Show simple item record

dc.contributor.authorAmini, Alexander
dc.contributor.authorAraki, Brandon
dc.contributor.authorRus, Daniela
dc.contributor.authorSchwarting, Wilko
dc.contributor.authorRosman, Guy
dc.contributor.authorKaraman, Sertac
dc.contributor.authorRus, Daniela L
dc.date.accessioned2018-09-18T16:21:36Z
dc.date.available2018-09-18T16:21:36Z
dc.date.issued2018-10
dc.identifier.urihttp://hdl.handle.net/1721.1/118139
dc.description.abstractThis paper introduces a new method for end-to-end training of deep neural networks (DNNs) and evaluates it in the context of autonomous driving. DNN training has been shown to result in high accuracy for perception to action learning given sufficient training data. However, the trained models may fail without warning in situations with insufficient or biased training data. In this paper, we propose and evaluate a novel architecture for self-supervised learning of latent variables to detect the insufficiently trained situations. Our method also addresses training data imbalance, by learning a set of underlying latent variables that characterize the training data and evaluate potential biases. We show how these latent distributions can be leveraged to adapt and accelerate the training pipeline by training on only a fraction of the total dataset. We evaluate our approach on a challenging dataset for driving. The data is collected from a full-scale autonomous vehicle. Our method provides qualitative explanation for the latent variables learned in the model. Finally, we show how our model can be additionally trained as an end-to-end controller, directly outputting a steering control command for an autonomous vehicle.en_US
dc.language.isoen_US
dc.relation.isversionofhttps://www.iros2018.org/en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceAminien_US
dc.titleVariational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasingen_US
dc.typeArticleen_US
dc.identifier.citationAmini, Alexander, Wilko Schwarting, Guy Rosman, Brandon Araki. Sertac Karaman and Daniela Rus. "Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing." 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Palacio Municipal de Congresos, Madrid, Spain, Oct.1-5 2018)en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Aeronautics and Astronauticsen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineeringen_US
dc.contributor.approverAmini, Alexanderen_US
dc.contributor.mitauthorSchwarting, Wilko
dc.contributor.mitauthorRosman, Guy
dc.contributor.mitauthorKaraman, Sertac
dc.contributor.mitauthorRus, Daniela L
dc.relation.journal2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsAmini, Alexander; Schwarting, Wilko; Rosman, Guy, Araki, Brandon; Karaman, Sertac; Rus Danielaen_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-9334-1706
dc.identifier.orcidhttps://orcid.org/0000-0002-2225-7275
dc.identifier.orcidhttps://orcid.org/0000-0001-5473-3566
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record