{"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/trafficpredict-trajectory-prediction-for","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","arxiv_id":"1811.02146","date":"2018-11-06","proceeding":null,"authors":["Yuexin Ma","Xinge Zhu","Sibo Zhang","Ruigang Yang","Wenping Wang","Dinesh Manocha"],"abstract":"To safely and efficiently navigate in complex urban traffic, autonomous\nvehicles must make responsible predictions in relation to surrounding\ntraffic-agents (vehicles, bicycles, pedestrians, etc.). A challenging and\ncritical task is to explore the movement patterns of different traffic-agents\nand predict their future trajectories accurately to help the autonomous vehicle\nmake reasonable navigation decision. To solve this problem, we propose a long\nshort-term memory-based (LSTM-based) realtime traffic prediction algorithm,\nTrafficPredict. Our approach uses an instance layer to learn instances'\nmovements and interactions and has a category layer to learn the similarities\nof instances belonging to the same type to refine the prediction. In order to\nevaluate its performance, we collected trajectory datasets in a large city\nconsisting of varying conditions and traffic densities. The dataset includes\nmany challenging scenarios where vehicles, bicycles, and pedestrians move among\none another. We evaluate the performance of TrafficPredict on our new dataset\nand highlight its higher accuracy for trajectory prediction by comparing with\nprior prediction methods.","url_abs":"http://arxiv.org/abs/1811.02146v5","url_pdf":"http://arxiv.org/pdf/1811.02146v5.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":"trafficpredict-trajectory-prediction-for","repo_url":"https://github.com/ApolloScapeAuto/dataset-api","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[],"datasets_introduced":[{"slug":"apolloscape-trajectory","name":"Apolloscape Trajectory","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-prediction-on-apolloscape-1","task":"Trajectory Prediction","dataset":"Apolloscape Trajectory","model":"Trafficpredict","rank_in_archive_order":1,"of":1,"metrics":{"ADE":"8.5881"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02146","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}