{"url":"/task/trajectory-forecasting","name":"Trajectory Forecasting","slug":"trajectory-forecasting","description_markdown":"Trajectory forecasting is a sequential prediction task, where a forecasting model predicts future trajectories of all moving agents (humans, vehicles, etc.) in a scene, based on their past trajectories and/or the scene context.\r\n\r\n(Illustrative figure from [Social NCE: Contrastive Learning of Socially-aware Motion Representations](https://github.com/vita-epfl/social-nce))","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":187,"papers_with_code":89,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/trajectory-forecasting-on-trajnet","slug":"trajectory-forecasting-on-trajnet","dataset":"TrajNet++","dataset_url":"/dataset/trajnet-1","rows_in_archive":3,"metrics":["FDE","COL"],"first_row_in_archive_order":{"model":"Social NCE + Social LSTM","paper_title":"Social NCE: Contrastive Learning of Socially-aware Motion Representations","paper_url":"/paper/social-nce-contrastive-learning-of-socially","paper_date":"2020-12-21","arxiv_id":"2012.11717","code_links":[{"title":"vita-epfl/social-nce","url":"https://github.com/vita-epfl/social-nce"},{"title":"vita-epfl/social-nce-crowdnav","url":"https://github.com/vita-epfl/social-nce-crowdnav"},{"title":"YuejiangLIU/social-nce-trajectron-plus-plus","url":"https://github.com/YuejiangLIU/social-nce-trajectron-plus-plus"},{"title":"qiyan98/social-nce-stgcnn","url":"https://github.com/qiyan98/social-nce-stgcnn"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/trajectory-forecasting-on-actev","slug":"trajectory-forecasting-on-actev","dataset":"ActEV","dataset_url":null,"rows_in_archive":2,"metrics":["ADE-8/12"],"first_row_in_archive_order":{"model":"SimAug","paper_title":"SimAug: Learning Robust Representations from Simulation for Trajectory Prediction","paper_url":"/paper/simaug-learning-robust-representations-from-1","paper_date":"","arxiv_id":null,"code_links":[{"title":"JunweiLiang/Multiverse","url":"https://github.com/JunweiLiang/Multiverse"}],"syntology":null}},{"leaderboard":"/sota/trajectory-forecasting-on-forkingpaths","slug":"trajectory-forecasting-on-forkingpaths","dataset":"ForkingPaths","dataset_url":null,"rows_in_archive":1,"metrics":["ADE"],"first_row_in_archive_order":{"model":"Multiverse","paper_title":"The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction","paper_url":"/paper/the-garden-of-forking-paths-towards-multi","paper_date":"2019-12-13","arxiv_id":"1912.06445","code_links":[{"title":"JunweiLiang/Multiverse","url":"https://github.com/JunweiLiang/Multiverse"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/trajectory-forecasting-on-stanford-drone","slug":"trajectory-forecasting-on-stanford-drone","dataset":"Stanford Drone","dataset_url":null,"rows_in_archive":1,"metrics":["ADE-8/12 @K = 20"],"first_row_in_archive_order":{"model":"SimAug","paper_title":"SimAug: Learning Robust Representations from Simulation for Trajectory Prediction","paper_url":"/paper/simaug-learning-robust-representations-from-1","paper_date":"","arxiv_id":null,"code_links":[{"title":"JunweiLiang/Multiverse","url":"https://github.com/JunweiLiang/Multiverse"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucy","name":"UCY","full_name":"","num_papers_in_archive":170},{"url":"/dataset/highd-dataseth","name":"highD Dataset","full_name":"The Highway Drone Dataset Naturalistic Trajectories of 110 500 Vehicles Recorded at German Highways","num_papers_in_archive":115},{"url":"/dataset/ind-dataset","name":"inD Dataset","full_name":"Intersection Drone Dataset","num_papers_in_archive":49},{"url":"/dataset/jaad","name":"JAAD","full_name":"Joint Attention in Autonomous Driving","num_papers_in_archive":21},{"url":"/dataset/round-dataset","name":"rounD Dataset","full_name":"The Roundabout Drone Dataset","num_papers_in_archive":19},{"url":"/dataset/trajnet-1","name":"TrajNet","full_name":"","num_papers_in_archive":12},{"url":"/dataset/fpl","name":"FPL","full_name":"First-Person Locomotion","num_papers_in_archive":7},{"url":"/dataset/exid-dataset","name":"exiD Dataset","full_name":"The Entries and Exits Drone Dataset","num_papers_in_archive":6},{"url":"/dataset/pie","name":"PIE","full_name":"Pedestrian Intention Estimation","num_papers_in_archive":6},{"url":"/dataset/egopat3d-dt","name":"EgoPAT3D-DT","full_name":"EgoPAT3D-DT","num_papers_in_archive":3},{"url":"/dataset/trajair","name":"TrajAir: A General Aviation Trajectory Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/nba-sportvu","name":"NBA SportVU","full_name":"","num_papers_in_archive":2},{"url":"/dataset/euro-pvi","name":"Euro-PVI","full_name":"","num_papers_in_archive":1},{"url":"/dataset/followme-vehicle-behaviour-prediction-dataset","name":"FollowMe Vehicle Behaviour Prediction Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/meteor","name":"METEOR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/unid-dataset","name":"uniD Dataset","full_name":"University Drone Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/trajectory-prediction","name":"Trajectory Prediction"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":89,"tagged_in_all":187,"items":[{"url":"/paper/social-gan-socially-acceptable-trajectories","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","date":"2018-03-29","arxiv_id":"1803.10892","repositories_listed":8,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/social-nce-contrastive-learning-of-socially","title":"Social NCE: Contrastive Learning of Socially-aware Motion Representations","date":"2020-12-21","arxiv_id":"2012.11717","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/it-is-not-the-journey-but-the-destination","title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","date":"2020-04-04","arxiv_id":"2004.02025","repositories_listed":4,"syntology":null},{"url":"/paper/trajdata-a-unified-interface-to-multiple-1","title":"trajdata: A Unified Interface to Multiple Human Trajectory Datasets","date":"2023-07-26","arxiv_id":"2307.13924","repositories_listed":3,"syntology":null},{"url":"/paper/road-barlow-twins-redundancy-reduction-for","title":"RedMotion: Motion Prediction via Redundancy Reduction","date":"2023-06-19","arxiv_id":"2306.10840","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/social-stgcnn-a-social-spatio-temporal-graph","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","date":"2020-02-27","arxiv_id":"2002.11927","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/trajectron-multi-agent-generative-trajectory","title":"Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data","date":"2020-01-09","arxiv_id":"2001.03093","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/argoverse-3d-tracking-and-forecasting-with-1","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","date":"2019-11-06","arxiv_id":"1911.02620","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/shape-and-time-distortion-loss-for-training","title":"Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models","date":"2019-09-19","arxiv_id":"1909.09020","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/a-survey-of-world-models-for-autonomous","title":"A Survey of World Models for Autonomous Driving","date":"2025-01-20","arxiv_id":"2501.11260","repositories_listed":2,"syntology":null},{"url":"/paper/imageflownet-forecasting-multiscale","title":"ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images","date":"2024-06-20","arxiv_id":"2406.14794","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/eigentrajectory-low-rank-descriptors-for","title":"EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting","date":"2023-07-18","arxiv_id":"2307.09306","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/deepprog-a-transformer-based-framework-for","title":"CLIMAT: Clinically-Inspired Multi-Agent Transformers for Knee Osteoarthritis Trajectory Forecasting","date":"2021-04-08","arxiv_id":"2104.03642","repositories_listed":2,"syntology":null},{"url":"/paper/agentformer-agent-aware-transformers-for","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","date":"2021-03-25","arxiv_id":"2103.14023","repositories_listed":2,"syntology":{"n":17,"n_ran":4,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/from-goals-waypoints-paths-to-long-term-human","title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","date":"2020-12-02","arxiv_id":"2012.01526","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-dynamic-context-for-multi-path","title":"Exploring Dynamic Context for Multi-path Trajectory Prediction","date":"2020-10-30","arxiv_id":"2010.16267","repositories_listed":2,"syntology":null},{"url":"/paper/opentraj-assessing-prediction-complexity-in","title":"OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets","date":"2020-10-02","arxiv_id":"2010.00890","repositories_listed":2,"syntology":null},{"url":"/paper/peeking-into-the-future-predicting-future","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","date":"2019-02-11","arxiv_id":"1902.03748","repositories_listed":2,"syntology":{"n":27,"n_ran":2,"n_unverified":25,"n_pointer_only":22}},{"url":"/paper/ecam-a-contrastive-learning-approach-to-avoid","title":"ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting","date":"2025-06-11","arxiv_id":"2506.09626","repositories_listed":1,"syntology":null},{"url":"/paper/egocentric-event-based-vision-for-ping-pong","title":"Egocentric Event-Based Vision for Ping Pong Ball Trajectory Prediction","date":"2025-06-09","arxiv_id":"2506.07860","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-knowledge-distillation-based","title":"Multi-modal Knowledge Distillation-based Human Trajectory Forecasting","date":"2025-03-28","arxiv_id":"2503.22201","repositories_listed":1,"syntology":null},{"url":"/paper/controllable-motion-generation-via-diffusion","title":"Controllable Motion Generation via Diffusion Modal Coupling","date":"2025-03-04","arxiv_id":"2503.02353","repositories_listed":1,"syntology":null},{"url":"/paper/emt-a-visual-multi-task-benchmark-dataset-for","title":"EMT: A Visual Multi-Task Benchmark Dataset for Autonomous Driving in the Arab Gulf Region","date":"2025-02-26","arxiv_id":"2502.19260","repositories_listed":1,"syntology":null},{"url":"/paper/trajflow-a-generative-framework-for-occupancy","title":"TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows","date":"2025-01-24","arxiv_id":"2501.14266","repositories_listed":1,"syntology":null},{"url":"/paper/socially-informed-reconstruction-for","title":"Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting","date":"2024-12-05","arxiv_id":"2412.04673","repositories_listed":1,"syntology":null},{"url":"/paper/tft-multi-simultaneous-forecasting-of-vital","title":"TFT-multi: simultaneous forecasting of vital sign trajectories in the ICU","date":"2024-09-23","arxiv_id":"2409.15586","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/situate-indoor-human-trajectory-prediction","title":"SITUATE: Indoor Human Trajectory Prediction through Geometric Features and Self-Supervised Vision Representation","date":"2024-09-01","arxiv_id":"2409.00774","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-online-mapping-and-behavior","title":"Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention","date":"2024-07-09","arxiv_id":"2407.06683","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-forecasting-through-low-rank","title":"Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes","date":"2024-05-31","arxiv_id":"2405.20743","repositories_listed":1,"syntology":null},{"url":"/paper/ki-gan-knowledge-informed-generative","title":"KI-GAN: Knowledge-Informed Generative Adversarial Networks for Enhanced Multi-Vehicle Trajectory Forecasting at Signalized Intersections","date":"2024-04-17","arxiv_id":"2404.11181","repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}