Abu Ubaidah Shamsudin

Electrical Capacitance Tomography (ECT) is categorized as a soft-field sensor that functions as a non-invasive and non-intrusive measurement instrument capable of visualizing the cross-sectional distribution of multiphase flows. ECT facilitates a better understanding of gas–solid static flow interactions, particularly in industrial pipeline and vessel systems. This study was conducted to investigate electrical potential distribution in Electrical Capacitance Tomography (ECT) systems using simplified homogeneous and non-homogeneous phantom models. The non-homogeneous condition is represented by a static phantom model to approximate material distribution within the pipe. To enhance measurement performance, a segmented excitation strategy was implemented in the ECT system. The study established three primary objectives, namely, to compare different excitation methods and determine the most effective technique capable of producing the highest potential value at the center of the pipe within an ECT piping system. A simulation of a sixteen-channel ECT sensor was performed using COMSOL Multiphysics. Potential values were evaluated at five distinct measurement points within the piping domain under different pipe material conditions. The results indicate that the segmented excitation method, in which four electrodes were excited simultaneously, produced the highest potential value at the pipe center compared to the conventional single-electrode excitation method. The implementation of segmented excitation significantly enhances potential distribution within the sensing region, particularly in the central zone of the pipe. Consequently, this approach contributes to mitigating limitations associated with the forward problem in soft-field sensing systems. Overall, the findings of this study provide valuable insights for optimizing ECT measurement performance and serve as a foundation for further development and improvement of ECT systems in future research.

This research introduces a two-degree-of-freedom rehabilitation robotic platform to enhance Constraint-Induced Movement Therapy (CIMT) for post-stroke upper limb rehabilitation. Unlike conventional CIMT, that depends on therapist intervention, the proposed system integrates a control framework balancing assistance and autonomy to improve patient engagement and recovery efficiency. The main contribution is a hybrid control architecture combining a low-level impedance controller with a high-level discrete event system (DES) controller. This dual-layer control enables real-time adaptation to a patient’s motor impairment stage, offering dynamic and personalized rehabilitation. The high-level controller, structured around the Chedoke-McMaster Assessment (CMA), facilitates intelligent transitions between rehabilitation states, ensuring robotic assistance matches recovery progress. The design emphasizes simplicity, portability, and user-friendliness, employing a lightweight, cable-driven mechanism that produces smooth and natural movements, closely replicating manual therapy. Experiments with healthy subjects simulating impaired conditions demonstrated the system’s ability to adjust assistance levels and movement velocities according to motor function stages. The results confirm the feasibility of an adaptive, patient-centric control framework that enhances motor engagement and supports progressive rehabilitation. Future work will focus on clinical validation with stroke patients, expanding movement directions, and long-term evaluation of therapeutic outcomes in real-world settings. Overall, this study offers a scalable, data-driven approach bridging robotic automation and therapist-guided rehabilitation, opening new possibilities for improving neuroplasticity and motor recovery after stroke.

Retrieving ground robots from dangerous environments after their operation is a challenging task that poses risks for the personnel. Some researchers often employ drones for retrieval, which makes operations safer. However, this set-up requires an accurate method that guarantees drone and ground robot alignment due to inaccuracies in standard GPS devices, drone drifts, and wind gusts. Hence, this research article introduces simultaneous object detection and tilt correction as part of visual servoing to achieve precise drone-rover alignment. Drone detection using YOLOv8 and a tilt correction algorithm was integrated for the proposed visual servo of the ground robot. The study collected 3024 images as a data set for drone detection. The experimental results show that the trained instance segmentation model detected and captured drone objects. The study conducted an initial test for visual servo control of the ground robot in various surface terrains, resulting in a maximum alignment error on rough surfaces. Furthermore, the study conducted drone-ground robot alignment real test in an outdoor field setting. The alignment between the drone and the ground robot produced a maximum alignment error of 20.3 cm, below the threshold error. The open field experiments verified the effectiveness of the ground robot's visual servo control with an actual drone operation.

This research into autonomous mobile robots introduces an innovative, educational approach using artificial intelligence (AI) and advanced navigation technologies to enhance learning in robotics, engineering, and computer science. The study focuses on developing an intelligent navigation system for robotic waiters that can operate independently in complex, dynamic environments like restaurants. Through this project, students gain insights into real-world applications of AI in robotics, particularly in employing LiDAR-based Simultaneous Localization and Mapping (SLAM) for precise navigation. Key to this system is the use of LiDAR sensors, which emit laser pulses to create detailed maps, enabling the robot to navigate effectively even in challenging lighting conditions. The Nvidia Jetson Nano, a powerful compact computer, functions as the robot’s “brain,” controlling its movements and processing navigation data in real time. This aspect of the project offers hands-on learning in embedded systems, giving students practical experience with computing hardware and data handling. Beyond technical skills, this research encourages students to consider the broader impacts of AI and robotics in hospitality. By exploring how autonomous robots can safely navigate and serve in crowded spaces, students engage with both engineering challenges and the transformative potential of AI in service industries. This initiative provides a holistic, hands-on educational experience aligned with cutting-edge developments in robotics, preparing students with vital skills for a technology-driven future. JEL classification: Classify your work using the suitable JEL codes. E.g. G12, G14

This research examines the integration of robotic C-arm technology in angiography, a critical tool for treating cardiac conditions. The robotic C-arm, which includes an X-ray tube, is essential for scanning patients during procedures. The study also investigates the associated risks, specifically in Indonesian hospitals with cardiac facilities. Angiography is used to diagnose and treat heart disease by visualizing blood vessels and facilitating catheterization procedures. However, its mobility poses hazards and can impact the process. To address potential risks, failure mode and effect analysis (FMEA) is utilized. Traditionally, risk assessment using risk priority numbers (RPN) is conducted, but these may not accurately reflect failures due to complex evaluating processes. To overcome this limitation, fuzzy logic is employed, enhancing risk assessment accuracy. Through this approach, twenty-seven failure modes are identified across two brands, with ten major ones prioritized using fuzzy logic. These findings facilitate the development of preventive measures to mitigate future failures and enhance patient safety during angiography in hospitals. In conclusion, the study underscores the importance of robust risk management in medical equipment, particularly in dynamic environments. By integrating fuzzy logic into risk assessment, the study improves prioritization accuracy, enabling effective allocation of resources for preventive actions.

Conceptually, Fast-RRT applies fast sampling and random steering which makes the initial path quickly obtained. Referring to the initial path, the optimality of the path is improved by applying path fusion and path optimization. Theoretically, path fusion will only be optimal if there is always a unique/different path to be fused with the previously obtained path. However, in the conditions of solving path planning problems in narrow corridors, the potential for obtaining a different path from the previous one is very small. So that fusion does not run properly, but checking the relationship between nodes to nodes still occurs. Instead of getting an optimal path in conditions like this, the computation will increase, the solution time will be long, and the resulting path will still be sub-optimal. As an effort to solve this problem, Grey Wolf Optimization (GWO) is involved through this study. While an initial path is found, the beacons are repositioned. From the path, the number of nodes is unpredictable, causing the decision variables in optimization to become large. For this reason, the GWO is chosen because it is independent of population representation and is not affected by the number of decision variables. This proposed method is claimed to be more effective in solving path planning problems in terms of convergence rate and optimality. Therefore, the proposed method is evaluated and compared with previous methods and gives the result that the average working speed of Fast-RRT is improved by 90.25% and the optimality average increased by 5.67%.

Nowadays, the advancement in autonomous robots is the latest influenced by the development of a world surrounded by new technologies. Deep Reinforcement Learning (DRL) allows systems to operate automatically, so the robot will learn the next movement based on the interaction with the environment. Moreover, since robots require continuous action, Soft Actor Critic Deep Reinforcement Learning (SAC DRL) is considered the latest DRL approach solution. SAC is used because its ability to control continuous action to produce more accurate movements. SAC fundamental is robust against unpredictability, but some weaknesses have been identified, particularly in the exploration process for accuracy learning with faster maturity. To address this issue, the study identified a solution using a reward function appropriate for the system to guide in the learning process. This research proposes several types of reward functions based on sparse and shaping reward in SAC method to investigate the effectiveness of mobile robot learning. Finally, the experiment shows that using fusion sparse and shaping rewards in the SAC DRL successfully navigates to the target position and can also increase accuracy based on the average error result of 4.99%.

Conventional car rental systems face challenges due to lengthy procedures, resulting in poor outcomes for clients and rental companies. This study proposes an i Conventional car rental systems face challenges due to lengthy procedures, resulting in poor outcomes for clients and rental companies. This study proposes an i

Functional Electrical Stimulation (FES) cycling, or FES-Cycling, holds great therapeutic potential for individuals with paralysis, such as those with Spinal Cord Injury (SCI), traumatic brain injury, or stroke, aiming to restore mobility. However, the nonlinear nature of the musculoskeletal system poses a significant challenge in controlling FES-Cycling. To address this, an integrated closed-loop phase angle fuzzy-based system was developed. This system offers real-time control by adjusting stimulation intensity (pulse width) within the range of 50 to 200μs while maintaining a constant frequency of 35Hz, thereby ensuring precise pedaling trajectory and cadence patterns. An experimental study involved three healthy individuals (Cases A, B, and C) and one individual with hemiplegia stroke (Case D). Results showed that the proposed system consistently reduced average angle trajectory errors for Cases A, B, and C, with values of 2.6945, 3.2958, and 2.9922 degrees, respectively. Case D, affected by hemiplegia stroke, faced greater challenges and exhibited a higher error of 3.4562 degrees. Fatigue resistance, evaluated through fatigue indices, showed promising results for Cases A, B, and C with values of 0.10778, 0.06866, and 0.04603, respectively. However, Case D experienced higher fatigue (0.2304) due to the unique challenges of hemiplegia stroke. These findings highlight the effectiveness of the proposed control system in optimizing FES-Cycling, particularly for healthy individuals. For individuals with paralysis, like Case D, further research is needed to adapt the system to their specific conditions and cycling patterns. This system holds the potential for enhancing FES-Cycling as a therapeutic strategy and warrants additional investigation and customization for different patient populations.

Most of the robots nowadays become more intelligent in line AI technology are being applied in industry. Deep Reinforcement Learning (DRL) is involves gaining knowledge by making errors and fixing them. Hence, the robot will learn from mistakes and keep improving by process. Deep Reinforcement Learning is a kind of machine learning method that focuses on teaching models to act in ways that maximize rewards in an environment. Since the algorithm receives feedback in the form of rewards or consequences for its actions, this is often accomplished through trial and error. Soft Actor Critic (SAC) is the most recent Deep Reinforcement Learning technique. In this research, to design a simulation robot that can be trained by using Soft-Actor Critic. This purpose is to train and evaluate the performance of robot in MATLAB and VMware platform. According to this study, robots might learn and adapt to their surroundings more quickly and effectively with the aid of a system that utilises a suitable reward together with a guidance technique. Decisively, the simulation shows that the Soft Actor Critic algorithm successfully simulates the control of flying fire fighter robot in terms of stability.