{"url":"/sota/visual-navigation-on-room-to-room-1","task":{"name":"Visual Navigation","url":"/task/visual-navigation","note":null},"dataset":{"name":"R2R","url":"/dataset/room-to-room"},"category":"Computer Vision","categories":["Computer Vision","Robots"],"category_note":null,"description":"**Visual Navigation** is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.\n\n\n<span class=\"description-source\">Source: [Vision-based Navigation Using Deep Reinforcement Learning ](https://arxiv.org/abs/1908.03627)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["spl"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"spl":null}},"counts":{"rows":11,"rows_with_code":9,"rows_with_paper_page":11,"rows_dated":11,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SUSA","metrics":{"spl":"0.6383"},"uses_additional_data":false,"paper_date":"2024-12-09","paper":"/paper/agent-journey-beyond-rgb-unveiling-hybrid","paper_url":"https://arxiv.org/abs/2412.06465v4","paper_title":"Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation","code":"https://github.com/HCI-LMC/VLN-SUSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Meta-Explore","metrics":{"spl":"0.61"},"uses_additional_data":false,"paper_date":"2023-03-07","paper":"/paper/meta-explore-exploratory-hierarchical-vision","paper_url":"https://arxiv.org/abs/2303.04077v1","paper_title":"Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"BEV-BERT","metrics":{"spl":"0.60"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/bevbert-topo-metric-map-pre-training-for","paper_url":"https://arxiv.org/abs/2212.04385v2","paper_title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","code":"https://github.com/marsaki/vln-bevbert","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"NaviLLM","metrics":{"spl":"0.60"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/towards-learning-a-generalist-model-for","paper_url":"https://arxiv.org/abs/2312.02010v3","paper_title":"Towards Learning a Generalist Model for Embodied Navigation","code":"https://github.com/zd11024/NaviLLM","n_code_links":2,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"HOP","metrics":{"spl":"0.59"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/hop-history-and-order-aware-pre-training-for","paper_url":"https://arxiv.org/abs/2203.11591v1","paper_title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","code":"https://github.com/yanyuanqiao/hop-vln","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"VLN-PETL","metrics":{"spl":"0.58"},"uses_additional_data":false,"paper_date":"2023-08-20","paper":"/paper/vln-petl-parameter-efficient-transfer","paper_url":"https://arxiv.org/abs/2308.10172v1","paper_title":"VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation","code":"https://github.com/yanyuanqiao/vln-petl","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DUET","metrics":{"spl":"0.58"},"uses_additional_data":false,"paper_date":"2022-02-23","paper":"/paper/think-global-act-local-dual-scale-graph","paper_url":"https://arxiv.org/abs/2202.11742v1","paper_title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","code":"https://github.com/cshizhe/vln-duet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":8,"model":"VLN-BERT","metrics":{"spl":"0.57"},"uses_additional_data":false,"paper_date":"2020-11-26","paper":"/paper/a-recurrent-vision-and-language-bert-for","paper_url":"https://arxiv.org/abs/2011.13922v2","paper_title":"A Recurrent Vision-and-Language BERT for Navigation","code":"https://github.com/YicongHong/Recurrent-VLN-BERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Prevalent","metrics":{"spl":"0.51"},"uses_additional_data":false,"paper_date":"2020-02-25","paper":"/paper/towards-learning-a-generic-agent-for-vision","paper_url":"https://arxiv.org/abs/2002.10638v2","paper_title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","code":"https://github.com/weituo12321/PREVALENT","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"RCM+SIL(no early exploration)","metrics":{"spl":"0.38"},"uses_additional_data":false,"paper_date":"2018-11-25","paper":"/paper/reinforced-cross-modal-matching-and-self","paper_url":"http://arxiv.org/abs/1811.10092v2","paper_title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Seq2Seq baseline","metrics":{"spl":"0.18"},"uses_additional_data":false,"paper_date":"2017-11-20","paper":"/paper/vision-and-language-navigation-interpreting","paper_url":"http://arxiv.org/abs/1711.07280v3","paper_title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","code":"https://github.com/peteanderson80/Matterport3DSimulator","n_code_links":8,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":18,"n_unverified":15,"n_samples":33,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":18,"n_unverified":15,"n_samples":33,"n_pointer_only_licence":5,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}