基于情景经验与稀疏点云的移动机器人导航

Mobile robot navigation based on situational experience and sparse point cloud

针对稀疏点云地图用于自主导航任务的信息不充分问题,融合情景经验实现环境认知,提出一种基于情景经验与稀疏点云的移动机器人导航系统,获取全局最优路径,提高机器人导航精度.构建点云地图来保存环境显著路标.受人类基于情景经验方式导航启发,模拟经验积累过程,构建封装了场景感知、位姿信息和事件转移集的情景经验地图,实现机器人对环境在拓扑关系上的理解.结合环境稀疏点云地图定位机器人,根据情景经验地图规划路径与控制机器人行为.实验结果表明:该导航系统能够根据不同的导航任务规划出全局最优路径,并且具有较高的导航精度.

To solve the problem of insufficient information of sparse point cloud map under autonomous navigation tasks,a novel mobile robot navigation system which realized environmental cognition based on situational experience and sparse point cloud was proposed.The system improved robot navigation accuracy while the global optimal path was calculated.Significant landmarks in the environment were stored in the sparse point cloud map.Inspired by human navigation ways with situational experience,the process of experience accumulation simulated was used for constructing situational experience map encapsulating scene perception,posture and event transfer set,which reconstructed the topological relation of environment.The mobile robot localized itself based on sparse point cloud map while planning paths and controlling behaviors with the situational experience map.The experimental results show this navigation system can generate the global optimal path according to different navigation tasks with high navigation accuracy.