“In contrast, hierarchical frameworks decouple navigation into two stages [2,13,55]: a waypoint prediction module that generates candidate subgoals from the surrounding environment, and a waypoint selection module that integrates multi-modal inputs to choose the next navigational target.”
Self-citationMaintaining topological maps for mobile robots
Muravyev, K., & Yakovlev, K. (2024) · International Conference on Machine Vision · doi:10.1117/12.3023459 · Cited by 1
“For instance, the method proposed by Chaplot et al. 18 tackles the ObjectGoal Navigation task, while the approaches by An et al. 19 and Kim et al. 20 focus on ImageGoal Navigation.”
Methodg3D-LF: Generalizable 3D-Language Feature Fields for Embodied TasksPreprint
Wang, Z., & Lee, G. H. (2024) · Qeios · doi:10.32388/841d1t · Cited by 1
Self-citationBrain-inspired spatial intelligence for embodied agents
Ruan, S., Wang, L., Kang, C., Zhu, Q., Liu, S., Wei, X., & Su, H. (2026) · Nature Communications · doi:10.1038/s41467-026-74358-5 · Cited by 1
“…embodied navigation frameworks con fi ned to localized modeling with a single granularity, such as purely dense grids 30,31 or sparse topologies 32,33 , the hierarchicalspatialarchitecture ofBSC-Nav achievesthedecouplingof spatial knowledge while incorporating targeted adaptive update…”
InfluentialSelf-citationExploring Graph-aware Reasoning and Bidirectional Selection for Vision-Language Navigation
Zhou, D., Deng, J., Pang, Z., & Li, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888565 · Cited by 2
“An et al [27] proposed a method to split the agent navigation process into high-level planning and low-level control.”
Enhancing Vision-and-Language Navigation in Continuous Environment via Data Synthesis
Wang, Z., & Xu, Y. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11063767 · Cited by 1
“ETPNav [16] is employed as the navigation agent to validate the efficacy of our synthesized data.”
Self-citationLandmark-Guided Knowledge for Vision-and-Language Navigation
Yang, D., Zhu, M., & Yu, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9856-1_35
“Vision-and-language navigation (VLN) [2,3,29,30] is one of the core tasks in embodied artificial intelligence (embodied AI) [43,44], which requires an agent to navigate in an unseen environment by following natural language instructions.”
Li, S., Hou, J., Huang, D., Fu, Y., & Xue, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755232 · Cited by 1
Luo, K., Qin, J., & Chen, Y. (2025) · International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI) · doi:10.1109/iotaai66837.2025.11213348
“…simulate human visual perception and enhance navigation [4]; Jacob Krantz introduced a pretrained, language-conditioned waypoint predictor coupled with a low-level controller [5]; and Dong An proposed a topological mapping method with “ghost nodes” to represent unexplored but perceived areas [6].”
Language-Conditioned Waypoint Predictor for Continuous Vision-and-Language Navigation
Wang, Z., Qi, Y., An, D. U., Xu, Y., Li, H., & Zhang, Z. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209085
“Despite the improvements provided by the waypoint predictors, limitations exist: Previous RGBD [18] or depth-only [20] waypoint predictors have largely overlooked language information.”
Self-citationBetween Monocular and Panoramic: Multi-View Vision-and-Language Navigation
Li, M. (2025) · International Conference on Image and Video Processing (ICIVP) · doi:10.1109/icivp66296.2025.00031 · Cited by 1
“By leveraging the multi-view semantic map and 3D feature field, we successfully adapt VLN-CE model [16] with panoramic observation capabilities to real-world monocular robots, achieving outstanding performance.”
InfluentialFEG-VON: Frontier Embedding Graph for Efficient Visual Object Navigation
Dai, Y., Xie, P., Liu, Y., Chen, S., Yang, W., & Wang, G. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247225
“Building a graph to encode the semantic and relation information of the whole scene is not a novel idea for navigation tasks [18], [25], [26].”
Bio-Inspired Topological Autonomous Navigation with Active Inference in Robotics
de Tinguy, D., Verbelen, T., Gamba, E., & Dhoedt, B. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301261 · Cited by 1
“Hybrid methods combining planning with learned priors [15] show promise but face challenges in real-time, general-purpose navigation.”
SPENav: Dynamic Object Filtering With Spatial Perception Enhancement for Vision-Language Navigation
Yuan, S., Zhang, H., Liu, L., Zhu, L., & Dong, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3651320 · Cited by 5
“1, such as [9], [10], [11], [12], which alleviate long-term forgetting by explicitly storing node-level information.”
Hou, J., Kan, M., Zhang, L., Liang, H., Shan, S., & Xilin, C. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3662659
“Each node n i ∈ N represents a reachable location, storing its global 3D coordinates, p i ∈ R 3 , and panoramic-pooled visual features derived from the vision encoder (12-view average pooling for visited nodes; observable-view pooling for ghost nodes [5]).”
InfluentialView Invariant Learning for Vision-Language Navigation in Continuous Environments
Sun, J. Q., Weng, H., Xing, X., Yeum, C. M., & Crowley, M. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3669785 · Cited by 10
“Other works focus on designing more efficient neural networks for vision-and-language fusion [20], [21], [22], [23], [24].”
InfluentialRSG-VLN: Relevance Semantic Map Guided Vision-Language Navigation
Chen, L., Guo, Z., Wang, N., Ji, H., Chen, W., Wang, Y., & Sun, H. (2025) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc60802.2025.11423232
“State-of-the-art VLN frameworks unify language encoders, vision transformers, and action decoders into end-to-end architectures, achieving competitive performance on benchmarks [18], [19].”
AgentVLN: Towards Agentic Vision-and-Language Navigation
Xin, Z., Li, W., Jiang, Y., Huang, Z., Wang, B., Li, P., Zhu, J., Qin, J., & Huang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37167-6_7 · Cited by 14
Chen, P., Zhang, G., Ma, J., & Li, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_32 · Cited by 5
Spatial-Aware and Viewpoint-Robust Vision-Language Navigation
Zhong, Z., Lu, J., Liu, X., Yu, R., Zheng, X., Liu, Z., Wang, H., & Li, H. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3682894 · Cited by 4
“For action execution, a low-level controller [19] executes the navigation steps.”
InfluentialSelf-citationDual-Anchoring: Addressing State Drift in Vision-Language Navigation
Wu, K., Li, P., Lyu, K., Lin, X., Zhao, L., He, Q., Wang, J., & Liu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36984-0_24 · Cited by 7
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Wen, J., Sun, P., Zhang, W., Qiu, S., Xu, W., Yang, X., & Chu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37252-9_26
Embodied Navigation with Auxiliary Task of Action Description Prediction
Kondoh, H., & Kanezaki, A. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00660 · Cited by 3
“…include splitting long instructions into shorter segments [31, 82], effectively integrating historical and multi-modal information [13, 35, 40], optimizing the use of the topological map [1, 2, 14], and enhancing performance by augmenting trajectory-instruction paired data [27, 38, 63, 68, 69].”
Wang, X., Feng, T., Liu, H., & Zhu, W. (2026) · Springer eBooks · doi:10.1007/978-981-95-7750-7_1 · Cited by 3
Wang, R., Liu, Z., Chen, W., He, B., & Wang, Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116308 · Cited by 1
Self-citationAbeywansa, C., Gunasekara, S., Silva, D. D., Dissanayake, S., Rodrigo, R. P., & Jayasekara, P. G. (2026) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar69571.2026.11549553
“While recent research enhances VLN in continuous environments, it still relies on the use of pre-computed navigation graphs [17], [18], [19] and 360-degree panoramic visuals [12], and remains limited to simulation-only implementations.”
Xu, H., Liu, Z., Luomei, Y., & Xu, F. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3701286 · Cited by 14
“A variety of learning-based methods have been proposed under this setting, including cross-modal attention [26], memory-augmented agents [27], and planning-based approaches [28], [29], [30].”
Decision-Invariant Sim-to-Real Vision-and-Language Navigation with Pseudo-Panoramic Observations
Zheng, Y., Shen, X., Sun, Y., Shen, Y., & Zhang, L. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810871
“However, the majority of existing methods are developed and evaluated exclusively in simulation [1, 2, 4, 6, 8, 9, 11, 13, 14, 16– 18, 20, 21, 25–27], either in a discrete (VLN) [4] or a continuous setting (VLN-CE) [15], leading to a pronounced sim-to-real gap.”
InfluentialXi, Y., Liu, S., Pang, B. J., Zhou, T., Song, Y. H., Yuan, X., & Xu, Q. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3703976
“Following existing work [1], [12], [14], we use the common evaluation metrics in the VLN to measure the agent’s navigation performance, including: Trajectory Length (TL), Navigation Error (NE), Success Rate (SR), Oracle Success Rate (OSR), and Success Rate weighted by Path Length (SPL).”
InfluentialKnowledge-Guided Instruction Grounding with Hybrid Map for Vision-Language Navigation
Wang, Y., Kang, J., Chen, B., Zhong, P., Yang, H., & Liu, L. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582363
“In contrast, map-based methods explicitly model the environment using topological graphs [5] that capture spatial connectivity between key locations, semantic maps [4] that integrate high-level semantic information such as object categories and room functions, and grid-based feature maps [6] that…”
Wang, L., Sheng, K., He, Z., Li, J., Qin, Y., Dai, H., Wang, X. F., Yang, J., Yan, Q., Liu, C., et al. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3711284 · Cited by 3
“(1) Topological graph-based policies incrementally construct an online topological graph during navigation [17], [30], [38].”
InfluentialSelf-citationSysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation
Zhu, H., Li, Z., Liu, Z., Guo, K., Lin, Z., Cai, Y., Chen, G., Lv, C., Wang, W., Oh, J., et al. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3713730 · Cited by 10
“Others [28], [29], [30] explicitly construct viewpoints in the scene graph, enabling VLMs to reason over the graph and choose among viewpoints to guide navigation.”
Self-citationOVTG: Open-Vocabulary Topological Semantic Graph Construction Method for Unknown Environments
Li, R. K., Liu, W., & Deng, Z. (2026) · International Conference on Robotics and Control Engineering (RobCE) · doi:10.1145/3820709.3820713
“Graph attention networks (GAT [20]/GNN) have been applied to propagate context among nodes, enabling multi-hop reasoning across rooms and floors, and to weigh nodes by relevance to language queries [2, 6].”
Motion-VLN: Learning ego-motion from optical flow for VLN-CE
Gao, T., Wang, L., Fu, Y., Liu, Z., Jiang, Z., Zhang, T., & Wang, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134756
Self-citationVision-and-Language Navigation: A Component-Centric Survey of Interactions, Coupling, and Deployment
Wu, X., Wu, Y., & Peng, X. (2026) · Applied Sciences · doi:10.3390/app16168050
Dual-modal chain-of-thought reasoning for continuous vision-language navigation
Liu, M., Wu, D., Xu, Y., Zhou, F., & Zhang, X. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105699
EntityNav: an Entity-Centric Stepwise Planning Framework for Vision-Language Navigation
Yang, H., Zhou, Y., Liu, S., & Jiang, J. (2026) · IEEE International Conference on Joint Cloud Computing (JCC) · doi:10.1109/jcc72984.2026.00020
Yao, X., Gao, J., & Xu, C. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3728426
“I NTRODUCTION I N RECENT years, Embodied AI has witnessed remarkable progress, with Vision-and-Language Navigation in Continuous Environments (VLN-CE) [1], [2], [3], [4] establishing itself as a cornerstone task that has garnered significant research interest.”
InfluentialRO-VLMap: Real-Time Occupancy-Aware Visual Language Mapping for Robust Robot Navigation
Liu, Y., Hu, C., & Ding, N. (2026) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot70864.2026.00034
Vision-and-Language Navigation Based on Cosine Similarity and Bidirectional Alignment
Zhu, T. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682316
“…for zero-shot transfer; PaLM-E [10] fused LLMs with visual encoders; GOAT [11] applied causal reasoning to reduce spurious correlations; ETPnav [12] employed evolutionary topological planning; NavCoT [13] introduced chain-of-thought reasoning; and Long-Horizon VLN [14] designed…”
CoMaTrack: Competitive Multi-agent Game-Theoretic Tracking with Vision-Language-Action Models
Gao, L., Liu, L., Lv, M., & Cai, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37574-2_14 · Cited by 9
LiveVLN: Reducing Stop-and-Go Loops in Vision-Language Navigation
Wang, X., Zhu, W., Wang, T., Geng, T., Zhang, Z., Qi, Z., Yang, J., & Zheng, F. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3734886 · Cited by 5
“Later studies introduced explicit spatial reasoning via topological planning, graph-based reasoning, and map-centric representations [4], [13], [14], [15].”
Discrete to continuous VLN adaptation with collision mitigation through depth sensing
Khan, J. T., Salahuddin, H., Aafaq, N., & Ali, Q. (2026) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-026-00592-1
Trajectory-Diversity-Driven Robust Vision-And-Language Navigation
Li, J., Wan, C., Dong, S., Ding, C., Wang, Q., Ma, Z., & Gong, Y. (2026) · doi:10.1109/cvprf71909.2026.00877 · Cited by 2
HAVEN: A unified monocular RGB vision-and-language navigation framework for wheeled-legged robots
Dai, M., Huang, C., Zheng, B., Cheng, Z., Dong, W., & Wu, L. (2026) · Displays · doi:10.1016/j.displa.2026.103724
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.