Claim Missing Document
Check
Articles

Found 5 Documents
Search

Three-Dimensional Coordination Control of Multi-UAV for Partially Observable Multi-Target Tracking Maynad, Vincentius Charles; Nugraha, Yurid Eka; Alkaff, Abdullah
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22560

Abstract

This research deals with multi-UAV systems to track partially observable multi-targets in noisy three-dimensional environments, which are commonly encountered in defense and surveillance systems. It is a far extension from previous research which focused mainly on two-dimensional, fully observable, and/or perfect measurement settings. The targets are modeled as linear time-invariant systems with Gaussian noise and the pursuers UAV are represented in a standard six-degree-of-freedom model. Necessary equations to describe the relationship between observations regarding the target and the pursuers states are derived and represented as the Gauss-Markov model. Partially observable targets require the pursuers to maintain belief values for target positions. In the presence of a noisy environment, an extended Kalman filter is used to estimate and update those beliefs. A Decentralized Multi-Agent Reinforcement Learning (MARL) algorithm known as soft Double Q-Learning is proposed to learn the coordination control among the pursuers. The algorithm is enriched with an entropy regulation to train a certain stochastic policy and enable interactions among pursuers to foster cooperative behavior. The enrichment encourages the algorithm to explore wider and unknown search areas which is important for multi-target tracking systems. The algorithm was trained before it was deployed to complete several scenarios. The experiments using various sensor capabilities showed that the proposed algorithm had higher success rates compared to the baseline algorithm. A description of the many distinctions between two-dimensional and three-dimensional settings is also provided.
Sosialisasi Serta Pembuatan Buku Panduan Mengenai Bahaya dan Mitigasi Petir Guna Mengurangi Resiko Tersambar Petir di Desa Ngendut, Ponorogo Asfani, Dimas Anton; Negara, I Made Yulistya; Hernanda, I Gusti Ngurah Satriyadi; Handayani, Puji; Suryani, Titiek; Kuswidiastuti, Devy; Setijadi, Eko; Nugraha, Yurid Eka; Fahmi, Daniar
Sewagati Vol 8 No 3 (2024)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j26139960.v8i3.840

Abstract

Sambaran petir merupakan salah satu bencana alam yang dapat menyebabkan korban jiwa dan kerugian material. Desa Ngendut, Ponorogo merupakan salah satu desa yang sering dilanda sambaran petir. Untuk mengurangi risiko tersambar petir di desa ini melalui skema pengabdian kepada masyarakat yang dilakukan Laboratorium Tegangan Tinggi Departemen Teknik Elektro ITS turut menjawab permasalahan tersebut dengan melakukan sosialisasi bahaya dan mitigasi sambaran petir serta pembuatan buku penangkal petir sederhana guna mengurangi risiko tersambar petir di Desa Ngendut, Ponorogo. Materi sosialisasi meliputi bahaya sambaran petir, dan cara menghindari sambaran petir, serta membuat buku panduan bahaya petir dan prosedur keselamatannya untuk memudahkan warga desa dalam memahami materi sosialisasi. Sasaran kegiatan penyuluhan pada kegiatan pengabdian masyarakat ini adalah para Warga Desa Ngendut, Kabupaten Ponorogo. Hasil dari sosialisasi ini telah meningkatkan kesadaran Warga Desa Ngendut bahaya sambaran petir dan meningkatkan kemampuan mereka dalam melakukan mitigasi sambaran petir.
Fault-Tolerant Control for Multi-Quadcopter with Suspended Payload under Wind Disturbance FARRAS, ALIF AL; SANTOSO, ARI; NUGRAHA, YURID EKA
JAREE (Journal on Advanced Research in Electrical Engineering) Vol 8, No 2 (2024): July
Publisher : Department of Electrical Engineering ITS and FORTEI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/jaree.v8i2.406

Abstract

Delivering payload with multiple quadcopters necessitates a reliable backup system. This research introduces a fault-tolerant design specifically for multi-drone payload transportation. The system employs formation control, ensuring the weight is evenly distributed among all functioning drones. This research tackles the challenge of reliable payload delivery with multi-drone systems. It proposes a new fault-tolerant control system specifically designed for this purpose. The system addresses a limitation in existing solutions by incorporating a simple PD controller alongside a fault-tolerant strategy. This approach allows the system to maintain operation even if a drone malfunctions. The paper further demonstrates the system's effectiveness through simulations. Results show the system's ability to maintain stability with minimal altitude loss (only 6.3cm) and rapid position reconfiguration (within 3.96 seconds) even under windy conditions. These findings highlight the potential of this fault-tolerant design to significantly improve multi-drone payload delivery, especially for missions requiring high levels of stability and redundancy.
Three-Dimensional Coordination Control of Multi-UAV for Partially Observable Multi-Target Tracking Maynad, Vincentius Charles; Nugraha, Yurid Eka; Alkaff, Abdullah
Journal of Robotics and Control (JRC) Vol. 5 No. 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22560

Abstract

This research deals with multi-UAV systems to track partially observable multi-targets in noisy three-dimensional environments, which are commonly encountered in defense and surveillance systems. It is a far extension from previous research which focused mainly on two-dimensional, fully observable, and/or perfect measurement settings. The targets are modeled as linear time-invariant systems with Gaussian noise and the pursuers UAV are represented in a standard six-degree-of-freedom model. Necessary equations to describe the relationship between observations regarding the target and the pursuers states are derived and represented as the Gauss-Markov model. Partially observable targets require the pursuers to maintain belief values for target positions. In the presence of a noisy environment, an extended Kalman filter is used to estimate and update those beliefs. A Decentralized Multi-Agent Reinforcement Learning (MARL) algorithm known as soft Double Q-Learning is proposed to learn the coordination control among the pursuers. The algorithm is enriched with an entropy regulation to train a certain stochastic policy and enable interactions among pursuers to foster cooperative behavior. The enrichment encourages the algorithm to explore wider and unknown search areas which is important for multi-target tracking systems. The algorithm was trained before it was deployed to complete several scenarios. The experiments using various sensor capabilities showed that the proposed algorithm had higher success rates compared to the baseline algorithm. A description of the many distinctions between two-dimensional and three-dimensional settings is also provided.
Sistem Deteksi dan Tracking Keretakan Bangunan Dengan Unmanned Aerial Vehicle Menggunakan Algoritma CNN Majid, Muhammad Aqil Rayhan; Hady, Mohamad Abdul; Sahal, Mochammad; Nugraha, Yurid Eka
Seminar Nasional Teknik Elektro Vol. 3 No. 1 (2023): SNTE II
Publisher : Forum Pendidikan Tinggi Teknik Elektro Indonesia Pusat

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Perkembangan Kendaraan Udara Tanpa Awak (Unmanned Aerial Vehicle) pada era ini mengalami perkembangan pesat. Penggunaan Quadcopter pada zaman sekarang banyak dimanfaatkan dalam bidang seperti militer, penyelematan korban jiwa, dan inspeksi bangunan. Salah satu kempampuan drone yang dibutuhkan untuk melaksanakan tugasnya adalah kemampuan drone untuk mendeteksi suatu object. Selain kemampuan mendekteksi drone juga dapat menjakau tempat yang tinggi dan/atau dijangkau oleh manusia. Dalam deteksi keretakan bangunan menggunakan drone dibutuhkan kecepatan dan tingkat presisi yang tinggi. Untuk melakukan deteksi ini, Algoritma CNN telah dikembangkan ke beberapa cabang seperti YOLO. Penggunaan YOLO pada penelitian ini dikarenakan memiliki komputasi ringan dengan akurasi yang tinggi . Kemampuan drone untuk segera mengenali object ini sangatlah dibutuhkan agar drone dapat melakukan manuver-manuver yang dibutuhkan untuk menjalakan tugas-tugas yang diberikan.