A network robot system integrated with various types of robots via ubiquitous networks is a new concept which introduces an interactive robot living together with people. In this paper, we present a tangible network robot system composed of a mobile robot and vision sensors embedded in an environment, and show human behavior recognition methods necessary for providing diverse services desired by the people in good time. Typical human behaviors are described with logical sensors which are defined through data fusion processes spatially and temporally with the physical sensors of the mobile robot and those in the environment. Our system can be utilized to make human-robot communication and interaction friendlier and smarter

In the power plant under operation, there are many important equipments which the operator must inspect in the non-operation state. Our milestone of the humanoid robot which can inspect for the man is moving around the Power Plant and inspection experiments by using navigation system of autonomous and tele-operation fusion control. We constructed and implemented a navigation system, which is controlled by Tag (RF-ID) and Remote teaching human interface. The robot just reads a tag with information on the plant maintenance, and the robot can act with the information. Therefore, switching of the program movement of the robot and the remote control become very easy.

The authors propose a neural network (NN) model for pattern recognition which can learn new patterns without losing patterns memorized in the past. This model is called a neural network based on distance between patterns (NDP). The NDP uses the radial basis function (RBF) as the response function in place of the sigmoid function. The response function is a smooth function similar to the Gaussian base function and the probability density function. The response function learns patterns faster than the multilayered perceptron (MLP) as well as other RBF NNs. The most salient architectural feature of the NDP is self-organization by adding nodes in the output layer one by one. The NDP also varies the curve of the response function by tuning the center and the width of the response function, and separates the input space into regions for each category appropriately.