{"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/multimodal-trajectory-predictions-for","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","arxiv_id":"1809.10732","date":"2018-09-18","proceeding":null,"authors":["Henggang Cui","Vladan Radosavljevic","Fang-Chieh Chou","Tsung-Han Lin","Thi Nguyen","Tzu-Kuo Huang","Jeff Schneider","Nemanja Djuric"],"abstract":"Autonomous driving presents one of the largest problems that the robotics and\nartificial intelligence communities are facing at the moment, both in terms of\ndifficulty and potential societal impact. Self-driving vehicles (SDVs) are\nexpected to prevent road accidents and save millions of lives while improving\nthe livelihood and life quality of many more. However, despite large interest\nand a number of industry players working in the autonomous domain, there still\nremains more to be done in order to develop a system capable of operating at a\nlevel comparable to best human drivers. One reason for this is high uncertainty\nof traffic behavior and large number of situations that an SDV may encounter on\nthe roads, making it very difficult to create a fully generalizable system. To\nensure safe and efficient operations, an autonomous vehicle is required to\naccount for this uncertainty and to anticipate a multitude of possible\nbehaviors of traffic actors in its surrounding. We address this critical\nproblem and present a method to predict multiple possible trajectories of\nactors while also estimating their probabilities. The method encodes each\nactor's surrounding context into a raster image, used as input by deep\nconvolutional networks to automatically derive relevant features for the task.\nFollowing extensive offline evaluation and comparison to state-of-the-art\nbaselines, the method was successfully tested on SDVs in closed-course tests.","url_abs":"http://arxiv.org/abs/1809.10732v2","url_pdf":"http://arxiv.org/pdf/1809.10732v2.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":"multimodal-trajectory-predictions-for","repo_url":"https://github.com/alin256/multi-mode-prediction-with-mtp-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-trajectory-predictions-for","repo_url":"https://github.com/daeheepark/PathPredictNusc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multimodal-trajectory-predictions-for","repo_url":"https://github.com/MindCode-4/code-8/tree/main/multimodal-trajectory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"multimodal-trajectory-predictions-for","repo_url":"https://github.com/nanzhaogang/contrib/tree/master/application/multimodal-trajectory-predictions-for-autonomous-driving-using-deep-convolutional-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"motion-planning","task_name":"Motion Planning"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.10732","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}