FLS-Based Collision Avoidance Cyber Physical System for Warehouse Robots using FPGA

Abstract

The overperforming enormous number of Automated Guided Vehicles (AGV) that have been adopted in warehouses recently proved their capabilities of speeding up the parcel exchange process in comparing with human capabilities. In order to increase the overall performance of these AGVs, we introduced an Artificial Intelligence (AI) based processing unit for the purpose of enhancing the collaborative diagnostics and decision making in such applications by exchanging feedback data frames to the center hub. The proposed AI-based controller is based on a multi-core Fuzzy Logic System (FLS) is to differentiate the level of collision probability in a Cyber Physical System (CPS) using asymmetric data bus width architecture. The proposed systolic FLS architecture in this paper has been designed using VHDL to be interfaced with a three TFmini Plus Lidar Sensors and three MaxSonar ultrasonic sensors using the Intel Altera OpenVINO FPGA board. The proposed systolic FLS processing unit achieved a processing computational speed of about 14.36 GOPS at maximum operating frequency of 270.86 MHz while consuming about 58.56 mW as a core dynamic thermal power dissipation and around 28.38 mW as a 1/0 thermal power dissipation.