一种基于ROS 的分布式安防巡逻机器人系统

针对目前安防巡逻机器人系统中对机器人主控机负载能力要求较高的问题，设计一种基于机器人操作系统(robot operating system，ROS)的分布式安防巡逻机器人系统。将同时定位与建图(simultaneous localization andmapping，SLAM)节点以及视觉识别节点分布于局部ROS 网络中的机器人主控机和远程监控端，SLAM 方面采用gmapping 算法实现动态环境中的地图构建以及机器人的定位；视觉识别方面采用TensorFlow 深度学习框架，利用TensorFlow Object Detection API 实现场景里多个物体的识别。结果表明，该系统为基于ROS 的分布式安防巡逻机器人系统的设计提供了参考。

A Distributed Security Patrol Robot System Based on ROS

Aiming at the problem that the current security patrol robot system has a high requirement for the loadcapacity of the robot master controller, a distributed security patrol robot system based on robot operating system (ROS) isdesigned. The simultaneous Localization and mapping (SLAM) nodes and the vision recognition nodes are distributed inthe robot host and the remote monitor in the local ROS network. On the SLAM side, the gmapping algorithm is used torealize the mapping in the dynamic environment and the localization of the robot; In the aspect of visual recognition,TensorFlow deep learning framework is used to recognize multiple objects in the scene by using TensorFlow ObjectDetection API. The results show that the system provides a reference for the design of ROS-based distributed securitypatrol robot system.