A STUDY OF FUZZY-NEURAL FORCE CONTROL FOR A QUADRUPEDAL WALKING MACHINE

In this pager, the inverse kinematics and the foot force distributions of a planetary gear type quadrupedal walking machine are analyzed. Th is walking machine has four legs and each leg has three-degrees-of-fre edom. The whole system has a total of seventeen links. The planetary g ear leg is designed for a quadruped which can walk and trot under the following design criteria: high efficiency, compact size, and high pay load/weight ratio. A neural network structure fuzzy logic controller i s applied to control the foot force distribution of the quadruped walk ing machine. The performance of this fuzzy logic control algorithm is evaluated. Experimental results show that the fuzzy logic controller i s effective in controlling this walking machine.