越野环境下无人履带平台的道路可通行性分析  

Road Traversability Analysis of Unmanned Tracked Platform in Off-road Environment

作　　者：周梦如 陈慧岩[1] 熊光明[1] 关海杰 刘庆霄 ZHOU Mengru;CHEN Huiyan;XIONG Guangming;GUAN Haijie;LIU Qingxiao(School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学机械与车辆学院,北京100081

出　　处：《兵工学报》2022年第10期2485-2496,共12页Acta Armamentarii

摘　　要：针对越野环境下道路特征模糊、地形复杂的问题,基于相机与激光雷达融合感知的方案,提出一种针对无人履带平台道路可通行性分析方法。基于图像语义分割获取语义点云,进行可通行区域的粗提取;利用三维点云描述地面几何特征,同时考虑履带平台的通过性约束,对道路的可通行性进行分析;生成包含道路表面属性和地面几何信息的三维可通行性栅格地图。所提方法对于平台可通行性的定义反映了平台-环境的强耦合关系。试验结果表明,算法能够在线稳定地建立可通行性地图,对平台规划控制具有良好的引导作用,有利于无人履带平台在复杂越野环境下的稳定通行。To deal with the problems of fuzzy road features and complex terrain in off-road environment,a road traversability analysis method for unmanned tracked platforms is proposed based on the fusion scheme of camera and lidar for sensing.Firstly,the semantic point cloud is obtained based on image semantic segmentation,and the passable area is roughly extracted.Then the three-dimensional point cloud is used to describe the ground geometric features,and road traversability is analyzed considering the trafficability constraints of the tracked platform.Finally,a three-dimensional traversable grid map containing road surface attributes and ground geometry information is generated.The definition of platform traversability in the proposed method reflects the strong coupling relationship between the platform and the environment.The experimental results show that the algorithm can stably establish the traversable map,provide good guidance for platform planning and control,and is conducive to the stable trafficability of the unmanned tracked platform in the complex off-road environment.

关 键 词：无人履带平台 可通行性分析 语义分割 点云特征 三维栅格地图 

分 类 号：TP249[自动化与计算机技术—检测技术与自动化装置]