McKibben muscle is a kind of pneumatic artificial muscle. It can be used as the actuator to drive the robot and the rehabilitation device. So, its force characteristic is very important in order to control the contraction and extension of the McKibben muscle for the applications in the robot field. In this paper, a new force model, which describes the basic characteristics of the McKibben muscle such as nonlinear phenomena like hysteresis, is proposed based on the experimental results. The model can reproduce the experimental results exactly. Therefore, the model is very useful to analyze the behaviors of robots and rehabilitation devices driven by the McKibben muscles.
The purpose of this research is to find an easy and effective method for the vision-based mobile robot navigation in indoor environment. In our case, the line is the floor-line with especial colour, and the landmarks are some shapes with especial colours. The color models of the floor-line and landmarks are built, in which floor-line and landmarks color samples were extracted from sample images of floor-line and landmarks taken under different lighting conditions to make color models more robust. The robot tracks the floor-line by the peak of the floor-line colour probability distributions to move, and the robot's action policy is decided when the landmarks have been seen and recognized; the landmark is recognized by its colour and shape.
In the past years, we have developed neural control strategies and relevant image processing methods. Neural control by a neurocomputer has been used in the mobile vehicle control system. The hardware neurocomputer RN-2000 is the kernel part of the system. The purpose of this paper is to solve the problem of how to realize the hardware neurocomputer by back-propagation (BP) neural network learning on-line. The strategy presented in this paper is based on modifying the past patterns and adjusting the content of the driving patterns by a new algorithm proposed. Learning happens during the driving procedure of the mobile vehicle. This research shows the possibility of the neurocomputer whose the BP neural network is inside to learn human knowledge on-line by the aid of software.
This paper concerns a control system for a resource distribution in a complex of parallel operations. The operations are described by relational knowledge representation with uncertain parameters characterized by an expert. The knowledge obtained from an expert is further corrected online by applying an adaptation process. Three particular adaptive control algorithms are suggested, of which two use an artificial neural network. The paper presents selected results of simulations showing that the proposed concepts and algorithms may be practically useful.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.