Codesign of Edge Intelligence and Automated Guided Vehicle Control

Abstract: This work presents a harmonic design of autonomous guided vehicle (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 preferences of the destination and exact drop point, which are derived from an AI module at the network edge and shared with the AGV over a wireless network. The demonstration indicates that the proposed integrated design of hardware, software, and AI design achieve a technology readiness level (TRL) of range 4-5