Roberto H. Tsunaki

A genetic programming based system for the automatic construction of image filters

The manual selection of linear and nonlinear operators for producing image filters is not a trivial task in practice, so new proposals that can automatically improve and speed up the process can be of great help. This paper presents a new proposal for constructing image filters using an evolutionary programming approach, which has been implemented as the IFbyGP software. IFbyGP employs a variation of the Genetic Programming algorithm GP and can be applied to binary and gray level image processing. A solution to an image processing problem is represented by IFbyGP as a set of morphological, convolution and logical operators. The method has a wide range of applications, encompassing pattern recognition, emulation filters, edge detection, and image segmentation. The algorithm works with a training set consisting of input images, goal images, and a basic set of instructions supplied by the user, which would be suitable for a given application. By making the choice of operators and operands involved in the process more flexible, IFbyGP searches for the most efficient operator sequence for a given image processing application. Results obtained so far are encouraging and they stress the feasibility of the proposal implemented by IFbyGP. Also, the basic language used by IFbyGP makes its solutions suitable to be directly used for hardware control, in a context of evolutionary hardware. Although the proposal implemented by IFbyGP is general enough for dealing with binary, gray level and color images, only applications using the first two are considered in this paper; as it will become clear in the text, IFbyGP aims at the direct use of induced sequences of operations by hardware devices. Several application examples discussing and comparing IFbyGP results with those obtained by other methods available in the literature are presented and discussed.

An Adaptive Genetic Algorithm based approach for production reactive scheduling of manufacturing systems

The problem for scheduling the manufacturing systems production involves the system modeling task and the application of a technique to solve it. There are several ways used to model the scheduling problem and search strategies have been applied on the models to find a solution. The solutions consider performance parameters like makespan. However, depending on the size and complexity of the system, the response time becomes critical, mostly when itpsilas necessary to reschedule. Researches aim to use Genetic Algorithms as a search method to solve the scheduling problem. This paper proposes the use of Adaptive Genetic Algorithm (AGA) to solve this problem having as performance criteria the minimum makespan and the response time. The probability of crossover and mutation is dynamically adjusted according to the individualpsilas fitness value. The proposed approach is compared with a traditional Genetic Algorithm (GA).

An Intelligent Autonomous Vehicle Management System

This paper describes an intelligent vehicle management system, which uses Fuzzy logic to infer, from a set of input variables obtained from the vehicles environment, what is the best destination for the vehicle. This is a decentralized implementation, that is, each vehicle is capable of deciding what is the best destination for itself, and also communicate with other vehicles to see if its objective is the best one globally. To ensure a good response time from the vehicles, without the need of a powerful and expensive hardware, every vehicle uses a table with the output defuzzified values previously calculated for the inference process, instead of a complete fuzzy engine.

Automatic construction of image operators using a genetic programming approach

This paper presents a methodology for automatic construction of image operators using a linear genetic programming approach, for binary, gray level and color image processing, where the processing solution for a particular application is expressed in terms of the basic morphological operators, dilation and erosion, in conjunction with convolution and logical operators. Genetic Programming (GP), based on concepts of genetics and Darwins principle of natural selection, to genetically breed and evolve computer programs to solve a wide variety of problems, is a branch of evolutionary computation, and it is consolidating as a promising methodology to be used in applications involving pattern recognition, classification problems and modeling of complex systems. Mathematical morphology is based on the set theory (complete lattice), where the notion of order is very important. This processing technique has proved to be a powerful tool for many computer vision tasks. However, the manual design of complex operations involving image operators is not trivial in practice. Thus, the proposed methodology tries to solve these drawbacks. Some examples of applications are presented and the results are discussed and compared with other methods found in the literature.

Automated Generalized Petri Net Reduction Using an Evolutionary Approach Applied to a Manufacturing System Model

Petri Net (PN) is a graphical mathematical tool used to create models that provide a formal specification of systems, creating the possibility of running behaviour analysis and properties verification. This kind of model is used to specify several system types and a good example of area in which this formalism is applied is to develop Manufacturing Systems models. In general, using PN to model systems where too much detailing is needed, causes the problem called state space explosion, that consists of a great element profusion in the model. In order to mitigate this problem several kinds of reduction rules were created aiming at simplifying the models, so that they can be easily analysed or simulated, maintaining some properties like: bounded ness, liveness and fairness. The combination of rules together within an automated method motivates the development of the present research. The goal was to define a group of reduction rules and create a genetic algorithm to automatically reduce PN models. The method obtained good results when automatically reducing PN models using six well known reduction techniques.

A Multi-Agent System Using Fuzzy Logic to Increase AGV Fleet Performance in Warehouses

Market competition requires an ever increasing performance from warehouses. Coupled with information technologies, high automation levels are achieved. Such automation is seen in the use of AGVs for material handling. An important problem in AGV fleets is deciding what task should be assigned to each AGV. To tackle this problem, a multi-agent AGV system is proposed, which has three agents: an AGV agent, a Loading Point (LP) agent and a Storage Point (SP) agent. The AGV agent uses a Fuzzy system to decide what task it should take, and dispatch the AGV to the location of the task, using the A-star (A*) algorithm to find the shortest path to the task. The LP agent keeps a list of all available tasks in its corresponding loading point, such as a loading dock, and handles task requests from AGV agents. The SP agent manages a particular storage space, such as a rack section, and handles AGV requests for payloads stored in the rack or requests for free space. To validate the system, a warehouse operation was simulated and evaluated measuring the average task wait time, time to complete tasks and average jam time. Two other decision methods were used, First Come First Served (FCFS) and Contract Network (CNET), to compare with the Fuzzy method. Results show that the Fuzzy method enabled a greater average task wait time reduction than the other two decision methods, and also completed tasks in less time.

Design of an experimental flutter mount system

Aeroelastic instabilities may occur in aircraft surfaces, leading then to failure. Flutter is an aeroelastic instability that results in a self-sustained oscillatory behaviour of the structure. A two-degree-of-freedom flutter can occur with coupling of bending and torsion modes. A flexible mount system has been developed for flutter tests in wind tunnels. This apparatus must provide a well-defined 2DOF system on which rigid wings encounter flutter. Simulations and Experimental Tests are performed during the design period. The dimensions of the system are determined by Finite Element analysis and verified with an Aeroelastic Model. The system is modified until first bending and torsion modes become the first and second modes and other modes become higher than these. After this, a Modal Analysis is performed. An identification algorithm, ERA, is used to determine modes shape and frequencies from experimental data. Detailed results are presented for first bending and torsion modes, which are involved in flutter. The flutter mechanism is demonstrated by Frequency Response Functions obtained in several wind tunnel velocities until flutter achievement and by a V-g-f plot obtained from an identification process performed with an extended ERA. Mode coupling, damping behaviour and the self-sustained oscillatory behaviour are verified characterising flutter.

A new comparison of Kalman filtering methods for chaotic series

Kalman filters are rooted in the technical literature, as a way of predicting new states in nonlinear systems providing a recursive solution to the problem of linear optimal filtering. Therefore, 54 years after its discovery, many modifications have been proposed in order to obtain better accuracy and speed. Some of these changes are used in this work; these being the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF) and Kalman Filter Cubature, intense research demonstrate the performance of each of their possible modifications and improvements, such as the use of Neural Networks in order to obtain an approximate model of the real system. The objective of this work is to use a known model, and testing eight possible modifications of these algorithms, thus obtaining better algorithm for future implementation with Neural Networks (NN), this being used for servo positioning in unstructured environments.

Mathematical Morphology Applied in Object Tracking on Position-Based Visual Servoing

Position-based visual servoing is a technique for vision-based robot control, which operates in the 3D workspace and uses a known model of the object to perform tasks of feature extraction and positioning. Among the many applications, position-based visual servoing is used in industrial environments, for object manipulation operations on conveyor belts. Mathematical morphology, a well-known computer vision technique, can be used for features extraction, representation of objects and to perform actions such as recognition by images. The representation of the object occurs with the assistance of a structuring element and the morphological operations are used to locate the object center. This work explores the binary mathematical morphology whose operators are trained by a reconfigurable system developed in a FPGA with the representation of the 3D model of the object to be applied in visual servoing in controlled applications such as tasks in industrial environments.

Development of an automated and dedicated measuring system for straightness evaluation

This work presents an automated and dedicated system aiming at the measurement of straightness errors of mechanical components, using an industrial robot. A multi-probe error separation technique was used to make measurements independent from the coordinate system of the robot. A mathematical model that takes into account the readings from three sensors was specifically designed for the proposed measurements and produces inspection results by means of the solution of a system of linear equations, in only one operation. Also in this work, a new approach was developed to minimize the influence of the zero-adjustment errors of the sensors, which represent the major source of errors in the separation process. Experimental tests applied to the measurement of straightness errors of mechanical components were accomplished, which demonstrated the effectiveness of the employed methodology.