Claim Missing Document
Check
Articles

Found 3 Documents
Search

Multi quadrotors coverage optimization using reinforcement learning with negotiation Bonaventura Wijaya, Glenn; Agustinus Tamba, Tua
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp2978-2986

Abstract

This paper proposes an optimization scheme to maximize the area coverage of multiple quadrotor unmanned aerial vehicles that are deployed to monitor an operational area/space. Each quadrotor initially performs a single agent reinforcement learning to determine target points with optimal coverage area. Whenever each quadrotor encounters the others within a predetermined negotiation region that is defined by an inter-agent distance threshold, it will activate a multiagent reinforcement learning with action negotiation algorithm and coordinate its movement policies to maximize the total coverage area and avoids inter-agent coverage overlaps. Results of simulation evaluations are shown to illustrate the performance of the proposed learning-based coverage optimization method.
Design and implementation of linear quadratic regulator control for two-wheeled self-balancing robot Gilang Buana Putra, Leonardus; Wahab, Faisal; Agustinus Tamba, Tua
Bulletin of Electrical Engineering and Informatics Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i2.8689

Abstract

This research aimed to develop a control system for a self-balancing robot (SBR) based on the mathematical model of an inverted pendulum on a two-wheeled cart. The linear quadratic regulator (LQR) control was implemented to maintain the SBR’s balance under normal conditions. A linearization approach was used to convert the dynamic model into a linear form, enabling the application of LQR. Testing was conducted through simulations and a physical SBR prototype equipped with an MPU6050 sensor and NEMA 17 motor. The test results demonstrated the effectiveness of the LQR control in maintaining the SBR’s balance and its responsiveness to disturbances. Although there are differences between the simulations and physical implementation, the system successfully maintained the SBR’s balance. In conclusion, the use of the inverted pendulum mathematical model and the implementation of LQR control successfully produced a stable and effective control system for SBR balance. By testing various values of the LQR parameters, optimal robot control parameters can be obtained.
Implementasi Kontrol Umpan Balik Keluaran Berbasis Tapis Kalman dan Regulator Kuadratik Linier pada Sistem Pendulum Terbalik Rizky Octavia, Ajeng; Nathanlius, David; Agustinus Tamba, Tua
Jurnal Otomasi Kontrol dan Instrumentasi Vol 11 No 2 (2019): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2019.11.2.2

Abstract

Sistem pendulum terbalik merupakan salah satu contoh acuan atau benchmark yang sering digunakan dalam studi, analisis dan perancangan sistem kontrol modern. Sistem ini pada dasarnya terdiri dari sebuah tongkat yang dijaga agar senantiasa berada pada posisi vertikal di atas suatu gerobak/kereta melalui pengontrolan gerak horizontal dari gerobak/kereta tersebut. Makalah ini melaporkan hasil awal dari kegiatan studi dan penelitian yang dilakukan tim penulis dalam upaya merancang suatu purwarupa sistem pendulum terbalik. Model sistem pendulum yang ditinjau diturunkan secara analitik dalam bentuk model persamaan ruang keadaan linier dengan empat variabel keadaan yang mencakup (i) posisi dan kecepatan sudut simpangan dari tongkat pendulum serta (ii) posisi dan kecepatan gerak horizontal dari gerobak/kereta penyangga tongkat pendulum. Pada model yang digunakan, diasumsikan data pengukuran dari sensor yang dapat digunakan untuk merancang pengontrol hanya ada dua, yaitu sudut simpangan tongkat pendulum serta posisi kereta penyangga. Data pengukuran dari sensor tersebut juga diasumsikan telah tercampur dengan sinyal gangguan.Berdasarkan karakteristik model dinamik serta data pengukuran tersebut, pengontrolan sistem pendulum terbalik dilakukan dengan teknik kontrol umpan balik keluaran (output feedback control). Lebih spesifik, sistem kontrol yang digunakan terdiri dari (i) tapis Kalman (Kalmanfilter) untuk mengestimasi variabel keadaan sistem yang tidak terukur serta (ii) kontrol umpan balik berbasis LQR pada gerobak penyangga untuk menjaga tongkat pendulum pada posisi vertikal. Simulasi numerik hasil rancangan sistem kontrol umpan balik yang diusulkan dilaporkan untuk mengilustrasikan kinerja estimator dan pengontrol yang dikembangkan.