Enhancing Edge robotics through the use of context information

Cloud robotics aims at endowing robot systems with powerful capabilities by leveraging the computing resources available in the Cloud. To that end, the Cloud infrastructure consolidates services and information among the robots, enabling a degree of centralization which has the potential to improve operations. Despite being very promising, Cloud robotics presents two critical issues: (i) it is very hard to control the network between the robots and the Cloud (e.g., long delays, high jitter), and (ii) local context information (e.g., on the access network) is not available in the Cloud. This makes hard to achieve deterministic performance for robotics applications. Over the last few years, Edge computing has emerged as a trend to provide services and computing capabilities directly in the access network. This is so because of the additional benefits enabled by Edge computing: (i) it is easier to control the network end-to-end, and (ii) local context information (e.g., about the wireless channel) can be made available for use by applications. The goal of this paper is to showcase, by means of real-life experimentation, the benefits of residing at the Edge for robotics applications, due to the possibility of consuming context information locally available. In our experimentation, an application running in the Edge controls over a WiFi link the movement of a robot. Information related to the wireless channel is made available via a service at the Edge, which is then consumed by the application.Results show that a smoother driving of the robot can be achieved when wireless quality information is considered as input of the movement control algorithm.