Makoto Obayashi

Learn More
Although a large number of researches have been carried out into the analysis of nonlinear phenomena, little is reported about using reinforcement learning, which is widely used in artificial intelligent, intelligent control, and other fields. Here, we consider the problem of chaotic time series using a self-organized fuzzy neural network and reinforcement(More)
The present paper proposes an objective-based reinforcement learning system for multiple autonomous mobile robots to acquire cooperative behavior. The proposed system employs profit sharing (PS) as a learning method. A major characteristic of the system is using two kinds of PS tables. One is to learn cooperative behavior using information on other agents'(More)
Human learns incidents by own actions and reflects them on the subsequent action as own experiences. These experiences are memorized in his brain and recollected if necessary. This research incorporates such an intelligent information processing mechanism, and applies it to an autonomous agent that has three main functions: learning, memorization and(More)
Feeling and emotion are important to human being during his/her learning process, also valuable to be adopted into intelligent machines. This research presents a system which forms and expresses feelings of a robot. The vision information of robot is used and the environment features are categorized by a hierarchical SOM (Self-Organization Map). The(More)
In this paper, we present a method to initialize at a feasible point and unfailingly solve a non-convex optimization problem in which a set-point motion is planned for a multi-link manipulator under state and control constraints. We construct an initial feasible solution by analyzing the final time effect for feasibility problems of flatness based motion(More)
A new chaotic memory search model based on associative dynamics using features in stored patterns is proposed. In the present paper, two kinds of features are considered; external and internal ones. The former is assigned by a designer and the latter is automatically assigned by competitive learning. The control of chaotic and static states is realized(More)
We propose a path planning method to avoid moving obstacles only by steering. The method uses the tangent-arc-tangent-arc-tangent model to plan a path that satisfies two requirements: 1) the own vehicle modeled as a rigid body with a shape and direction doesn't collide with moving obstacles on the path (i.e., the path is collisionless); 2) the path takes(More)
This paper presents an effective TSP (Travel-ing Salesman Problem) solver for large-scale problems using neural networks. Firstly, in the proposed method, an intractable large-scale TSP is divided into some tractable small-scale problems (clusters) using a clustering technique. Secondly, a visiting order of clusters is determined using chaotic neural(More)
  • 1