基于激光雷达的纵向坡路动态可行驶性预测
|
摘要
为解决智能汽车在含有纵向坡路的环境中行驶时所涉及的环境感知与路面可行驶性理解问题,提出了一种基于激光雷达的动态、不确定性路面可行驶性预测方法。首先,利用PreScan,CarSim与MATLAB软件搭建虚拟行驶环境,并建立激光雷达物理模型提高虚拟点云的保真度。其次,进行基于激光雷达的动态可行驶性研究,利用路面激光雷达点云数据基于车辆未来行驶方向建立笛卡尔坐标系下的间隔栅格地图;在间隔内进行平面拟合得到路面的法向量,利用平面法向量计算路面纵向坡角并利用车辆姿态补偿得到大地坐标系下的间隔坡角和道路轮廓信息,并探讨天气对道路轮廓估计结果的影响;基于车辆纵向动力学特性和道路参数估计结果,计算可行驶性概率并预测可行驶性。为了快速仿真验证所提出的可行驶性预测方法,搭建相应的自动测试环境并设计测试方法。首先分析并测试车辆行驶过程中容易因失效造成预测失败的临界关键工况,接着在虚拟行驶环境中建立自动化测试流程,加强对关键工况区的采样,总计通过402组测试工况验证可行驶性预测算法,预测准确率达到87.81%。最后,在实车平台和真实测试道路上对算法流程进行验证。研究结果表明:该方法能够很好地对车辆在纵向坡路上的可行驶性进行动态的、基于概率性指标的预测。
To implement environmental perception and understanding of road traversability in a variable off-road driving environment for intelligent vehicles, a lidar-based dynamic stochastic road traversability prediction method was proposed. First, a collaborative simulation platform using PreScan, CarSim, and MATLAB was established, on which a physical lidar model was then built to improve the fidelity of virtual point clouds. Then, lidar-based dynamic traversability was researched. An interval grid map on the proceeding vehicle trajectory was built based on Cartesian coordinates with point clouds on the road. Normal vectors at every interval were calculated by plane fitting, and interval slope angles were further calculated. Vehicle poses were applied to convert slope angles into a ground-fixed coordinate and to estimate the road profile. In addition, the effects of lidar physical features in different types of weather were discussed. Both the traversable possibility and traversability were derived based on vehicle dynamics and road estimation. An automated test environment and test criteria were designed for rapid simulation tests. Critical scenarios that were failure sensitive were analyzed and tested. Test automation procedures were designed to enhance sampling on critical scenarios. A total of 402 tests were conducted and the results indicate that the proposed traversability prediction method has an accuracy rate of 87.81%. Finally, the proposed method was field tested on a vehicle platform to verify its feasibility for use in a real driving environment. The proposed method was shown to work well under dynamic driving conditions and could stochastically calculate the traversability probability as well as predict traversability.
To implement environmental perception and understanding of road traversability in a variable off-road driving environment for intelligent vehicles, a lidar-based dynamic stochastic road traversability prediction method was proposed. First, a collaborative simulation platform using PreScan, CarSim, and MATLAB was established, on which a physical lidar model was then built to improve the fidelity of virtual point clouds. Then, lidar-based dynamic traversability was researched. An interval grid map on the proceeding vehicle trajectory was built based on Cartesian coordinates with point clouds on the road. Normal vectors at every interval were calculated by plane fitting, and interval slope angles were further calculated. Vehicle poses were applied to convert slope angles into a ground-fixed coordinate and to estimate the road profile. In addition, the effects of lidar physical features in different types of weather were discussed. Both the traversable possibility and traversability were derived based on vehicle dynamics and road estimation. An automated test environment and test criteria were designed for rapid simulation tests. Critical scenarios that were failure sensitive were analyzed and tested. Test automation procedures were designed to enhance sampling on critical scenarios. A total of 402 tests were conducted and the results indicate that the proposed traversability prediction method has an accuracy rate of 87.81%. Finally, the proposed method was field tested on a vehicle platform to verify its feasibility for use in a real driving environment. The proposed method was shown to work well under dynamic driving conditions and could stochastically calculate the traversability probability as well as predict traversability.
引文
[1] SPOFFORD J R,RIMEY R D,MUNKEBY S H.Overview of the UGV/Demo Ⅱ Program [J].Proceedings of SPIE,1996 (2738):21-40.
[2] GONZALEZ-DE-SANTOS P,RIBEIRO A,FERNANDEZ-QUINTANILLA C,et al.Fleets of Robots for Environmentally-safe Pest Control in Agriculture [J].Precision Agriculture,2017,18 (4):574-614.
[3] BALTA H,BEDKOWSKI J,GOVINDARAJ S,et al.Integrated Data Management for a Fleet of Search-and-rescue Robots [J].Journal of Field Robotics,2017,34 (3):539-582.
[4] PAPADAKIS P.Terrain Traversability Analysis Methods for Unmanned Ground Vehicles:A Survey [J].Engineering Applications of Artificial Intelligence,2013,26 (4):1373-1385.
[5] WANG S,KODAGODA S,SHI L,et al.Road-terrain Classification for Land Vehicles:Employing an Acceleration-based Approach [J].IEEE Vehicular Technology Magazine,2017,12 (3):34-41.
[6] MARTIN S C.Proprioceptive Sensing of Traversability for Long-term Navigation of Robots [D].Brisbane:Queensland University of Technology,2018.
[7] EBADI F,NOROUZI M.Road Terrain Detection and Classification Algorithm based on the Color Feature Extraction [C] // IEEE.Proceedings of 2017 Artificial Intelligence and Robotics (IRANOPEN).New York:IEEE,2017:139-146.
[8] LEE B,DANIILIDIS K,LEE D D.Online Self-supervised Monocular Visual Odometry for Ground Vehicles [C] // IEEE.Proceedings of 2015 IEEE International Conference on Robotics and Automation (ICRA).New York:IEEE,2015:5232-5238.
[9] REINA G,MILELLA A,WORST R .LIDAR and Stereo Combination for Traversability Assessment of Off-road Robotic Vehicles [J].Robotica,2016,34 (12):2823-2841.
[10] 肖强.地面无人车辆越野环境多要素合成可通行区域检测[D].北京:北京理工大学,2015.XIAO Qiang.Multi-elements Composed Drivable Area Extraction for Unmanned Ground Vehicles in Field Terrain [D].Beijing:Beijing Institute of Technology,2015.
[11] AHTIAINEN J,STOYANOV T,SAARINEN J.Normal Distributions Transform Traversability Maps:LIDAR-only Approach for Traversability Mapping in Outdoor Environments [J].Journal of Field Robotics,2016,34 (3):1-22.
[12] CHEN C,HE Y,GU F,et al.A Real-time Relative Probabilistic Mapping Algorithm for High-speed Off-road Autonomous Driving [C] // IEEE.Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).New York:IEEE,2015:6252-6258.
[13] KRüSI P,FURGALE P,BOSSE M,et al.Driving on Point Clouds:Motion Planning,Trajectory Optimization,and Terrain Assessment in Generic Nonplanar Environments [J].Journal of Field Robotics,2017,34 (5):940-984.
[14] SILVER D,SOFMAN B,VANDAPEL N,et al.Experimental Analysis of Overhead Data Processing to Support Long Range Navigation [C] // IEEE.Proceedings of 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.New York:IEEE,2006:2443-2450.
[15] YAMASHITA H,JAYAKUMAR P,ALSALEH M,et al.Physics-based Deformable Tire-soil Interaction Model for Off-road Mobility Simulation and Experimental Validation [J].Journal of Computational and Nonlinear Dynamics,2018,13 (2):021002.
[16] CHAVEZ-GARCIA R O,GUZZI J,GAMBARDELLA L M,et al.Learning Ground Traversability From Simulations [J].IEEE Robotics and Automation Letters,2018,3 (3):1695-1702.
[17] RASSHOFER R H,SPIES M,SPIES H.Influences of Weather Phenomena on Automotive Laser Radar Systems [J].Advances in Radio Science,2011,9:49-60.
[18] GOODIN C,CARRUTH D,DOUDE M,et al.Predicting the Influence of Rain on LIDAR in ADAS [J].Electronics,2019,8 (1):89.
[19] ZHAO D,HUANG X,PENG H,et al.Accelerated Evaluation of Automated Vehicles in Car-following Maneuvers [J].IEEE Transactions on Intelligent Transportation Systems,2017,19 (3):733-744.
[20] ZHAO D,LAM H,PENG H,et al.Accelerated Evaluation of Automated Vehicles Safety in Lane-change Scenarios Based on Importance Sampling Techniques [J].IEEE Transactions on Intelligent Transportation Systems,2016,18 (3):595-607.
[21] KIM I I,MCARTHUR B,KOREVAAR E J.Comparison of Laser Beam Propagation at 785 nm and 1 550 nm in Fog and Haze for Optical Wireless Communications [J].Proceedings of SPIE,2001 (4214):26-38.
[22] SCHREIER M.Bayesian Environment Representation,Prediction,and Criticality Assessment for Driver Assistance Systems [D].Darmstadt:Technische University Darmstadt,2015.
[2] GONZALEZ-DE-SANTOS P,RIBEIRO A,FERNANDEZ-QUINTANILLA C,et al.Fleets of Robots for Environmentally-safe Pest Control in Agriculture [J].Precision Agriculture,2017,18 (4):574-614.
[3] BALTA H,BEDKOWSKI J,GOVINDARAJ S,et al.Integrated Data Management for a Fleet of Search-and-rescue Robots [J].Journal of Field Robotics,2017,34 (3):539-582.
[4] PAPADAKIS P.Terrain Traversability Analysis Methods for Unmanned Ground Vehicles:A Survey [J].Engineering Applications of Artificial Intelligence,2013,26 (4):1373-1385.
[5] WANG S,KODAGODA S,SHI L,et al.Road-terrain Classification for Land Vehicles:Employing an Acceleration-based Approach [J].IEEE Vehicular Technology Magazine,2017,12 (3):34-41.
[6] MARTIN S C.Proprioceptive Sensing of Traversability for Long-term Navigation of Robots [D].Brisbane:Queensland University of Technology,2018.
[7] EBADI F,NOROUZI M.Road Terrain Detection and Classification Algorithm based on the Color Feature Extraction [C] // IEEE.Proceedings of 2017 Artificial Intelligence and Robotics (IRANOPEN).New York:IEEE,2017:139-146.
[8] LEE B,DANIILIDIS K,LEE D D.Online Self-supervised Monocular Visual Odometry for Ground Vehicles [C] // IEEE.Proceedings of 2015 IEEE International Conference on Robotics and Automation (ICRA).New York:IEEE,2015:5232-5238.
[9] REINA G,MILELLA A,WORST R .LIDAR and Stereo Combination for Traversability Assessment of Off-road Robotic Vehicles [J].Robotica,2016,34 (12):2823-2841.
[10] 肖强.地面无人车辆越野环境多要素合成可通行区域检测[D].北京:北京理工大学,2015.XIAO Qiang.Multi-elements Composed Drivable Area Extraction for Unmanned Ground Vehicles in Field Terrain [D].Beijing:Beijing Institute of Technology,2015.
[11] AHTIAINEN J,STOYANOV T,SAARINEN J.Normal Distributions Transform Traversability Maps:LIDAR-only Approach for Traversability Mapping in Outdoor Environments [J].Journal of Field Robotics,2016,34 (3):1-22.
[12] CHEN C,HE Y,GU F,et al.A Real-time Relative Probabilistic Mapping Algorithm for High-speed Off-road Autonomous Driving [C] // IEEE.Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).New York:IEEE,2015:6252-6258.
[13] KRüSI P,FURGALE P,BOSSE M,et al.Driving on Point Clouds:Motion Planning,Trajectory Optimization,and Terrain Assessment in Generic Nonplanar Environments [J].Journal of Field Robotics,2017,34 (5):940-984.
[14] SILVER D,SOFMAN B,VANDAPEL N,et al.Experimental Analysis of Overhead Data Processing to Support Long Range Navigation [C] // IEEE.Proceedings of 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.New York:IEEE,2006:2443-2450.
[15] YAMASHITA H,JAYAKUMAR P,ALSALEH M,et al.Physics-based Deformable Tire-soil Interaction Model for Off-road Mobility Simulation and Experimental Validation [J].Journal of Computational and Nonlinear Dynamics,2018,13 (2):021002.
[16] CHAVEZ-GARCIA R O,GUZZI J,GAMBARDELLA L M,et al.Learning Ground Traversability From Simulations [J].IEEE Robotics and Automation Letters,2018,3 (3):1695-1702.
[17] RASSHOFER R H,SPIES M,SPIES H.Influences of Weather Phenomena on Automotive Laser Radar Systems [J].Advances in Radio Science,2011,9:49-60.
[18] GOODIN C,CARRUTH D,DOUDE M,et al.Predicting the Influence of Rain on LIDAR in ADAS [J].Electronics,2019,8 (1):89.
[19] ZHAO D,HUANG X,PENG H,et al.Accelerated Evaluation of Automated Vehicles in Car-following Maneuvers [J].IEEE Transactions on Intelligent Transportation Systems,2017,19 (3):733-744.
[20] ZHAO D,LAM H,PENG H,et al.Accelerated Evaluation of Automated Vehicles Safety in Lane-change Scenarios Based on Importance Sampling Techniques [J].IEEE Transactions on Intelligent Transportation Systems,2016,18 (3):595-607.
[21] KIM I I,MCARTHUR B,KOREVAAR E J.Comparison of Laser Beam Propagation at 785 nm and 1 550 nm in Fog and Haze for Optical Wireless Communications [J].Proceedings of SPIE,2001 (4214):26-38.
[22] SCHREIER M.Bayesian Environment Representation,Prediction,and Criticality Assessment for Driver Assistance Systems [D].Darmstadt:Technische University Darmstadt,2015.