cover
Contact Name
Alfian Ma'arif
Contact Email
alfian.maarif@te.uad.ac.id
Phone
-
Journal Mail Official
ijrcs@ascee.org
Editorial Address
Jalan Janti, Karangjambe 130B, Banguntapan, Bantul, Daerah Istimewa Yogyakarta, Indonesia
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
International Journal of Robotics and Control Systems
ISSN : -     EISSN : 27752658     DOI : https://doi.org/10.31763/ijrcs
Core Subject : Engineering,
International Journal of Robotics and Control Systems is open access and peer-reviewed international journal that invited academicians (students and lecturers), researchers, scientists, and engineers to exchange and disseminate their work, development, and contribution in the area of robotics and control technology systems experts. Its scope includes Industrial Robots, Humanoid Robot, Flying Robot, Mobile Robot, Proportional-Integral-Derivative (PID) Controller, Feedback Control, Linear Control (Compensator, State Feedback, Servo State Feedback, Observer, etc.), Nonlinear Control (Feedback Linearization, Sliding Mode Controller, Backstepping, etc.), Robust Control, Adaptive Control (Model Reference Adaptive Control, etc.), Geometry Control, Intelligent Control (Fuzzy Logic Controller (FLC), Neural Network Control), Power Electronic Control, Artificial Intelligence, Embedded Systems, Internet of Things (IoT) in Control and Robot, Network Control System, Controller Optimization (Linear Quadratic Regulator (LQR), Coefficient Diagram Method, Metaheuristic Algorithm, etc.), Modelling and Identification System.
Articles 50 Documents
Search results for , issue "Vol 5, No 2 (2025)" : 50 Documents clear
Four DOF Robot Manipulator Control Using Feedback Linearization Based on Sliding Mode Control Alqaisi, Walid Kh.; Soliman, Mostafa; Badawi, Ahmed; Elzein, I. M.; El-Bayeh, Claude Ziad
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1729

Abstract

This paper investigates the performance of a four-degree-of-freedom (4DOF) robot arm using feedback linearization based on sliding mode control (FLSM). FLSM simplifies complex nonlinear control solutions and mitigates the effects of the highly coupled dynamic behavior of the 4DOF manipulator. The controller takes into account uncertain dynamics and unexpected disturbances such as changes in payload, variations in wind, and gravity effects in different directions. The stability of the proposed controller is achieved using the manipulator model and FLSM without linearizing the model. Stability is analyzed using a Lyapunov function, and MATLAB Simulink is utilized to simulate the real parameters of the Quanser QArm. The results are compared with those obtained using a PID controller.
Cross-Age Face Verification Using Generative Adversarial Networks (GAN) with Landmark Feature Syuhada, Fahmi; Sa'adati, Yuan
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1755

Abstract

Cross-age face verification is a complex problem in biometric recognition in terms of aging, a naturally changing face structure, and face landmark configuration changes over time. In this paper, a new cross-age face verification method is proposed with a Generative Adversarial Network (GAN) and a mix of landmark-based features. Realistic aging of a face with identity-specific landmarks, such as eyes, nose, and mouth, is generated for effective face recognition in a range of age groups. Performance testing with an in-house collected face dataset of 200 face images exhibited effectiveness in changing face configuration and face shape transformations, such as a fuller face thinning and thin face becoming fuller. Comparison with direct face verification showed increased values of similarity, such as 32.57% to 63.80%, reduced values of feature distance, such as 0.6743 to 0.3620, and improvement in accuracy for the ArcFace, VGG-Face, and Facenet architectures. ArcFace exhibited an improvement in accuracy with an increase in value from 82.64% to 86.02%, VGG-Face with an improvement in value from 76.23% to 80.57%, and Facenet with an improvement in value from 67.54% to 74.48%. These observations validate the effectiveness of the proposed method in overcoming age-related complications and improving cross-age face verification performance. In future work, we plan to investigate a larger dataset and model refinement to realize performance improvement and real-life biometric suitability.
Enhanced Advanced Multi-Objective Path Planning (EAMOPP) for UAV Navigation in Complex Dynamic 3D Environments Airlangga, Gregorius; Bata, Julius; Nugroho, Oskar Ika Adi; Sugianto, Lai Ferry; Saputro, Pujo Hari; Makin, See Jong; Alamsyah, Alamsyah
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1759

Abstract

Unmanned Aerial Vehicles (UAVs) have emerged as vital tools in diverse applications, including disaster response, surveillance, and logistics. However, navigating complex, obstacle-rich 3D environments with dynamic elements remains a significant challenge. This study presents an Enhanced Advanced Multi-Objective Path Planning (EAMOPP) model designed to address these challenges by improving feasibility, collision avoidance, and path smoothness while maintaining computational efficiency. The proposed enhancement introduces a hybrid sampling strategy that combines random sampling with gradient-based adjustments and a refined cost function that prioritizes obstacle avoidance and path smoothness while balancing path length and energy efficiency. The EAMOPP was evaluated in a series of experiments involving dynamic environments with high obstacle density and compared against baseline algorithms, including A*, RRT*, Artificial Potential Field (APF), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA). Results demonstrate that the EAMOPP achieves a feasibility score of 0.9800, eliminates collision violations, and generates highly smooth paths with an average smoothness score of 9.3456. These improvements come with an efficient average execution time of 6.6410 seconds, outperforming both traditional and heuristic-based methods. Visual analyses further illustrate the model's ability to navigate effectively through dynamic obstacle configurations, ensuring reliable UAV operation. Future research will explore optimizations to further enhance the model's applicability in real-world UAV missions.
Study and Analysis of the Second Order Constant Coefficients and Cauchy-Euler Equations via Modified Conformable Operator Bouchenak, Ahmad; Batiha, Iqbal M.; Hatamleh, Raed; Aljazzazi, Mazin; Jebril, Iqbal H.; Al-Horani, Mohammed
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1577

Abstract

In this paper, we are concerned with a new modified conformable operator. Such an operator makes the study very easy in fractional calculus because it satisfies the most properties as the usual derivative and gives exact solutions. Furthermore, we will analyze and study the second-order fractional linear homogeneous differential equation with constant coefficients, which has two reasons for the importance of these types of differential equations. First of all, they often arise in applications. Second, it is relatively easy to find fundamental sets of solutions to these equations. In addition, we will also analyze the related fractional Cauchy–Euler type equation, which is used in various fields, physics, engineering, etc. Finally, as an application, we will illustrate the method on some numerical examples of the mentioned type of fractional differential equations.
Impact of Hyperparameter Tuning on ResNet-UNet Models for Enhanced Brain Tumor Segmentation in MRI Scans Pamungkas, Yuri; Triandini, Evi; Yunanto, Wawan; Thwe, Yamin
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1802

Abstract

Brain tumor segmentation in MRI scans is a crucial task in medical imaging, enabling early diagnosis and treatment planning. However, accurately segmenting tumors remains a challenge due to variations in tumor shape, size, and intensity. This study proposes a ResNet-UNet-based segmentation model using LGG dataset (from 110 patients), optimized through hyperparameter tuning to enhance segmentation performance and computational efficiency. The proposed model integrates different ResNet architectures (ResNet18, ResNet34, ResNet50, ResNet101, and ResNet152) with UNet, evaluating their performance under various learning rates (0.01, 0.001, 0.0001), optimizer types (Adam, SGD, RMSProp), and activation functions (Sigmoid). The methodology involves training and evaluating each model using Loss Function, Mean Intersection over Union (mIoU), Dice Similarity Coefficient (DSC), and Iterations per Second as performance metrics. Experiments were conducted on MRI brain tumor datasets to assess the impact of hyperparameter tuning on model performance. Results show that lower learning rates (0.0001 and 0.001) improve segmentation accuracy, while Adam and RMSProp outperform SGD in minimizing segmentation errors. Deeper models (ResNet50, ResNet101, and ResNet152) achieve the highest mIoU (up to 0.902) and DSC (up to 0.928), but at the cost of slower inference speeds. ResNet50 and ResNet34 with RMSProp or Adam provide an optimal trade-off between accuracy and computational efficiency. In conclusion, hyperparameter tuning significantly impacts MRI segmentation performance, and selecting an appropriate learning rate, optimizer, and model depth is crucial for achieving high segmentation accuracy with minimal computational cost.
Optimization of Harmonic Elimination in PV-Fed Asymmetric Multilevel Inverters Using Evolutionary Algorithms Almalaisi, Taha Abdulsalam; Abdul Wahab, Noor Izzri; Zaynal, Hussein I.; Hassan, Mohd Khair; Majdi, Hasan S.; Radhi, Ahmed Dheyaa; Solke, Nitin; Sekhar, Ravi
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1785

Abstract

Modern power electronics depend heavily on Multilevel Inverters (MLIs) to drive high-power systems operating in renewable energy systems electric vehicles along with industrial motor drives. MLIs create AC signals of high quality by joining multiple DC voltage sources which leads to minimal harmonic distortion outputs. The Cascaded H-Bridge MLI (CHB-MLI) stands out as a first choice among different topologies of MLI for photovoltaic (PV) applications because it includes modular features with fault tolerance capabilities and excellent multi-DC source integration. To achieve effective operation MLIs need optimized control strategies that reduce harmonics while maintaining highest performance. Using SHE-PWM technology provides an effective technique for harmonic frequency reduction which allows the improvement of waveform integrity. Technical restrictions make the solution of SHE-PWM nonlinear equations exceptionally challenging to implement. The resolution of complex non-linear equations requires implementation of GA combined with PSO and BO for optimal switching angle determination. The research investigates an 11-level asymmetric CHB-MLI using five solar panels where SHE-PWM switching angles are optimized through GA, PSO and BO applications. Simulation tests validate that the implemented algorithms succeed in minimizing Total Harmonic Distortion (THD) and removing fundamental harmonic disturbances. The evaluation demonstrates distinct capabilities of each optimization approach between accuracy rates and computational speed performance. These optimization methods yield practical advantages which boost the performance of multi-level inverters. The researchers who follow should study actual hardware deployments together with combined control approaches to enhance power electronic applications.
A Hybrid Adaptive Gradient-Based Sled Dog Optimizer for Enhanced Robotic Decision-Making in Industrial Applications Al Nasar, Mohammad Rustom
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1788

Abstract

As autonomous robotic systems are increasingly used in industrial applications, there is a growing need to create efficient and automated decision-making capabilities that can work in complex environments with a range of possible actions. RL offers an effective way to train robotic agents. Still, conventional RL techniques tend to have issues with slow and unstable policy learning, poor convergence, and weak exploration-exploitation balance. To solve this problem, this paper develops a Hybrid optimization approach that incorporates reinforcement learning, deep learning, and metaheuristic optimization for more robust robotic control and adaptability. The new approach utilizes a Deep Q-Network with Experience Replay for learning policies. At the same time, an Adaptive Gradient-Based Sled Dog Optimizer is used to improve and optimize decision-making. Epsilon-greedy selection combined with Noisy Network is used for hybrid exploration-exploitation, which helps learning. The effectiveness of the proposed method was validated against five existing methods, which include Conservative Q-Learning, Behavior Regularized Actor-Critic, Implicit Q-Learning, Twin Delayed Deep Deterministic Policy Gradient, and Soft Actor-Critic, over the three benchmark robotic datasets of MuJoCo, D4RL, and OpenAI Gym Robotics Suite. The vast majority of results provide compelling support for the argument that the proposed approach consistently outperformed the baseline approaches in terms of accuracy, precision, recall, stability, speed of convergence, and degree of generalization. The improvement in performance was confirmed by validation methods such as analyzing confidence intervals and computing results of p-values.
An Integrated Deep Learning Framework Combining LSTM-CRF, GRU-CRF, and CNN-CRF with Word Embedding Techniques for Arabic Named Entity Recognition Ali, Mahdi Ahmed; A. Alwahhab, Ahmed Bahaaulddin; Farjami, Yagoub
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1752

Abstract

Named entity recognition (NER) is the main function of natural language processing (NLP) and has many applications. Arabic NER systems aim to identify and classify Arabic NEs in Arabic text, which provide unique problems due to the language's complex morphology and syntactic structures. This paper provides an integrated deep learning system that incorporates three deep learning architectures—LSTM-CRF, GRU-CRF, and CNN-CRF—as well as three word embedding techniques: GloVe, Word2Vec, and FastText, all trained on Arabic corpus. To develop NER state-of-the-art in Arabic language, the present paper proposed a 3-stage process of pre-processing, feature extraction, and a combination of various deep network schemes. In the preprocessing section, operations such as removing irrelevant words, correcting words, etc. will be used to improve the system's efficiency. In the feature extraction section, three-word embedding methods, Glove, word2vec, and fasttext, which are trained with Arabic texts, are used, and finally, three LSTM-CRF, GRU-CRF, and CNN-CRF models are trained with each word embedding, and the results they are combined. Experimental results on benchmark dataset, ANERcorp show that our methodology is effective, with an accuracy of 94.39%, which outperforms other cutting-edge methods. However, combining multiple deep learning models with word embeddings increases computational complexity and resource requirements, potentially complicating implementation in resource-constrained contexts. Future efforts will concentrate on optimizing the framework to lower computational costs while keeping good performance.
Study and Analysis of PWM with DC-DC Converter for Inverting Buck-Boost Inverter Topology Gaber, Rajaa Khalaf; Shneen, Salam Waley; Jiaad, Suaad Makki
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1823

Abstract

The simulation aims to study and analyze the effect of the duty cycle on the output voltage and signal reflection. This type of simulation is important for many practical applications of inverter boost converters, such as renewable energy systems or portable electronics. A voltage converter is being developed to generate a negative voltage output, i.e., it has the ability to invert the output signal. The converter's input is connected to a DC voltage source, and is intended to generate a higher or lower voltage, depending on the application requirements, while maintaining the inverting output signal. This converter is used in many fields, most notably those powered by batteries, such as portable devices, where the required voltage varies depending on the load. Converters regulate and provide a stable and suitable voltage for the batteries. A study and analysis of these converters will address these challenges by building and designing a simulation model to generate a voltage suitable for covering the load or charging the batteries, operating efficiently and reliably under various operating conditions. Its effectiveness can be verified through proposed tests covering operating conditions suitable for real-time operation. The first contribution is to verify the possibility of changing the converter output signal to the same value as the converter output voltage during the pulse generator duty cycle (50%). The second contribution is to verify the possibility of increasing the value of the converter output voltage in the pulse generator duty cycle (70%) or decreasing the value of the converter output voltage in the pulse generator duty cycle (20%). The results demonstrated the effectiveness of the proposed model and the possibility of changing the output voltage value with changing the output signal.
Optimizing Small-Scale Wind Energy Generation: Site-Specific Wind Speed Analysis and Turbine Placement Strategies Ahmed, Shouket A.; Çiçek, Adem; Bektas, Enes; Yassin, Khalil Farhan; Radhi, Ahmed Dheyaa; Awad, Raad Hamza; Almalaisi, Taha Abdulsalam; Itankar, Nilisha; Sekhar, Ravi; Ahmed, Ahmed H.
International Journal of Robotics and Control Systems Vol 5, No 2 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i2.1792

Abstract

Wind is an effective renewable power source suitable for localized electricity production when regional environmental factors have substantial impact on system output. The research studies the best wind turbine placement through wind speed variability studies conducted with calibrated anemometers and data loggers that assess site conditions. A data-based assessment method creates the research's main contribution which facilitates the optimization of wind power potential measurement for enhanced energy efficiency. The research methodology includes continuous Vantage Pro2 equipment together with anemometers at different heights for wind speed observation while performing accuracy-based calibration analysis. The research shows that elevating the turbine from seven meters to ten meters leads to a 12 percent growth in the amount of power produced. The power output of wind energy decreases as wind speed changes because of environmental conditions so proper installation locations become essential. Energy performance increases best when selecting sites which feature reliable and elevated wind speeds. This research provides useful knowledge about enhancing decentralized power generation through wind energy but it cannot be easily scaled up to bigger systems. The study demonstrates that specific site assessments together with practical recommendations will enhance the efficiency of small-scale wind energy systems.