Journal of Robotics, Networking and Artificial Life

Volume 11, Issue 3, March 2026

Research Article
1. Implementation of Automated Weed Detection using Computer Vision Techniques
Renuka Devi Rajagopal, Rethvik Menon C, T S Pradeep Kumar, Heshalini Rajagopal, Norrima Mokhtar
Agriculture is one of the most ancient and most important professions forming the base of any society. The development of any country depends on the agricultural produce and its related areas to ensure greater growth in the country. One of the major problems affecting the agricultural produce of farmers worldwide is the unrestricted growth of weeds in the farm and agricultural areas which results in reduced produce for the farmers. One of the most elementary steps in the process of weed removal involves the detection of weeds in a field filled with agricultural produce. This process has been made easy by implementing the YOLOv8 process, which has produced great results ensuring easy detection of weeds and crops, making it easier and efficient for the farmers to increase and enhance their produce. YOLOv8 offers improved weed and crop detection with a precise classification rate of 0.9895 which indicates a highly accurate and successful classification. This allows farmers to efficiently identify and eliminate weeds, leading to higher productivity and better crop yields, ultimately supporting the agricultural growth of the country. This model can ensure easier, more efficient, and enhanced detection to improve the process of identifying the weeds and thereby eliminating them.
Pages: 180–184
Download article (PDF)

Research Article
2. The Research of an Augmented Reality System for the Implementation of Industrial Robots
Takuma Aiko, Eiji Hayashi, Gamolped Prem
The implementation of industrial robots is a critical strategy for mitigating the severe labor shortages affecting all industries in Japan. A significant barrier to their widespread adoption is the substantial capital investment required for the hardware and system integration. This study addresses this challenge through the development of a mobile Augmented Reality (AR) application designed to facilitate the robot adoption process. We have engineered and validated a system that enables the visualization and verification of a robot's operational trajectory prior to its physical installation, confirming its efficacy.
Pages: 185 - 189
Download article (PDF)

Research Article
3. A Research on an Editing Support System for Automatic Piano Performance to Improve Dynamics Prediction Accuracy
Taiyo Goto, Yoshiki Hori, Eiji Hayashi
Automated piano player systems enable highly precise keystrokes and pedal operations. However, a direct translation of score data into performance often results in a mechanical and inexpressive sound, failing to capture the nuanced dynamics of a human pianist's interpretation. This discrepancy arises because pianists uniquely determine various performance parameters, such as note loudness (Velo), the time between notes (Step), and individual note durations (Gate). While deep learning has been utilized in prior research to predict these parameters, the accuracy of Velo prediction, in particular, has remained a significant challenge. To address this limitation, this paper proposes a novel deep learning system specifically designed to enhance the accuracy of Velo prediction by integrating two distinct neural networks. Furthermore, experiments conducted with our system demonstrate improved prediction accuracy compared to previous studies.
Pages: 190 - 195
Download article (PDF)

Research Article
4. Enhancing ICS Situational Awareness: A Passive Network Traffic Analysis Approach
I-Hsien Liu, Chien-Wen Tseng, Jung-Shian Li, Chu-Fen Li
Monitoring the operational integrity of industrial control systems (ICS) is a fundamental concern in modern infrastructure environments. While previous studies have primarily relied on direct access to controllers’ data for system observation, this study adopts a passive network-based approach to minimize potential disruptions. By analyzing communication traffic within a simulated dam control system, the research investigates how network-observable information exchanged between devices can reflect system-level operational behavior. Through detailed inspection of packet-level data, including protocol usage, register values that reveal PLC operational states, the study aims to enhance situational awareness without interfering with system operations.
Pages: 196 - 199
Download article (PDF)

Research Article
5. Analyzing Learners’ Operation Logs in Three-Move Problems with the 2×2×2 ERC and IDDFS Algorithm
Takumi Ueda, So Takei, Akira Nakano, Kenji Kimura, Dinda Pramanta, Kazutaka Matsuzaki
Japan's high school curriculum now includes “Mathematics through Puzzles” in the “Human and Mathematical Activities” unit to foster spatial and strategic thinking, requiring new teaching tools. While the Rubik's Cube is popular, conventional methods cannot analyze operation records to evaluate learners' thinking. This study uses a 2×2×2 ERC and the IDDFS algorithm to analyze operations and introduces an evaluation value to quantify efficiency. We conducted experiments with 11 learners that evaluation value distinguishes the strategic thinking from trial-and-error. This result offers a new alternative objective method to assess cognitive processes in puzzle-based mathematical education in the future.
Pages: 200 - 203
Download article (PDF)

Research Article
6. Development of a Drone Navigation System Using Depth Estimation for Obstacle Avoidance
Sora Takahashi, Eiji Hayashi
This research introduces a drone obstacle avoidance system built upon depth estimation derived from monocular RGB images, with the objective of minimizing reliance on high-cost sensors such as LiDAR and RGB-D cameras. The proposed system incorporates ZoeDepth, a deep learning model for monocular depth prediction, and is implemented within a simulated environment using ROS and Gazebo. Two autonomous configurations were tested: one equipped with an RGB-D camera, and the other utilizing depth information inferred from RGB inputs. Evaluation results revealed that, although the RGB-D-equipped setup achieved higher accuracy, the RGB-based system was able to avoid obstacles and reach the target destination, despite exhibiting some localization errors. Future efforts will focus on increasing the system’s resilience in densely populated environments and conducting validation through real-world trials.
Pages: 204 - 209
Download article (PDF)

Research Article
7. Industrial Intrusion Detection System for Schneider Twido Systems
Nai-Yu Chen, Jung-Shian Li, Hui-Chun Pan, I-Hsien Liu
The Schneider Electric Twido PLCs are analyzed, focusing on the UMAS protocol vulnerabilities, which lack essential security features such as encryption, authentication, and replay attack protection. Key design flaws, including unencrypted communications and unrestricted memory access, are identified and real-world attacks are replicated using publicly disclosed CVEs. A Snort-based Intrusion Detection System (IDS) is developed to address these vulnerabilities, incorporating custom rules to detect abnormal traffic patterns and high-risk function codes within the UMAS protocol. Simulated attack scenarios confirm the IDS's ability to identify unauthorized operations. This solution is lightweight, scalable, and offers practical security improvements for industrial control systems relying on proprietary protocols like UMAS.
Pages: 210 - 213
Download article (PDF)

Research Article
8. MIXVRT: MIX Visual Regression Testing Tool Which Mixes Image Comparison and HTML Code Comparison
Naoki Aridome, Nobuya Takahashi, Tetsuro Katayama, Yoshihiro Kita, Hisaaki Yamaba, Kentaro Aburada, and Naonobu Okazaki
Image-based visual regression testing has the problem that it takes time required to find layout defects. Therefore, this paper develops MIXVRT (MIX Visual Regression Testing tool), which mixes image comparison and HTML code comparison. It highlights the layout defects. From evaluation experiments, we have confirmed that the time required to find layout defects can be reduced compared to the conventional methods of image-based visual regression testing, while detecting them accurately without omissions or false detections.
Pages: 214 - 219
Download article (PDF)

Research Article
9. Implementation of a Tool for Automatic Entry Fields Detection and for Labels Allocation to Generate Electronic Forms
Yuya Kimura, Nobuya Takahashi, Tetsuro Katayama, Yoshihiro Kita, Hisaaki Yamaba, Kentaro Aburada, and Naonobu Okazaki
An effective approach to manage the content entered in forms is the use of electronic forms. However, if you use a paper form, it takes time to generate electronic forms. This paper has implemented a tool for automatic entry fields detection and for labels allocation to reduce the time required to place entry fields. As a result, we have verified that the implemented tool is useful to reduce the time to place entry fields.
Pages: 220 - 225
Download article (PDF)

Research Article
10. An Underwater Imaging System for Fish Recognition and Behavior Estimation to Optimize Sustainable Aquaculture Feeding
Raji Alahmad, Dominic Solpico, Shoun Masuda, Mohammad Albaroudi, Abdullah Alraee, Takahito Ishizuka, Kenta Naramura Zhangchi Dong, Zongru Li, Hussam Alraie, Yuya Nishida, Kazuo Ishii
Aquaculture continues to expand as a response to rising seafood demand, but feeding remains a critical challenge due to its high costs and environmental impact. This study introduces an underwater imaging system that integrates video enhancement, YOLOv8-based fish detection, and velocity estimation to provide a data-driven solution for optimizing feeding strategies. Unlike conventional farmer intuition, the proposed approach offers objective monitoring of fish behavior under real aquaculture conditions. The system enhances underwater video quality by correcting color distortion, reducing noise, and sharpening contours, which improved fish detection accuracy from 69.3% to 73.2%. YOLOv8 achieved an overall detection accuracy of 85%, while velocity tracking successfully distinguished between normal and hunger-driven behaviors. These results confirm that fish velocity is a reliable indicator of feeding demand. By linking motion dynamics with feeding decisions, the system can reduce feed waste, lower costs, and improve fish health while minimizing environmental impacts. This work demonstrates the potential of integrating artificial intelligence and imaging technologies to establish standardized, sustainable, and more profitable aquaculture feeding practices. Future studies will focus on larger datasets, adaptive enhancement techniques, and real-time feeding control.
Pages: 226 - 235
Download article (PDF)

Research Article
11. Mirroring Humanity: Creating the Digital Twin via Advanced Human-Device Interfaces
Norrima Mokhtar, Mohd Ridha Muhamad, Meor Faisal Zulkifli, Tsutomu Ito, Takao Ito
The integration of Human-Device Interfaces (HDIs) is fundamentally transforming how humans interact with technology, moving from traditional inputs like keyboards toward seamless, effortless communication. This paper explores the concept of "Mirroring Humanity" through the creation of a Digital Twin, facilitated by advanced interfaces such as Brain-Computer Interfaces (BCIs), wearable sensors, and haptic feedback. By leveraging Artificial Intelligence (AI) and machine learning, these systems enable real-time decision-making and the personalization of technology to individual user needs. Drawing on case studies from ACRLAB at Universiti Malaya, this work highlights advancements in contactless navigation such as eye-driven wheelchairs and immersive virtual teaching environments. These technologies demonstrate a proof of concept for enhancing independence among disabled communities and improving efficiency across industries including healthcare and automation. However, the shift toward highly integrated digital twins introduces significant challenges regarding data security, reliability, and the ethical implications of augmenting human traits. The paper concludes that while HDIs offer immense potential for global betterment, robust regulations, ethics and inclusive design are essential to mitigate risks and ensure sustainable technological advancement.
Pages: 236 - 241
Download article (PDF)

Research Article
12. Digital Guardians: The Role of AI and Robotics in Protecting Construction Heritage
Muhammad Azizi Azizan, Nurfadzillah Ishak, Hazry Desa
The preservation of construction heritage faces increasing challenges associated with aging infrastructure, environmental degradation, and limited conservation resources. This study proposes a structured Digital Guardian Framework integrating artificial intelligence (AI), robotics, and digital twin technologies for intelligent heritage conservation. Unlike conventional review-based discussions, this research introduces a methodological framework that combines AI-driven predictive analytics, robotic inspection and intervention systems, and digital monitoring environments to support decision-making in heritage preservation. The framework is validated through analytical evaluation and application to the Sultan Abdul Samad Building in Malaysia, demonstrating how automated inspection, risk prediction, and non-invasive restoration strategies can enhance conservation efficiency while maintaining architectural authenticity. Quantitative performance indicators suggest improvements in inspection accuracy, risk reduction, and lifecycle sustainability compared with traditional conservation approaches. The study contributes a scalable interdisciplinary model bridging robotics engineering and heritage conservation, supporting future smart preservation ecosystems.
Pages: 242 - 246
Download article (PDF)

Research Article
13. Design Principle and Analysis of an Output Cam for a Rotary Actuator Capable of Multidirectional Rapid Motion and Variable Stiffness
Katsuaki Suzuki, Yuya Nishida, Kenji Kimura, Kazuo Ishii
Production processes such as high-mix, low-volume manufacturing, where product specifications and task conditions change frequently, require mechanisms that can flexibly switch functions and offer high adaptability. However, achieving multifunctionality by simply combining multiple actuators increases cost, control-system complexity, and mass. To address these issues, this study proposes a novel rotary actuator that achieves normal motion, rapid motion, and variable stiffness with direction-independent output characteristics, using only two motors in combination with mechanical elements such as cam mechanisms and a differential mechanism. This paper describes the structure and functions of the proposed mechanism, the design principles of the output cam that governs the output characteristics, and a mathematical model of its rapid motion. Furthermore, computer-aided engineering simulations using the designed output cam are conducted to evaluate the output characteristics in the variable-stiffness mode and to compare the simulated rapid motion with the mathematical model, thereby validating the theoretical model.
Pages: 247 - 253
Download article (PDF)

Research Article
14. Research on Player Position Estimation from Various Views in Volleyball
Iori Iwata, Kazuma Sakamoto, Riku Kaiba, Yoshihiro Ueda
In recent years, data-driven approaches have become increasingly important in sports analytics, particularly in the context of tactical analysis. In the domain of volleyball, the precise estimation of player positions is of paramount importance for the purpose of performance evaluation. Conventional methodologies are contingent on projective transformation employing fixed reference points; a process which restricts its applicability when considering variable viewpoints. This limitation assumes particular relevance in the context of broadcast footage. The present study proposes a robust system for estimating player positions from arbitrary camera angles, including legacy and zoomed-in footage. The proposed methodology utilizes the YOLOv9 model for player detection and employs manual identification of court lines and the net to define dynamic reference points for homography. The findings of Experiment 1 demonstrate that player positions can be estimated with an average error of 0.30 meters, which is sufficient for tactical use. Furthermore, experiment 2 introduces a dual-camera triangulation approach to address the challenge of estimating airborne players, where conventional ground-contact assumptions are inadequate. The synchronization of cameras and the utilization of calibration through the employment of chessboard patterns facilitate the computation of the three-dimensional position of jumping players, yielding an average error of 0.43 meters. This outcome underscores the method's aptitude for effectively managing real volleyball dynamics, incorporating in-air motion. Collectively, these methodologies furnish a versatile and precise instrument for volleyball analysis, thereby establishing a foundation for more extensive implementations within the domain of sports informatics.
Pages: 254 - 261
Download article (PDF)

Research Article
15. Mathematical Modeling and Simulation of a Simple Pendulum-Based Hide Tanning Equipment
Renchinvanjil Yadam, Dondogjamts Batbaatar
Limited access to electricity in rural areas of developing countries has driven innovation in gravityassisted human-powered mechanical systems. This study presents the mathematical modeling and simulation of a newly designed hide tanning device that utilizes a simple pendulum mechanism powered by human muscle force. The equipment integrates a simple pendulum, cylindrical gear transmission, bearings, and hide straps into a dynamic system. Equations of motion were derived using the Lagrangian method, validated through numerical simulation over a ten-second period. The torque resistance of the hide strap was evaluated using finite element analysis (FEA) in a previous study, enabling the calculation of the strap’s resistance coefficient. Simulation results demonstrated the damping effect caused by the hide straps on the pendulum’s oscillation and quantified the required excitation force applied by hand. The device is capable of tanning up to six hide straps simultaneously. The findings confirm that the proposed equipment effectively reduces physical effort, improves labor efficiency, and offers a sustainable and user-friendly solution suitable for traditional hide processing in remote and off-grid communities.
Pages: 262 - 268
Download article (PDF)