ระบบอัจฉริยะสำหรับหุ่นยนต์สองขา

Abstract

This paper addresses applications of intelligent control techniques: neural networks, fuzzy logic and genetic algorithms and their related hybrid methods: neuro-fuzzy networks, neuro-genetic and fuzzy-genetic algorithms. These techniques and computing methods are currently used in most of biped and humanoid robotic systems. This paper summaries basic principles and concepts of intelligent controls, implemented in humanoid robotics as well as recent algorithms being devised for advanced control of humanoid robots. Subsequently, we determine a relationship between joint trajectories and located forces on robot’s foot through a neuro-fuzzy technique. In addition, we propose our method for force control at foot and a discussion pertaining to some problems for controlling humanoid robots is included herein.