Saifudin Razali

Machine Vision System for Automatic Weeding Strategy in Oil Palm Plantation using Image Filtering Technique

Machine vision is an application of computer vision to automate conventional work in industry, manufacturing or any other field. Nowadays, people in agriculture industry have embarked into research on implementation of engineering technology in their farming activities. One of the precision farming activities that involve machine vision system is automatic weeding strategy. Automatic weeding strategy in oil palm plantation could minimize the volume of herbicides that is sprayed to the fields. This paper discusses an automatic weeding strategy in oil palm plantation using machine vision system for the detection and differential spraying of weeds. The implementation of vision system involved the used of image processing technique to analyze weed images in order to recognized and distinguished its types. Image filtering technique has been used to process the images as well as a feature extraction method to classify the type of weed images. As a result, the image processing technique contributes a promising result of classification to be implemented in machine vision system for automated weeding strategy.

An unscented Rauch-Tung-Striebel smoother for a bearing only tracking problem

The unscented Kalman filter (UKF) has become a new technique used in a number of nonlinear estimation problems to overcome the limitation of Taylor series linearization. It uses a deterministic sampling approach known as sigma points to propagate nonlinear systems and has been discussed in many literature. However, a nonlinear smoothing problem has received less attention than the filtering problem. Therefore, in this article we examine an unscented smoother based on Rauch-Tung-Striebel form for discrete-time dynamic systems. This smoother has advantages available in unscented transformation over approximation by Taylor expansion as well as its benefit in derivative free. To evaluate the performance of this smoother, we compare this algorithm with an extended Rauch-Tung-Striebel algorithm through the simulations of a bearing-only tracking problem.

A Kalman Filter approach to PCB drill path optimization problem

Drill path optimization problem is an important problem in holes drilling with computer numerically controlled (CNC) machine. Due to the exponential increase in the number of possible solutions when the number of holes to be drilled increase, the metaheuristic optimization algorithm seems to be a good choice in solving this type of optimization problem. This paper presents a Kalman Filter approach in solving printed circuit board (PCB) routing problem by using the Simulated Kalman Filter (SKF) algorithm. The experimental results are compared with those obtained by swarm intelligence approach, which are the Particle Swarm Optimization (PSO) variants, Ant Colony System (ACS) and Cuckoo Search (CS). The implementation proves to be effortless with good global convergence capability.

Analyzing the mobile robot localization performance in partially observable conditions

This paper deals with theoretical investigation of robot localization considering partial observability conditions. The problem is very important as most of the mobile robot applications are controllable but not observable due to some aspects. The paper investigate the importance of correlation to the mobile robot estimation through the technique of decorrelating some of the elements of state covariance of the updated state covariance. To demonstrate the effect of correlation, two cases of partial observability are examined which are the unstable and stable partial observability. The cases are build based on the configurations of the state covariance for mobile robot references when doing observations. Our preliminary results suggest that the system with stable partial observability shows very good and consistent estimation while the unstable case lead to inconsistency and erroneous estimation.

Fuzzy Logic Controller Design for A Robot Grasping System with Different Membership Functions

This paper investigates the effects of the membership function to the object grasping for a three fingered gripper system. The performance of three famously used membership functions is compared to identify their behavior in lifting a defined object shape. MATLAB Simulink and SimMechanics toolboxes are used to examine the performance. Our preliminary results proposed that the Gaussian membership function surpassed the two other membership functions; triangular and trapezoid memberships especially in the context of firmer grasping and less time consumption during operations. Therefore, Gaussian membership function could be the best solution when time consumption and firmer grasp are considered.

An unscented Rauch-Tung-Striebel smoother for a vehicle localization problem

The unscented Kalman filter (UKF) has become relatively a new technique used in a number of nonlinear estimation problems to overcome the limitation of Taylor series linearization. It uses a deterministic sampling approach known as sigma points to propagate nonlinear systems and has been discussed in many literature. However, a nonlinear smoothing problem has received less attention than the filtering problem. Therefore, in this article we examine an unscented smoother based on Rauch-Tung-Striebel form for discrete-time dynamic systems. This smoother has advantages available in unscented transformation over approximation by Taylor expansion as well as its benefit in derivative free. This smoothing technique has been implemented and evaluated through vehicle localization problem.

A Spherical Simplex Unscented Rauch-Tung Striebel Smoother for a Vehicle Localization Problem

The unscented Kalman filter (UKF) has become relatively a new technique used in a number of nonlinear estimation problems to overcome the limitation of Taylor series linearization. It uses a deterministic sampling approach known as sigma points to propagate nonlinear systems and has been discussed in many literature. However, a nonlinear smoothing problem has received less attention than the filtering problem. Therefore, in this article an unscented smoother based on Rauch-Tung-Striebel form is examined for discrete-time dynamic systems. It has advantages available in unscented transformation over approximation by Taylor expansion as well as its benefit in derivative free. In addition, new sampling technique known as a spherical simplex has been introduced and evaluated. To show the effectiveness of the proposed method, the unscented smoother is implemented and evaluated through a vehicle localization problem