中文摘要：

随着机器人技术的发展和硬件的普及,机器人的市场应用前景越来越广泛.但是,目前的机器人仍存在着许多局限,具体表现为可移植性弱,本地计算成本高,服务应用较少等.云机器人的提出,将机器人的计算能力从本地迁移到云端,不但提高了机器人的计算能力,降低了机器人硬件成本,而且能使资源的分配更为均衡,为解决机器人发展面临的困难提供了有效的解决途径.在云机器人的基础思想之上,提出一种基于ROS的云机器人服务框架.该服务框架使用开源的机器人操作系统ROS作为机器人运行的基础,增强了其对于不同硬件和软件环境的可移植性.同时,在框架的云端部分加入了机器人的服务管理系统和服务解析模块,能够方便快速地对机器人服务进行扩展和调用.在最后的实验部分,通过人脸识别服务模块对云机器人服务框架进行了实验验证.

英文摘要：

With the development of robot technology and the popularity of hardware, the prospect of robot market is much brighter than in the past. However, there are still many limitations of robots, in particular the weakness of portability, high computing costs and few applications. With the raise of cloud robotics, computing process can be migrated from local robot to cloud, not only improves the computing power and reduces hardware costs of robot, but also allows a more balanced allocation of resources. In this paper, it proposes a service framework for ROS-based cloud robot. This service framework uses open-source robot operating system ROS as the basis for running the robot, enhancing its portability to different hardware and software environments. Meanwhile, it joins the service management system and service analysis module in the cloud, so that robot service can be easily expanded and quickly called. As the experiment part of the paper, it uses a face recognition service module to testing our framework for ROS-based cloud robot.