Rule-Based Learning untuk Robot Humanoid T-FLoW Belajar Berjalan

FAIZ ULURRASYADI, ALIRIDHO BARAKBAH, RADEN SANGGAR DEWANTO, DADET PRAMADIHANTO

Sari


ABSTRAK

Riset tentang penggunaan learning dalam motion robot humanoid telah banyak dilakukan di seluruh dunia. Salah satunya adalah melakukan learning gerakan berjalan pada robot. Penelitian ini akan menjelaskan suatu metode learning “Rule Based†yang simple dan cepat dalam menemukan solusi gerakan berjalan yang stabil pada robot humanoid T-FLoW . Robot diibaratkan seperti anak kecil yang belajar berjalan, dia tahu cara berjalan, akan tetapi tidak tahu seberapa besar dia harus menggerakkan sendi-sendi atau joint di kakinya agar dapat berjalan seimbang. Oleh karena itu sistem learning akan menemukan nilai point-point trayektori yang cocok untuk berjalan dengan stabil. Dengan menggunakan software simulasi CoppeliaSim, kami menerapkan metode tersebut. Hasilnya, robot humanoid T-FLoW dapat berjalan dengan stabil sejauh 170 langkah hanya dengan melakukan learning sebanyak 400 episode.

Kata kunci: Robot humanoid T-FLoW, Rule-Based Learning, Learning, CoppeliaSim, Trayektori.

 

ABSTRACT

Research about the use of learning in motion of humanoid robot has been done in many countries. One of them was done by learning a stable walking gait in humanoid robot. This research will explain a fast and simple Rule Based learning method to find the solution of stable walking motion for T-FLoW humanoid robot. A robot was assumed like a child trying to walk, he knows how to walk, but doesn’t know how much he has to move his legged joints to get a stable walking. So, our learning system will find those trajectory point values that is suitable to walk stably. By using CoppeliaSim software, we implement our method. The result is, T-FLoW humanoid robot was able to walk stably for about 170 steps with only 400 episodes of learning.

Keywords: T-FLoW humanoid robot, Rule-Based Learning, Learning, CoppeliaSim, Trajectory.


Kata Kunci


Humanoid Robot T-FLoW; Rule-Based Learning; Trayektori Learning; CoppeliaSim

Teks Lengkap:

PDF

Referensi


Agravante, D. J., Sherikov, A., Wieber, P. B., Cherubini, A., & Kheddar, A. (2016). Walking Pattern Generators Designed For Physical Collaboration. IEEE International Conference on Robotics and Automation, (pp. 1573-1578).

Arfaq, M., Dewanto, R. S., & Pramadihanto, D. (2019). Fall Detection in T-FLoW Humanoid Robot: V-REP Simulation. International Electronics Symposium on Engineering Technology and Applications, (pp. 224–228).

Darsih, D. D. (2015). Metode Rule-Base Untuk Analisis Mutu Pembelajaran E-Learning Pada Perguruan Tinggi. Jurnal Sistem Informasi Bisnis, 5(1), 72–78.

Elhasairi, A., & Pechev, A. (2015). Humanoid Robot Balance Control Using The Spherical Inverted Pendulum Mode. Frontiers Robotics AI, 2(21), 1–13.

Hwang, K. S., Lin, J. L., & Yeh, K. H. (2015). Learning to Adjust and Refine Gait Patterns for a Biped Robot. IEEE Transactions on Systems, Man and Cybernetics Systems, 45(12), 1481–1490.

Hwang, K. S., Lin, J. L., & Li, J. S. (2016). Biped Balance Control By Reinforcement Learning. Journal of Information Science and Engineering, 32(4), 1041–1060.

Khomariah, N. E., Pramadihanto, D., & Dewanto, R. S. (2015). Flow Bipedal Robot : Walking Pattern Generation. International Electronics Symposium, (pp. 73-78).

Kormushev, P., Ugurlu, B., Calinon, S., Tsagarakis, N. G., & Caldwell, D. G. (2011). Bipedal Walking Energy Minimization By Reinforcement Learning With Evolving Policy Parameterization. IEEE International Conference on Intelligent Robots and Systems , (pp. 318–324).

Le, T. D., Le, A. T., & Nguyen, D. T. (2017). Model-Based Q-Learning for Humanoid Robots. International Conference on Advanced Robotics, (pp. 608–613).

Li, T. H. S., Su, Y. Te, Liu, S. H., Hu, J. J., & Chen, C. C. (2012). Dynamic Balance Control For Biped Robot Walking Using Sensor Fusion, Kalman Filter And Fuzzy Logic. IEEE Transactions on Industrial Electronics, 59(11), 4394–4408.

Missura, M., & Behnke, S. (2015). Online Learning of Bipedal Walking Stabilization. KI - Kunstliche Intelligenz, 29(4), 401–405.

Noreils, F. (2019). Human gait and mass distribution analysis TR 2017-01. 10.13140/RG.2.2.30605.49126.

Silva, I. J., Perico, D. H., Costa, A. H., & Bianchi, R. A. (2017). Using Reinforcement Learning to Optimize Gait Generation. Simposio Brasileiro de Automacao Inteligente, (pp. 288–294).

Silva, I. J., Perico, D. H., Homem, T. P. D., Vilao, C. O., Tonidandel, F., & Bianchi, R. A. (2016). Using Reinforcement Learning to Improve the Stability of a Humanoid Robot: Walking on Sloped Terrain. 12th LARS Latin American Robotics Symposium and 3rd SBR Brazilian Robotics Symposium, (pp. 210–215).

Zhang, Y., Huang, Q., Bi, S., Min, H., Zheng, Q., & Luo, Y. (2015). Biped Walking On Rough Terfrain Using Reinforcement Learning. IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, (pp. 2061–2066).




DOI: https://doi.org/10.26760/elkomika.v10i1.46

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (cetak) : 2338-8323 | ISSN (elektronik) : 2459-9638

diterbitkan oleh :

Teknik Elektro Institut Teknologi Nasional Bandung

Alamat : Gedung 20 Jl. PHH. Mustofa 23 Bandung 40124

Kontak : Tel. 7272215 (ext. 206) Fax. 7202892

Surat Elektronik : jte.itenas@itenas.ac.id________________________________________________________________________________________________________________________

Statistik Pengunjung

Free counters!

Web Analytics Made Easy - StatCounter

Lihat Statistik Jurnal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License