摘要
With the rapid development of the smart driving technology, the security of smart driving algorithms is becoming more and more important. Four core smart driving algorithms are determined by studying the architecture of smart driving algorithm. These algorithms comprise local path planning, pedestrian detection, lane detection and obstacle detection. The security issues of these algorithms are investigated by closely examining the work carried out by the algorithms. We found that there are vulnerabilities in all four algorithms. These vulnerabilities can cause abnormality and even road accidents for the smart cars. The final experiment shows that the vulnerabilities of these algorithms do exist under certain circumstances and therefore have high security risks. This study will lay a foundation to improve the security of the smart driving system.
With the rapid development of the smart driving technology, the security of smart driving algorithms is becoming more and more important. Four core smart driving algorithms are determined by studying the architecture of smart driving algorithm. These algorithms comprise local path planning, pedestrian detection, lane detection and obstacle detection. The security issues of these algorithms are investigated by closely examining the work carried out by the algorithms. We found that there are vulnerabilities in all four algorithms. These vulnerabilities can cause abnormality and even road accidents for the smart cars. The final experiment shows that the vulnerabilities of these algorithms do exist under certain circumstances and therefore have high security risks. This study will lay a foundation to improve the security of the smart driving system.
引文
[1]China Government Network,“Made in China 2015”,available at http://www.gov.cn/zhuanti/2016/MadeinChina2025-plan/index.html,2016-03-25.
[2]Y.Zhang and F.Y.Du,“Local path planning algorithm based on improved Morphin search tree”,Electric Light&Control,Vol.7,pp.15-19,2016.
[3]G.C.Zhu and Z.M.Tang,“UGV local path planning algorithm based on multi-layer Morphin search tree”,Robot,Vol.36,pp.491-497,2014.
[4]I.Ulrich and J.Borenstein,“VFH+:reliable obstacle avoidance for fast mobile robots”,IEEE International Conference on Robotics and Automation,Vol.2,pp.1572-1577,2002.
[5]J.Y.Zhuang,L.Zhang,H.B.Sun,et al.,“Local path planning of unmanned boats using improved random tree algorithm”,Journal of Harbin Institute of Technology,Vol.47,pp.112-117,2015.
[6]J.R.Ding,C.P.Du,Y.Zhao,et al.,“UAV path planning algorithm based on improved artificial potential field method”,Computer Application,Vol.36,pp.287-290,2016.
[7]B.Q.Ye,M.F.Zhao and Y.Wang,“Research of path planning method for mobile robot based on artificial potential field”,IEEE International Conference on Multimedia Technology,Hangzhou,China,pp.3192-3195,2011.
[8]W.Liu,C.W.Duan,B.Yu,et al.,“Multi-Pose Pedestrian Detection Based on Posterior HOG Feature”,Acta Electronica Sinica,Vol.43,No.2,pp.217-224,2015.(in Chinese)
[9]P.Dollar,C.Wojek,B.Schiele,et al.,“Pedestrian detection:an evaluation of the state of the art”,IEEE Transactions on Pattern Analysis&Machine Intelligence,Vol.34,No.4,pp.743,2012.
[10]X.Wang,T.X.Han and S.Yan,“An HOG-LBP human detector with partial occlusion handling”,IEEE International Conference on Computer Vision,Vol.30,No.2,pp.32-39,2010.
[11]B.Wang,“Pedestrian detection based on Deep Learning”,M.E.Thesis,Beijing Jiaotong University,2015.
[12]He Yi,Sang Nong,Gao Changxin,et al.,“Online unsupervised learning classification of pedestrian and vehicle for video surveillance”,Chinese Journal of Electronics,Vol.26,No.1,pp.145-151,2017.
[13]Y.D.Li,H.B.Huang,X.P.Li,et al.,“Nighttime lane markings detection based on canny operator and hough transform”,Science Technology and Engineering,Vol.16,No.31,pp.234-237,2016.
[14]C.Fan,S.Di and L.L.Hou,“Lane marking detection technique based on improved RANSAC algorithm automotive”,Automotive Engineering,Vol.36,No.4,pp.503-508,2014.
[15]J.Li,X.Mei,D.Prokhorov,et al.,“Deep neural network for structural prediction and lane detection in traffic scene”,IEEE Transactions on Neural Networks&Learning Systems,Vol.28,No.3,pp.690-703,2016.
[16]J.Canny,“Collision detection for moving polyhedra”,IEEETransactions on Pattern Analysis&Machine Intelligence,Vol.8,No.2,pp.200,1986.
[17]F.X.Chen and R.S.Wang,“Fast RANSAC with preview model parameters evaluation”,Journal of Software,Vol.16,No.8,pp.1431-1437,2005.
[18]M.F.Zhang,X.Y.Liu and R.Fu,“Laser point cloud clustering algorithm for road obstacle recognition”,Laser and Infrared,Vol.9,pp.1186-1192,2017.
[19]X.Xin,H.W.Liang and T.Tao,“Detection and representation of dynamic obstacles in unmanned vehicles based on laser sensors”,Robots,Vol.36,No.6,pp.654-661,2014.
[20]M.Wang,S.D.Zhou and W.X.Peng,“Auto blind zone detection system based on ultrasonic sensors”,Automation Technology and Applications,Vol.36,pp.110-112,2017.
[21]Z.L.Wang and Y.Niu,“Robotic obstacle detection based on multi-sensor information fusion”,China Test,Vol.43,pp.80-85,2017.
[22]L.N.Zeng,“Research on obstacle detection and recognition method in vehicle vision system”,M.E.Thesis,Nanjing University of Aeronautics and Astronautics,2016.
[23]T.T.Wang,Y.G.Zhao and F.L.Chang,“Obstacle detection based on vision sensor”,Computer Engineering and Applications,Vol.4,No.23,pp.180-183,2015.
[24]J.Shannon,“Advanced Lane Finding Project”,available at https://github.com/jeremy-shannon/CarND-Advanced-LaneLines,2017-2-27.