{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-goals-waypoints-paths-to-long-term-human","title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","arxiv_id":"2012.01526","date":"2020-12-02","proceeding":"ICCV 2021 10","authors":["Karttikeya Mangalam","Yang An","Harshayu Girase","Jitendra Malik"],"abstract":"Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works. Finally, we presentY-net, a scene com-pliant trajectory forecasting network that exploits the pro-posed epistemic & aleatoric structure for diverse trajectory predictions across long prediction horizons.Y-net significantly improves previous state-of-the-art performance on both (a) The well studied short prediction horizon settings on the Stanford Drone & ETH/UCY datasets and (b) The proposed long prediction horizon setting on the re-purposed Stanford Drone & Intersection Drone datasets.","url_abs":"https://arxiv.org/abs/2012.01526v1","url_pdf":"https://arxiv.org/pdf/2012.01526v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"from-goals-waypoints-paths-to-long-term-human","repo_url":"https://github.com/HarshayuGirase/PECNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"from-goals-waypoints-paths-to-long-term-human","repo_url":"https://github.com/harshayugirase/human-path-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"trajectory-forecasting","task_name":"Trajectory Forecasting"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-prediction-on-ethucy","task":"Trajectory Prediction","dataset":"ETH/UCY","model":"Y-Net","rank_in_archive_order":2,"of":20,"metrics":{"ADE-8/12":"0.18","FDE-8/12":"0.27"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-prediction-on-stanford-drone","task":"Trajectory Prediction","dataset":"Stanford Drone","model":"Y-Net","rank_in_archive_order":5,"of":24,"metrics":{"ADE-8/12 @K = 20":"7.85","FDE-8/12 @K= 20":"11.85"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.01526","atlas_url":"https://app.syntology.ai/?focus=2012.01526","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}