International Journal of Intelligent Engineering and Systems
Mobile robotic systems must have the ability to guarantee safety for operating in close proximity... more Mobile robotic systems must have the ability to guarantee safety for operating in close proximity with other moving objects. This paper aims to develop collision avoidance method based on velocity control with respect to several modal of moving objects in the vicinity of wheeled mobile robot. We propose a method that is called Hybrid Velocity Obstacles to avoid multi modal moving objects. This is different from Hybrid Reciprocal Velocity Obstacles approaches in the assumption that objects in the robot's surrounding move with arbitrary speed and directions. The main advantage of the method is in the ability to avoid unknown nonlinear trajectories of moving objects. Collision avoidance is achieved by considering static objects, other mobile robots, and moving objects with nonlinear trajectories. These different characteristics of robot's surrounding objects are calculated to produce avoidance velocity. Our approach is implemented in simulations for a two-wheeled differential-steering mobile robot in the environment contains moving objects. The results show that our approach is capable to avoid collision with multi modal moving objects by maintaining safety with average value 0.17 of Proximity Index. It is envisaged that the proposed method can be very useful for developing transport robot that operate in human environment.
International Journal of Intelligent Engineering and Systems
The Convolutional Neural Network (CNN) is an object classification method that has been widely us... more The Convolutional Neural Network (CNN) is an object classification method that has been widely used in recent research. In this paper, we propose CNN for use in the self-localization of wheeled soccer robots on a soccer field. If the soccer field is divided into equally sized quadrants with imaginary vertical and horizontal lines intersecting in the middle of the field, then the soccer field has an identical shape for each quadrant. Every quadrant is a reflection of the other quadrants. Superficially similar images appearing in different positions may result in positioning mistakes. This paper proposes a solution to this problem by using a visual modelling of the gyrocompass line mark and omni-vision image for the CNN-based self-localization system. A gyrocompass is used to obtain the angle of the robot on the soccer field. A 360° omni-vision camera is used to capture images that cover all parts of the soccer field wherever the robot is located. The angle of the robot is added to th...
TELKOMNIKA (Telecommunication Computing Electronics and Control)
Most gases are odorless, colorless and also hazard to be sensed by the human olfactory system. He... more Most gases are odorless, colorless and also hazard to be sensed by the human olfactory system. Hence, an electronic nose system is required for the gas classification process. This study presents the design of electronic nose system using a combination of Gas Chromatography Column and a Surface Acoustic Wave (SAW). The Gas Chromatography Column is a technique based on the compound partition at a certain temperature. Whereas, the SAW sensor works based on the resonant frequency change. In this study, gas samples including methanol, acetonitrile, and benzene are used for system performance measurement. Each gas sample generates a specific acoustic signal data in the form of a frequency change recorded by the SAW sensor. Then, the acoustic signal data is analyzed to obtain the acoustic features, i.e. the peak amplitude, the negative slope, the positive slope, and the length. The Support Vector Machine (SVM) method using the acoustic feature as its input parameters are applied to classify the gas sample. Radial Basis Function is used to build the optimal hyperplane model which devided into two processes i.e., the training process and the external validation process. According to the result performance, the training process has the accuracy of 98.7% and the external validation process has the accuracy of 93.3%. Our electronic nose system has the average sensitivity of 51.43 Hz/mL to sense the gas samples.
In recent years, there have been suspicious objects containing chemical materials intentionally p... more In recent years, there have been suspicious objects containing chemical materials intentionally placed on roads, fields and parking lots. The objects are considered harmful to be examined. Therefore, we need tools that can replace people in checking the dangerous objects. Robot is considered as a technology that can be applied to handle it. This study has designed a mobile robot system equipped with robotic arm and electronic nose to inspect the suspected object. The robotic arm is used to bring the electronic nose closer to the object's surface. This robot can find the source of gas and surround the object with a distance of 20 cm. The movement of the mobile robot and robotic arm is controlled using fuzzy logic. The Support Vector Machine method is used to identify gas types. This olfactory arm mobile robot can find a gas source and recognize the type of gas with a success rate of 92%.
Penginderaan visual atau machine vision merupakan suatu proses manipulasi data citra. Data terseb... more Penginderaan visual atau machine vision merupakan suatu proses manipulasi data citra. Data tersebut dapat digunakan untuk melakukan intepretasi banyak hal, salah satunya yaitu pengenalan gesture. Pengenalan gesture adalah antarmuka yang dapat mengenali gerak-isyarat seorang manusia dan mentranslasikan gerakan tersebut sebagai instruksi yang dapat dipahami oleh komputer. Pengenalan gesture dapat digunakan untuk penerjemahkan bahasa isyarat pada orang tunawicara. Hal ini karena banyaknya orang yang tidak mengerti bahasa tangan orang tunawicara. Sehingga, orang tunawicara kesulitan dalam berinteraksi di masyarakat. Pada tugas akhir ini pengenalan gesture untuk penerjemahan bahasa isyarat lebih mengarah pada hand recognition, yaitu pendeteksian perubahan gerak tangan, dengan menggunakan android mobile phone sebagai divaisnya. Android mobile phone memiliki kamera untuk menangkap citra orang tuna wicara saat berkomunikasi menggunakan bahasa isyarat berupa gerakan tangan. Selanjutnya, citra diproses oleh processing unit android untuk melakukan proses hand recognition. Setelah proses tersebut selesai, maka layar display akan memunculkan huruf atau kata dari perubahan posisi gerak tangan yang dilakukan orang tunawicara yang berada di depan kamera. Kata kunci-pengenalan gesture, kamera, machine vision, android, hand recognition.
Salah satu hal yang penting dalam mengarahkan senjata secara otomatis ke target adalah informasi ... more Salah satu hal yang penting dalam mengarahkan senjata secara otomatis ke target adalah informasi posisi dari target terhadap senjata. Terdapat banyak metode untuk mengetahui posisi target. Salah satunya adalah dengan metode pengukuran triangulasi. Metode ini membutuhkan minimal dua citra untuk medapatkan informasi jarak target terhadap kamera. Kemudian, informasi jarak tersebut bisa diolah untuk mengetahui posisi target terhadap senjata. Di dalam sistem ini, stereo visual digunakan untuk mendukung proses pengukuran triangulasi. Stereo visual menggunakan dua kamera untuk menghasilkan dua citra. Dalam sistem ini, salah satu kamera bertindak sebagai pemilih target. Citra yang ditangkap dua kamera tersebut akan diproses oleh processing unit untuk mendapatkan informasi posisi target terhadap senjata. Informasi ini digunakan untuk menggerakkan motor pada platform senjata agar senjata mengarah ke target. Hasil pengujian yang dilakukan pada sistem ini adalah sistem dapat menentukan posisi target yang dipilih oleh operator dan juga dapat mengarahkan senjata ke arah target tersebut. Akurasi tertinggi dalam penentuan posisi target dicapai ketika jarak antar dua kamera sekitar 30 cm. Kata Kunci-pengukuran posisi, stereo visual, triangulasi, teknologi senjata.
International Journal of Intelligent Engineering and Systems
Mobile robotic systems must have the ability to guarantee safety for operating in close proximity... more Mobile robotic systems must have the ability to guarantee safety for operating in close proximity with other moving objects. This paper aims to develop collision avoidance method based on velocity control with respect to several modal of moving objects in the vicinity of wheeled mobile robot. We propose a method that is called Hybrid Velocity Obstacles to avoid multi modal moving objects. This is different from Hybrid Reciprocal Velocity Obstacles approaches in the assumption that objects in the robot's surrounding move with arbitrary speed and directions. The main advantage of the method is in the ability to avoid unknown nonlinear trajectories of moving objects. Collision avoidance is achieved by considering static objects, other mobile robots, and moving objects with nonlinear trajectories. These different characteristics of robot's surrounding objects are calculated to produce avoidance velocity. Our approach is implemented in simulations for a two-wheeled differential-steering mobile robot in the environment contains moving objects. The results show that our approach is capable to avoid collision with multi modal moving objects by maintaining safety with average value 0.17 of Proximity Index. It is envisaged that the proposed method can be very useful for developing transport robot that operate in human environment.
International Journal of Intelligent Engineering and Systems
The Convolutional Neural Network (CNN) is an object classification method that has been widely us... more The Convolutional Neural Network (CNN) is an object classification method that has been widely used in recent research. In this paper, we propose CNN for use in the self-localization of wheeled soccer robots on a soccer field. If the soccer field is divided into equally sized quadrants with imaginary vertical and horizontal lines intersecting in the middle of the field, then the soccer field has an identical shape for each quadrant. Every quadrant is a reflection of the other quadrants. Superficially similar images appearing in different positions may result in positioning mistakes. This paper proposes a solution to this problem by using a visual modelling of the gyrocompass line mark and omni-vision image for the CNN-based self-localization system. A gyrocompass is used to obtain the angle of the robot on the soccer field. A 360° omni-vision camera is used to capture images that cover all parts of the soccer field wherever the robot is located. The angle of the robot is added to th...
TELKOMNIKA (Telecommunication Computing Electronics and Control)
Most gases are odorless, colorless and also hazard to be sensed by the human olfactory system. He... more Most gases are odorless, colorless and also hazard to be sensed by the human olfactory system. Hence, an electronic nose system is required for the gas classification process. This study presents the design of electronic nose system using a combination of Gas Chromatography Column and a Surface Acoustic Wave (SAW). The Gas Chromatography Column is a technique based on the compound partition at a certain temperature. Whereas, the SAW sensor works based on the resonant frequency change. In this study, gas samples including methanol, acetonitrile, and benzene are used for system performance measurement. Each gas sample generates a specific acoustic signal data in the form of a frequency change recorded by the SAW sensor. Then, the acoustic signal data is analyzed to obtain the acoustic features, i.e. the peak amplitude, the negative slope, the positive slope, and the length. The Support Vector Machine (SVM) method using the acoustic feature as its input parameters are applied to classify the gas sample. Radial Basis Function is used to build the optimal hyperplane model which devided into two processes i.e., the training process and the external validation process. According to the result performance, the training process has the accuracy of 98.7% and the external validation process has the accuracy of 93.3%. Our electronic nose system has the average sensitivity of 51.43 Hz/mL to sense the gas samples.
In recent years, there have been suspicious objects containing chemical materials intentionally p... more In recent years, there have been suspicious objects containing chemical materials intentionally placed on roads, fields and parking lots. The objects are considered harmful to be examined. Therefore, we need tools that can replace people in checking the dangerous objects. Robot is considered as a technology that can be applied to handle it. This study has designed a mobile robot system equipped with robotic arm and electronic nose to inspect the suspected object. The robotic arm is used to bring the electronic nose closer to the object's surface. This robot can find the source of gas and surround the object with a distance of 20 cm. The movement of the mobile robot and robotic arm is controlled using fuzzy logic. The Support Vector Machine method is used to identify gas types. This olfactory arm mobile robot can find a gas source and recognize the type of gas with a success rate of 92%.
Penginderaan visual atau machine vision merupakan suatu proses manipulasi data citra. Data terseb... more Penginderaan visual atau machine vision merupakan suatu proses manipulasi data citra. Data tersebut dapat digunakan untuk melakukan intepretasi banyak hal, salah satunya yaitu pengenalan gesture. Pengenalan gesture adalah antarmuka yang dapat mengenali gerak-isyarat seorang manusia dan mentranslasikan gerakan tersebut sebagai instruksi yang dapat dipahami oleh komputer. Pengenalan gesture dapat digunakan untuk penerjemahkan bahasa isyarat pada orang tunawicara. Hal ini karena banyaknya orang yang tidak mengerti bahasa tangan orang tunawicara. Sehingga, orang tunawicara kesulitan dalam berinteraksi di masyarakat. Pada tugas akhir ini pengenalan gesture untuk penerjemahan bahasa isyarat lebih mengarah pada hand recognition, yaitu pendeteksian perubahan gerak tangan, dengan menggunakan android mobile phone sebagai divaisnya. Android mobile phone memiliki kamera untuk menangkap citra orang tuna wicara saat berkomunikasi menggunakan bahasa isyarat berupa gerakan tangan. Selanjutnya, citra diproses oleh processing unit android untuk melakukan proses hand recognition. Setelah proses tersebut selesai, maka layar display akan memunculkan huruf atau kata dari perubahan posisi gerak tangan yang dilakukan orang tunawicara yang berada di depan kamera. Kata kunci-pengenalan gesture, kamera, machine vision, android, hand recognition.
Salah satu hal yang penting dalam mengarahkan senjata secara otomatis ke target adalah informasi ... more Salah satu hal yang penting dalam mengarahkan senjata secara otomatis ke target adalah informasi posisi dari target terhadap senjata. Terdapat banyak metode untuk mengetahui posisi target. Salah satunya adalah dengan metode pengukuran triangulasi. Metode ini membutuhkan minimal dua citra untuk medapatkan informasi jarak target terhadap kamera. Kemudian, informasi jarak tersebut bisa diolah untuk mengetahui posisi target terhadap senjata. Di dalam sistem ini, stereo visual digunakan untuk mendukung proses pengukuran triangulasi. Stereo visual menggunakan dua kamera untuk menghasilkan dua citra. Dalam sistem ini, salah satu kamera bertindak sebagai pemilih target. Citra yang ditangkap dua kamera tersebut akan diproses oleh processing unit untuk mendapatkan informasi posisi target terhadap senjata. Informasi ini digunakan untuk menggerakkan motor pada platform senjata agar senjata mengarah ke target. Hasil pengujian yang dilakukan pada sistem ini adalah sistem dapat menentukan posisi target yang dipilih oleh operator dan juga dapat mengarahkan senjata ke arah target tersebut. Akurasi tertinggi dalam penentuan posisi target dicapai ketika jarak antar dua kamera sekitar 30 cm. Kata Kunci-pengukuran posisi, stereo visual, triangulasi, teknologi senjata.
Uploads
Papers by Djoko Purwanto