Bianca Ghinoiu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Bianca Ghinoiu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Abigail Pop
Robotics Department, Institute of Solid Mechanics of the Romanian Academy
2 shared publications - Lingfeng Sang
Ningbo Key Laboratory of Aging Health Equipment and Service Technology, Ningbo Polytechnic, Ningbo 315800, China
2 shared publications - Luige Vladareanu
Robotics and Mechatronics Department, Institute of Solid Mechanics of the Romanian Academy, 010141 Bucharest, Romania
2 shared publications - Victor Vladareanu
Robotics Department, Institute of Solid Mechanics of the Romanian Academy
2 shared publications - Ana-Maria Travediu
Institute of Solid Mechanics of the Romanian Academy, 010141 Bucharest, Romania
1 shared publication - Andreea Zamfirescu
Department of Geriatrics and Gerontology, Faculty of Midwifery and Nursing, “Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, Romania
1 shared publication
Latest Publications
- 20 June 2025
- Published by Springer Nature
- p. 125-135
From Cobot to Dog Intelligent Robot GO2 and Humanoid Intelligent Robots G1/H1. Educational and Economic Applications
- 20 June 2025
- Published by Springer Nature
- p. 125-135
From Cobot to Dog Intelligent Robot GO2 and Humanoid Intelligent Robots G1/H1. Educational and Economic Applications
- Open Access
Design, Simulation, and Testing of Active Cooperative Control Strategies for a Light Sensation Transfer Nursing Robot
The transfer of patients, especially elderly or long-term bedridden individuals, has emerged as an important problem due to the growing aging population. The advancement of transfer nursing robots provides an intelligent solution to this problem. This paper presents a Parallel Master–Slave Cross-Coupled (PMSCC) cooperative control strategy based on adaptive fuzzy controllers to address the motion control challenges of a self-developed light Sensation Transfer Nursing Robot (LSTNR). First, the working principle of the LSTNR is introduced, followed by the establishment of its motion model. Next, the robot’s velocity is designed based on PMSCC cooperative control strategies, with an adaptive fuzzy controller performing motion control. Finally, the proposed cooperative control strategy is simulated and analyzed, and the robot is tested for patient transfer. The results show that the proposed control strategy reduces the velocity cooperation error between the robot’s motors. The average velocity error of the robot is reduced by 92.69%, 92.08%, 47.35%, and 87.78%, respectively, compared to the non-cooperatively controlled robot. This significantly addresses issues such as belt slack, tightness, and patient position deformation during operation, improving the transfer efficiency and effectiveness of the LSTNR.
Open AccessDesign, Simulation, and Testing of Active Cooperative Control Strategies for a Light Sensation Transfer Nursing Robot
The transfer of patients, especially elderly or long-term bedridden individuals, has emerged as an important problem due to the growing aging population. The advancement of transfer nursing robots provides an intelligent solution to this problem. This paper presents a Parallel Master–Slave Cross-Coupled (PMSCC) cooperative control strategy based on adaptive fuzzy controllers to address the motion control challenges of a self-developed light Sensation Transfer Nursing Robot (LSTNR). First, the working principle of the LSTNR is introduced, followed by the establishment of its motion model. Next, the robot’s velocity is designed based on PMSCC cooperative control strategies, with an adaptive fuzzy controller performing motion control. Finally, the proposed cooperative control strategy is simulated and analyzed, and the robot is tested for patient transfer. The results show that the proposed control strategy reduces the velocity cooperation error between the robot’s motors. The average velocity error of the robot is reduced by 92.69%, 92.08%, 47.35%, and 87.78%, respectively, compared to the non-cooperatively controlled robot. This significantly addresses issues such as belt slack, tightness, and patient position deformation during operation, improving the transfer efficiency and effectiveness of the LSTNR.
- Open Access
- 14 December 2024
- Published by MDPI AG in Technologies
- Vol. 12 (12) , 261
EEG-Based Mobile Robot Control Using Deep Learning and ROS Integration
Efficient BCIs (Brain-Computer Interfaces) harnessing EEG (Electroencephalography) have shown potential in controlling mobile robots, also presenting new possibilities for assistive technologies. This study explores the integration of advanced deep learning models—ASTGCN, EEGNetv4, and a combined CNN-LSTM architecture—with ROS (Robot Operating System) to control a two-wheeled mobile robot. The models were trained using a published EEG dataset, which includes signals from subjects performing thought-based tasks. Each model was evaluated based on its accuracy, F1-score, and latency. The CNN-LSTM architecture model exhibited the best performance on the cross-subject strategy with an accuracy of 88.5%, demonstrating significant potential for real-time applications. Integration with ROS was facilitated through a custom middleware, enabling seamless translation of neural commands into robot movements. The findings indicate that the CNN-LSTM model not only outperforms existing EEG-based systems in terms of accuracy but also underscores the practical feasibility of implementing such systems in real-world scenarios. Considering its efficacy, CNN-LSTM shows a great potential for assistive technology in the future. This research contributes to the development of a more intuitive and accessible robotic control system, potentially enhancing the quality of life for individuals with mobility impairments.
- 14 December 2024
- Published by MDPI AG in Technologies
- Vol. 12 (12) , 261
Open AccessEEG-Based Mobile Robot Control Using Deep Learning and ROS Integration
Efficient BCIs (Brain-Computer Interfaces) harnessing EEG (Electroencephalography) have shown potential in controlling mobile robots, also presenting new possibilities for assistive technologies. This study explores the integration of advanced deep learning models—ASTGCN, EEGNetv4, and a combined CNN-LSTM architecture—with ROS (Robot Operating System) to control a two-wheeled mobile robot. The models were trained using a published EEG dataset, which includes signals from subjects performing thought-based tasks. Each model was evaluated based on its accuracy, F1-score, and latency. The CNN-LSTM architecture model exhibited the best performance on the cross-subject strategy with an accuracy of 88.5%, demonstrating significant potential for real-time applications. Integration with ROS was facilitated through a custom middleware, enabling seamless translation of neural commands into robot movements. The findings indicate that the CNN-LSTM model not only outperforms existing EEG-based systems in terms of accuracy but also underscores the practical feasibility of implementing such systems in real-world scenarios. Considering its efficacy, CNN-LSTM shows a great potential for assistive technology in the future. This research contributes to the development of a more intuitive and accessible robotic control system, potentially enhancing the quality of life for individuals with mobility impairments.