基于深度信息的巡逻机器人避障系统实现

针对巡逻机器人的避障导航,基于Realsense深度摄像头获取环境深度信息,在使用机载计算机对深度图像进行分层处理的基础上,设计了巡逻机器人避障导航系统,同时对巡逻机器人通信协议以及决策流程等进行了改进设计,最后在ROS机器人开源操作系统上对其进行实验及验证。实验结果表明,在相同环境下,该方法能使巡逻机器人快速、安全、有效地避开静态障碍物而到达目标点。该方法不仅能够提高避障的成功率,获得实时避障效果,而且能够降低巡逻机器人的数据处理量,有利于巡逻机器人的移植。

Implementation of Patrol Robot Obstacle Avoidance System Based on Depth Information

For the obstacle avoidance navigation of patrol robots,based on the environment depth information which was obtained by the Realsense depth camera and the layered processing of the depth image by the onboard computer,the patrol robot obstacle avoidance navigation system was designed,at the same time,the patrol robot communication protocol and the decision process were elaborated.Finally,the proposed strategy was tested and verified on the ROS(robot operating system)robot open source operating system.The results show that the method of using Realsense depth camera can make the patrol reach the target quickly,safely and efectively abiod static obstacles under the same envirnment.This method can not only improve the success rate of obstacle avoidance and obtain the real-time obstacle avoidance effect,but also reduce the data processing volume of the patrol robot,which is beneficial to the transplantation of the patrol robot.