摘要
自主车是一种能够在城市环境和野外环境中连续自主驾驶的移动机器人,其在国防军事和民用交通都有重大的研究价值和广阔的应用前景。本文主要面向自主车在结构化和非结构化环境中的自主驾驶,旨在从理论和实践上对三维激光雷达在自主车环境感知中的应用进行相关研究。
本文的主要研究成果和创新点如下:
1、针对基于极坐标栅格地图的分块直线拟合方法不能描述起伏路面,而采用二维高斯过程回归进行地面分割计算量比较大的缺点,本文提出了一种基于分块高斯过程回归的地面分割算法,该方法将极坐标栅格地图和一维高斯过程回归相结合,既能够对各种道路情况进行路面分割,又能够减少计算量,满足自主车导航的实时性要求。
2、根据三维激光雷达的数据分布特性,本文改进了一种基于Toe-Finding算法的路口检测算法,该方法首先分析了车前方的可通行性,然后利用激光雷达的光束模型和带有车宽约束的Toe-Finding算法分析路口类型,其能够检测出自主车20米外的各种类型的路口,实车采集的数据证明了该算法的可靠性;同时针对具有低信噪比的路边,本文提出了一种基于最大最小值栅格地图的路边检测算法,该方法在最大最小值栅格地图中使用霍夫变换提取直线,并通过路边与自主车的相互关系对所提取的直线进行约束,提高了路边检测的可靠性。
3、改进了一种基于车辆观测模型和粒子滤波的动态车辆跟踪算法,该方法直接采用方盒模型对相邻两帧激光雷达数据的差分结果进行车辆表示,省略了其中复杂的数据关联步骤,本文采用粒子滤波算法对动态车辆进行了跟踪,获得了很好的实验效果。
上述研究成果已经成功应用于我校的自主车“开路雄狮”,该自主车在第三届“中国智能车未来挑战赛”中,以21分钟自主行驶10公里的绝对优势获得了冠军。
Autonomous Land Vehicle is a kind of mobile robot, which can drive both in urban and countryside environment. It has great research value and broad application prospect both in national defense and civilian traffic field. This thesis mainly aimed at the autonomous driving in both structure and non-structure environment, it carried out the research on three-dimension LIDAR-based environment perception for Autonomous Land Vehicle theoretically and practically.
The main results and innovations of this thesis are as follows:
Firstly, because fitting the line in every sector cannot describe the ground in countryside, and the computation efficiency of the two-dimension Gaussian Process regression in the elevation map is very low, a novel ground segmentation algorithm was proposed, which use the one-dimension Gaussian Process regression and Incremental Sample Consensus for every sector in the polar grid map. This method can segment all kinds of grounds in daily life and reduce the cost of computation to meet the real-time demand of Autonomous Land Vehicle.
Secondly, considering upon the data distribution of three-dimension LIDAR, an improved Toe-Finding algorithm for road intersection detection was presented; this method first analyzes the admissible space in front of the vehicle, then uses the beam model of the laser range finder and Toe-Finding algorithm with constraint of vehicle width to detect the road intersection, it can recognize all kinds of intersections twenty meters away from the Autonomous Land Vehicle. Experiment results show the reliability of the algorithm. Because of the poor SNR of the curb, a new method based on the max-min elevation map was proposed, it uses the Hough Transform algorithm to extract the candidate lines, and to select the best result with the constraint of the vehicle-curb relationship. This method can extract the curb in urban environment accurately.
Thirdly, an improved vehicle tracking method which is based on the vehicle measurement model and particle filter was proposed. This method directly uses the box model to represent the results computed by differencing two consecutive frames, and eliminates the need for data association. According to the model, a particle filter based vehicle tracking algorithm was implemented with great efficiency.
We have used these methods in our Autonomous Land Vehicle which won the champion in the third Chinese Future Challenge. The robot ran ten kilometers autonomously in urban environment of the city Ordos in twenty-one minutes.
引文
[1]孙振平, "自主驾驶汽车智能控制系统,"机电工程与自动化学院.工学博士长沙:国防科技大学, 2004.
[2]宋金泽, "自主泊车系统关键技术研究,"机电工程与自动化学院.工学博士长沙:国防科技大学, 2009.
[3] X. Yuan, C. X. Zhao, and H. F. Zhang, "Road Detection and Corner Extraction Using High Definition Lidar," Information Technology Journal, vol. 9, pp. 1022-1030, 2010.
[4]万忠涛, "基于激光雷达的道路检测与障碍物分类,"机电工程与自动化学院.工学硕士长沙:国防科技大学, 2010.
[5] F. Moosmann, O. Pink, and C. Stiller, "Segmentation of 3D Lidar Data in non-flat Urban Environment using a Local Convexity Criterion," in Intelligent Vehicle Symposium (IV) Xian, 2009.
[6] B. Douillard, J. Underwood, N. Melkumyan, S.Singh, S. Vasudevan, C. Brunner, and A. Quadros, "Hybrid Elevation Map: 3D Surface Models for Segmentation," in International Conference on Intellignet Robots and Systems (IROS), 2010.
[7] M. Himmelsbach, Felix V. Hundelshausen, and H. J. Wuensche, "Fast Segmentation of 3D Point Clouds for Ground Vehicles," in Intelligent Vehicle Symposlum (IV) USA, 2010, pp. 560-565.
[8] B. Douillard, J. Underwood, N. Kuntz, V. Vlaskine, A. Quadros, P. Morton, and A. Frenkel, "On the Segmentation of 3D LIDAR Point Clouds," in IEEE International Conference on Robotics and Automation (ICRA) Shanghai, 2011, pp. 2798-2805.
[9] J. H. Lee, T. Tsubouchi, K. Yamamoto, and S. Egawa, "People Tracking Using a Robot in Motion wuth Laser Range Finder," in International Conference on Intelligent Robots and Systems (IROS) Beijing, 2006, pp. 2936-2942.
[10] D. Brscic and H. Hashimoto, "Tracking of Objects in Intelligent Space Using Laser Range Finders," in International Conference on Intelligent Robots and Systems (IROS), 2006, pp. 1723-1728.
[11] F. Scholer, J. Behley, V. Steinhage, D. Schulz, and A. B. Cremers, "Person Tracking in Three-Dimensional Laser Ranger Data with Explicit Occlusion Adaption," in International Conference on Robotics and Automation (ICRA) Shanghai, 2011, pp. 1297-1303.
[12] L. Spinello, M. Luber, and K. O. Arras, "Tracking People in 3D Using a Bottom-Up Top-Down Detector," in International Conference on Robotics and Automation (ICRA) Shanghai, 2011, pp. 1304-1310.
[13] L. E. Navarro-Serment, C. Mertz, N. Vandapel, and M. Hebert, "LADAR-based Pedestrian Detection and Tracking," in IEEE Workshop on Human Detection from Mobile Platforms California, 2008.
[14] T. D. Vu and O. Aycard, "Laser-based Detection and Tracking Moving Objects using Data-Driven Markov Chain Monte Carlo," in International Conference on Robotics and Automation (ICRA) Japan, 2009, pp. 3800-3806.
[15] A. Petrovskaya and S. Thrun, "Model Bsaed Vehicle Tracking in Urban Environments," in International Conference on Robotics and Automation (ICRA), 2009.
[16]王磊, "全区域覆盖移动机器人同时定位与建图,"计算机学院.工学硕士南京:南京理工大学, 2005.
[17] D. Vivet, P. Checchin, and R. Chapuis, "On the fly localization and mapping using a 360 Field-of-view Microwave Radar Sensor," in International Conference on Intelligent Robots and Systems (IROS), 2009.
[18] K. pathak, A. Birk, N. Vaskevicius, M. Pfingsthorn, Soren Schwertfeger, and J. Poppinga, "Online Three-Dimensional SLAM by Registration of Large Planar Surface Segments and Closed-Form Pose-Graph Relaxation," Journal of Field Robotics (JFR), vol. 27, pp. 52-84, 2010.
[19] S. Y. Park, S. I. Choi, J.Moon, J. Kim, and Y. W. Park, "Localization of an Unmanned Ground Vehicle using 3D Registration of Laser Range Data and DSM," 2010.
[20] B. Wu, "Compression of 3D range data with adaptive thresholding using the Integral Image," in Computer Science and Information Engineering Kaohsiung: National University of Kaohsiung, 2011.
[21] Y. C. Lin, "Large scale 3D scene registration using data from Velodyne LIDAR," in Computer Science and Information Engineering Kaohsiung: National University of Kaohsiung, 2011.
[22] H. Kurniawati, J. C. Schulmeister, T. Bandyopadhyay, G. Papadopoulos, F. S. Hover, and N. M. Patrikalakis, "Infrastructure for 3D Model Reconstruction of Marine Structures," in International Conference on Robotics and Automation (ICRA), 2010.
[23] C. Glennie and D . D. Lichti, "Static Calibration and Analysis of the Velodyne HDL-64E S2 for High Accuracy Mobile Scanning," Remote Sensing, pp. 1610-1624, 2010.
[24] M. Hill, "HDL-64E S2 User's Manual," in Velodyne Lidar Inc CA, 2008.
[25] N. Muhammad and S. Lacroix, "Calibration of a rotating multi-beam Lidar," in International Confernece on Intellignent Robots and System (IROS) Taiwan, 2010.
[26] J. Underwood, A.Hill, and S. Scheding, "Calibration of range sensor pose on mobile platforms," in International Conference on Intelligent Robots and System (IROS), IEEE, Ed. USA, 2007.
[27]刘钊, "多传感器时空一致及其信息融合技术研究,"机电工程与自动化学院.工学硕士长沙:国防科技大学, 2008.
[28] B. Siciliano and O. Khatib, Springer handbook of robotics: springer, 2008.
[29] S. Thrun and et al, "Stanley: The Robot that Won the DARPA Grand Challenge," journal of Field Robotics (JFR), vol. 23, pp. 661-692, 2006.
[30] P. Pfaff and W. Burgard, "An efficient extension to elevation maps for outdoor terrain mapping and loop closing," International Journal of Robotics Research (IJRR), vol. 26, pp. 217-230, 2007.
[31] P. Pfaff and W. Burgard, "An efficient extension of elevation maps for outdoor terrian mapping," in International Conference on Field and Service Robotics (FSR), 2005, pp. 165-176.
[32] P. Pfaff and W. Burgard, "An efficient extension to elevation maps for outdoor terrain mapping and loop closing," International Journal of Robotics Research (IJRR), vol. 26(2), pp. 217-230, 2007.
[33] A. Kelly, A. Stentz, O. Amidi, M. Bode, D. Bardley, A. Diaz-Calderon, M. Happold, H. Herman, T. Pilarski, P. Rander, S. Thayer, N. Vallidis, and R. Warner, "Toward reliable off road autonomous vehicles operating in challenging environments," International Journal of Robotics Research (IJRR), 2006.
[34] R. Simmons, L. Henriksen, L. Chrisman, and G. Whelan, "Obstacle avoidance and safeguarding for a lunar rover," in AIAA Forum on Advanced Developments in Space Robotics, 1996.
[35] M. Levoy and T. Whitted, "The use of points as display primitives," Department of Computer Science, Chapel Hill1985.
[36] Radu Bugdon Rusu, Zoltan Csaba Marton, Nicl Blodow, and Michael Beetz, "Persistent Point Feature Histograms for 3D Point Clouds."in Proceeding of 10th International Conference on Intelligent Autonomous Systems (IAS10), 2008.
[37] A. M. and A. A., "On normals and projection operators for surfaces defined by point sets," in Symposium on Point-Based Graphics, 2004, pp. 149-155.
[38] K. H. Bae and D. D. Lichti, "Automated registration of unorganized point clouds from terrestrial laser scanners," in International Archives of Photogrammetry and Remote Sensing(IAPRS), 2004, pp. 222-227.
[39] T. Rabbani, F. van den Heuvel, and G. Vosselman, "Segmentation of point clouds using smoothness constraint," in IEVM06, 2006.
[40] F. Sadjadi and E. Hall, "Three-Dimensional Moment Invariants," IEEE trans. on PAMI, vol. 2, pp. 127-136, 1980.
[41] G. Burel and H. Henocq, "Three-Dimensional invarians and their application to object recognition," Signal Process, vol. 45, pp. 1-22, 1995.
[42] N. Gelfand, N. J. Guibas, and H. Pottmann, "Robust Global Registration," in Proc. Symp. Geom, 2005.
[43] G. Hetzel, B. Leibe, P. Levi, and B. Schiele, "3D Object Recognition from Range Images using Local Feature Histograms," in International Conference on Computer Vision and Pattern Recognition (CVPR). vol. 2, 2001, pp. 394-399.
[44] X. Li and I. Guskov, "3D object recognition from range images using pyramid matching," in International Conference on Computer Vision (ICCV), 2007, pp. 1-6.
[45] E. Wahl, U. Hillenbrand, and G. Hirzinger, "Surflet-Pair-Relation Histograms: A Statistical 3D-Shape Representation for Rapid Classification," in 3DIM, 2003, pp. 474-481.
[46] B. Douillard, "Laser and Vision Based Classification in Urban Environments," in Australian Center for Field Robotics. vol. PhD Sydney: The University of Sydney, 2009.
[47] T. Pavlidis and S. L. Horowitz, "Segmentation of Plane Curves," IEEE trans. on Computers, vol. 23, pp. 860-870, 1974.
[48] K. O. Arras and R. Siegwart, "Feature Extraction and Scene Interpretation for Map-Based Navigation and Map Building," in The Symposium on Intelligent Systems and Advanced manufacturing, 1997.
[49] V. Nguyen, S. Gachter, A. Martinelli, N. Tomatis, and R. Siegwart, "A comparision of line extraction algorithms using 2D range data for indoor mobile robotics," Automatics Robots (AR), vol. 23, pp. 97-111, 2007.
[50] M. Fischler and R. Bolles, "Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartographf," Communications of the ACM, vol. 24(6), pp. 381-395, 1981.
[51] D. A. Forsyth and J. Ponce, Computer Vision: A Modern Approach: Prentice Hall, 2003.
[52] J. Lam, K. Kusevic, P. Mrstik, R. Harrap, and M. Greenspan, "Urban Scene Extraction from Mobile Griund Based LIDAR Data," in 5th International Symposium on 3D Data, Visualization & transmission, France, 2010, pp. 1-8.
[53] G. Vosselman, B. Gorte, G. Sithole, and T. Rabbani, "Recognizing structure in laser scanner point clouds," in The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences (IAPRS), 2004, pp. 33-38.
[54] S. Vasudevan, F. Ramos, E. Nettleton, and H. D. Whyte, "Non-stationary dependent Gaussian Processes for data fusion in large-scale terrain modeling," in IEEE International Conference on Robotics and Automation (ICRA) Shanghai, 2011, pp. 1875-1882.
[55] C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning: MIT Press, 2006.
[56] S. Vasudevan, F. Ramos, E. Nettleton, and H. D. Whyte, "Gaussian Process modeling of large-scale terrain," Journal of Field Robotics (JFR), vol. 26, pp. 812-840, 2009.
[57] K. Sarath, W. Wijesoma, and B. Arjuna, "Road Curb and Intersection Detection using a 2D LMS," in International Conference on Intelligent Robotics and Systems (IROS) USA, 2002.
[58] M. S. Kurdziel, "A Monocular Color Vision System for Road Intersection Detection," in Department of Computer Engineering. vol. Master of Science in Computer Engineering New York: Rochester Institute of Technology, 2008.
[59] R. Danescu and S. Nedevschi, "Detection and Classification of Painted Road Objects for Intersection Assistance Application," in International Conference on Intelligent Transportation System (ITSC) USA, 2010.
[60] J. Iisaka, T. Sakurai-Amano, and I. T. Lukowski, "Automated Detection of Road Intersection From ESR-1 SAR," in Geoscience and Remote Sensing Symposium (IGARSS), 1995.
[61] A. Fathi and J. Krumm, "Detection Road Intersection from GPS Trace," in International Conference on Gerographic Information Science, IEEE, Ed. Zurich, 2010.
[62] J. X. Hu, A. Razdan, J. C. Remiani, M. Cui, and P. Wonka, "Road Network Extraction and Intersection Detection from Aerial Images by Tracking Road Footprints," Transactions on Geosciences and Remote Sensing, pp. 4144-4157, 2007.
[63] T. Hosomura, "Road Extraction from High Resolution Satellite Image by Using Circle Area," in ISPRS XXI Congress, 2008.
[64] G. Koutaki and K. Uchimura, "Automatic Road Extraction Based on Cross Detection in Suburb," in SPIE, USA, 2003.
[65] T. R. Kushner and S. Puri, "Progress in Road Intersection Detection for Autonomous Vehicle Navigation," in SPIE Conference on Mobile Robots, USA, 1987.
[66] S. Thrun and W. Burgard, Probabilistic Robotics. London, England: MIT Press, 2005.
[67] D. Hearn and M. P. Baker, Computer Graphics with OpenGL (Third Edition). Beijing: Publishing House of Electronics Industry, 2005.
[68] S. Z. Sam, Q. Zhang, A. T. Abraham, and B. Rebsamen, "Simultaneous Path Planning and Topological Mapping (SPPATM) for Environment Exploration and Goal Oriented Navigation," Robotics and Autonomous Systems, 2010.
[69] H. Cheng and Y. Sun, "A Hierarchical Approach to Color Image Segmentationusing Homogeneity " IEEE trans. Image Process, vol. 9, pp. 2071-2082, 2000.
[70] W. S. Wijesoma, K. R. S. Kodagoda, and A. P. Balasuriya, "Road-boundary Detection and Tracking Using Ladar Sensing," IEEE Transactions on Robotics and Automation, vol. 20, 2004.
[71] K. R. S. Kodagoda, W. S. Wijesoma, and A. P. Balasuriya, "Road Curb and Intersection Detection Using a 2D LMS," in International Conference In Intelligent Robots and Systems (IROS), 2002.
[72] L. Smadja, J. Ninot, and T. Gavrilovic, "Road Extraction and Environment Interpretation From Lidar Sensors," in IAPRS France, 2010, pp. 281-286.
[73] J. Stuckler, H. Schulz, and S. Behnke, "In-Lane Localization in Road Networks Using Curbs Detected in Omnidirectional Height Images," in IEEE International Conference on Robotics and Automation (ICRA), 2008.
[74] F. Oniga, S. Nedevschi, and M. M. Meinecke, "Curb Detection Based on a Multi-Frame Persistence Map for Urban Driving Scenarios," in International Conference on Intelligent Transportation System (ITSC), 2008.
[75] J. Siegemund, D. Pfeiffer, U. Franke, and W. Forstner, "Curb Reconstruction using Conditional Random Fields," in IEEE Intelligent Vehicles Symposium (IV), 2010, pp. 203-210.
[76] L. Zhao and C. Thorpe, "Qualitative and Quantitative Car Tracking From A Range Image Sequence," in Computer Vision and Pattern Recognition (CVPR), 1998.
[77] D. Streller, K. Furstenberg, and K. Dietmayer, "Vehicle and Object Models for Robust Tracking in Traffic Scenes Using Laser Range Images," Intelligent Transportion System (ITS), 2002.
[78] C. Wang, C. Thorpe, S. Thrun, M. Hebert, and H. Durrant-Whyte, "Simultaneous localization, mapping and moving object tracking," International Journal of Robotics Research (IJRR), vol. 26, pp. 889-916, 2007.
[79] S. Wender and K. Dietmayer, "3D Vehicle Detection Using a Laser Scanner and a Video Camera," in 6th European Congress in ITS, 2007.
[80] A. Petrovskaya and S. Thrun, "Model Based Vehicle Detection and Tracking for Autonomous Urban Driving," Autonomous Robots Journal, vol. 26, pp. 123-139, 2009.
[81] M. Himmelsbach, A. Muller, T. Lutter, and H. J. Wuensche, "LIDAR-based 3D Object Perception ", in Proceeding of 1st International Workshop on Cognition for Technical Systems, 2008.
[82] A. Petrovskaya and S. Thrun, "Efficient Techniques for Dynamic Vehicle Detection," in ISER Greece, 2008.
[83] M. Darms, P. Rybski, and C. Urmson, "Classification and Tracking of Dynamic Objects with Multiple Sensoes for Autonomous Driving in Urban Environments."in Intelligent Vehicles Symposium (IV), 2008, pp. 1197-1202.
[84] T. Zielke, M. M. Brauckmann, and W. V. Seelen, "Intensity and Edge based Symmstry detection applied to car following " in European Conference on Computer Vision (ECCV) Germany, 1992.
[85] F. Dellaert and C. Thorpe, "Robust Car Tracking Using Kalman Filtering and Bayesian Templates," in Conference on Intelligent Transportation Systems (ITSC), 1997.
[86] A. Petrovskaya, "Towards Dependable Robotic Perception," in The Department of Computer Science. vol. Doctor of Fhilosophy: Stanford University, 2011.
[87] Daniel Streller and Klaus Dietmayer, "Object Tracking and Classification Using a Multiple Hypothesis Approach," in International Vehicle Symposium (IV), IEEE, Ed. Parma, Italy, 2004, pp. 808-812.
[88] D. Schulz, W. Burgard, D. Fox, and A. B. Cremers, "Tracking multiple moving targets with a mobile robot using particle filters and statistical data association," in International Conference on Robotics and Automation (ICRA), 2001.
[89]王润生,信息融合.湖南,长沙:科学出版社, 2007.
[90] J. Liu and R. Chen, "Sequential Monte Carlo Methods for Dynamical Systems," in American Statistical Association. vol. 93, 1998, pp. 1032-1044.
