采茶机器人导航避障及路径规划研究

Research on Tea Picking Robot’s Navigation, Barrier Avoidance and Path Planning

为实现采茶机器人在室外复杂茶园环境中定位与环境地图构建,使用改进的ORB-SLAM2算法进行机器人自身定位与三维点云地图的构建。在环境地图构建完成的基础上,完成地图的保存,并将三维点云地图转换为八叉树地图。在八叉树地图上实现采茶机器人的碰撞检测算法与路径规划算法,路径规划算法采用RRT(Rapidly-exploringRandomTree,快速遍历随机树)算法。于模拟茶园环境中,在实际机器人平台上进行实验,实验结果表明,所提方案实际运行结果良好,可以满足采茶机器人导航避障及路径规划要求。

To achieve tea picking robot’s localization and build environment map in outdoor complex tea garden environment,modified ORB-SLAM2 algorithm is used to achieve robot’s self-positioning and 3D point cloud map constructing.On the basis of built environment map,3D point cloud map is saved and transformed to octomap.Tea picking robot’s collision detection algorithm and path planning algorithm are achieved on octomap.RRT(Rapidly-exploring Random Tree)algorithm is used as path planning algorithm.Experiment is accomplished on actual robot platform in simulated tea garden environment.The experiment shows that the project suggested works well and it can satisfy the requirement of tea picking robot’s navigation,barrier avoidance and path planning.