[1]王科俊,赵彦东,邢向磊.深度学习在无人驾驶汽车领域应用的研究进展[J].智能系统学报,2018,(01):55-69.[doi:10.11992/tis.201609029]
 WANG Kejun,ZHAO Yandong,XING Xianglei.Deep learning in driverless vehicles[J].CAAI Transactions on Intelligent Systems,2018,(01):55-69.[doi:10.11992/tis.201609029]
点击复制

深度学习在无人驾驶汽车领域应用的研究进展(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
期数:
2018年01期
页码:
55-69
栏目:
出版日期:
2018-01-24

文章信息/Info

Title:
Deep learning in driverless vehicles
作者:
王科俊 赵彦东 邢向磊
哈尔滨工程大学 自动化学院, 黑龙江 哈尔滨 150001
Author(s):
WANG Kejun ZHAO Yandong XING Xianglei
School of Automation, Harbin Engineering University, Harbin 150001, China
关键词:
无人驾驶图像处理深度学习卷积神经网络计算机视觉
Keywords:
driverless vehiclesimage processingdeep learningconvolutional Neural Networkscomputer Vision
分类号:
TP18
DOI:
10.11992/tis.201609029
摘要:
首先阐述了汽车界对无人驾驶的定义,然后详细分析了国内外无人驾驶汽车的发展历史以及各车企和互联网公司的研究现状。通过详细分析无人驾驶汽车工作原理、体系架构设计以及具体实现方法,简单说明了目前无人驾驶汽车遇到的关键问题和难题,同时重点描述了目前深度学习在图像处理方面的突破性进展以及在无人驾驶汽车领域的应用实践,最后对无人驾驶的未来发展做了展望。
Abstract:
In this paper, we first define the unmanned vehicle and analyze the current technology and key problems of driverless vehicles.Then, we discuss the principles and architectural design of driverless cars and identify their key problems. Lastly, we describe the development of deep learning with respect to image processing, discuss the application of deep learning to driverless vehicles, and consider the future of driverless vehicles.

参考文献/References:

[1] 倪暖. 自动驾驶也分三六九等?[EB/OL].(2016-8-07)[2016-09-27] http://www.ednchina.com/news/article/201608170801.
[2] 佚名. 无人驾驶汽车[EB/OL]. (2016-06-10)[2016-09-27]http://baike.baidu.com/link?url=iObG6G1U5wmuVNCdgm7wXDpV8418yWtKAlBAVjC4xyVEL7Lgy3fgfkpsda4qiABZHCsxtQ9J9xqqcsZdTu_vF6kAT6xwu7zedQw2ggyuqa.
[3] 腾讯汽车. 国外无人驾驶技术发展调研报告[EB/OL]. (2015-05-23)[2016-09-27] https://wenku.baidu.com/view/472fa34458f5f61fb636664d.html.
[4] 张翔. 2013年全球汽车技术发展趋势[J]. 汽车工程师, 2013(3): 19-21, 52.
ZHANG Xiang. The development trend of global automotive technology at 2013[J]. Tianjin auto, 2013(3): 19-21, 52.
[5] 林靖东. 美国内华达州批准谷歌无人驾驶汽车上路测[EB/OL].(2012-05-08)[2016-09-27] http://tech.qq.com/a/20120508/000235.htm.
[6] GREENBLATT N A. Self-driving cars and the law[J]. IEEE spectrum, 2016, 53(2): 46-51.
[7] 欧阳. 谷歌的“笑脸”GoogleSelf-DrivingCar[J]. 计算机应用文摘, 2014(12): 72.
OU Yang. Google’s “smiling face” Google Self-Driving Car[J]. PCDigest, 2014(12): 72
[8] BIRDSALL M. Google and ITE: The road ahead for self-driving cars[J]. Institute of Transportation Engineers. Ite Journal, 2014, 84(5): 36
[9] GUIZZO E. How Google’s Self-driving Car Works[J]. IEEE Spectrum Online, 2011(8): 18
[10] JAFFE E. The first look at how google’s self-driving car handles city streets[J]. The atlantic, 2014: 431-443.
[11] TAO Yuping. The construction and intelligent management of self-driving car campsite under the visual field of low-carbon environmental protection[J]. Advanced materials research, 2012, 573-574: 841-847.
[12] 张桂林, 赵宇飞, 黎华玲. “无人驾驶”如何驶进现实[J]. 瞭望, 2016(19): 20-21.
ZHANG Guilin, ZHAO Yufeli, LI Hualing. “Unmanned” how to enter the reality[J]. Outlook Weekly, 2016(19): 20-21.
[13] 恒亮. 百度获得加州第15张无人驾驶测试牌照,另外14张在哪? [EB/OL]. (2016-09-02) [2016-09-27] http://www.sohu.com/a/113368428114877
[14] 腾讯汽车. 宝马因特合作2021年前生产驾驶无人汽车[EB/OL]. (2016-07-02)[2017-0-20]http://auto.qq.com/a/20160702/005058.htm.
[15] SURDEN H, WILLIAMSM A. How self-driving cars work[EB/OL]. (2016-05-25)[2017-09-20] https://ssrn.com/abstract=2784465.
[16] PATIDAR A, KUMAR S. A review paper on self-driving car’s and its applications[J/OL]. International journal for innovative research in science and technolog, 2016: 33-35.http://www.ijirst.org/articles/IMPACTP015.pdf.
[17] BRETT J A. Thinking local about self-driving cars: a local framework for autonomous vehicle development in the united states[D]. Washington DC: University of Washington, 2016.
[18] MICULESCU D, KARAMAN S. Polling-systems-based autonomous vehicle coordination in traffic intersections with no traffic signals[J]. arXiv preprint arXiv: 1607. 07896, 2016.
[19] CORNICK M, KOECHLING J, STANLEY B, et al. Localizing ground penetrating RADAR: a step toward robust autonomous ground vehicle localization[J]. Journal of field robotics, 2016, 33(1): 82-102.
[20] MACHT J. Automatic for the People[J]. Tennis, 2000, 2010(6):28-29.
[21] CHEN Gang, ZHANG Weigong. Design of prototype simulation system for driving performance of electromagnetic unmanned robot applied to automotive test[J]. Industrial robot: an international journal, 2015, 42(1): 74-82.
[22] ZHANG Xuemei, PEN Qiyuan. A study on tourism information and self-driving tour traffic[C]//Proceedings of 1st International Conference on Transportation Engineering. Chengdu, China, 2007: 3884-3889.
[23] DIELS C, BOS J E. Self-driving carsickness[J]. Applied ergonomics, 2016, 53: 374-382.
[24] BERGER C, DUKACZEWSKI M. Comparison of architectural design decisions for resource-constrained self-driving cars-A multiple case-study[C]//Proceedings of the informatik. Bonn, Germany, 2014: 2157-2168.
[25] SCHELLEKENS M. Self-driving cars and the chilling effect of liability law[J]. Computer law and security review, 2015, 31(4): 506-517.
[26] KIM J, KIM H, LAKSHMANAN K, et al. Parallel scheduling for cyber-physical systems: analysis and case study on a self-driving car[C]//Proceedings of the ACM/IEEE 4th International Conference on Cyber-Physical Systems. Philadelphia, Pennsylvania, 2013: 31-40.
[27] LEE G H, FAUNDORFER F, POLLEFEYS M. Motion estimation for self-driving cars with a generalized camera[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington DC, USA, 2013: 2746-2753.
[28] HE Baohong, CHEN Jun, WANG Wei. Behavioral characteristics of self-driving tourists: a case study in Kunming[C]//Proceedings of the 7th International Conference onTraffic and Transportation Studies 2010. Kunming, China, 2010: 577-586.
[29] 段建民, 石慧, 战宇辰. 基于机器视觉筛选GPS卫星信号的无人驾驶汽车组合导航方法[J]. 电子技术应用, 2016,42(1): 111-114.
DUAN Jianmin, SHI Hui, ZHAN Yuchen. Integrated navigation system for unmanned intelligent vehicle based on vision[J]. Application of electronic technique, 2016, 42(1): 111-114.
[30] 戴斌, 聂一呜, 孙振平, 等. 地面无人驾驶技术现状及应用[J]. 汽车与安全, 2012(3):46-49.
DAI Bin, NIE Yiming, SUN Zhenping, et al. The present situation and application of ground unmanned Technology[J]. Auto and safe, 2012(3):46-49.
[31] 杨帆. 无人驾驶汽车的发展现状和展望[J]. 上海汽车, 2014(3):35-40.
YANG Fan. Development Status and Prospects of Driverless Vehicles[J]. Shanghai automotive, 2014 (3): 35-40.
[32] W.KJ. 教机器学会“看路”的新系统助力无人驾驶汽车研发[J]. 军民两用技术与产品, 2016(1): 23.
W. KJ. Teach the machine learn “to see the road” of the new system to help driverless car research and development[J]. Dual use technology and product, 2016(1): 23.
[33] 王雪玉. 无人驾驶驶入现实[J]. 金融科技时代, 2016, 24(7): 87.
WANG Xueyu. Autonomous vehicles into the reality[J]. Financial technology time, 2016, 24(7):87
[34] 王雪玉. 百度无人驾驶汽车: 符号意义大于实际意义[J]. 金融科技时代, 2016, 24(1): 77.
WANG Xueyu. Baidu driverless car: Symbolic meaning is greater than the actual meaning[J]. Financial technology time, 2016, 24(7):77
[35] 王丽娜. 蓄势待发的无人驾驶汽车[J]. 科技导报, 2016, 34(6): 8.
WANG Lina. Autonomous vehicles begins[J]. Science and technology review, 2016, 34(6): 8
[36] 张伟.读懂百度L3事业部|中国智能汽车国际论坛[EB/OL].(2016-11-07)[2017-01-06] https://www.leiphone.com/news/201611/DkiMOUA3c8wcD7Mz.html.
[37] Roberto Baldwin.2018年自动驾驶汽车如何发展?看看国外都做了啥[EB/OL]. (2017-12-26)[2017-01-06]http://tech.163.com/17/1226/08/D6IOKV2F00098IEO.html.
[38] 郭永辉. 宇通公司研发的无人汽车驾驶大客车在全开放道路测试陈宫[EB/OL].(2015-09-08)[2016-09-20] http://www.cheyun.com/content/19995.
[39] 姜红德. IT助跑长安智能汽车[J]. 中国信息化, 2016(5): 49-51.
JIANG Hongde. Changan smart car run by IT[J]. China information technology, 2016(5):49-51
[40] 宋杰. 国家首个无人驾驶汽车测试基地正式开园中国未来智能汽车“摇篮”选址上海嘉定[J]. 中国经济周刊, 2016(24): 74-75.
SONG Jie. The country’s first unmanned vehicle test base open officially. China’s future mart car sites Jiading, Shanghai[J]. China economic weekly, 2016 (24): 74-75.
[41] 王晨曦. 争夺无人驾驶测试场[J]. 经营者, 2016(3): 69-70.
WANG Chenxi. Competition for pilotless test field[J]. Operators, 2016(3): 69-70.
[42] NAMIK H, INAMURA T, STOL K. Development of a robotic driver for vehicle dynamometer testing[C]//Proceedings of 2006 Australasian Conference on Robotics and Automation. Auckland, New Zealand, 2006: 1-9.
[43] 王艺帆. 自动驾驶汽车感知系统关键技术综述[J]. 汽车电器, 2016(12):12-16.
WANG YIFAN. A review of key technologies of autonomous Vehicle Perception system[J]. Automotive, 2016(12): 12-16.
[44] 陈诚. 无人驾驶汽车市场应用研究[J]. 现代制造技术与装备, 2016(1): 167-168.
CHEN Cheng. Application research of unmanned vehicle market[J]. Modern manufacturing technology and equipment, 2016(1): 167-168.
[45] 小猴机器人. 一张图看清自动驾驶产业[EB/OL].(2016-06-23)[2016-09-20] http://chuansong.me/n/374839151851.2016-07-20.
[46] 黄如林, 梁华为, 陈佳佳, 等. 基于激光雷达的无人驾驶汽车动态障碍物检测、跟踪与识别方法[J]. 机器人, 2016, 38(4): 437-443.
HUANG Rulin, LIANG Huawei, CHEN Jiajia, et al. Lidar based dynamic obstacle detection, tracking and recognition method for driverless cars[J]. Robot, 2016, 38(4): 437-443.
[47] 丁日智. 浅谈无人驾驶汽车技术原理[J]. 科学中国人, 2016(15): 31.
DING Rizhi. About the principle of driverless car[J]. Chinese journal of ecology, 2016 (15): 31.
[48] 思慕. 一颗摄像头, 就能实现无人驾驶[EB/OL]. (2015-08-03)[2016-07-20] https://www.Leiphone.com/news/201508/tolnlbcnTwv6RhwQ.htmlTOMè.
[49] TOMè D, MONTI F, BAROFFIO L, et al. Deep convolutional neural networks for pedestrian detection[J]. Signal processing: image communication, 2016, 47: 482-489.
[50] KRIZHEVSKY, ALEX, SUTSKEVER, et al. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2012, 60(2):2012.: 1097-1105.
[51] JACKEL L D, SHARMAN D, STENARD C E, et al. Optical character recognition for self-service banking[J]. AT and T technical journal, 1995, 74(4): 16-24.
[52] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International journal of computer vision, 2015, 115(3): 211-252.
[53] WONG N, CHAMBERS C, STOL K, et al. Autonomous vehicle following using a robotic driver[C]//Proceedings of the 15th International Conference on Mechatronics and Machine Vision in Practice. Auckland, New Zealand, 2008: 115-120.
[54] YESHODARA N S, NAGOJAPPA N S, KISHORE N. Cloud based self driving cars[C]//Proceedings of 2014 IEEE International Conference on Cloud Computing in Emerging Markets. Bangalore, India, 2014: 1-7.
[55] LOKHMOTOV A, FURSIN G. Optimizing convolutional neural networks on embedded platforms with OpenCL[C]//Proceedings of the 4th International Workshop on OpenCL. Vienna, Austria, 2016: 10.
[56] NVIDIA. 自动驾驶汽车的人工智能车辆计算机[EB/OL]. (2016-3-15) [2016-09-20] www.nvidia.com/object/drive-px.html.
[57] CHO. 神秘不再 NVIDIA下一代GPU架构Pascal初探[EB/OL]. (2016-04-08)[2016-09-20] https://www.evolife.cn/html/2016/86937.html.
[58] FLORENTINE E, ANDERSEN H, ANG M A, et al. Self-driving vehicle acknowledgement of pedestrian presence conveyed via Light-Emitting Diodes[C]//Proceedings of 2015 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management. Cebu City, Philippines, 2015: 1-6.
[59] 中国投资咨询网. 无人驾驶汽车产业链报告: 东方既白, 关键环节日渐成熟[EB/OL].(2016-04-26)[2016-08-29]http://www.ocn.com.cn/chanye/201604/zzyoh26084645.shtml.
[60] BADRINARAYANAN V, HANDA A, CIPOLLA R. SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling[J]. Computer Science, 2015: 13–23
[61] KENDALL A, CIPOLLA R. Modelling uncertainty in deep learning for camera relocalization[C]//Proceedings of 2016 IEEE International Conference on Robotics and Automation. Stockholm, Sweden, 2015(31): 4762–4769.
[62] JAYCIL Z. VARGHESE. Overview of autonomous vehicle sensors and systems[C]//Proceedings of the 2015 International Conference on Operations Excellence and Service Engineering Orlando, Florida, 2015(9): 178–191.
[63] HUANG Wuling, WEN Ding, GENGJ, et al. Task-specific performanceevaluationof UGVs: case studies at the IVFC[J].IEEE transactions on intelligent transportation systems, 2014, 15(5): 1969-1979.
[64] CHEN Xiang, QIAO Yu. Road segmentation via iterative deep analysis[C]//Proceedings of 2015 IEEE International Conference on Robotics and Biomimetics. Zhuhai, China, 2015: 2640-2645.
[65] MONTEMERLOM, BECKERJ, BHAT S, et al. Junior: the Stanford entry in the urban challenge[J].Journal of field robotics, 2008, 25(9): 569-597.
[66] ?BONTAR J, LECUN Y. Stereo matching by training a convolutional neural network to compare image patches[J]. The journal of machine learning research, 2016, 17(1): 2287-2318.
[67] POMERLEAU D A. Alvinn: an autonomous land vehicle in a neural network[R]. Pittsburgh:Carnegie-Mellon University, 1989.
[68] ?BONTAR J, LECUN Y. Computing the stereo matching cost with a convolutional neural network[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA,2015: 1592-1599.
[69] POMERLEAU D A. Alvinn: an autonomous land vehicle in a neural network[R]. Pittsburgh:Carnegie-Mellon University, 1989.
[70] SANTANA E, HOTZ G. Learning a driving simulator[J]. arXiv preprint arXiv: 1608.01230, 2016.
[71] SHALEV-SHWARTZ S, BEN-ZRIHEM N, COHEN A, et al. Long-term planning by short-term prediction[J]. arXiv preprint arXiv: 1602.01580, 2016.
[72] BOJARSKI M, DEL TESTA D, DWORAKOWSKI D, et al. End to end learning for self-driving cars[J]. arXiv preprint arXiv: 1604.07316, 2016.
[73] KENDALL A, GRIMES M, CIPOLLA R. PoseNet: a convolutional network for real-time 6-DOF camera relocalization[J]. arXiv preprint arXiv: 1505.07427, 2016.
[74] 孙皓天. 深度学习在无人驾驶汽车中的应用[J]. 电脑知识与技术, 2015, 11(24): 121-123.
SUN Haotian. Deep learning on the application of the driverless cars[J]. Computer knowledge and technology, 2015, 11(24): 121-123.
[75] 徐彬, 李明喜, 周晶晶, 等. 洞察无人车辆技术发展[J]. 机器人产业, 2016(1): 67-74.
XU Bin, LI Mingxi, ZHOU Jingjing, et al. Annual insight into the technical development of unmanned vehicles [J] .Botman Industry, 2016 (1): 67-74.
[76] HE U, CHEN H, PAN I, et al. Using edit distance and junction feature to detect and recognize arrow road marking[C]//Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems. Qingdao, China, 2014.
[77] DIELS C, BOS J E. User interface considerations to prevent self-driving carsickness[C]//Adjunct Proceedings of the 7th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. Nottingham, United Kingdom, 2015: 14-19.

相似文献/References:

[1]李庆武,蔡艳梅,徐立中.基于分块分类的智能视频监控背景更新算法[J].智能系统学报,2010,(03):272.
 LI Qing-wu,CAI Yan-mei,XU Li-zhong.Background update algorithm based on blocks classification forintelligent video surveillance[J].CAAI Transactions on Intelligent Systems,2010,(01):272.
[2]邵真天,袁杰.一种基于曲波变换的图像去块算法[J].智能系统学报,2012,(02):102.
 SHAO Zhentian,YUAN Jie.An image deblocking algorithm based on curvelet transformation[J].CAAI Transactions on Intelligent Systems,2012,(01):102.
[3]王锦榕,袁学海,刘增良.基于图像处理技术的瞳孔和角膜反射中心提取算法[J].智能系统学报,2012,(05):423.
 WANG Jinrong,YUAN Xuehai,LIU Zengliang.An extraction method of pupil and corneal reflection centers based on image processing technology[J].CAAI Transactions on Intelligent Systems,2012,(01):423.
[4]傅博,姜勇,王洪光,等.输电线路巡检图像智能诊断系统[J].智能系统学报,2016,(1):70.[doi:10.11992/tis.201503043]
 FU Bo,JIANG Yong,WANG Hongguang,et al.Intelligent diagnosis system for patrol check images of power transmission lines[J].CAAI Transactions on Intelligent Systems,2016,(01):70.[doi:10.11992/tis.201503043]
[5]任晓霞,孙秀明,耿鹏,等.多小波和NSDFB组合域递归滤波多聚焦图像融合[J].智能系统学报,2016,(2):241.[doi:10.11992/tis.201509017]
 REN Xiaoxia,SUN Xiuming,GENG Peng,et al.Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB[J].CAAI Transactions on Intelligent Systems,2016,(01):241.[doi:10.11992/tis.201509017]
[6]梁义辉,战强.一种面向无线图像传输的视觉平台[J].智能系统学报,2016,(5):608.[doi:10.11992/tis.201512014]
 LIANG Yihui,ZHAN Qiang.A visual platform for wireless image transmission[J].CAAI Transactions on Intelligent Systems,2016,(01):608.[doi:10.11992/tis.201512014]
[7]李霞丽,吴立成,樊艳明.易于硬件实现的压缩感知观测矩阵的研究与构造[J].智能系统学报,2017,(03):279.[doi:10.11992/tis.201606037]
 LI Xiali,WU Licheng,FAN Yanming.Study and construction of a compressed sensing measurement matrix that is easy to implement in hardware[J].CAAI Transactions on Intelligent Systems,2017,(01):279.[doi:10.11992/tis.201606037]
[8]姜婷,袭肖明,岳厚光.基于分布先验的半监督FCM的肺结节分类[J].智能系统学报,2017,(05):729.[doi:10.11992/tis.201706018]
 JIANG Ting,XI Xiaoming,YUE Houguang.Classification of pulmonary nodules by semi-supervised FCM based on prior distribution[J].CAAI Transactions on Intelligent Systems,2017,(01):729.[doi:10.11992/tis.201706018]

备注/Memo

备注/Memo:
收稿日期:2016-09-29。
基金项目:国家自然科学基金面上项目(61573114, 61703119);黑龙江省自然科学基金面上项目(F2015033, QC2017070);中央高校基本科研基金项目(HEUCFJ170404).
作者简介:王科俊,男,1962年生,教授,博士生导师,哈尔滨工程大学自动化学院模式识别与智能系统学科带头人。主要研究方向为模糊混沌神经网络、自适应逆控制理论、可拓控制、网络智能控制、模式识别、多模态生物特征识别、联脱机指纹考试身份鉴别系统、微小型机器人系统等;赵彦东,男,1990年出生,硕士研究生,主要研究方向为模式识别和生物特征识别;邢向磊,男,1983年生,讲师,主要研究方向为多集合度量学习和远距离身份识别工作。
通讯作者:邢向磊.E-mail:xingxl@hrbeu.edu.cn.
更新日期/Last Update: 2018-02-01