刘家银, 唐振民, 王安东, 石朝侠. 基于多激光雷达与组合特征的非结构化环境负障碍物检测[J]. 机器人, 2017, 39(5): 638-651.DOI: 10.13973/j.cnki.robot.2017.0638.
LIU Jiayin, TANG Zhenmin, WANG Andong, SHI Chaoxia. Negative Obstacle Detection in Unstructured Environment Based on Multiple LiDARs and Compositional Features. ROBOT, 2017, 39(5): 638-651. DOI: 10.13973/j.cnki.robot.2017.0638.
摘要针对非结构化环境下自主式地面车辆（ALV）的负障碍物检测问题，提出一种基于多激光雷达与组合特征的方法．首先，设计了一种具有互补能力的多激光雷达安装方式．其次，提出了基于幅向局部凸性和后沿壁局部密集特征的64线雷达负障碍物特征点对检测方法，以及基于径向距离跳变和后沿壁局部密集特征的32线雷达负障碍物特征点对检测方法．进而从负障碍物的时空融合角度，采用贝叶斯法则对多传感器多帧特征点对进行融合，然后采用DBSCAN（density-based spatial clustering of applications with noise）对融合后的特征点对进行聚类与过滤．最后对数据进行栅格化，提取负障碍物栅格．实验结果表明，本方法在非结构化复杂地形环境下具有良好的负障碍物检测性能．
Abstract：For negative obstacle detection of autonomous land vehicle (ALV) in unstructured environment, a method based on multiple LiDARs and compositional features is proposed. Firstly, a multi-LiDAR installation manner with complementary ability is proposed. Secondly, two methods are presented:a negative obstacle feature point pair detection method with 64-beam LiDAR based on local convexity in amplitude direction and local dense features at up-side of a ditch, and a negative obstacle feature point pair detection method with 32-beam LiDAR based on range jump in radial direction and local dense features at up-side of a ditch. From the view of spatial and temporal fusion of the negative obstacle, a Bayesian rule is adopted to fuse the feature point pairs from multiple sensors and multiple frames. Then the DBSCAN (density-based spatial clustering of applications with noise) algorithm is applied to clustering and filtering the feature point pairs after fusion. Finally, the data are discretized to extract negative obstacle grid. The experimental results show that the proposed method obtains a good performance for detecting negative obstacles in unstructured environment.
[1] Papadakis P. Terrain traversability analysis methods for unmanned ground vehicles:A survey[J]. Engineering Applications of Artificial Intelligence, 2013, 26(4):1373-1385.
[2] Matthies L, Rankin A. Negative obstacle detection by thermal signature[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2003:906-913.
[3] Hu T B, Nie Y M, Wu T, et al. Negative obstacle detection from image sequences[C]//3rd International Conference on Digital Image Processing. Bellingham, USA:SPIE, 2011:No.80090Y.
[4] Rankin A L, Huertas A, Matthies L H. Night-time negative obstacle detection for off-road autonomous navigation[C]//Pro-ceedings of Unmanned Systems Technology IX. Bellingham, USA:SPIE, 2007:doi:10.1117/12.720513.
[5] 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 R L, Liang H W, Chen J J, et al. Lidar based dynamic obstacle detection, tracking and recognition method for driverless cars[J]. Robot, 2016, 38(4):437-443.
[6] 胡庭波,吴涛.一种快速鲁棒的越野环境下自主移动机器人障碍检测算法[J].机器人,2011,33(3):287-291,298.Hu T B, Wu T. A fast and robust obstacle detection algorithm for off-road autonomous mobile robots[J]. Robot, 2011, 33(3):287-291,298.
[7] 黄武陵.激光雷达在无人驾驶环境感知中的应用[J].单片机与嵌入式系统应用,2016,16(10):3-7.Huang W L. Application of lidar in perception of autonomous driving environment[J]. Mircrocontrollers & Embedded Systems, 2016, 16(10):3-7.
[8] 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 Q. Multi-elements composed drivable area extraction for unmanned ground vehicles in field terrain[D]. Beijing:Beijing Institute of Technology, 2015.
[9] Schafer H, Hach A, Proetzsch M, et al. 3D obstacle detection and avoidance in vegetated off-road terrain[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2008:923-928.
[10] 宁火明.未知环境中移动机器人异常检测及负高度障碍检测[D].长沙:中南大学,2007.Ning H M. Exceptional status detection of robot and negative elevation area detection[D]. Changsha:Central South University, 2007.
[11] 张博,陈慧岩,席军强.智能车辆非结构化路面障碍检测[J].汽车工程,2009,31(6):526-530.Zhang B, Chen H Y, Xi J Q. Obstacle detection on unstructured terrain for unmanned ground vehicles[J]. Automotive Engineering, 2009, 31(6):526-530.
[12] Heckman N, Lalonde J F, Vandapel N, et al. Potential negative obstacle detection by occlusion labeling[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2007:2168-2173.
[13] Larson J, Trivedi M. Lidar based off-road negative obstacle detection and analysis[C]//14th International IEEE Conference on Intelligent Transportation Systems. Piscataway, USA:IEEE, 2011:192-197.
[14] Morton R D, Olson E. Positive and negative obstacle detection using the HLD classifier[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2011:1579-1584.
[15] Sinha A, Papadakis P. Mind the gap:Detection and traversability analysis of terrain gaps using LiDAR for safe robot navigation[J]. Robotica, 2013, 31(7):1085-1101.
[16] Shang E K, An X J, Wu T, et al. LiDAR based negative obstacle detection for field autonomous land vehicles[J]. Journal of Field Robotics, 2016, 33(5):591-617.
[17] Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//2nd International Conference Knowledge Discovery and Data Mining. Menlo Park, USA:AAAI, 1996:226-231.
[18] Matthies L, Grandjean P. Stochastic performance, modeling and evaluation of obstacle detectability with imaging range sensors[J]. IEEE Transactions on Robotics and Automation, 1994, 10(6):783-792.
