Handy Wicaksono

Q learning behavior on autonomous navigation of physical robot

Behavior based architecture gives robot fast and reliable action. If there are many behaviors in robot, behavior coordination is needed. Subsumption architecture is behavior coordination method that give quick and robust response. Learning mechanism improve robots performance in handling uncertainty. Q learning is popular reinforcement learning method that has been used in robot learning because it is simple, convergent and off policy. In this paper, Q learning will be used as learning mechanism for obstacle avoidance behavior in autonomous robot navigation. Learning rate of Q learning affect robots performance in learning phase. As the result, Q learning algorithm is successfully implemented in a physical robot with its imperfect environment.

Towards A Relational Approach For Tool Creation By Robots.

Like a human, a robot may benefit from being able to use a tool to solve a complex task. When an appropriate tool is not available, a very useful ability for a robot would be to create a novel one based on its past experience. With the advent of inexpensive 3D printing, it is now possible to give robots such an ability, at least to create simple tools. We propose a method for learning how to use an object as a tool and, if needed, to design and construct a new tool.

Compact Fuzzy Q Learning for Autonomous Mobile Robot Navigation

Handy Wicaksono, Khairul Anam, Prihastono, Indra Adjie Sulistijono, Son Kuswadi 1 Department of Electrical Engineering, Petra Christian University 2 Department of Electrical Engineering, University of Jember Department of Electrical Engineering, University of Bhayangkara Department of Electrical Engineering, Electronics Engineering Polytechnic Institute of Surabaya Jl. Siwalankerto 121 – 131 Surabaya, Indonesia handywicaksono@yahoo.com

Miniatur Loading Arm Dock-3 PT Badak NGL Bontang dengan Sistem Emergency Shut Down (ESD)

Loading Arms in PT Badak NGL are used to distribute natural gas for shipping. The position of the ship cannot be fixed due to the wind, sea wave, stream flow, etc. If the distance is out of tolerance limit, then the Emergency Shut Down (ESD) system will be activated. ESD will release the part that is connected to the ship so that the whole distribution pipe is safe. The loading arms are controlled via Programmable Logic Controller (PLC) manually. The miniature of the loading arms is useful to train the new employees to operate them well. It is build with 1:10 ratio and controlled by PLC OMRON C200 HG. Several DC motors are used to move the arms while potentiometers are used as position sensors. The PLC will monitor whether the position is within tolerance limit or not. From the experiments, the ESD can be implemented with 16.48s for slewing motion and 16.5s for extension motion. Abstract in Bahasa Indonesia: Loading Arm di PT Badak NGL dipergunakan untuk menyalurkan gas alam ke kapal tanker. Posisi kapal tanker bisa jadi akan bergeser karena ombak, angin, arus laut, dll. Jika pergeseran posisi tersebut melewati batas toleransi yang diijinkan, maka sistem Emergency Shut Down (ESD) akan aktif. ESD akan melepaskan bagian valve yang melekat pada kapal sehingga pipa penyalur secara keseluruhan tidak tertarik oleh pergerakan kapal. Loading arm dikendalikan dengan PLC secara manual. Keberadaan miniatur ini akan menolong pekerja yang baru untuk mempelajari hal-hal yang mungkin pada pengoperasian Loading Arm tersebut. Miniatur dibuat dengan skala 1:10 dan dikendalikan oleh PLC OMRON C200HG. Sebagai penggerak dipergunakan motor DC. Potensiometer akan difungsikan sebagai sensor posisi sudut. PLC akan memonitor apakah sudut yang terbaca masih dalam batas toleransi atau tidak. Dari hasil pengujian, terlihat bahwa simulasi proses ESD dapat dijalankan dengan baik dengan waktu 16,48 detik untuk gerakan slewing dan 16,5 detik untuk gerakan ekstension. Kata kunci : Emergency shut down, PLC, loading arm

Communication Between TSX Micro 37-21 PLCs on Beverage Production Plant

The optimum operation condition of power system obtained from optimal calculation is determined without considering its dynamic stability limit. If the load of system is changed, power generating should accommodate the changes to make the demand of load supplied. This changing will shift dynamic stability system condition. This article deals with dynamic stability correction as a result of load of system changing by generation rescheduling using the biggest sensitivity of the sensitivity trajectory variable with respect to its parameters i.e. the power out put generators. The simulation in the 3-machines 9 bus power system with 25%, 50% and 75% load increasing of initial load caused eigen value position better, 1,2 and 3,4 of 25% load increasing each of them is 1,1 x 10-5 and 0,5 x 10-5, to 50% load increasing is 3,47 x 10-4 and 0,98 x 10-4, to 75% load increasing is 1,11 x 10-4 and 1,67 x 10-4 more far from imaginary axis compare to before generating rescheduling. The simulation result with this method indicates that there is dynamic stability correction, in this manner the system operates with better dynamic stability condition. Abstract in Bahasa Indonesia : Kondisi operasi optimum sistem tenaga yang diperoleh dari perhitungan optimasi dilakukan tanpa memasukkan batas stabilitas dinamiknya. Jika terjadi perubahan pada beban maka pembangkitan daya harus menyesuaikan perubahan tersebut agar tetap memenuhi kebutuhan beban. Perubahan pembangkitan akan mengubah kondisi stabilitas dinamik sistem. Makalah ini membahas tentang perbaikan stabilitas dinamik akibat perubahan beban sistem melalui penjadwalan ulang pembangkit menggunakan sensitivitas terbesar dari sensitivitas trayektori variabel keadaan sistem yaitu sudut rotor relatif terhadap parameternya yaitu daya output generator. Pengujian pada sistem tenaga 3-mesin 9-bus dengan kenaikkan beban 25%, 50% dan 75% dari beban dasar menyebabkan letak nilai eigen terkait lebih baik, 1,2 dan 3,4 untuk kenaikkan beban 25% masing-masing adalah 1,1 x 10-5 dan 0,5 x 10-5, untuk kenaikkan beban 50% adalah 3,47 x 10-4 dan 0,98 x 10-4, untuk kenaikkan beban 75% adalah 1,11 x 10-4 dan 1,67 x 10-4 lebih jauh dari sumbu imajiner dibandingkan sebelum penjadwalan ulang pembangkit. Hasil pengujian dengan metode ini menunjukkan adanya perbaikan stabilitas dinamik, sehingga sistem tenaga beroperasi dengan kondisi stabilitas dinamik yang lebih baik. Kata kunci: stabilitas dinamik, penjadwalan ulang pembangkit, perhitungan optimasi, dan sensitivitas trayektori.