Claim Missing Document
Check
Articles

Found 7 Documents
Search

Humanoid Walking Control Using LQR and ANFIS Auzan, Muhammad; Lelono, Danang; Dharmawan, Andi
Journal of Robotics and Control (JRC) Vol 4, No 4 (2023)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v4i4.16444

Abstract

Humanoid robots possess remarkable mobility and adaptability for diverse environments. Nonetheless, accurate walking pattern tracking remains challenging, especially when employing the linear quadratic regulator (LQR) due to delays in high-mobility setpoint tracking. We propose a novel control approach to address this limitation by integrating an artificial neuro-fuzzy inference system (ANFIS) with the LQR to enhance pattern tracking. The research contributes to developing a control system that combines LQR and ANFIS to enable humanoid robots to follow various walking patterns with increased precision and efficiency and also the scheme to incorporate LQR and ANFIS. The study involves four experiments: step response, walking phase, static straight walking, and varied straight walking. Each test runs for 5 seconds with a 100-millisecond sampling rate, repeated five times, and employs the Integral Absolute Value (IAE) metric for evaluation. The LQR-ANFIS method exhibits superior performance, achieving a maximum overshoot of 0%, a rise time of 0.3 seconds, a settling time of 0.3 seconds, and a steady-state error of 0% in the step response experiment. The proposed control system also enables stable walking with step periods ranging from 0.15 to 4 seconds and step ranges of 0.05 to 0.03 meters. In conclusion, the integration of ANFIS with the LQR significantly enhances the mobility of humanoid robots, enabling them to navigate diverse environments and accurately track various walking patterns proficiently.
Inspeksi Kualitas Pengelasan Besi Menggunakan Teknik Segmentasi Citra Berbasis Convolutional Neural Network Wahyono, Wahyono; Dharmawan, Andi; Awaludin, Lukman; Nathan, Oskar; Baskara, Baskara
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 14, No 1 (2024): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.89034

Abstract

Inspeksi pengelasan merupakan kebutuhan mutlak bagi dunia industri terutama yang bergerak dibidang otomotif untuk memastikan kualitas las. Namun demikian, sebagian besar industri masih menggunakan pemeriksaan manual yang bersifat subjektif dan penuh dengan bias yang dapat berakibat pada inkonsistensi dalam penilaian standar kualitas. Oleh karena itu, diperlukan suatu sistem cerdas yang dapat memeriksa kualitas pengelasan dengan konsisten. Penelitian ini bertujuan untuk membuat model kecerdasan buatan berbasis deep learning dan computer vision untuk mendeteksi area-area pengelasan dan mengklasifikasikannya kedalam kategori baik dan buruk. Model CNN dengan arsitektur UNet diadopsi untuk melakukan segmentasi citra pada gambar pengelasan besi. Studi penggunaan beberapa teknik ekstraksi fitur juga dilakukan untuk mendapatkan performa model terbaik berdasarkan skor IoU dan kecepatan konvergensi model. Berdasarkan hasil eksperimen, teknik CNN UNet terbukti mampu meningkatkan performa model dengan skor IoU sebesar 78,1% dan dengan kecepatan konvergensi dalam 144 epoch.--Welding inspection is an absolute necessity for the industrial world, especially those engaged in the automotive sector to ensure weld quality. However, most industries still use manual inspection which is subjective and full of bias which can result in inconsistencies in the assessment of quality standards. Therefore, intelligent system that can check the quality of welding consistently is needed. This study aims to create an artificial intelligence model based on deep learning and computer vision to detect welding spots and classify them into good and bad categories. CNN model with UNet architecture is adopted to perform image segmentation on iron welding images. Studies using several feature extraction techniques are also conducted to obtain the best model performance based on IoU scores and model convergence speed. Based on the experimental results, the UNet technique is proven to be able to improve the performance of the model with an IoU score of 78.1% and with a convergence speed of 144 epochs.
Sistem Deteksi Kebakaran Hutan menggunakan E-nose Berbasis pada JST Backpropagation Perwira, Zandy Yudha; Lelono, Danang; Dharmawan, Andi
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 14, No 2 (2024): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.76255

Abstract

Indonesia memiliki hutan yang sangat luas yaitu 93,95 juta ha setara dengan 50% luas daratan Indonesia. Luasan hutan di Indonesia terus mengalami penurunan setiap tahunnya diakibatkan oleh kebakaran hutan. Maka untuk menekan penurunan kebakaran hutan diperlukan alat untuk mendeteksi kebakaran sedini mungkin dikarenakan kebakaran hutan jika sudah menyebar sulit untuk dipadamkan. Pendeteksian kebakaran hutan saat ini masih dilakukan manual dengan bantuan visual yang kurang dapat mendeteksi lebih dini. Penelitian tentang sistem detektor kebakaran hutan sangat perlu dikembangkan untuk menanggulangi kebakaran yang lebih besar. Pada penelitian ini, pendeteksian menggunakan sebuah electronic nose (e-nose), sensor suhu, kelembapan, serta debu untuk mendeteksi asap kebakaran hutan dan ditambah dengan sensor FLIR (Forward Looking Infrared) sebagai detektor dini kebakaran hutan.Sensor-sensor membaca asap dalam bentuk sinyal dengan pola tertentu untuk tiap sampel asap. Pola-pola tersebut kemudian dilakukan prapemrosesan data dengan melakukan normalisasi baseline dan ekstraksi ciri 4 metode yang berbeda. Ciri yang didapat kemudian akan dikenali dengan menggunakan metode pengenalan pola yaitu Jaringan Saraf Tiruan (JST) Backpropogation. Proses pengenalan dilakukan dengan melakukan pelatihan untuk mencapai parameter-parameter yang optimal sehingga didapat model optimal. Pengujian model terbaik dengan beberapa titik api menghasikan akurasi dalam membedakan jenis asap 98% untuk satu titik dan 100%  untuk beberapa titik.
Characterization Roasting Level of Arabica Coffee (Coffea arabica) Komasti and Andungsari Priantari, Ika; Dharmawan, Andi
Jurnal Biologi Universitas Andalas Vol 10 No 1 (2022)
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jbioua.10.1.33-41.2022

Abstract

Coffee is one of the drinks that are often consumed by the public Indonesia. Indonesian Coffee and Cacao Research Institute (ICCRI) is a national coffee and cocoa research and development institution has 2 superior Arabica coffee seeds, namely Andungsari 2K Arabica Coffee and Komasti (Andungsari 3 Composite). In general, the sequence of dry processing of coffee cherries includes fruit picking, fruit sorting, fruit drying, pulping and hulling. Next is the roasting process before it becomes coffee grounds. The roasting process converts unsavory raw coffee beans into a drink with a delicious aroma and taste. The perfection of coffee roasting is influenced by 2 factors, namely heat and time, equipment and tools roasting and quality of coffee beans. From the results of treatments 2, 4, 6, 8, 10, 12, 14, 16 and 18 minutes, coffee with city roast criteria was produced in the 7th treatment, namely 14 minutes, with the first crack at 11.30 minutes at 154 °C, the color of the beans dark chocolate, has the most popular taste. For treatment 8 (14 minutes) and 9 (18 minutes) the color is more black, oily and smokey, the taste is more espresso. The roasting equipment used is in the dark roast category at a temperature of 170-195 °C.
Camera-based simultaneous localization and mapping: methods, camera types, and deep learning trends Dwimantara, Anak Agung Ngurah Bagus; Natan, Oskar; Indarto, Novelio Putra; Dharmawan, Andi
IAES International Journal of Robotics and Automation (IJRA) Vol 14, No 2: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijra.v14i2.pp162-172

Abstract

The development of simultaneous localization and mapping (SLAM) technology is crucial for advancing autonomous systems in robotics and navigation. However, camera-based SLAM systems face significant challenges in accuracy, robustness, and computational efficiency, particularly under conditions of environmental variability, dynamic scenes, and hardware limitations. This paper provides a comprehensive review of camera-based SLAM methodologies, focusing on their different approaches for pose estimation, map reconstruction, and camera type. The application of deep learning also will be discussed on how it is expected to improve performance. The objective of this paper is to advance the understanding of camera-based SLAM systems and to provide a foundation for future innovations in robust, efficient, and adaptable SLAM solutions. Additionally, it offers pertinent references and insights for the design and implementation of next-generation SLAM systems across various applications.
Edge-aware distilled segmentation with pseudo-label refinement for autonomous driving perception Indarto, Novelio Putra; Natan, Oskar; Dharmawan, Andi
IAES International Journal of Robotics and Automation (IJRA) Vol 14, No 3: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijra.v14i3.pp376-386

Abstract

Achieving precise semantic segmentation is essential for enabling real-time perception in autonomous systems, yet leading approaches typically require substantial annotated data and powerful hardware, restricting their use on devices with limited resources. This work introduces an efficient segmentation framework that integrates pseudo-label refinement, knowledge distillation, and entropy-based confidence filtering to train compact student networks suitable for edge deployment. High-quality pseudo-labels are first produced by a robust teacher network, then further improved using a dense conditional random field to boost spatial consistency. An entropy-based selection mechanism removes unreliable predictions, ensuring that only the most trustworthy labels guide the student model's training. The use of knowledge distillation effectively transfers detailed semantic understanding from the teacher to the student, enhancing accuracy without added computational overhead. Experimental results with multiple EfficientNet backbones reveal that this pipeline improves segmentation accuracy and output clarity, while also supporting real-time or near real-time inference on CPUs with limited processing power. Extensive ablation and qualitative studies further confirm the method's robustness and flexibility for real-world edge applications.
Humanoid robot balance control system during backward walking using linear quadratic regulator Arsyi, Muhammad; Dharmawan, Andi; Sumbodo, Bakhtiar Alldino Ardi; Auzan, Muhammad; Istiyanto, Jazi Eko; Natan, Oskar
IAES International Journal of Robotics and Automation (IJRA) Vol 14, No 3: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijra.v14i3.pp320-330

Abstract

Humanoid robots are designed to replicate human activities, including tasks in hazardous environments. However, maintaining balance during backward walking remains a significant challenge due to center of mass (CoM) shifts beyond the support polygon and limited knee joint motion. This study proposes a control strategy that integrates a linear quadratic regulator (LQR) with optimized walking patterns to enhance dynamic stability. The approach combines LQR-based control with CoM trajectory planning to ensure safe and stable backward walking. The methodology includes inverse kinematics for generating walking patterns and the use of Inertial Measurement Unit (IMU) sensors to estimate the CoM trajectory. LQR parameters were tuned through simulation to improve responsiveness to disturbances. Evaluation metrics focused on CoM deviation, rise time, settling time, and overshoot. Experimental results demonstrate that the proposed LQR system effectively maintains the CoM within 5% of the support polygon boundary. The system achieved rise times under one second and settling times below two seconds, while minimizing pitch and roll overshoots. Compared to proportional control, the proposed method significantly improves stability and reduces the risk of falling. This research advances control strategies for humanoid robots, contributing to improved mobility and operational safety. Moreover, it supports Sustainable Development Goal (SDG) 9 by promoting innovation in intelligent robotic systems that can assist in complex or high-risk environments.