{"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/learning-end-to-end-autonomous-driving-using","title":"Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision","arxiv_id":"1808.10393","date":"2018-08-30","proceeding":null,"authors":["Ashish Mehta","Adithya Subramanian","Anbumani Subramanian"],"abstract":"Learning to drive faithfully in highly stochastic urban settings remains an\nopen problem. To that end, we propose a Multi-task Learning from Demonstration\n(MT-LfD) framework which uses supervised auxiliary task prediction to guide the\nmain task of predicting the driving commands. Our framework involves an\nend-to-end trainable network for imitating the expert demonstrator's driving\ncommands. The network intermediately predicts visual affordances and action\nprimitives through direct supervision which provide the aforementioned\nauxiliary supervised guidance. We demonstrate that such joint learning and\nsupervised guidance facilitates hierarchical task decomposition, assisting the\nagent to learn faster, achieve better driving performance and increases\ntransparency of the otherwise black-box end-to-end network. We run our\nexperiments to validate the MT-LfD framework in CARLA, an open-source urban\ndriving simulator. We introduce multiple non-player agents in CARLA and induce\ntemporal noise in them for realistic stochasticity.","url_abs":"http://arxiv.org/abs/1808.10393v1","url_pdf":"http://arxiv.org/pdf/1808.10393v1.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":"learning-end-to-end-autonomous-driving-using","repo_url":"https://github.com/AshishMehtaIO/MTLfD-CARLA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}