Neuro-fuzzy algorithm for obstacle avoidance mission of a mobile robot using FPGA

Abstract

Navigation and obstacle avoidance are some of the important tasks or mission deployed and accomplished by an autonomous mobile robot. This paper presents the designed obstacle avoidance program for mobile robot that incorporates a neuro-fuzzy algorithm using Altera Field Programmable Gate Array (FPGA) development board. To generate collision-free path for mobile robot, a proper motion planning is needed. The neuro-fuzzy-based-obstacle avoidance program is simulated and implemented on the hardware system using Altera Quartus® II design software, System-on-programmable-chip (SOPC) Builder, Nios® II Integrated Design Environment (IDE) software, and FPGA development and education board (DE2). Simulation and weight training process are carried out with the aid of Nios® II IDE software. A mobile robot serves as the test platform of the program. An ultrasonic sensor and servo motors are used as the test platform's sensing element and actuator, respectively. The neuro-fuzzy algorithm is successfully implemented on the Altera FPGA development board and tested with our remote mobile robot for obstacle avoidance missions via an established radio frequency (RF) communication.