Many robotic tasks require heavy computation, which can easily exceed therobot's onboard computer capability. A promising solution to address thischallenge is outsourcing the computation to the cloud. However, exploiting thepotential of cloud resources in robotic software is difficult, because itinvolves complex code modification and extensive (re)configuration procedures.Moreover, quality of service (QoS) such as timeliness, which is critical torobot's behavior, have to be considered. In this paper, we propose atransparent and QoS-aware software framework called Cloudroid for cloud roboticapplications. This framework supports direct deployment of existing roboticsoftware packages to the cloud, transparently transforming them intoInternet-accessible cloud services. And with the automatically generatedservice stubs, robotic applications can outsource their computation to thecloud without any code modification. Furthermore, the robot and the cloud cancooperate to maintain the specific QoS property such as request response time,even in a highly dynamic and resource-competitive environment. We evaluatedCloudroid based on a group of typical robotic scenarios and a set of softwarepackages widely adopted in real-world robot practices. Results show thatrobot's capability can be enhanced significantly without code modification andspecific QoS objectives can be guaranteed. In certain tasks, the "cloud +robot" setup shows improved performance in orders of magnitude compared withthe robot native setup.
展开▼
