For the mobile robot with certain ability of obstacle negotiation , the discrimination of environment passability is often treated as an important goal of terrain classification and terrain parameter estimation .According to the diversity of outdoor terrain complexity ,a hierarchical terrain classification and geometric modeling method is proposed for mobile robots′ scene recognition and motion planning .Based on the terrain representation of layered elevation map ,rapid discrimination of passable area and obstacle area on flat road surface can be realized .By fuzzy classification of point cloud ,the misjudgment of robots′passability by elevation map on complex terrain can be effectively corrected .On the basis of this result ,point cloud matrix is segmented into terrain segment sequences by different terrain properties ,and then ,the semantic terrain structure represented by each segment is distinguished by the topology relation of the sequence .T he typical terrain structures are divided by using region growing method and corresponding geometric parameters are estimated ,thereby typical terrain modeling and obstacle negotiation assistance are then realized .Experimental results show the validity and the practicability of the proposed approach .% 对于具有一定越障能力的移动机器人，环境可通过性判别经常作为地形分类与地形参数估计的重要目标。针对室外地形复杂程度的差异，提出一种分级的地形分类与几何建模方法，为移动机器人的场景识别与运动规划提供参考。基于分层高程地图的地形表示方法，可实现对平坦路面上的可通行区域与障碍区域的快速判别。通过点云模糊分类，可有效校正高程地图在复杂地形状况下对机器人可通过性的误判。在此基础上，根据不同的地形属性将点云数据矩阵分割为地形片段序列，并根据片段间的拓扑关系判别其所代表的语义地形结构。采用区域生长法划分典型地形结构并估计其几何参数，从而实现室外典型地形建模以及机器人的越障辅助。实验结果验证了该方法的有效性和实用性。
展开▼
