This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the...This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the safety requirement of the UAV, free space is represented by free voxels, which have enough space margin for the UAV to pass through. A bounding box array is created in the whole 3D space to evaluate the free voxel connectivity. The probabilistic roadmap method （PRM） is improved by random sampling in the bounding box array to ensure a more efficient distribution of roadmap nodes in 3D space. According to the connectivity evaluation, the roadmap is used to plan a feasible path by using A＊ algorithm. Experimental results indicate that the proposed algorithm is valid in complex 3D environments.展开更多
针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采...针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采样,从而构建与其相对应的拓扑结构,并结合BOW(Bag of words)模型对室外三维环境中的典型景物进行辨识.采用面向拓扑结构和高程图单元的分级匹配策略,实现不同场景间的精确匹配,构建具有全局一致性的拓扑高程地图.利用辨识出来的环境特征和高程地图产生双重环境约束,实现与室外地形相适应的自主路径规划.实验结果和数据分析证明了本文环境建模与路径规划方法的有效性和实用性.展开更多
基金supported by National Natural Science Foundation of China(No.61305128)Fundamental Research Funds for the Central Universities,and U.S.Army Research Ofce(No.W911NF-091-0565)
文摘This paper presents a 3D path planning algorithm for an unmanned aerial vehicle （UAV） in complex environments. In this algorithm, the environments are divided into voxels by octree algorithm. In order to satisfy the safety requirement of the UAV, free space is represented by free voxels, which have enough space margin for the UAV to pass through. A bounding box array is created in the whole 3D space to evaluate the free voxel connectivity. The probabilistic roadmap method （PRM） is improved by random sampling in the bounding box array to ensure a more efficient distribution of roadmap nodes in 3D space. According to the connectivity evaluation, the roadmap is used to plan a feasible path by using A＊ algorithm. Experimental results indicate that the proposed algorithm is valid in complex 3D environments.
文摘针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采样,从而构建与其相对应的拓扑结构,并结合BOW(Bag of words)模型对室外三维环境中的典型景物进行辨识.采用面向拓扑结构和高程图单元的分级匹配策略,实现不同场景间的精确匹配,构建具有全局一致性的拓扑高程地图.利用辨识出来的环境特征和高程地图产生双重环境约束,实现与室外地形相适应的自主路径规划.实验结果和数据分析证明了本文环境建模与路径规划方法的有效性和实用性.
