Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Buletin Ilmiah Sarjana Teknik Elektro Journal of Robotics and Control (JRC) International Journal of Robotics and Control Systems
Anuchart Srisiriwat
Pathumwan Institute of Technology
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Mechanical Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Comparative Study of Takagi-Sugeno-Kang and Madani Algorithms in Type-1 and Interval Type-2 Fuzzy Control for Self-Balancing Wheelchairs Manutsawee Kiew-ong-art; Phichitphon Chotikunnan; Anantasak Wongkamhang; Rawiphon Chotikunnan; Anuchit Nirapai; Pariwat Imura; Manas Sangworasil; Nuntachai Thongpance; Anuchart Srisiriwat
International Journal of Robotics and Control Systems Vol 3, No 4 (2023)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v3i4.1154

Abstract

This study examines the effectiveness of four different fuzzy logic controllers in self-balancing wheelchairs. The controllers under consideration are Type-1 Takagi-Sugeno-Kang (TSK) FLC, Interval Type-2 TSK FLC, Type-1 Mamdani FLC, and Interval Type-2 Mamdani FLC. A MATLAB-based simulation environment serves for the evaluation, focusing on key performance indicators like percentage overshoot, rise time, settling time, and displacement. Two testing methodologies were designed to simulate both ideal conditions and real-world hardware limitations. The simulations reveal distinct advantages for each controller type. For example, Type-1 TSK excels in minimizing overshoot but requires higher force. Interval Type-2 TSK shows the quickest settling times but needs the most force. Type-1 Mamdani has the fastest rise time with the lowest force requirement but experiences a higher percentage of overshoot. Interval Type-2 Mamdani offers balanced performance across all metrics. When a 2.7 N control input cap is imposed, Type-2 controllers prove notably more efficient in minimizing overshoot. These results offer valuable insights for future design and real-world application of self-balancing wheelchairs. Further studies are recommended for the empirical testing and refinement of these controllers, especially since the initial findings were limited to four-wheeled self-balancing robotic wheelchairs.
Exploring ResNet-18 Estimation Design through Multiple Implementation Iterations and Techniques in Legacy Databases Nuntachai Thongpance; Pareena Dangyai; Kittipan Roongprasert; Anantasak Wongkamhang; Ratchanee Saosuwan; Rawiphon Chotikunnan; Pariwat Imura; Anuchit Nirapai; Phichitphon Chotikunnan; Manas Sangworasil; Anuchart Srisiriwat
Journal of Robotics and Control (JRC) Vol 4, No 5 (2023)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v4i5.19589

Abstract

In a rapidly evolving landscape where automated systems and database applications are increasingly crucial, there is a pressing need for precise and efficient object recognition methods. This study contributes to this burgeoning field by examining the ResNet-18 architecture, a proven deep learning model, in the context of fruit image classification. The research employs an elaborate experimental setup featuring a diverse fruit dataset that includes Rambutan, Mango, Santol, Mangosteen, and Guava. The efficacy of single versus multiple ResNet-18 models is compared, shedding light on their relative classification accuracy. A unique aspect of this study is the establishment of a 90% decision threshold, introduced to mitigate the risk of incorrect classification. Our statistical analysis reveals a significant performance advantage of multiple ResNet-18 models over single models, with an average improvement margin of 15%. This finding substantiates the study’s central hypothesis. The implemented 90% decision threshold is determined to play a pivotal role in augmenting the system’s overall accuracy by minimizing false positives. However, it’s worth noting that the increased computational complexity associated with deploying multiple models necessitates further scrutiny. In sum, this study provides a nuanced evaluation of single and multiple ResNet-18 models in the realm of fruit image classification, emphasizing their utility in practical, real-world applications. The research opens avenues for future exploration by refining these methodologies and investigating their applicability to broader object recognition tasks.
Kinematic Modeling of 6-DOF Articulated Robot Arm Denso VS 6577 Wiroj Khawlaor; Anuchart Srisiriwat
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 4 (2026): August
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i4.16049

Abstract

This paper presents a virtual-to-real validation framework for the kinematic modeling of a 6-DOF articulated industrial manipulator, Denso VS-6577. The proposed framework integrates analytical forward and inverse kinematics with a virtual simulation environment and physical robot experiments to evaluate trajectory consistency between simulated and real-world robotic environments. Closed-form inverse kinematic solutions based on the Denavit–Hartenberg (DH) convention are derived to enable computationally efficient real-time joint computation and continuous and smooth joint trajectory generation. A graphical simulation environment developed using MATLAB and V-Realm is employed to visualize and analyze robot motion under multiple joint configurations, including elbow-up posture selection and continuity-aware joint configuration management to maintain continuous manipulator motion throughout trajectory execution. To validate the proposed framework, identical circular trajectories are executed in both simulation and physical robot environments using the built-in closed-loop servo control system of the industrial manipulator. Trajectory tracking performance is evaluated by comparing Cartesian position errors along the x, y, and z axes using root-mean-square error (RMSE) analysis. Experimental results show simulation RMSE values of 1.85 mm, 0.49 mm, and 0.054 mm along the x, y, and z axes, respectively, while the physical robot experiments produce RMSE values of 3.125 mm, 1.318 mm, and 0.089 mm. The computational cost of the analytical inverse kinematic solution is less than 5 ms, demonstrating suitability for real-time robotic implementation. The results demonstrate satisfactory agreement between simulation and physical robot trajectories during continuous circular motion, while larger deviations are observed during transitional point-to-point movements. These discrepancies are primarily attributed to actuator dynamics, servo response delay, joint compliance, and mechanical backlash that are not represented in the analytical kinematic model. The proposed framework provides a unified approach for analytical kinematic validation, trajectory evaluation, and virtual-to-real robotic verification. The proposed framework can support future development of digital twin systems, advanced motion planning, and industrial robotic trajectory optimization.
Co-Authors Anantasak Wongkamhang Anuchit Nirapai Kittipan Roongprasert Manas Sangworasil Manutsawee Kiew-ong-art Nuntachai Thongpance Pareena Dangyai Pariwat Imura Phichitphon Chotikunnan Ratchanee Saosuwan Rawiphon Chotikunnan Wiroj Khawlaor