Kusprasapta Mutijarsa

Design and implementation of software architecture behavioral-based robot control system using Active Object Computing Model

In this paper, we propose software architecture of behavioural-based robot control system using Active Object Computing Model. Active Object Computing Model is a programming technique that combines the three components, Event Driven Programming paradigm, Event Driven Software Architecture and UML State chart formalism. The scope of this project includes the activities of designing and implementing behavior-based navigation system software, designing and building autonomous mobile robot for software implementation, testing, observing and analyzing the behaviour of autonomous mobile robot which is controlled by behaviour-based navigation system software. The software has been tested on an autonomous mobile robot and run on ARM Cortex M3 processor using mbed NXP LPC1768 microcontroller and successfully demonstrated the behaviour of obstacle avoidance and object Following. Software Architecture is built using Quantum Platform™ from Quantum Leaps.

Color-based segmentation and feature detection for ball and goal post on mobile soccer robot game field

This study presents the real time implementation of object detection and tracking algorithm on mobile soccer robot. Object detection is considered as one of the most important task because ball and goal post are the main component in soccer. The system uses the combination of color-based segmentation and feature detection to detect the color and also the shape feature of the object used in the soccer robot game. The color segmentation uses thresholding method in Hue, Saturation, and Value (HSV) color space to differentiate the ball and goal post color from other objects in the field. Then, morphological operation is applied to the thersholded image to minimize the error. After that, Hough line transform is applied to detect the feature of the goal post. Then, ellipse detection is also applied to find the ball feature. This step is used so the desired object is correctly detected, not other object that have the same color. The final step is to calculate the image moments to determine the centroid of the objects and tracking it. Objects color, feature, and coordinate are obtained from this purposed method. In the implementation, the robot has successfully detect ball, goal post, and its position in a real time manner.

Humanoid robosoccer goal detection using hough transform

Goal posts detection is a critical robot soccer ability which is needed to be accurate, robust and efficient. A goal detection method using Hough transform to get the detailed goal features is presented in this paper. In the beginning, the image preprocessing and Hough transform implementation are described in detail. A new modification on the θ parameter range in Hough transform is explained and applied to speed up the detection process. Line processing algorithm is used to classify the line detected, and then the goal feature extraction method, including the line intersection calculation, is done. Finally, the goal distance from the robot body is estimated using triangle similarity. The experiment is performed on our university humanoid robot with the goal dimension of 225 cm in width and 110 cm in height, in yellow color. The result shows that the goal detection method, including the modification in Hough transform, is able to extract the goal features seen by the robot correctly, with the lowest speed of 5 frames per second. Additionally, the goal distance estimation is accomplished with maximum error of 20 centimeters.

Development of multimedia system for supporting education in rural areas

In Indonesia, the condition of education still tends to be unbalanced. The quality of education in urban areas is generally far better than the quality of education in rural areas. Education processes in rural areas face some problems like limited teaching resources, slight teaching tools, and monotonous teaching method. Therefore, an idea is emerged, a thinking to create a system in order to improve the quality of education in rural areas. Virtual Classbox 4.1 is a distance learning system developed to improve the quality of education in rural areas with video conferencing technology. Virtual Classbox 4.1 is designed based on Design Science in Information System Research. In order to produce a great system, a scientific guidance must be used. Remarkable system need astounding design, like a good house needs a strong foundation. Because of that, Design Science in Information System Research, which is very well known in information system design research world, is used.

Mobile robot localization using augmented reality landmark and fuzzy inference system

Localization is an important ability in autonomous vehicle application. This paper reports the implementation of localization system using single wireless camera as visual sensor and an augmented reality computer vision library, ARToolkit, for executing tracking activity. Augmented reality tag were used as landmarks to be tracked which are placed arround within 2×2 metres testing environment. The experiment result shows that the ARToolkit distance measurement is not perfect, instead it has error function respecting to distance which can be approach using 2nd order polynomial. The fuzzy logic inference system was designed to give weighting value for each measurement for handling case while there are two or more landmark are detected at the same time. The position of vehicle and landmarks within the testing environment were visualized in 2D map using visual C# application and the vehicles coordinate can be logged offline manner by outputing its value. The experiment result shows that the distance measurements error for multiple landmark varies from −6.8% to 2,4%.

System security requirement identification of electronic payment system for angkot using NIST SP 800-160

Electronic payments system for angkot is an example of information technology system. In developing information technology system, one important aspect to be considered is information security aspect. NIST publication recommends ways to incorporate security design principles and concept into system engineering, that is NIST SP 800-160 System Security Engineering: Considerations for a Multidisciplinary Approach in the Engineering of Trustworthy Secure Systems. This paper is part of the development framework of electronic payment system for angkot. Result from early stage research has built the prototype of microcontroller-based system. In this paper, conducted reengineering process with reference to the stage in NIST SP 800-160 document. Among 30 stages of the system engineering process described in the document, this paper emphasizes the early stages that is business/mission analysis process. The results are system security requirements to establish an electronic payment system of angkot.

Heart rate prediction based on cycling cadence using feedforward neural network

It is important to monitor heart rate during cycling. By monitoring heart rate during cycling, cyclists can control the cycling session such as cycling cadence to determine the intensity of exercise. By controlling the intensity of cycling, cyclists can avoid the risks of over training and heart attack. Exercise intensity can be measured by heart rate of cyclist. The heart rate can be measured by wearable sensor. But there are data that are not recorded by the sensor at a regular time for example, one second, two seconds, etc. So we need a prediction model of heart rate to complete the missing data. The purpose of this study is to create a predictive model for heart rate based on cycling cadence using Feedforward Neural Network. The inputs are heart rate (HRt) and cadence (cadt) on the second. The output is the predictive value of heart rate on the next second (HRt+1). Feedforward Neural Network is used as a mathematical model of the relationship between heart rate and cycling cadence. The prediction model was trained using 10000 data of cyclist number 1 in a cycling session. The test data use dataset of 6 cyclists. Experiments show that the prediction model generates the predictive value of heart rate that is close to the value of heart rate measured by the sensor. The error of training data is 2.43 while the average error of test data is 3.02.

Missing data handling using machine learning for human activity recognition on mobile device

Human activity recognition is important technology in mobile computing era because it can be applied to many real-life, human-centric problems such as eldercare and healthcare. Successful research has so far focused on recognizing simple human activities. Currently, the smartphone is equipped with various sensors such as an accelerometer, gyroscope, digital compass, microphone, GPS and camera. The sensors have been used in various areas such as human gesture and activity recognition which is opening a new area of research and significantly impact in daily life. Activity recognition between the personal computer and smartphone is different. A mobile device has limited computational and memory capacity which has a chance that some data are missing when limitation of the mobile device is happening. In this research, some algorithms are tested to perform their ability to handling missing data, they are Bayesian Network, Multilayer Perceptron (MLP), C4.5 and k-Nearest Neighbour (k-NN). Missing data are implemented with increment scaling from 5%-40%. Optimal result based on accuracy mean is obtained by kNN with 89,4752%. Based on class, Bayesian Network obtained mean 992 recognized on Sitting class and kNN obtained mean 1010 recognized on Walking class. Multilayer Perceptron is obtained endurance point with decreasing about 9.9109% from normal experiment without missing data.

Consensus algorithm for obstacle avoidance and formation control

This article proposes a new formulation for walking behavior of a group of autonomous robots that adopts socio-dynamic capabilities of a pedestrian crowd. The socio-dynamic capabilities here mean the ability to receive position information from the other robots, to follow the behavior of the group without compromising its safety. The socio-dynamic behavior which will be implemented in the robot group adopted from the model of human walking behavior in a pedestrian crowd, which is known as Social Force Model (SFM). In this research, factors contained in SFM will be induced into a consensus algorithm and then will be implemented into a group of humanoid robots. The aim of the integration of SFM into consensus algorithm is to create a group of robots that are capable of carrying out its collective tasks while still able to maintain its safety. The attractive feature of the proposed algorithm is the fact that robots are still back to the formation after it avoid obstacle. Simulation and experiment results show the effectiveness of the proposed algorithm. Experiments were performed in this research is the first consensus algorithm implementation on a group of humanoid robot.

Terrain adaptation gait algorithm in a hexapod walking robot

This paper proposed a simple but effective gait algorithm for hexapod robot to navigate in an uneven and rough terrain. The robot has six legs with three joints in each leg and actuated with 18 servo motors. The tactile sensor, which is simply a normally open push button, is placed in each end of leg to sense if the leg touch the ground. The main purpose of this research is to make the robot able to walk in an uneven terrain with the simple gait algorithm. The inverse kinematics method is used to calculate every angle of the joint from the given desired position of six legs. The implementation result in the end of this paper shows this algorithm succeed to make the robot navigate in rough an unstructured terrain.