Task Offloading Using Multi-Armed Bandit Optimization in Autonomous Mobile Robots

Evolution in ubiquitous and wireless services has enabled the massive adoption of autonomous cyber-physical systems for improving the workflows in dynamic environments. Among other applications, it has been witnessed that these modern technologies with the help of machine learning and high-speed communications can enable optimum and safe utilization of resources to complete various repetitive yet hazardous tasks. The industry 5.0 vision requires a multitude of devices to work with such orchestration that compute-intensive tasks may be offloaded to nearby nodes to enable collaboration for such time-critical yet compute-intensive tasks. In this work, we present a multi-armed bandit-based approach for task offloading in unmanned autonomous robots. Through experimental validation, a proof of concept is given. It has been demonstrated that using the proposed technique we have achieved a higher task delivery rate with reduced average delay.