Design and implementation of a fully autonomous humanoid soccer robot

摘要

Purpose The purpose of this paper is to design and implement a team of kid size humanoid soccer robots conforming to RoboCup Humanoid league. Design/methodology/approach The project is described in two main parts: hardware and software. The hardware section consists of the mechanical structure and the driver circuit board enabling each robot to walk, fast walk, autonomously get up, kick and dribble when it catches the ball. The software is developed as a robot application which consists of motion controller, autonomous motion robot, self localization based on vision system, AI, trajectory planning and network. Findings This year, the authors' developments for the humanoid robot include: the design and construction of our new humanoid robots structure and implementation of a new recurrent hybrid neural network for walking control. The control system consists of two neural network controllers, two standard PD controllers and a robot walking planar. The proposed neural network controller has three layers, which are input, hidden, and output layers. Originality/value This paper presents results of research work in the field of autonomous robot‐middle size soccer robot, supported by IAU‐ Isfahan Branch (Khorasgan).