A Nonlinear Robust Control Using a Fuzzy Reasoning and Its Application to a Robot Manipulator

A simplified adaptive nonlinear robust controller (SANROC) has beenstudied in the literature. However, this is based on using the so-calledmatching condition. The present controller is not based on using such acondition. The estimate of an upper bound for uncertainties is usuallyincreased by using the adaptive mechanism, e.g., by consisting of amonotonically increased function. In this paper, instead of using such ananalytically adaptive mechanism, a fuzzy reasoning technique is alsoincorporated with the adaptive mechanism of SANROC. The proposed method isapplied to a pantagraph type robot manipulator. The effectiveness of thepresent method is illustrated by some experiments.     

Improvements of detection accuracy and its confidence of defective areas by YOLOv2 using a data set augmentation method

Artificial Life and Robotics - Recently, CNN (Convolutional Neural Network) and Grad-CAM (Gradient-weighted Class Activation Map) are being applied to various kinds of defect detection and position...     

CAD/CAM-based force controller using a neural network-based effective stiffness estimator

In industries manufacturing metallic molds, various NC machine tools are used. We have already proposed a desktop NC machine tool with compliance control capability to automatically cope with the finishing process of LED lens molds. The NC machine tool has the ability to control the polishing force acting between an abrasive tool and a work piece. The force control method is called impedance model force control. The most effective gain is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition after considering the effective stiffness in the force control system. However, there is a problem in that the effective stiffness of the NC machine tool has undesirable nonlinearity. The nonlinearity has a bad influence on the force control stability. In this article, a fine tuning method of the desired damping is considered using neural networks. The neural networks acquire the nonlinearity of effective stiffness. The promise is evaluated through an experiment.     

Water-assisted self-sustained burning of metallic single-walled carbon nanotubes for scalable transistor fabrication

Nano Research - Although aligned arrays of semiconducting single-walled carbon nanotubes (s-SWNTs) are promising for use in next-generation electronics owing to their ultrathin bodies and ideal...     

A computational model of emotion through the perspective of benevolent agents for a cooperative task

This paper deals with a computational model of emotions and its application for cooperative benevolent agents. A stochastic emotion model based on Markov theory is adapted to perform their well organized tasks to achieve goal. The emotional model consists of four basic emotions: joy, anger, fear and sad. Different emotional behavior is obtained by updating the state transition matrix of stochastic model. Perception of stimuli has an impact on emotion inducing factors and thus, affects on emotion dynamics. With the developed model, a Matlab based simulation is performed to analyze the behavior of the agents with the emotional capability. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Thermal design and its on-orbit performance of the AKARI cryostat

The AKARI satellite (formerly known as ASTRO-F) is Japan’s first infrared astronomical satellite. AKARI is equipped with the infrared camera (IRC) and the far-infrared surveyor (FIS), which are cooled below 7 K. The AKARI’s 68.5 cm telescope, which is made of SiC, is also cooled below 7 K. A unique feature of the AKARI cryostat is that it uses both cryogen and mechanical coolers. Using mechanical coolers, the helium lifetime can be greater than one year with 170 L of liquid helium. AKARI was launched on February 21, 2006 (UT), from the Uchinoura Space Center (USC). It has been performing successfully in orbit.     

Three-dimensional laparoscope based on the manipulation of polarized light by a cellophane half-wave plate

A three-dimensional laparoscope that can capture three-dimensional images during surgery is reported. The principle is solely based on the manipulation of polarized light by a cellophane half-wave plate rather than computer processing; hence there is no time delay (it operates in real time) and lesions are viewed in true color, which is important for diagnostics. Three-dimensional images are obtained with a single laparoscope. A unique feature of this three-dimensional laparoscope is that it includes a virtual ruler to measure distances without physically touching the affected areas. The structure is simple, sturdy, lightweight, and its diameter is no bigger than a standard 10 mm diam laparoscope.     

An automatic parking system using an optimized image-based fuzzy controller by genetic algorithms

An automatic parking system of a car-like mobile robot is an important issue in commercial applications. An image-based fuzzy controller for an automatic parking system of a car-like mobile robot was developed in previous work, where the membership functions were tuned by experimentally. The aim of this paper is to optimize the parameters of the membership functions, which were performed in previous work, using a genetic algorithm against the complicated tuning of the controller. The details of GA implementation, such as the design parameters and choice of fitness function, are described. Simulation results illustrate the effectiveness of the developed schemes.     

A Neuro-interface with fuzzy compensator for controlling nonholonomic mobile robots

This paper describes a control method for mobile robots represented by a nonlinear dynamical system, which is subjected to an output deviation caused by drastically changed disturbances. We here propose some controllers in the framework of neuro-interface. It is assumed that a neural network (NN)-based feedforward controller is construcetd by following the concept of virtual master-slave robot, in which a virtual master robot as a feedforward controller is used to control the slave (i.e., actual) robot. The whole system of the present neuro-interface consists of an NN-based feedforward controller, a feedback PD controller and an adaptive fuzzy feedback compensator. The NN-based feedforward controller is trained offline by using a gradient method, the gains of the PD controller are to be chosen constant, and the adaptive fuzzy compensator is constructed with a simplified fuzzy reasoning. Some simulations are presented to confirm the validity of the present approach, where a nonholonomic mobile robot with two independent driving wheels is assmued to have a disturbance due to the change of mass for the robot.