Koji Shimojima

Self-tuning fuzzy modeling with adaptive membership function, rules, and hierarchical structure based on genetic algorithm

Abstract Recently, fuzzy systems have been used in many fields and places. In order to apply the fuzzy system to the various fields, the tuning and optimizing method of the fuzzy system is the key issue. Some self-tuning methods have been proposed so far. However, these conventional self-tuning methods do not have sufficient capability of learning. In this paper, we propose a new supervised self-tuning fuzzy modeling, which consist of some membership function expressed by the radial basis function with insensitive region. Learning is carried out by the genetic algorithms. The descent method is also utilized for tuning the shapes of the membership function and consequent parts. The effectiveness of the proposed methods is shown by some numerical examples.

The role of virus infection in virus-evolutionary genetic algorithm

This paper deals with a genetic algorithm based on virus theory of evolution (VEGA). The VEGA realizes horizontal propagation and vertical inheritance of genetic information in a population with virus infection operators and genetic operators. The main operator of the VEGA is the reverse transcription operator, which plays the roles of a cross over and a selection simultaneously. The convergence and genetic diversity of the VEGA depend on the frequency of the virus infection. We apply the VEGA to a travelling salesman problem, a knapsack problem, and function optimization problems, and discuss the effectiveness of the virus infection through the numerical simulation.

Trajectory generation for redundant manipulator using virus evolutionary genetic algorithm

This paper deals with an application of a virus-evolutionary genetic algorithm (VEGA) to hierarchical trajectory planning of a redundant manipulator. The hierarchical trajectory planning is composed of a trajectory generator and position generator. The position generator generates collision-free intermediate positions of the redundant manipulator. The trajectory generator generates a collision-free trajectory based on some intermediate positions sent from the position generator. To generate a collision-free trajectory of the redundant manipulator, the VEGA is applied to the hierarchical trajectory planning only based on forward kinematics. The VEGA realizes horizontal propagation and vertical inheritance of genetic information in a population of candidate solutions. The main operator of the VEGA is a reverse transcription operator, which plays the roles of a crossover and selection simultaneously. In this paper, self-adaptive mutation is applied to the VEGA for local search of trajectory planning to obtain higher performance and the quick solution. Simulation results of the hierarchical trajectory planning show that the VEGA can generate a collision-free trajectory.

RBF-fuzzy system with GA based unsupervised/supervised learning method

Fuzzy systems are used in many fields and places so far. In order to apply the fuzzy systems to the various fields and places, the tuning and optimizing method of the fuzzy system is the key issue. And the optimization of structure of fuzzy system (the number of membership function, the number of rules) is also very important to simplify the fuzzy systems. Some self-tuning methods have been proposed so far. However these conventional self-tuning methods do not have sufficient capability of learning. In this paper, we propose new unsupervised/supervised self-tuning fuzzy system, which consists of some membership functions expressed by the radial basis function with insensitive region. Learning are based on the genetic algorithms. The descent method is also utilized for tuning the shapes of membership function and consequent parts in case of supervised learning. The effectiveness of the proposed methods is shown by some numerical examples and simulations.<<ETX>>

Self-scaling reinforcement learning for fuzzy logic controller-applications to motion control of two-link brachiation robot

In this paper, we propose a new reinforcement learning algorithm to generate a fuzzy controller for robot motions. This algorithm generates a range of continuous real-valued actions, and the reinforcement signal is self-scaled. This prevents the weights from overshooting when the system receives very large reinforcement values. Therefore, this algorithm can obtain a solution in fewer iterations. The proposed method is applied to the control of the brachiation robot, which moves dynamically from branch to branch like a gibbon swinging its body in a pendulum-like fashion. Through computer simulations, we show the fast convergence and the robustness against disturbances.

Micro autonomous robotic system and biologically inspired immune swarm strategy as a multi agent robotic system

This paper presents both the hardware and the software architectures for the multi agent robotic system. For the hardware architecture of the multi agent robotic system, the authors show the programmable MARS (micro autonomous robotic system). This robot can work for one of the agents of the multi agent robotic system. The size of this robot is 20 mm cubic. The authors can rewrite and download any programs by the infrared communication function and the programmable function. For the software architecture of the multi agent system, the authors propose the algorithm which can adapt and generate the swarm strategy in the dynamic environment, based on the biological immune system. The authors adopt the self and non-self recognition network of the immune system in their algorithm.

Genetic algorithm with age structure and its application to self-organizing manufacturing system

The genetic algorithm has recently been demonstrated its effectiveness in optimization issues, but it has two major problems: a premature local convergence and a bias by the genetic drift. In order to solve these problems, we propose a new genetic algorithm with an age structure of a continuous generation model. The new genetic algorithm is applied to a self-organizing manufacturing system-a process which self-organizes to other processes in a flexible manufacturing system environment. The effectiveness of the genetic algorithm with age structure is demonstrated through numerical simulations of the reorganization of a press machining line as an example of the self-organizing manufacturing system.<<ETX>>

Multimedia tele-surgery using high speed optical fiber network and its application to intravascular neurosurgery - system configuration and computer networked robotic implementation

We propose a multimedia tele-surgery system for training, diagnosis, and assistance in surgery. To realize this system, a high speed optical fiber network with asynchronous transfer mode (ATM) is used to provide high quality moving pictures. We designed a new teleoperation system based on ATM, which is different from the conventional one that is based on Ethernet. We built a prototype of the virtual simulator system for the intravascular neurosurgery that consists of a 3D-computer graphics simulator and two types of joysticks. The joysticks are used for the controller and force display of catheter head direction, position, and orientation. A visual assistance method is proposed to assist the operator. We performed teleoperation experiments between Nagoya and Tokyo, about 350 km apart from each other, using high speed optical fiber network, and evaluated the effectiveness of the proposed system.

Distributed virtual environment for intravascular tele-surgery using multimedia telecommunication

The number of specialized medical doctors is decreasing. It is important to assist doctors in their operation of surgical tools. To solve this problem, we propose a distributed VR system using multimedia telecommunication for training, diagnosis, and assistance in surgery. To realize this system, it is important to exchange high quality moving pictures. We use high speed optical fiber network with ATM (Asynchronous Transfer Mode). ATM has excellent features such as bandwidth allocation which is suitable for multimedia communication on computer networks. Based on this new information infrastructure we built a prototype telesurgery system for intravascular neurosurgery. We made a virtual simulator for the operation of a catheter, that is designed for minimum invasive surgery inside complex and narrow brain blood vessels. A force display and visual assistance method are proposed to assist the doctor. We undertook teleoperation experiments between Nagoya and Tokyo, about 350 km away each other, using high speed optical fiber network, and evaluated the effectiveness of the proposed system.

Trajectory planning of cellular manipulator system using virus-evolutionary genetic algorithm

This paper deals with an application of a genetic algorithm based on a virus theory of evolution (VEGA) to trajectory planning of a cellular manipulator system. A cellular manipulator system is composed of a large number of autonomous parts and tools. The form of the cellular manipulator system is dynamically reconfigured according to its environment and given tasks. In this paper, the VEGA is applied to a trajectory planning problem. The VEGA realizes a horizontal propagation and a vertical inheritance of genetic information in a population. The main operator of the VEGA is a reverse transcription operator, which plays the roles of a crossover and a selection at the same time. Simulation results of trajectory planning shows that the VEGA generates a collision-free trajectory.