In this paper we present the feed-forward neural network controller of robotic arm, which makes use of tracking method applied to stereo-vision cameras mounted on the head of the humanoid robot Nao, in order to touch the tracked object. The Tracking-Learning-Detection (TLD) method, which we use to detect and track the object, is known for its state-of-art performance and high robustness. This method was adjusted to be usable with a stereo-vision camera system, in order to provide 3D spatial coordinates of the object. These coordinates are used as the input for the feed-forward controller, which controls the arm of a humanoid robot. The goal of the controller is to move the hand of the robot to the object by setting arm joints into position corresponding to the object location. The controller is implemented as an artificial neural network and trained using the error back-propagation algorithm. The experiment, which demonstrates the proof of the concept, is also denoted in this paper.

Small turbojet engines represent a special class of All these aims comply and put emphasis mostly on safety turbine driven engines. They are suitable for scientific issues of turbo-jet engines. Other special feature resulting purposes and research of certain thermodynamic processes from our third aim is direct use of old obsolete small ongoing in turbojet engines. Moreover such engines can be used for research in the area of alternative fuels and new turbojet engines as sources of energy with use of cheap methods of digital control and measurement. Our research, alternative fuels. We have to take in consideration that which is also presented in this article, is headed toward these there exist a huge number of such small turbojet engines in aims. We evaluate and propose a system of digital old aircraft that are in non flying condition. Such engines measurement of a particular small turbojet engine -MPM can be refurbished and used again for other purposes. All 20. Such engine can be considered as highly non-linear large knowledge obtained by experiments with such engine can scale system. According to obtained data and experiments we be expanded to higher levels and certain principles may be propose situational model and situational control algorithms used for design of particular algorithms of control that for the engine with use of certain methods of artificial could also be used in normal class turbojet engines. intelligence as new methods of control of large scale systems. II SITUATIONAL CONTROL OF LARGE SCALE SYSTEMS I INTRODUCTION Situational control was designed for the control of complex Present state of technological development and growing systems, where the traditional cybernetic models weren't complexity of systems offers many challenges and also sufficient [8]. Model proposed in [8] wasn't sufficient to opportunities to achieve better results. In the area of jet control systems characterized by features like unique,propulsion, terms like safety, economic profitability and at dynamics, incompleteness and indete.minacy of the same time high efficiency come into foreground. The description, ambiguity and presence of a free will. For traditional systems of control are becoming obsolete anda systems, where it is difficult to describe their specific traditional systems of control are becoming obsolete and a structure and behavior and where the presence of a human with the need to satisfy the mentioned terms it is needed to factor has an unforeseeable character and also where the incorporate the newest technologies of control even for use system is developing by itself in time, methods of in older systems to bring them up to nowadays standards. It situational control have been developed [7] More general wouldn't be economically favorable to test such approach to situational control is formatter control of technologies within expensive and also very complex big complexes [1] Formatter control of a complex means not turbojet engines also with regard to safety of such testing. only the control of its parameters, ...

No abstract

Abstract.A large scale system in general is a high dimensional high parametric system with complex dynamics. For efficient and optimal function of such systems, it is necessary to propose and implement newest knowledge from the areas of cybernetics and artificial intelligence. Present control systems are often limited to control a complex system only at some given conditions. However in real-world applications these systems find themselves in very different working conditions, what influences parameters of their operation and characteristics of behavior and may lead to errors and critical states. The article deals with overview of methods of situational control and is aimed on implementation of these methods in the area of turbojet propulsion.

No abstract