MOTIVE - Time-Optimized Contextual Information Flow on Unmanned Vehicles

Abstract

The last decades, an increasing interest has been witnessed on the exploitation of unmanned vehicles in fields such as environmental monitoring, commercial air surveillance, domestic policing, geophysical surveys, disaster relief, scientific research, civilian casualties, search and rescue operations, maritime patrol,traffic management, etc. Regardless of the domain (i.e., aerial, ground or surface) that they belong to, the key elements that distinguish them as the leading edge of their technology, are the provided degree of autonomy (i.e., the ability to make decisions without human intervention) and the endurance and the payload that they can support. The mobile IoT paradigm has been significantly expanded with the proliferation of drones and unmanned robotic devices. End-to-end communication and edge decision support are major challenges when operating with mobile nodes and especially with drones. In this paper, we propose a framework that uses two decision making stochastic optimization models of on-line control unit applied on transmission functionalities of mobile and static nodes adaptive to changes in network quality statistics. This is driven by a novel dynamic suppression control of telemetry process and control messages based on the principles of the Optimal Stopping Theory (OST). MOTIVE's time-optimized control mechanism ensures the optimal delivery of critical information from unmanned vehicles to ground control station and vice versa. The main goal, through this proposal, is to significantly enhance the operation of unmanned vehicles when operating under saturated, high traffic wireless networks.