{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:12:28Z","timestamp":1776107548425,"version":"3.50.1"},"reference-count":175,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2019,11,14]],"date-time":"2019-11-14T00:00:00Z","timestamp":1573689600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Field Robotics"],"published-print":{"date-parts":[[2020,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The last decade witnessed increasingly rapid progress in self\u2010driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state\u2010of\u2010the\u2010art on deep learning technologies used in autonomous driving. We start by presenting AI\u2010based self\u2010driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception\u2010planning\u2010action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.<\/jats:p>","DOI":"10.1002\/rob.21918","type":"journal-article","created":{"date-parts":[[2019,11,14]],"date-time":"2019-11-14T13:06:22Z","timestamp":1573736782000},"page":"362-386","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1460,"title":["A survey of deep learning techniques for autonomous driving"],"prefix":"10.1002","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4763-5540","authenticated-orcid":false,"given":"Sorin","family":"Grigorescu","sequence":"first","affiliation":[{"name":"Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of\u00a0Brasov Brasov Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6169-1181","authenticated-orcid":false,"given":"Bogdan","family":"Trasnea","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of\u00a0Brasov Brasov Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4311-0018","authenticated-orcid":false,"given":"Tiberiu","family":"Cocias","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of\u00a0Brasov Brasov Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9906-501X","authenticated-orcid":false,"given":"Gigel","family":"Macesanu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of\u00a0Brasov Brasov Romania"}]}],"member":"311","published-online":{"date-parts":[[2019,11,14]]},"reference":[{"key":"e_1_2_13_2_1","article-title":"Concrete problems in AI safety","author":"Amodei D.","year":"2016","journal-title":"arXiv preprint"},{"key":"e_1_2_13_3_1","article-title":"Learning dexterous in\u2010hand manipulation","author":"Andrychowicz M.","year":"2018","journal-title":"arXiv preprint"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_2_13_5_1","doi-asserted-by":"crossref","unstructured":"Barnes D. Maddern W. Pascoe G. &Posner I.(2018). Driven to distraction: Self\u2010supervised distractor learning for robust monocular visual odometry in urban environments. In2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE.","DOI":"10.1109\/ICRA.2018.8460564"},{"key":"e_1_2_13_6_1","unstructured":"Barsan I. A. Wang S. Pokrovsky A. &Urtasun R.(2018). Learning to localize using a LiDAR intensity map. InProceedings of the 2nd Conference on Robot Learning (CoRL)."},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2018.00011"},{"key":"e_1_2_13_8_1","volume-title":"Dynamic programming","author":"Bellman R.","year":"1957"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_13_10_1","unstructured":"Bernd S. Detlev R. Susanne E. Ulf W. Wolfgang B. &Carsten P.(2012). Challenges in applying the ISO 26262 for driver assistance systems. InSchwerpunkt Vernetzung 5. Tagung Fahrerassistenz."},{"key":"e_1_2_13_11_1","unstructured":"Bojarski M. Del Testa D. Dworakowski D. Firner B. Flepp B. Goyal P. \u2026Zhao J.(2016). End to End learning for self\u2010driving cars. arXiv preprint 1604.07316."},{"key":"e_1_2_13_12_1","unstructured":"Bojarski M. Yeres P. Choromanska A. Choromanski K. Firner B. Jackel L. &Muller U.(2017). Explaining how a deep neural network trained with end\u2010to\u2010end learning steers a car. arXiv preprint 1704.07911."},{"key":"e_1_2_13_13_1","doi-asserted-by":"crossref","unstructured":"Brachmann E. &Rother C.(2018). Learning less is more\u20146D camera localization via 3D surface regression. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018.","DOI":"10.1109\/CVPR.2018.00489"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2017.2749181"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264027"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66284-8_1"},{"key":"e_1_2_13_18_1","doi-asserted-by":"crossref","unstructured":"Caesar H. Bankiti V. Lang A. H. Vora S. Liong V. E. Xu Q. \u2026Beijbom O.(2019). nuScenes: A multimodal dataset for autonomous driving. arXiv preprint 1903.11027.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788613"},{"key":"e_1_2_13_20_1","unstructured":"Chakarov A. Nori A. Rajamani S. Sen S. &Vijaykeerthy D.(2018). Debugging machine learning tasks. arXiv preprint 1603.07292."},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_2_13_22_1","doi-asserted-by":"crossref","unstructured":"Chen X. Ma H. Wan J. Li B. &Xia T.(2017). Multi\u2010view 3D object detection network for autonomous driving. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017.","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_2_13_23_1","unstructured":"Cityscapes. (2018).Cityscapes data collection.\u00a0Retrieved fromhttps:\/\/www.cityscapes\u2010dataset.com\/"},{"key":"e_1_2_13_24_1","doi-asserted-by":"crossref","unstructured":"Cong J. Fang Z. Lo M. Wang H. Xu J. &Zhang S.(2018). Understanding performance differences of FPGAs and GPUs: (Abtract only). InProceedings of the 2018 ACM\/SIGDA International Symposium on Field\u2010Programmable Gate Arrays (FPGA \u201918) (p. 288). New York NY: ACM.","DOI":"10.1145\/3174243.3174970"},{"key":"e_1_2_13_25_1","unstructured":"Dai J. Li Y. He K. &Sun J.(2016). R\u2010FCN: Object detection via region\u2010based fully convolutional networks.Advances in Neural Information Processing Systems NIPS 2016 379\u2013387."},{"key":"e_1_2_13_26_1","unstructured":"Dalal N. &Triggs B.(2005). Histograms of oriented gradients for human detection. InIEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2005."},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1872"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01212361"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"e_1_2_13_30_1","first-page":"133","article-title":"Aggressive deep driving: Combining convolutional neural networks and model predictive control","volume":"78","author":"Drews P.","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"e_1_2_13_31_1","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi J.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_13_32_1","article-title":"End\u2010to\u2010end deep learning for steering autonomous vehicles considering temporal dependencies","author":"Eraqi H. M.","year":"2017","journal-title":"Machine Learning for Intelligent Transportation Systems Workshop in the 31st Conference on Neural Information Processing Systems NIPS 2017."},{"key":"e_1_2_13_33_1","article-title":"Machine Learning Safety: An Overview","author":"Faria J. M.","year":"2018","journal-title":"Safety\u2010Critical Systems Club"},{"key":"e_1_2_13_34_1","unstructured":"Ferrel T.(2010).Engineering safety\u2010critical systems in the 21st century."},{"key":"e_1_2_13_35_1","unstructured":"Flohr F. &Gavrila D. M.(2013). Daimler pedestrian segmentation benchmark dataset. InProceedings of the British Machine Vision Conference."},{"key":"e_1_2_13_36_1","unstructured":"Fridman L. Brown D. E. Glazer M. Angell W. Dodd S. Jenik B. \u2026Reimer B.(2017). MIT autonomous vehicle technology study: Large\u2010scale deep learning based analysis of driver behavior and interaction with automation. InIEEE Access 2017."},{"key":"e_1_2_13_37_1","unstructured":"Garcia\u2010Favrot O. &Parent M.(2009). Laser scanner based SLAM in real road and traffic environment. InIEEE International Conference on Robotics and Automation (ICRA09). Workshop on Safe Navigation in Open and Dynamic Environments Application to Autonomous Vehicles."},{"key":"e_1_2_13_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_2_13_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_13_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_13_41_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00762ED1V01Y201703HLT037"},{"key":"e_1_2_13_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"e_1_2_13_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926224"},{"key":"e_1_2_13_44_1","first-page":"2829","volume-title":"International Conference on Machine Learning ICML 2016","author":"Gu S.","year":"2016"},{"key":"e_1_2_13_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2016.7535466"},{"key":"e_1_2_13_46_1","article-title":"Google reports self\u2010driving car mistakes: 272 Failures and 13 near misses","author":"Harris M.","year":"2016","journal-title":"The Guardian"},{"key":"e_1_2_13_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795918"},{"key":"e_1_2_13_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_13_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_13_50_1","doi-asserted-by":"crossref","unstructured":"Hecker S. Dai D. &VanGool L.(2018). End\u2010to\u2010end learning of driving models with surround\u2010view cameras and route planners. InEuropean Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-030-01234-2_27"},{"key":"e_1_2_13_51_1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"Hessel M.","year":"2018","journal-title":"Artificial Intelligence 2018?"},{"key":"e_1_2_13_52_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_13_53_1","doi-asserted-by":"crossref","unstructured":"Hoermann S. Bach M. &Dietmayer K.(2017). Dynamic occupancy grid prediction for urban autonomous driving: Deep learning approach with fully automatic labeling. InIEEE International Conference on Robotics and Automation (ICRA).","DOI":"10.1109\/ICRA.2018.8460874"},{"key":"e_1_2_13_54_1","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1963.sp007079"},{"key":"e_1_2_13_55_1","unstructured":"Iandola F. N. Han S. Moskewicz M. W. Ashraf K. Dally W. J. &Keutzer K.(2016). SqueezeNet: AlexNet\u2010level accuracy with 50x fewer parameters and <0.5 Mb model size. arXiv preprint 1602.07360."},{"key":"e_1_2_13_56_1","article-title":"Computer vision for autonomous vehicles: Problems, datasets and state\u2010of\u2010the\u2010art","author":"Janai J.","year":"2017","journal-title":"ArXiv preprint, 1704.05519"},{"key":"e_1_2_13_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"e_1_2_13_58_1","first-page":"10","article-title":"A review on motion control of unmanned ground and aerial vehicles based on model predictive control techniques","volume":"2","author":"Kamel M.","year":"2018","journal-title":"Engineering Science and Military Technologies"},{"key":"e_1_2_13_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7171151"},{"key":"e_1_2_13_60_1","doi-asserted-by":"crossref","unstructured":"Katz G. Barrett C. W. Dill D. L. Julian K. &Kochenderfer M. J.(2017). Reluplex: An efficient SMT solver for verifying deep neural networks. InCAV.","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"e_1_2_13_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"e_1_2_13_62_1","author":"Kendall A.","year":"2018","journal-title":"Learning to drive in a day"},{"key":"e_1_2_13_63_1","unstructured":"Kingma D. P. &Ba J.(2015). Adam: A method for stochastic optimization. InThird International Conference on Learning Representations (ICLR 2015). San Diego CA."},{"key":"e_1_2_13_64_1","doi-asserted-by":"crossref","unstructured":"Koopman P.(2017). Challenges in autonomous vehicle validation: Keynote presentation abstract. InProceedings of the 1st International Workshop on Safe Control of Connected and Autonomous Vehicles.","DOI":"10.1145\/3055378.3055379"},{"key":"e_1_2_13_65_1","doi-asserted-by":"crossref","unstructured":"Koschorrek P. Piccini T. \u00d6berg P. Felsberg M. Nielsen L. &Mester R.(2013). A multi\u2010sensor traffic scene dataset with omnidirectional video. InGround Truth\u2014What is a Good Dataset? CVPR Workshop 2013.","DOI":"10.1109\/CVPRW.2013.110"},{"key":"e_1_2_13_66_1","first-page":"1097","volume-title":"Advances in neural information processing systems (NIPS)","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_2_13_67_1","doi-asserted-by":"crossref","unstructured":"Ku J. Mozifian M. Lee J. Harakeh A. &Waslander S. L.(2018). Joint 3D proposal generation and object detection from view aggregation. InIEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 2018. IEEE.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"e_1_2_13_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-006-0039-9"},{"key":"e_1_2_13_69_1","doi-asserted-by":"crossref","unstructured":"Laskar Z. Melekhov I. Kalia S. &Kannala J.(2017). Camera relocalization by computing pairwise relative poses using convolutional neural network. InThe IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCVW.2017.113"},{"key":"e_1_2_13_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_2_13_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_13_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225802"},{"key":"e_1_2_13_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2498192"},{"key":"e_1_2_13_74_1","unstructured":"Levin S.(2018).Tesla fatal crash: \u2018Autopilot\u2019 mode sped up car before driver killed report finds. The Guardian.https:\/\/www.theguardian.com\/technology\/2016\/jun\/30\/tesla-autopilot-death-self-driving-car-elon-musk"},{"key":"e_1_2_13_75_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym10070235"},{"key":"e_1_2_13_76_1","first-page":"1028","volume-title":"2016 IEEE Intelligent Vehicles Symposium (IV)","author":"Li X.","year":"2016"},{"key":"e_1_2_13_77_1","author":"Lillicrap T. P.","year":"2016","journal-title":"Continuous control with deep reinforcement learning"},{"key":"e_1_2_13_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.378"},{"key":"e_1_2_13_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_13_80_1","doi-asserted-by":"crossref","unstructured":"Luo W. Yang B. &Urtasun R.(2018). Fast and furious: Real time end\u2010to\u2010end 3D detection tracking and motion forecasting with a single convolutional net. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018).","DOI":"10.1109\/CVPR.2018.00376"},{"key":"e_1_2_13_81_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"e_1_2_13_82_1","doi-asserted-by":"crossref","unstructured":"Marina L. Trasnea B. Cocias T. Vasilcoi A. Moldoveanu F. &Grigorescu S.(2019). Deep grid net (DGN): A deep learning system for real\u2010time driving context understanding. InInternational Conference on Robotic Computing (ICRC 2019). Naples Italy.","DOI":"10.1109\/IRC.2019.00073"},{"key":"e_1_2_13_83_1","article-title":"How Uber's self\u2010driving technology could have failed in the fatal tempe crash","author":"McPherson J.","year":"2018","journal-title":"Forbes"},{"key":"e_1_2_13_84_1","doi-asserted-by":"crossref","unstructured":"Meier F. Hennig P. &Schaal S.(2014). Efficient Bayesian local model learning for control. InIEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2016) (pp. 2244\u20132249). IEEE.","DOI":"10.1109\/IROS.2014.6942865"},{"key":"e_1_2_13_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.107"},{"key":"e_1_2_13_86_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_2_13_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-1433-5_3"},{"key":"e_1_2_13_88_1","first-page":"739","article-title":"Off\u2010road obstacle avoidance through end\u2010to\u2010end learning","author":"Muller U.","year":"2006","journal-title":"Advances in neural information processing systems NIPS 2006"},{"key":"e_1_2_13_89_1","first-page":"1193","volume-title":"Proceedings of the Neural Information Processing Systems Conference","author":"Nguyen\u2010Tuong D.","year":"2008"},{"key":"e_1_2_13_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021740"},{"key":"e_1_2_13_91_1","doi-asserted-by":"crossref","unstructured":"Nushi B. Kamar E. Horvitz E. &Kossmann D.(2017). On human intellect and machine failures: Troubleshooting integrative machine learning systems. InAAAI.","DOI":"10.1609\/aaai.v31i1.10633"},{"key":"e_1_2_13_92_1","unstructured":"NVIDIA.Denver core. Retrieved fromhttps:\/\/en.wikichip.org\/wiki\/nvidia\/microarchitectures\/denver"},{"key":"e_1_2_13_93_1","unstructured":"NVIDIA.NVIDIA AI car computer drive PX. Retrieved fromhttps:\/\/www.nvidia.com\/en\u2010au\/self\u2010driving\u2010cars\/drive\u2010px\/"},{"key":"e_1_2_13_94_1","unstructured":"NVIDIA.NVIDIA drive AGX.\u00a0Retrieved fromhttps:\/\/www.nvidia.com\/en\u2010us\/self\u2010driving\u2010cars\/drive\u2010platform\/hardware\/"},{"key":"e_1_2_13_95_1","unstructured":"NVIDIA.NVIDIA Volta.\u00a0Retrieved fromhttps:\/\/www.nvidia.com\/en\u2010us\/data\u2010center\/volta\u2010gpu\u2010architecture\/"},{"key":"e_1_2_13_96_1","unstructured":"NVIDIA.Pascal microarchitecture.\u00a0Retrieved fromhttps:\/\/www.nvidia.com\/en\u2010us\/data\u2010center\/pascal\u2010gpu\u2010architecture\/"},{"key":"e_1_2_13_97_1","unstructured":"NVIDIA.Tegra X2.\u00a0Retrieved fromhttps:\/\/devblogs.nvidia.com\/jetson\u2010tx2\u2010delivers\u2010twice\u2010intelligence\u2010edge\/"},{"key":"e_1_2_13_98_1","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(95)00067-4"},{"key":"e_1_2_13_99_1","article-title":"How Tesla and Waymo are tackling a major problem for self\u2010driving cars: Data","author":"O'Kane S.","year":"2018","journal-title":"Transportation"},{"key":"e_1_2_13_100_1","unstructured":"Ondruska P. Dequaire J. Wang D. Z. &Posner I.(2016).End\u2010to\u2010end tracking and semantic segmentation using recurrent neural networks. ArXiv preprint 1604.05091."},{"key":"e_1_2_13_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696350"},{"key":"e_1_2_13_102_1","unstructured":"Ostafew C. J.(2016).Learning\u2010based control for autonomous mobile robots(Ph.D. thesis). Canada: University of Toronto."},{"key":"e_1_2_13_103_1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21587"},{"key":"e_1_2_13_104_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916645661"},{"key":"e_1_2_13_105_1","article-title":"Accelerating deep convolutional neural networks using specialized hardware","author":"Ovtcharov K.","year":"2015","journal-title":"Microsoft whitepaper"},{"key":"e_1_2_13_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"e_1_2_13_107_1","first-page":"1","volume-title":"Robotics: Science and Systems 2018","author":"Pan Y.","year":"2018"},{"key":"e_1_2_13_108_1","volume-title":"31st Conference on Neural Information Processing Systems NIPS 2017","author":"Pan Y.","year":"2017"},{"key":"e_1_2_13_109_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911400640"},{"key":"e_1_2_13_110_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12239-017-0107-4"},{"key":"e_1_2_13_111_1","doi-asserted-by":"crossref","unstructured":"Panov A. I. Yakovlev K. S. &Suvorov R.(2018). Grid path planning with deep reinforcement learning: Preliminary results. In8th Annual International Conference on Biologically Inspired Cognitive Architectures (BICA 2017). Procedia Computer Science 123 347\u2013353.","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"e_1_2_13_112_1","doi-asserted-by":"publisher","DOI":"10.1518\/001872097778543886"},{"key":"e_1_2_13_113_1","unstructured":"Paszke A. Chaurasia A. Kim S. &Culurciello E.(2016). Enet: A deep neural network architecture for real\u2010time semantic segmentation. arXiv preprint 1606.02147."},{"key":"e_1_2_13_114_1","doi-asserted-by":"crossref","unstructured":"Paxton C. Raman V. Hager G. D. &Kobilarov M.(2017). Combining neural networks and tree search for task and motion planning in challenging environments. In2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). abs\/1703.07887.","DOI":"10.1109\/IROS.2017.8206505"},{"key":"e_1_2_13_115_1","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010006"},{"key":"e_1_2_13_116_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"e_1_2_13_117_1","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"Pomerleau D. A.","year":"1989","journal-title":"Advances in neural information processing systems NIPS 1989"},{"key":"e_1_2_13_118_1","doi-asserted-by":"crossref","unstructured":"Qi C. R. Liu W. Wu C. Su H. &Guibas L. J.(2018). Frustum PointNets for 3D object detection from RGB\u2010D data. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"e_1_2_13_119_1","unstructured":"Qi C. R. Su H. Mo K. &Guibas L. J.(2017). PointNet: Deep learning on point sets for 3D classification and segmentation. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_13_120_1","first-page":"5","article-title":"On the safety of machine learning: Cyber\u2010physical systems, decision sciences, and data products","author":"Varshney K. P.","year":"2016","journal-title":"Big Data"},{"key":"e_1_2_13_121_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869640"},{"key":"e_1_2_13_122_1","doi-asserted-by":"crossref","unstructured":"Ramos S. Gehrig S. K. Pinggera P. Franke U. &Rother C.(2016). Detecting unexpected obstacles for self\u2010driving cars: Fusing deep learning and geometric modeling. InIEEE Intelligent Vehicles Symposium(Vol. 4).","DOI":"10.1109\/IVS.2017.7995849"},{"key":"e_1_2_13_123_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963716"},{"key":"e_1_2_13_124_1","volume-title":"Model predictive control: Theory and design","author":"Rawlings J.","year":"2009"},{"key":"e_1_2_13_125_1","unstructured":"2016 J. Redmon S. Divvala R. Girshick A. Farhadi You only look once: Unified real\u2010time object detectionProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 779 788"},{"key":"e_1_2_13_126_1","doi-asserted-by":"crossref","unstructured":"Redmon J. &Farhadi A.(2017). YOLO9000: Better faster stronger. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_13_127_1","unstructured":"Redmon J. &Farhadi A.(2018). Yolov3: An incremental improvement. arXiv preprint 1804.02767."},{"key":"e_1_2_13_128_1","unstructured":"Rehder E. Quehl J. &Stiller C.(2017). Driving like a human: Imitation learning for path planning using convolutional neural networks. InInternational Conference on Robotics and Automation Workshops."},{"key":"e_1_2_13_129_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_13_130_1","unstructured":"Renesas.R\u2010Car H3. Retrieved fromhttps:\/\/www.renesas.com\/sg\/en\/solutions\/automotive\/soc\/r\u2010car\u2010h3.html\/"},{"key":"e_1_2_13_131_1","unstructured":"Renesas.R\u2010Car V3H. Retrieved fromhttps:\/\/www.renesas.com\/eu\/en\/solutions\/automotive\/soc\/r\u2010car\u2010v3h.html\/"},{"key":"e_1_2_13_132_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963748"},{"key":"e_1_2_13_133_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"e_1_2_13_134_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_13_135_1","author":"SAE Committee","year":"2014","journal-title":"Taxonomy and definitions for terms related to on\u2010road motor vehicle automated driving systems"},{"key":"e_1_2_13_136_1","doi-asserted-by":"crossref","unstructured":"Salay R. Queiroz R. &Czarnecki K.(2017).An analysis of ISO 26262: Machine learning and safety in automotive software(SAE Technical Paper).https:\/\/www.sae.org\/publications\/technical-papers\/content\/2018-01-1075\/","DOI":"10.4271\/2018-01-1075"},{"key":"e_1_2_13_137_1","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"e_1_2_13_138_1","article-title":"Deep reinforcement learning framework for autonomous driving","author":"Sallab A. E.","year":"2017","journal-title":"CoRR"},{"key":"e_1_2_13_139_1","unstructured":"Sarlin P. Debraine F. Dymczyk M. Siegwart R. &Cadena C.(2018). Leveraging deep visual descriptors for hierarchical efficient localization. InProceedings of the 2nd Conference on Robot Learning (CoRL)."},{"key":"e_1_2_13_140_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"e_1_2_13_141_1","unstructured":"Seeger C. M\u00fcller A. &Schwarz L.(2016). Towards road type classification with occupancy grids. InIntelligent Vehicles Symposium\u2014Workshop: DeepDriving\u2014Learning Representations for Intelligent Vehicles IEEE. Gothenburg Sweden."},{"key":"e_1_2_13_142_1","author":"Shalev\u2010Shwartz S.","year":"2016","journal-title":"Safe, multi\u2010agent, reinforcement learning for autonomous driving"},{"key":"e_1_2_13_143_1","first-page":"2510","article-title":"RoarNet: A robust 3D object detection based on region approximation refinement","author":"Shin K.","year":"2018","journal-title":"2019 IEEE Intelligent Vehicles Symposium (IV)"},{"key":"e_1_2_13_144_1","unstructured":"Sick.(2018).Sick LiDAR for data collection.\u00a0Retrieved fromhttps:\/\/www.sick.com\/"},{"key":"e_1_2_13_145_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.006"},{"key":"e_1_2_13_146_1","article-title":"Very deep convolutional networks for large\u2010scale image recognition","author":"Simonyan K.","year":"2014","journal-title":"International Conference on Learning Representations 2015"},{"key":"e_1_2_13_147_1","doi-asserted-by":"crossref","unstructured":"Sun L. Peng C. Zhan W. &Tomizuka M.(2018). A fast integrated planning and control framework for autonomous driving via imitation learning. InASME 2018 Dynamic Systems and Control Conference(Vol. 3).","DOI":"10.1115\/DSCC2018-9249"},{"key":"e_1_2_13_148_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_2_13_149_1","doi-asserted-by":"crossref","unstructured":"Szegedy C. Liu W. Jia Y. Sermanet P. Reed S. Anguelov D. \u2026Rabinovich A.(2015). Going deeper with convolutions. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_13_150_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.861360"},{"key":"e_1_2_13_151_1","volume-title":"Probabilistic robotics (Intelligent robotics and autonomous agents)","author":"Thrun S.","year":"2005"},{"key":"e_1_2_13_152_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2895264"},{"key":"e_1_2_13_153_1","author":"Treml M.","year":"2016","journal-title":"Speeding up semantic segmentation for autonomous driving."},{"key":"e_1_2_13_154_1","unstructured":"Udacity.(2018).Udacity data collection.\u00a0Retrieved fromhttp:\/\/academictorrents.com\/collection\/self\u2010driving\u2010cars"},{"key":"e_1_2_13_155_1","first-page":"283","volume-title":"Proceedings of the 2nd Conference on Robot Learning (CoRL)","author":"Ushani A. K.","year":"2018"},{"key":"e_1_2_13_156_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989540"},{"key":"e_1_2_13_157_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2016.7888195"},{"key":"e_1_2_13_158_1","unstructured":"Velodyne(2018).Velodyne LiDAR for data collection.https:\/\/velodynelidar.com\/"},{"key":"e_1_2_13_159_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"e_1_2_13_160_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.75"},{"key":"e_1_2_13_161_1","doi-asserted-by":"crossref","unstructured":"Wang Y. Chao W.\u2010L. Garg D. Hariharan B. Campbell M. &Weinberger K.(2019). Pseudo\u2010LiDAR from visual depth estimation: Bridging the gap in 3D object detection for autonomous driving. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019).","DOI":"10.1109\/CVPR.2019.00864"},{"key":"e_1_2_13_162_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_2_13_163_1","doi-asserted-by":"crossref","unstructured":"Wulfmeier M. Wang D. Z. &Posner I.(2016). Watch this: Scalable cost\u2010function learning for path planning in urban environments. In2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). abs\/1607.02329.","DOI":"10.1109\/IROS.2016.7759328"},{"key":"e_1_2_13_164_1","doi-asserted-by":"crossref","unstructured":"Xu H. Gao Y. Yu F. &Darrell T.(2017). End\u2010to\u2010end learning of driving models from large\u2010scale video datasets. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2017.376"},{"key":"e_1_2_13_165_1","doi-asserted-by":"crossref","unstructured":"Yang S. Wang W. Liu C. Deng K. &Hedrick J. K.(2017a). Feature analysis and selection for training an end\u2010to\u2010end autonomous vehicle controller using the deep learning approach. In2017 IEEE Intelligent Vehicles Symposium(Vol. 1).","DOI":"10.1109\/IVS.2017.7995850"},{"key":"e_1_2_13_166_1","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417710634"},{"key":"e_1_2_13_167_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317828"},{"key":"e_1_2_13_168_1","unstructured":"Yu F. Xian W. Chen Y. Liu F. Liao M. Madhavan V. &Darrell T.(2018).BDD100K: A diverse driving video database with scalable annotation tooling. ArXiv preprint 1805.04687."},{"key":"e_1_2_13_169_1","first-page":"1","article-title":"Intelligent land\u2010vehicle model transfer trajectory planning method based on deep reinforcement learning","volume":"18","author":"Yu L.","year":"2018","journal-title":"Sensors (Basel, Switzerland)"},{"key":"e_1_2_13_170_1","doi-asserted-by":"crossref","unstructured":"Zhang S. Wen L. Bian X. Lei Z. &Li S. Z.(2017). Single\u2010shot refinement neural network for object detection. InIEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00442"},{"key":"e_1_2_13_171_1","doi-asserted-by":"crossref","unstructured":"Zhang T. Kahn G. Levine S. &Abbeel P.(2016). Learning deep control policies for autonomous aerial vehicles with MPC\u2010guided policy search. In2016 IEEE International Conference on Robotics and Automation (ICRA).","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"e_1_2_13_172_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"e_1_2_13_173_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_2_13_174_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"e_1_2_13_175_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"e_1_2_13_176_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2658662"}],"container-title":["Journal of Field Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.21918","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/rob.21918","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rob.21918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T20:40:50Z","timestamp":1694032850000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/rob.21918"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,14]]},"references-count":175,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["10.1002\/rob.21918"],"URL":"https:\/\/doi.org\/10.1002\/rob.21918","archive":["Portico"],"relation":{},"ISSN":["1556-4959","1556-4967"],"issn-type":[{"value":"1556-4959","type":"print"},{"value":"1556-4967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,14]]},"assertion":[{"value":"2019-02-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-11-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}