The evolution of the microprocessor industry, combined with the reduction on cost and increase of efficiency, gives rise to new scenario for ubiquitous computing where humans trigger seamlessly activities and tasks using unusual (often imperceptible) interfaces according to physical space and context. Many problems must be faced: adaptivity, hybrid control strategies, system (hardware) integration, and ubiquitous networking access. In this paper, a solution that attempts to provide a flexible and dependable solution to these complicated problems is illustrated. First, an extensible markup language (XML)-derived technologies is proposed to define fuzzy markup language (FML), a markup language skilled for defining detailed structure of fuzzy control independent from its legacy representation. FML is essentially composed of three layers: 1) XML in order to create a new markup language for fuzzy logic control; 2) document type definition in order to define the legal building blocks; and 3) extensible stylesheet language transformations in order to convert a fuzzy controller description into a specific programming language. Then an agent-based framework designed for providing proactive services in domotic environments, is presented. The agent architecture, exploiting mobile computation, is able to maximize the fuzzy control deployment for the natively FML representation by performing an efficient distribution of pieces of the global control flow over the different computers. Agents are also used to capture user habits, to identify requests, and to apply the artefact-mediated activity through an adaptive fuzzy control strategy. The architecture adopts interoperability techniques that, combined with sophisticated control facilities, represent an efficient experience for adaptive domotic framework.

Fuzzy control interoperability and scalability for adaptive domotic framework

The unmanned control of the steering wheel is, at present, one of the most important challenges facing researchers in autonomous vehicles within the field of intelligent transportation systems (ITSs). In this paper, we present a two-layer control architecture for automatically moving the steering wheel of a mass-produced vehicle. The first layer is designed to calculate the target position of the steering wheel at any time and is based on fuzzy logic. The second is a classic control layer that moves the steering bar by means of an actuator to achieve the position targeted by the first layer. Real-time kinematic differential global positioning system (RTK-DGPS) equipment is the main sensor input for positioning. It is accurate to about 1 cm and can finely locate the vehicle trajectory. The developed systems are installed on a Citroe/spl uml/n Berlingo van, which is used as a testbed vehicle. Once this control architecture has been implemented, installed, and tuned, the resulting steering maneuvering is very similar to human driving, and the trajectory errors from the reference route are reduced to a minimum. The experimental results show that the combination of GPS and artificial-intelligence-based techniques behaves outstandingly. We can also draw other important conclusions regarding the design of a control system derived from human driving experience, providing an alternative mathematical formalism for computation, human reasoning, and integration of qualitative and quantitative information.

/pdf/power-steering-control-architecture-for-automatic-driving-4t476jwtiu.pdf

Power-steering control architecture for automatic driving

Agent-based architecture for designing hybrid control systems

The model and regulation of traffic systems are difficult tasks. Nevertheless Systems Theory and classic tools can be used to obtain the model and to regulate traffic respectively. A common way to organize traffic in a town area is to do a centralized control of the red lights based on queuing theory. Our approach is to distribute the control between a central system and on board car controllers that command every vehicle automatically according to the traffic rules. In order to do it we will implement fuzzy expert systems in computers augmented with fuzzy coprocessors and we will equip the vehicles with the necessary computers, instrumentation and communications.

Fuzzy Traffic Police for Autonomous Vehicles

Fuzzy control has received the legacy of classical control systems, more specifically in the realm of industrial process control. This legacy is accompanied by the inheritance of an important requirement: execution performance. Nowadays, for an application developer, talking about improved performance means talking about parallelism, both on software or hardware. There has been substantial progress in the design of special purpose hardware to support fuzzy controllers, but there are problems with parallel software implementations. The purpose of the paper is to present a layer-based model and a knowledge database structure that materializes the implementation of a distributed universal fuzzy controller.

A layer-based computational model plus a database structure as a framework to build parallel fuzzy controllers

The authors have implemented a distributed universal fuzzy controller capable of adapting itself to deal with a specific process. Due to its distributed nature the controller can run sequentially, in a processor, or in parallel, in a net of processors when the application requires it. In order to implement the distributed universal fuzzy controller the authors have developed a system with the following components: (1) a language to describe the control problem in terms of fuzzy inputs, outputs and rules, defined by a Pb-grammar; (2) a language to represent internally the control problem in terms of elementary fuzzy processes defined by a Pe-grammar; (3) a library of the elementary fuzzy processes, mentioned in (2); and (4) a set of software tools. Among the software tools there are an extractor, a loader and an ender procedure. The extractor identifies the elementary and independent processes in which the fuzzy controller can be divided. This extractor receives the Pb-description of the control problem and it provides the Ps-description. The loader receives the Ps description and puts the elementary processes into the physical processors and also it starts its execution. When the user wants to finish the control task, the ender turns off the set of processes. The distributed universal fuzzy controller has been implemented sequentially and in parallel on a network of transputers, its performance is being tested in an industrial application: the tuning of high frequency amplifiers. >

M.T. Carvalho de Andrade

Papers

Software tools to obtain a distributed universal fuzzy controller