Learning to Drive in a Day

We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain r...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-09
Main Authors: Kendall, Alex, Hawke, Jeffrey, Janz, David, Mazur, Przemyslaw, Reda, Daniele, John-Mark, Allen, Lam, Vinh-Dieu, Bewley, Alex, Shah, Amar
Format: Article
Language:English
Subjects:
Algorithms
Drivers
Machine learning
Mapping
Optimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Kendall, Alex
Hawke, Jeffrey
Janz, David
Mazur, Przemyslaw
Reda, Daniele
John-Mark, Allen
Lam, Vinh-Dieu
Bewley, Alex
Shah, Amar
description We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073478986</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073478986</sourcerecordid><originalsourceid>FETCH-proquest_journals_20734789863</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSQ8klNLMrLzEtXKMlXcCnKLEtVyMxTSFRwSazkYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwNzYxNzC0sLM2PiVAEAbjIqDg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073478986</pqid></control><display><type>article</type><title>Learning to Drive in a Day</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Kendall, Alex ; Hawke, Jeffrey ; Janz, David ; Mazur, Przemyslaw ; Reda, Daniele ; John-Mark, Allen ; Lam, Vinh-Dieu ; Bewley, Alex ; Shah, Amar</creator><creatorcontrib>Kendall, Alex ; Hawke, Jeffrey ; Janz, David ; Mazur, Przemyslaw ; Reda, Daniele ; John-Mark, Allen ; Lam, Vinh-Dieu ; Bewley, Alex ; Shah, Amar</creatorcontrib><description>We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Drivers ; Machine learning ; Mapping ; Optimization</subject><ispartof>arXiv.org, 2018-09</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2073478986?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Kendall, Alex</creatorcontrib><creatorcontrib>Hawke, Jeffrey</creatorcontrib><creatorcontrib>Janz, David</creatorcontrib><creatorcontrib>Mazur, Przemyslaw</creatorcontrib><creatorcontrib>Reda, Daniele</creatorcontrib><creatorcontrib>John-Mark, Allen</creatorcontrib><creatorcontrib>Lam, Vinh-Dieu</creatorcontrib><creatorcontrib>Bewley, Alex</creatorcontrib><creatorcontrib>Shah, Amar</creatorcontrib><title>Learning to Drive in a Day</title><title>arXiv.org</title><description>We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.</description><subject>Algorithms</subject><subject>Drivers</subject><subject>Machine learning</subject><subject>Mapping</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSQ8klNLMrLzEtXKMlXcCnKLEtVyMxTSFRwSazkYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwNzYxNzC0sLM2PiVAEAbjIqDg</recordid><startdate>20180911</startdate><enddate>20180911</enddate><creator>Kendall, Alex</creator><creator>Hawke, Jeffrey</creator><creator>Janz, David</creator><creator>Mazur, Przemyslaw</creator><creator>Reda, Daniele</creator><creator>John-Mark, Allen</creator><creator>Lam, Vinh-Dieu</creator><creator>Bewley, Alex</creator><creator>Shah, Amar</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180911</creationdate><title>Learning to Drive in a Day</title><author>Kendall, Alex ; Hawke, Jeffrey ; Janz, David ; Mazur, Przemyslaw ; Reda, Daniele ; John-Mark, Allen ; Lam, Vinh-Dieu ; Bewley, Alex ; Shah, Amar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20734789863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Drivers</topic><topic>Machine learning</topic><topic>Mapping</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Kendall, Alex</creatorcontrib><creatorcontrib>Hawke, Jeffrey</creatorcontrib><creatorcontrib>Janz, David</creatorcontrib><creatorcontrib>Mazur, Przemyslaw</creatorcontrib><creatorcontrib>Reda, Daniele</creatorcontrib><creatorcontrib>John-Mark, Allen</creatorcontrib><creatorcontrib>Lam, Vinh-Dieu</creatorcontrib><creatorcontrib>Bewley, Alex</creatorcontrib><creatorcontrib>Shah, Amar</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kendall, Alex</au><au>Hawke, Jeffrey</au><au>Janz, David</au><au>Mazur, Przemyslaw</au><au>Reda, Daniele</au><au>John-Mark, Allen</au><au>Lam, Vinh-Dieu</au><au>Bewley, Alex</au><au>Shah, Amar</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Learning to Drive in a Day</atitle><jtitle>arXiv.org</jtitle><date>2018-09-11</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2073478986
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Algorithms
Drivers
Machine learning
Mapping
Optimization
title Learning to Drive in a Day
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T14%3A23%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Learning%20to%20Drive%20in%20a%20Day&rft.jtitle=arXiv.org&rft.au=Kendall,%20Alex&rft.date=2018-09-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073478986%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20734789863%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2073478986&rft_id=info:pmid/&rfr_iscdi=true