{"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/end-to-end-learning-of-driving-models-from","title":"End-to-end Learning of Driving Models from Large-scale Video Datasets","arxiv_id":"1612.01079","date":"2016-12-04","proceeding":"CVPR 2017 7","authors":["Huazhe Xu","Yang Gao","Fisher Yu","Trevor Darrell"],"abstract":"Robust perception-action models should be learned from training data with\ndiverse visual appearances and realistic behaviors, yet current approaches to\ndeep visuomotor policy learning have been generally limited to in-situ models\nlearned from a single vehicle or a simulation environment. We advocate learning\na generic vehicle motion model from large scale crowd-sourced video data, and\ndevelop an end-to-end trainable architecture for learning to predict a\ndistribution over future vehicle egomotion from instantaneous monocular camera\nobservations and previous vehicle state. Our model incorporates a novel\nFCN-LSTM architecture, which can be learned from large-scale crowd-sourced\nvehicle action data, and leverages available scene segmentation side tasks to\nimprove performance under a privileged learning paradigm.","url_abs":"http://arxiv.org/abs/1612.01079v2","url_pdf":"http://arxiv.org/pdf/1612.01079v2.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":"end-to-end-learning-of-driving-models-from","repo_url":"https://github.com/gy20073/BDD_Driving_Model","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"end-to-end-learning-of-driving-models-from","repo_url":"https://github.com/NupurBhaisare/BDD-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"berkeley-deepdrive-video","name":"Berkeley DeepDrive Video","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.01079","atlas_url":"https://app.syntology.ai/?focus=1612.01079","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}