{"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/robust-and-subject-independent-driving","title":"Robust and Subject-Independent Driving Manoeuvre Anticipation through Domain-Adversarial Recurrent Neural Networks","arxiv_id":"1902.09820","date":"2019-02-26","proceeding":null,"authors":["Michele Tonutti","Emanuele Ruffaldi","Alessandro Cattaneo","Carlo Alberto Avizzano"],"abstract":"Through deep learning and computer vision techniques, driving manoeuvres can\nbe predicted accurately a few seconds in advance. Even though adapting a\nlearned model to new drivers and different vehicles is key for robust\ndriver-assistance systems, this problem has received little attention so far.\nThis work proposes to tackle this challenge through domain adaptation, a\ntechnique closely related to transfer learning. A proof of concept for the\napplication of a Domain-Adversarial Recurrent Neural Network (DA-RNN) to\nmulti-modal time series driving data is presented, in which domain-invariant\nfeatures are learned by maximizing the loss of an auxiliary domain classifier.\nOur implementation is evaluated using a leave-one-driver-out approach on\nindividual drivers from the Brain4Cars dataset, as well as using a new dataset\nacquired through driving simulations, yielding an average increase in\nperformance of 30% and 114% respectively compared to no adaptation. We also\nshow the importance of fine-tuning sections of the network to optimise the\nextraction of domain-independent features. The results demonstrate the\napplicability of the approach to driver-assistance systems as well as training\nand simulation environments.","url_abs":"http://arxiv.org/abs/1902.09820v1","url_pdf":"http://arxiv.org/pdf/1902.09820v1.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":"robust-and-subject-independent-driving","repo_url":"https://github.com/michetonu/DA-RNN_manoeuver_anticipation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}