{"url":"/sota/trajectory-prediction-on-stanford-drone","task":{"name":"Trajectory Prediction","url":"/task/trajectory-prediction","note":null},"dataset":{"name":"Stanford Drone","url":null},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":"**Trajectory Prediction** is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.\r\n\r\n\r\n<span class=\"description-source\">Source: [Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs ](https://arxiv.org/abs/1912.01118)</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":["ADE-8/12 @K = 20","FDE-8/12 @K= 20","ADE (8/12) @K=5","FDE(8/12) @K=5","ADE (in world coordinates)","FDE (in world coordinates)","AMD","AMV","Avg AMD/AMV 8/12"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ADE-8/12 @K = 20":null,"FDE-8/12 @K= 20":null,"ADE (8/12) @K=5":null,"FDE(8/12) @K=5":null,"ADE (in world coordinates)":null,"FDE (in world coordinates)":null,"AMD":null,"AMV":null,"Avg AMD/AMV 8/12":null}},"counts":{"rows":24,"rows_with_code":19,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"NSP-SFM","metrics":{"ADE-8/12 @K = 20":"6.52","FDE-8/12 @K= 20":"10.61"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/human-trajectory-prediction-via-neural-social","paper_url":"https://arxiv.org/abs/2207.10435v2","paper_title":"Human Trajectory Prediction via Neural Social Physics","code":"https://github.com/realcrane/human-trajectory-prediction-via-neural-social-physics","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":2,"model":"TDOR","metrics":{"ADE-8/12 @K = 20":"6.77","FDE-8/12 @K= 20":"10.46"},"uses_additional_data":false,"paper_date":"2022-03-31","paper":"/paper/end-to-end-trajectory-distribution-prediction","paper_url":"https://arxiv.org/abs/2203.16910v1","paper_title":"End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps","code":"https://github.com/kguo-cs/tdor","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PPT","metrics":{"ADE-8/12 @K = 20":"7.03","FDE-8/12 @K= 20":"10.65"},"uses_additional_data":false,"paper_date":"2024-07-16","paper":"/paper/progressive-pretext-task-learning-for-human","paper_url":"https://arxiv.org/abs/2407.11588v1","paper_title":"Progressive Pretext Task Learning for Human Trajectory Prediction","code":"https://github.com/isee-laboratory/ppt","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"V^2-Net","metrics":{"ADE-8/12 @K = 20":"7.12","FDE-8/12 @K= 20":"11.39"},"uses_additional_data":false,"paper_date":"2021-10-14","paper":"/paper/view-vertically-a-hierarchical-network-for","paper_url":"https://arxiv.org/abs/2110.07288v2","paper_title":"View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums","code":"https://github.com/cocoon2wong/Vertical","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Y-Net","metrics":{"ADE-8/12 @K = 20":"7.85","FDE-8/12 @K= 20":"11.85"},"uses_additional_data":false,"paper_date":"2020-12-02","paper":"/paper/from-goals-waypoints-paths-to-long-term-human","paper_url":"https://arxiv.org/abs/2012.01526v1","paper_title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","code":"https://github.com/harshayugirase/human-path-prediction","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"SMEMO","metrics":{"ADE (8/12) @K=5":"11.64","ADE-8/12 @K = 20":"8.11","FDE(8/12) @K=5":"21.12","FDE-8/12 @K= 20":"13.06"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/smemo-social-memory-for-trajectory","paper_url":"https://arxiv.org/abs/2203.12446v2","paper_title":"SMEMO: Social Memory for Trajectory Forecasting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MemoNet","metrics":{"ADE-8/12 @K = 20":"8.56","FDE-8/12 @K= 20":"12.66"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/remember-intentions-retrospective-memory","paper_url":"https://arxiv.org/abs/2203.11474v1","paper_title":"Remember Intentions: Retrospective-Memory-based Trajectory Prediction","code":"https://github.com/mediabrain-sjtu/memonet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MANTRA","metrics":{"ADE (8/12) @K=5":"13.51","ADE-8/12 @K = 20":"8.96","FDE(8/12) @K=5":"27.34","FDE-8/12 @K= 20":"17.76"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/mantra-memory-augmented-networks-for-multiple-1","paper_url":"https://arxiv.org/abs/2006.03340v2","paper_title":"MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction","code":"https://github.com/Marchetz/MANTRA-CVPR20","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"PECNet","metrics":{"ADE-8/12 @K = 20":"9.96","FDE-8/12 @K= 20":"15.88"},"uses_additional_data":false,"paper_date":"2020-04-04","paper":"/paper/it-is-not-the-journey-but-the-destination","paper_url":"https://arxiv.org/abs/2004.02025v3","paper_title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","code":"https://github.com/harshayugirase/human-path-prediction","n_code_links":4,"syntology":null},{"rank_in_archive_order":10,"model":"SimAug","metrics":{"ADE-8/12 @K = 20":"10.27","FDE-8/12 @K= 20":"19.71"},"uses_additional_data":false,"paper_date":"2020-04-04","paper":"/paper/simaug-learning-robust-representations-from","paper_url":"https://arxiv.org/abs/2004.02022v2","paper_title":"SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras","code":"https://github.com/JunweiLiang/Multiverse/tree/master/SimAug","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"P2TIRL","metrics":{"ADE-8/12 @K = 20":"12.58","FDE-8/12 @K= 20":"22.07"},"uses_additional_data":false,"paper_date":"2020-01-03","paper":"/paper/trajectory-forecasts-in-unknown-environments","paper_url":"https://arxiv.org/abs/2001.00735v2","paper_title":"Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans","code":"https://github.com/nachiket92/P2T","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"CF-VAE","metrics":{"ADE-8/12 @K = 20":"12.60","FDE-8/12 @K= 20":"22.30"},"uses_additional_data":false,"paper_date":"2019-08-24","paper":"/paper/conditional-flow-variational-autoencoders-for","paper_url":"https://arxiv.org/abs/1908.09008v3","paper_title":"Conditional Flow Variational Autoencoders for Structured Sequence Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"EvolveGraph","metrics":{"ADE-8/12 @K = 20":"13.9","FDE-8/12 @K= 20":"22.9"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/evolvegraph-heterogeneous-multi-agent-multi","paper_url":"https://arxiv.org/abs/2003.13924v4","paper_title":"EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"Multiverse","metrics":{"ADE-8/12 @K = 20":"14.78","FDE-8/12 @K= 20":"27.09"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/the-garden-of-forking-paths-towards-multi","paper_url":"https://arxiv.org/abs/1912.06445v3","paper_title":"The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction","code":"https://github.com/JunweiLiang/Multiverse","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"CGNS","metrics":{"ADE-8/12 @K = 20":"15.6","FDE-8/12 @K= 20":"28.2"},"uses_additional_data":false,"paper_date":"2019-05-05","paper":"/paper/conditional-generative-neural-system-for","paper_url":"https://arxiv.org/abs/1905.01631v2","paper_title":"Conditional Generative Neural System for Probabilistic Trajectory Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"Sophie","metrics":{"ADE-8/12 @K = 20":"16.27","FDE-8/12 @K= 20":"29.38"},"uses_additional_data":false,"paper_date":"2018-06-05","paper":"/paper/sophie-an-attentive-gan-for-predicting-paths","paper_url":"http://arxiv.org/abs/1806.01482v2","paper_title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","code":"https://github.com/coolsunxu/sophie","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":17,"model":"DESIRE","metrics":{"ADE (8/12) @K=5":"19.25","ADE-8/12 @K = 20":"19.25","FDE(8/12) @K=5":"34.05","FDE-8/12 @K= 20":"34.05"},"uses_additional_data":false,"paper_date":"2017-04-14","paper":"/paper/desire-distant-future-prediction-in-dynamic","paper_url":"http://arxiv.org/abs/1704.04394v1","paper_title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","code":"https://github.com/yadrimz/DESIRE","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"Social GAN","metrics":{"ADE (8/12) @K=5":"27.25","ADE-8/12 @K = 20":"27.23","FDE(8/12) @K=5":"41.44","FDE-8/12 @K= 20":"41.44"},"uses_additional_data":false,"paper_date":"2018-03-29","paper":"/paper/social-gan-socially-acceptable-trajectories","paper_url":"http://arxiv.org/abs/1803.10892v1","paper_title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","code":"https://github.com/agrimgupta92/sgan","n_code_links":8,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":4}},{"rank_in_archive_order":19,"model":"TNT","metrics":{"ADE (8/12) @K=5":"12.23","FDE(8/12) @K=5":"21.16"},"uses_additional_data":false,"paper_date":"2020-08-19","paper":"/paper/tnt-target-driven-trajectory-prediction","paper_url":"https://arxiv.org/abs/2008.08294v2","paper_title":"TNT: Target-driveN Trajectory Prediction","code":"https://github.com/henry1iu/tnt-trajectory-predition","n_code_links":4,"syntology":null},{"rank_in_archive_order":20,"model":"SoPhie","metrics":{"ADE (8/12) @K=5":"16.27","FDE(8/12) @K=5":"29.38"},"uses_additional_data":false,"paper_date":"2018-06-05","paper":"/paper/sophie-an-attentive-gan-for-predicting-paths","paper_url":"http://arxiv.org/abs/1806.01482v2","paper_title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","code":"https://github.com/coolsunxu/sophie","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":21,"model":"Social LSTM","metrics":{"ADE (8/12) @K=5":"31.19","FDE(8/12) @K=5":"56.97"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/social-lstm-human-trajectory-prediction-in","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Alahi_Social_LSTM_Human_CVPR_2016_paper.html","paper_title":"Social LSTM: Human Trajectory Prediction in Crowded Spaces","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"Social-Implicit","metrics":{"ADE (in world coordinates)":"0.47","AMD":"2.83","AMV":"0.077","Avg AMD/AMV 8/12":"1.45","FDE (in world coordinates)":"0.89"},"uses_additional_data":false,"paper_date":"2022-03-06","paper":"/paper/social-implicit-rethinking-trajectory","paper_url":"https://arxiv.org/abs/2203.03057v2","paper_title":"Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation","code":"https://github.com/abduallahmohamed/social-implicit","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"DAG-Net","metrics":{"ADE (in world coordinates)":"0.54","FDE (in world coordinates)":"1.05"},"uses_additional_data":false,"paper_date":"2020-05-26","paper":"/paper/dag-net-double-attentive-graph-neural-network","paper_url":"https://arxiv.org/abs/2005.12661v2","paper_title":"DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting","code":"https://github.com/alexmonti19/dagnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Social-Ways","metrics":{"ADE (in world coordinates)":"0.62","FDE (in world coordinates)":"1.16"},"uses_additional_data":false,"paper_date":"2019-04-20","paper":"/paper/social-ways-learning-multi-modal","paper_url":"http://arxiv.org/abs/1904.09507v2","paper_title":"Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs","code":"https://github.com/amiryanj/socialways","n_code_links":1,"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":10,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":31,"n_unverified":16,"n_samples":47,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":34,"n_unverified":16,"n_samples":50,"n_pointer_only_licence":17,"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"}}}