Annual Review in Automatic Programming最新文献

Block diagrams have been recently successfully applied in programming safety critical control systems. This presentation investigates the interest of using recursion within this framework. First it identifies the necessary concepts for using recursion while remaining within the domain of real-time bounded memory, bounded response time systems and then it presents examples, which hopefully illustrate the interest of the approach.

This paper describes the architecture of a supervisory control and data-acquisition system. It works like an operator support tool by diagnosing malfunctions of a production process and inspecting the quality of the product. The system provides the operator in a plant with relevant process data and, at the same time, has to meet tough real-time requirements. The integration of intelligent alarm processing into a large supervisory control system will be described and techniques covering on-line processing of real-time data and intelligent alarm processing will be discussed. The system is based on a blackboard architecture which integrates a sequence of problem-solving methods and exhibits an incremental and opportunistic problem-solving style.

In this paper we develop a technique to achieve robust high performance real-time wallfollowing behavior of a mobile robot in an indoor office environment, more specifically, in a corridor environment. The mobile robot achieves increasingly better performance by learning the environment's (most important) features in successive runs through it. This allows the robot to perform the task repeatedly, reliably, increasing the speed at which it is done after every step, without losing accuracy. We are basing our approach in the Spatial Semantic Hiearchy [Kuipers et. al. 1993].

This paper describes a wheelchair for physically disable people. In this wheelchair, a dependent-user recognition voice system and ultrasonic and infrared sensor systems have been integrated. In this way, the wheelchair can be driven whit oral commands and with the possibility of obstacle avoidance and downstairs or hole detection. The wheelchair allows autonomous driving (for example following walls). This project has been developed in the Electronic Department of the Alcala University and it has been financed by the ONCE Foundation. The electronic control system we have built allows an easy and handy driving with the only use of the human voice. The system drives itself through structured environments (hospitals, rehabilitation centers and so on). System structure is in a way that is possible to add more features, easy and economically (like appliance control, door opening and closing and other telecontrol, etc.).

Some of the theory-bound evolutional trends in real-time AI applications are pointed out based on analysis of essential properties of real-time systems as well as AI based systems. The evolutional mainstream is increasing interdisciplinary integration. Three subtrends are illustrated on examples: mechanical combination of methods, AI methods used for approximate solution of “classical” problems, and abstract methods applied in new domains. In addition similarity between integrated circuits and real-time systems design and increased use of formal verification at the early stages of systems development are pointed out.

The problem of identification of model parameters often arises when trying to work directly with nonlinear model representations. This problem also appears using fuzzy rule-based models. In this paper an alternative approach is presented. By combining the feasibility of linear, simple models and the flexibility of fuzzy logic a composite, nonlinear model is obtained. Such a hybrid model is both accurate enough and easy to adjust. This model is used for the control system design and debugging, leaving the real system trials for fine adjustment of the obtained controller.

It has been developed, built and tested an artificial vision based system to follow roads, which provides control signals, in a short time, by means of a joint of artificial neural nets. The image is segmented in “road” or “not road.” The obtained segmentation is the input for two neural nets, a classic architecture net (NN), and a TDNN (Time Delay Neural Network) one. The outputs provided by both nets, with a trajectory estimation, are introduced to a decision-making block, which selects the alternative containing less error. The classifier parameters are updated according to the current segmentation.

One of the key problems in real-time control Artificial Intelligent systems design is the development of an architecture able to manage efficiently the different elements of the process. In the management of Waste Water Treatment Plants (WWTP), with a great interrelation between the different units, there is a problem in order to identify and solve the different specific situations. A Supervisory System recognizes predefined problems and uses a determined strategy in order to keep the process controlled. The main goal of the paper is to present a knowledge-based distributed architecture for real time supervision and control of WWTP that overcomes some of these troubles. It is discussed the development of the application and the methodology employed in it. The prototype's architecture being developed DAI-DEPUR is detailed together with some obtained results.

In the design of autonomous computer-based systems, we often face the embarrassing situation of having to specify, to the system, how it should carry out certain tasks, which involve computations known to be intractable or are suspected of being so. To circumvent such impasses, we resort to complexity-reducing strategies and tactics which trade some loss of accuracy for significant reductions in complexity. The term computational intelligence refers to such complexity reduction methods and to the research aimed at identifying such methods. In this paper we describe briefly some of our own work in this area and then develop a computational intelligence view of the task of process monitoring and optimization, as performed by autonomous systems. Some important current fields of discovery in computational intelligence include neural-net computing, evolutionary programming, fuzzy sets, associative memory and so on.

In rule-based fuzzy control systems there is a need to evaluate the rulebase to detect redundant or contradictory rules, and to monitor the performance of the knowledge acquisition process, knowledge coming either from an human expert or from a learning mechanisms if present. When faulty situations are detected corrective steps should be taken by the knowledge engineer or by a rulebase-maintenance metaknowledge. In this paper, a new ideal defuzzifier framework is presented with its use to develop matrix expressions for the consistency of the rules in a base and asessing the quality and quantity of the knowledge represented by them.