{"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/naturalistic-driver-intention-and-path","title":"Naturalistic Driver Intention and Path Prediction using Recurrent Neural Networks","arxiv_id":"1807.09995","date":"2018-07-26","proceeding":null,"authors":["Alex Zyner","Stewart Worrall","Eduardo Nebot"],"abstract":"Understanding the intentions of drivers at intersections is a critical\ncomponent for autonomous vehicles. Urban intersections that do not have traffic\nsignals are a common epicentre of highly variable vehicle movement and\ninteractions. We present a method for predicting driver intent at urban\nintersections through multi-modal trajectory prediction with uncertainty. Our\nmethod is based on recurrent neural networks combined with a mixture density\nnetwork output layer. To consolidate the multi-modal nature of the output\nprobability distribution, we introduce a clustering algorithm that extracts the\nset of possible paths that exist in the prediction output, and ranks them\naccording to likelihood. To verify the method's performance and\ngeneralizability, we present a real-world dataset that consists of over 23,000\nvehicles traversing five different intersections, collected using a vehicle\nmounted Lidar based tracking system. An array of metrics is used to demonstrate\nthe performance of the model against several baselines.","url_abs":"http://arxiv.org/abs/1807.09995v1","url_pdf":"http://arxiv.org/pdf/1807.09995v1.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":"naturalistic-driver-intention-and-path","repo_url":"https://github.com/azyner/radip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.09995","atlas_url":"https://app.syntology.ai/?focus=1807.09995","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}