Gérard Lachiver

Fuzzy detection of edge-direction for video line doubling

Video line doubling can be realized using time-space interpolation filters. To improve their performances for moving diagonal lines, we have developed a fuzzy edge-direction detector. This fuzzy detector works by identifying small pixel variations in five orientations (0/spl deg/, /spl plusmn/45/spl deg/, and /spl plusmn/60/spl deg/) and by using rules to infer the prevailing direction. This direction is then used to spatially rotate the interpolation filter. For the fuzzy detector, three fuzzy sets are used to characterize the inputs, and two rule bases have been validated. This article presents the characteristics of the fuzzy edge-direction detector along with the methodology used for fuzzy sets positioning. Detection and interpolation results are also presented.

An Optoelectronic Device to Read and Spell Braille-Braillect

We report on design and performance of a hand-held probe that recognizes the point patterns of braille, and on the associated circuitry that pronounces the characters read.

Fuzzy selection and blending of behaviors for situated autonomous agent

Intelligent control is a field of research attempting to attain demanding control goals in complex systems. To do so, many methods and theories must be combined and used efficiently. We propose a new control architecture that tries to unify the principles and characteristics associated with intelligence. This architecture uses behaviors as its basic control components. These behaviors are selected dynamically and their actions are combined according to the intentions of the agent. Introspection of its reactions is one major new ability given to the agent by this architecture. A simulated world for mobile robots is used to validate the characteristics and the principles associated with our proposed architecture. This article focuses on the use of fuzzy logic for the implementation of the architecture in this particular application.

Architectural Methodology Based on Intentional Configuration of Behaviors

Intelligence has been an object of study for a long time. Different architectures try to capture and reproduce these aspects into artificial systems (or agents), but there is still no agreement on how to integrate them into a general framework. With this objective in mind, we propose an architectural methodology based on the idea of intentional configuration of behaviors. Behavior‐producing modules are used as basic control components that are selected and modified dynamically according to the intentions of the agent. These intentions are influenced by the situation perceived, knowledge about the world, and internal variables that monitor the state of the agent. The architectural methodology preserves the emergence of functionality associated with the behavior‐based paradigm in the more abstract levels involved in configuring the behaviors. Validation of this architecture is done using a simulated world for mobile robots, in which the agent must deal with various goals such as managing its energy and its well‐being, finding targets, and acquiring knowledge about its environment. Fuzzy logic, a topologic map learning algorithm, and activation variables with a propagation mechanism are used to implement the architecture for this agent.

ROBUS [autonomous mobile robotic platform]

We have developed an autonomous mobile robotic platform named Robot Universite de Sherbrooke (ROBUS) that can be used in various activities of both curricula and adequately reflects the challenges of ECE projects. This article describes the mobile boric platform, ROBUS, that we developed and explains how it is used in various activities, such as course work, pedagogical activities, and the RoboToy Contest.

Micro-genetic algorithms in the optimisation of neuro-fuzzy controllers

The neuro-fuzzy network is a combination of fuzzy logic and neural nets which benefits from both approaches. A backpropagation algorithm applied to such a network may converge towards a local optimum. The authors apply the micro-genetic algorithm to optimise the architecture of the neuro-fuzzy network and to ensure its convergence towards the global optimum. This algorithm accomplishes crude approximation of the network architecture near a global optimum, towards which its direct convergence is afterwards brought about by backpropagation.

A sensorless control scheme based on fuzzy logic for AC servo drives using a permanent-magnet synchronous motor

In this paper, a control scheme for an AC servomotor drive using a permanent magnet synchronous motor is presented and analyzed. In the proposed scheme, fuzzy logic is used to estimate the rotor position and generate the reference currents. Two strategies, maximum torque and unit power factor, are analyzed using numerical simulation and their performances are shown.

Optimal speed tracking control of induction motor using artificial intelligence techniques

This paper presents a novel neural network based control architecture which use on line training to identify and control the nonlinear induction motor. The aim of this control is to force the shaft speed to follow a prescribed trajectory. The architecture incorporates two artificial neural networks and a fuzzy logic controller. Accepting that not all elements of the state are measurable, the first ANN is used as observer to give an estimate of the state. A state space description is applied, and the trained nonlinear innovation state space model of the motor is used. Since the motor is nonlinear, and since the observer, as well as, the controller (second ANN) are trained based on optimal criteria, the method is named non linear quadratic Gaussian. A fuzzy logic controller is used to provide an inner loop inspired by conventional vector control strategy. Simulated results are presented to validate the proposed architecture showing that speed control is stable, rapid to stabilize, and insensitive to parameter uncertainty and load disturbance.

Gain scheduling control of induction motor with artificial neural networks

This paper presents a nonlinear gain scheduling control of a nonlinear, time varying induction motor dynamics with unknown parameters based on pole placement control design. The objective of this control is to force the rotor speed to follow an arbitrarily prescribed trajectory. Neural networks are considered to produce a non parametric model of a nonlinear inverted-fed induction motor. However its possible to extract a so called gain matrix from a trained neural network model. A partition of this gain matrix allows on-line estimation of the actual relevant parameters. The inverted-fed induction motor will be identified as a NARMAX model and the order of the input-output will be determined by evaluating the modification of an index which is defined as Lipschitz number. The architecture incorporates an artificial neural network and a fuzzy logic controller. The ANN is used to identify the induction motor in order to extract a linear model, and a fuzzy logic controller is used to provide an inner loop inspired by conventional vector control strategy. Simulated results are presented to validate the proposed architecture showing that speed control is stable, rapid to stabilize, and insensitive to parameter uncertainty and load disturbance.

Fuzzy logic-based controller of traffic intersection

The widely used conventional control of traffic intersections is based on classic logic. The strategy of this approach can be divided in two main procedures: fired-time system and on-line system. The fired-time system uses predefined time intervals to control the car-flow through the intersection. The on-line system utilises the proximity sensors and combines the predefined time intervals with changes in the particular cycles. Usually, sets of measurements must be taken to determine the proper adjustment of time cycles. The measurements are based an observations of flow patterns and car counting during different periods of the day. The major inconvenience of the current traffic lights control is the low accuracy, allowing only crude changes in the green-red cycle. Fuzzy logic control can be used as an alternative approach to the traffic environment. A fuzzy controller can provide smoother and more flexible control of the timing of the green-red phases, depending on the flow density of vehicles. The purpose of the proposed method is to minimize the waiting time of vehicles in an intersection.