Neural Network Control of Humanoid Robot

Abstract

This paper handles ZMP based control that is inspired by neural networks for humanoid robot walking on varying sloped surfaces. Humanoid robots are currently one of the most exciting research topics in the field of robotics, and maintaining stability while they are standing, walking or moving is a key concern. To ensure a steady and smooth walking gait of such robots, a feedforward type of neural network architecture, trained by the back propagation algorithm is employed. The inputs and outputs of the neural network architecture are the ZMPx and ZMPy errors of the robot, and the x, y positions of the robot, respectively. The neural network developed allows the controller to generate the desired balance of the robot positions, resulting in a steady gait for the robot as it moves around on a flat floor, and when it is descending slope. In this paper, experiments of humanoid robot walking are carried out, in which the actual position data from a prototype robot are measured in real time situations, and fed into a neural network inspired controller designed for stable bipedal walking.Keywords: neural network, humanoid robot control, ZMP (Zero Moment Point) I. 서론 Throughout history, the human body and mind have inspired artists, engineers, and scientists. The field of humanoid robotics focuses on the creation of robots that are directly inspired by human capabilities. These robots usually share similar kinematics to humans, as well as similar sensing and behavior. The motivations that have driven the development of humanoid robots vary widely [1]. The primary motives are expected to assist human beings, cooperate with people and be stable enough not to fall down to avoid hurting nearby humans, other objects as well as damaging their own bodies. Keeping the humanoid robots stable and steady when they are standing, walking or moving is one of the fundamental functions and most important issue that needs to be addressed. To handle this important issue, many intelligent control schemes have been proposed [2][3][4][5]. However, most of these proposed schemes have produced restricted simulation results only, and so it is difficult to analyze the real stabilities of actual humanoid robots based on their walking patterns.As for the indices of biped walking robots to improve robotic stability, the zero moment point (ZMP) has been introduced and is commonly used for the gait planning of biped humanoid robots. This is a key point in the control of ASIMO [6], a 26-DOF humanoid robot developed by Honda Motor Company in 2000. Vukobratovic et al., [7] investigated the walking dynamics and has proposed ZMP as a good index for walking stability. Kim et al. [8,9] employed various computational intelligence methods to design a model of robotic locomotion based on the determination of the ZMP trajectories. The ZMP, which is defined as the point on the ground about which the sum of all the moments of the active forces equals zero, is indispensable in ensuring dynamic stability of a biped robot. If the ZMP is inside the ground s...

Intelligent control algorithm for ship dynamic positioning

“…The hydrodynamic coefficients of ship model are very difficult to accurately determine, and dynamically vary with the change of environment. In recent years, intelligent control approaches have been put forward to deal with dynamic uncertainties of nonlinear systems via FLS [17] or NN [18]. This paper considers uncertainties of both dynamic and disturbance in DPS control design, which is more practical.…”