Computational Offloading for Autonomous Systems: Real-World Experiments and Modeling

We focus on computation offloading from moving devices, such as mobile robots or autonomous vehicles to Multi-Access Edge Computing (MEC) servers via mobile network. To this end, we develop and implement a prototype of small autonomous vehicle with capability to offload processing of sensor data to MEC server via mobile network. Then, we investigate an impact of communication channel on delay and energy consumed by the autonomous vehicle for two practical applications, namely road sign recognition and path planning, in the real-world environment with a real physical equipment. Via experiments, we demonstrate benefits of the computation offloading on both energy and delay. The experiments highlight the potential of MEC for the autonomous systems allowing to reduce cost and increase scalability of such autonomous systems. Furthermore, based on the real-world experiments, we derive detailed models of energy consumption and delay for both practical applications.

Computational Offloading for Autonomous Systems: Real-World Experiments and Modeling

Jan Daněk, Zdenek Becvar, Adam Janes, Czech Technical University in Prague