Hexapod Robot Wall-Following Control Using Fuzzy Controller with Advanced Differential Evolution

• Main Authors: Ying-Han Chen, 陳盈翰
• Other Authors: Chia-Feng Juang
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/08498478739892016808

碩士 === 國立中興大學 === 電機工程學系所 === 100 === This thesis proposes advanced species differential evolution (ASDE) algorithm designed fuzzy controller (FC) to perform hexapod robot wall following. The ASDE uses the concept of the species (clustering). The solution vectors are clustered into different species based on their performances at each iteration. The ASDE dynamically generates a species-based mutant vector or a general mutant vector in the mutation operation according to an iteration-based adaptive probability value. The ASDE is applied to design an FC for robot wall-following control. All of the free parameters in the FC are learned through ASDE, which avoids the time-consuming manual design task. The FC inputs are three infrared distance sensor values. The FC controls the swing angle changes of the left- and right-middle legs of the hexapod robot to perform a suitable turning direction while moving forward at the same time. A new cost function is defined to quantitatively evaluate the performance an FC. Two different training environments are created for building this wall-following behavior without an exhaustive collection of input-output training pairs in advance. Simulations are conducted to verify the effectiveness of the evolutionary wall-following learning approach. Comparisons with other advanced differential evolution algorithms show that the ASDE achieves better performance in the wall-following control task.