Codesign of edge intelligence and automated guided vehicle control

Abstract

In recent years, edge Artificial Intelligence (AI) coupled with other technologies such as autonomous systems have gained a lot of attention. This work presents a harmonic design of Autonomous Guided Vehicles (AGV) control, edge intelligence, and human input to enable autonomous transportation in industrial environments. The AGV has the capability to navigate between a source and destinations and pick/place objects. The human input implicitly provides the preferences of the destination and exact drop point, which are derived from the AI at the network edge and shared with the AGV over a wireless network. Design and integration of autonomous control of AGV, edge intelligence, and communication therein are carried out in this work and presented as a unified demonstration. The demonstration indicates that the proposed design of hardware, software, and intelligence design achieves the Technology Readiness Level (TRL) of range 4–5.