{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T13:00:37Z","timestamp":1775307637173,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/itsc.2018.8569977","type":"proceedings-article","created":{"date-parts":[[2018,12,12]],"date-time":"2018-12-12T20:21:46Z","timestamp":1544646106000},"page":"2391-2397","source":"Crossref","is-referenced-by-count":37,"title":["Deep Reinforcement Learning for Predictive Longitudinal Control of Automated Vehicles"],"prefix":"10.1109","author":[{"given":"Martin","family":"Buechel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"7043","DOI":"10.3182\/20140824-6-ZA-1003.02042","article-title":"On-line Reinforcement Learning for Nonlinear Motion Control: Quadratic and Non-quadratic Reward Functions","volume":"19","author":"engel","year":"2014","journal-title":"IFAC Proceedings Volumes (IFAC-PapersOnline)"},{"key":"ref38","first-page":"13179","article-title":"Design of Experiments for Nonlinear Dynamic System Identification","author":"deflorian","year":"2011","journal-title":"18th IFAC World Con-gress"},{"key":"ref33","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref31","first-page":"1","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref30","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"},{"key":"ref37","article-title":"Dynamic Powertrain Calibration: Using Transient DoE and Modelling Techniques","volume":"49","author":"vogels","year":"2005","journal-title":"Design of experiments (DoE) In Engine Development II Haus der Technik Fachbuch"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04323-3"},{"key":"ref35","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"},{"key":"ref34","first-page":"1","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"494","DOI":"10.3390\/wevj3030494","article-title":"Predictive Cruise Control in Hybrid Electric Vehicles","volume":"3","author":"keulen","year":"2009","journal-title":"World Electric Vehicle Journal"},{"key":"ref40","first-page":"1","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2015.7260933"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.09.034"},{"key":"ref13","article-title":"A Parallel Hybrid Electric Vehicle Energy Management Strategy Using Stochastic Model Predictive Control With Road Grade Preview","author":"xiangrui","year":"2015","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2354052"},{"key":"ref15","author":"chiang","year":"2008","journal-title":"Longitudinal and Lateral Control Design for Vehicle Automated Driving"},{"key":"ref16","year":"2016","journal-title":"SAE Document J3016 - Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2017.8003215"},{"key":"ref18","first-page":"333","author":"sutton","year":"2017","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the Game of Go with Deep Neural Networks and Tree Search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref28","author":"bischoff","year":"2013","journal-title":"Learning Throttle Valve Control Using Policy Search"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.07.729"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2271276"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2699283"},{"key":"ref6","article-title":"Designing a Far-Reaching View for Highway Traffic Scenarios with 5G-Based Intelligent Infrastructure","author":"hinz","year":"2017","journal-title":"8 Tagung Fahrerassistenzsysteme TUEV - Sued"},{"key":"ref29","author":"duan","year":"2016","journal-title":"Benchmarking deep reinforcement learning for continuous control"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2016.7587829"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.ifacol.2015.11.277","article-title":"Nonlinear MPC for Emission Efficient Cooperative Adaptive Cruise Control","volume":"48","author":"schmied","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref7","author":"radke","year":"2013","journal-title":"Energieoptimale La?ngsfu?hrung von Kraftfahrzeugen Durch Einsatz Vorausschauender Fahrstrategien"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417740711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2006.285897"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ifacol.2017.08.2191","article-title":"Finite-Time Stabilization of Longitudinal Control for Autonomous Vehicles via a Model-Free Approach","author":"polack","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref20","first-page":"1","author":"silver","year":"2017","journal-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007630"},{"key":"ref24","first-page":"32","author":"mirchevska","year":"2017","journal-title":"Reinforcement Learning for Autonomous Maneuvering in Highway Scenarios"},{"key":"ref41","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref23","author":"bojarski","year":"2016","journal-title":"End to End Learning for Self-Driving Cars"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.853698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2157145"}],"event":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","location":"Maui, HI","start":{"date-parts":[[2018,11,4]]},"end":{"date-parts":[[2018,11,7]]}},"container-title":["2018 21st International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8543039\/8569013\/08569977.pdf?arnumber=8569977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T12:05:14Z","timestamp":1775304314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8569977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/itsc.2018.8569977","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}