Ruijie Tang

Ruijie Tang

Auto-generated profile, based on publicly available information

Ruijie Tang

Department of Electronic Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 June 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SYShilong Yao
Shilong Yao
RTRuijie Tang
Ruijie Tang
LBLong Bai
Long Bai
HYHong Yan
Hong Yan
Hongliang RenHongliang Ren
Hongliang Ren
LLLi Liu
Li Liu
Micro force sensing in various clinical scenarios is a challenging issue to be addressed. It is highly difficult to trade off the size, cost, and measurement accuracy of a micro force sensing system. In this paper, a compact and affordable micro force sensing system enhanced by deep neural network is proposed. A three-axis force sensor is designed and fabricated with a footprint of only 14 mm and is employed to transform the force on the material structure into more accurate distance information. Such a sensor configuration can be seamlessly interfaced with the distal end of our in-house compliant and flexible continuum robot. On top of that, the RNN-LSTM network is exploited to augment the micro force sensing capability of the distal end-effector of the robot, which addresses the limitation on the nonlinear force issue of the continuum robot and the material itself. The RNN-LSTM network alone can be employed to perform force curve fitting for specific interventional tasks. The results indicate that more than 90% accuracy has been achieved, and the network can be applied to large-scale continuum robot-assisted interventional scenario deployment and teleoperation force perception.

18 January 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
RTRuijie Tang
Ruijie Tang
Hongliang RenHongliang Ren
Hongliang Ren
Soft robots driven by the external magnetic field can be widely applied in medical areas to realize noninvasive diagnosis and treatment. These robots gain advantages in flexibility, untethered remote control, and safe human interaction. Thus, they can achieve functions such as endo-imaging, drug delivery, and biopsy. However, developing a multi-functional magnetic-driven soft robot to carry out various medical missions remains challenging. In this work, we design a tripedal soft magnetic robot with three radial-magnetized cylindric permanent magnets embedded in three soles. The diverse motion modalities as the prerequisites to realize multi-functionality are explored in this work. The motion generation of the devised robot is investigated by applying an external uniform magnetic field. The motion modalities for movement include butterfly crawling (along the x and y axis), scorpion crawling, and rolling. We develop the different control signals from a three-directional magnetic field in various shapes, frequencies, amplitudes, and offsets for our tripedal soft magnetic robot. At different frequencies, the robot exhibits different behaviors in terms of speed and trajectory under different moving modalities. The motion trajectory of the robot in its designated direction shows a wave-like upward trend. The maximum velocity of the butterfly crawling and scorpion crawling motion at the frequency of 1 Hz is measured to be 5.30 mm/s and 9.06 mm/s. The robot can overcome obstacles such as polyps and wrinkles using the scorpion crawling and rolling mechanisms. Aiming at the potential medical application such as biopsy, we designed the leg raising modality ranging from a low frequency to a high frequency (0.02 Hz, 0.1 Hz, 0.5 Hz) using different control signal profiles (step, cosine, inverse exponential).

23 October 2023 in IEEE Sensors Journal
Verified
Journal Article
Open access
LBLong Bai
Long Bai
SYShilong Yao
Shilong Yao
KGKun Gao
Kun Gao
YHYanjun Huang
Yanjun Huang
RTRuijie Tang
Ruijie Tang
Hongliang RenHongliang Ren
Hongliang Ren
Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic Aperture Radar (SAR) and multispectral pseudo-color fusion method. Firstly, the traditional Brovey transform is employed as a pre-processing method on the paired SAR and multispectral images. Then, CDL is used to capture the correlation between the pre-processed image pairs based on the dictionaries generated from the source images via enforced joint sparse coding. Afterward, the joint sparse representation in the pair of dictionaries is utilized to construct an image mask via calculating the reconstruction errors, and therefore generate the final fusion image. The experimental verification results of the SAR images from the Sentinel-1 satellite and the multispectral images from the Landsat-8 satellite show that the proposed method can achieve superior visual effects, and excellent quantitative indicators in terms of spectral distortion, correlation coefficient, MSE, NIQE, BRISQUE, and PIQE.

23 January 2024 in IEEE Sensors Journal
Verified
Journal Article
Open access
RTRuijie Tang
Ruijie Tang
SYShilong Yao
Shilong Yao
LBLong Bai
Long Bai
HYHong Yan
Hong Yan
MMMax Q.-H. Meng
Max Q.-H. Meng
Hongliang RenHongliang Ren
Hongliang Ren
During the training of medical operators, forming muscle memory through repetitions is a routine path. Needle insertion is a fundamental skill that all medical staff need to master. However, such training courses often require human resources at a relatively high cost. Therefore, a needle insertion simulator for large-scale deployment and practical training is expected. In this paper, we design a passive, compliant force estimator that is low-cost, easily fabricated, and commonly demanded by needle insertion simulators. A triaxial decoupling force sensor design comprises commercial Force Sensing Resistors (FSR), soft silicon materials, and a 3D-printed connector for force decoupling. The total cost of the sensor and fabrication process is less than 5 USD. To achieve the prediction of a 3D force profile when the corresponding medical tasks are performed, we propose and compare two data-driven estimators, including least square (LS) regression and feedforward neural network (FNN). We demonstrate that FNN models outperformed the LS model regarding devised corresponding evaluation metrics. The predicted accuracy of FNN is above 90%, while the LS has a lower average accuracy of 78.02%. Finally, we test the performance of a pre-trained model on different angle gaps (15°, 30°). The force profiles of the 15° angle gap present relatively large fluctuations compared to reference with average accuracy at 84.36%. The test on the 30° angle gap has an error at 35.28%, which also shows randomness deviations from standard profiles. Therefore, the force information with a 15° or 30° angle gap can warn the trainer that an angle deviation exists from the standard setting.

28 April 2022 in Actuators
Verified
Journal Article
Open access
PDF file
WYWenchao YUE
Wenchao YUE
RTRuijie Tang
Ruijie Tang
JWJoei Si Min Wong
Joei Si Min Wong
Hongliang RenHongliang Ren
Hongliang Ren
Deployable mechanism has received more attention in the medical field due to its simple structure, dexterity, and flexibility. Meanwhile, the advantages of the Magnetic Anchoring and Guidance System (MAGS) are further highlighted by the fact that the operators can remotely control the corresponding active and passive magnetic parts in vivo. Additionally, MAGS allows the untethered manipulation of intracorporeal devices. However, the conventional instruments in MAGS are normally rigid, compact, and less flexible. Therefore, to solve this problem, four novel deployable tubular mechanisms, Design 1 (Omega-shape mechanism), Design 2 (Fulcrum-shape mechanism), Design 3 (Archway-shape mechanism), and Design 4 (Scissor-shape mechanism) in this paper, are proposed integrated with MAGS to realize the laser steering capability. Firstly, this paper introduces the motion mechanism of the four designs and analyzes the motion characterization of each structure through simulation studies. Further, the prototypes of four designs are fabricated using tubular structures with embedded magnets. The actuation success rate, the workspace characterization, the force generation and the load capability of four mechanisms are tested and analyzed based on experiments. Then, the demonstration of direct laser steering via macro setup shows that the four mechanisms can realize the laser steering capability within the error of 0.6 cm. Finally, the feasibility of indirect laser steering via a macro-mini setup is proven. Therefore, such exploration demonstrates that the application of the deployable tubular mechanisms integrated with MAGS towards in vivo treatment is promising.

14 January 2026 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
TZTao Zhang
Tao Zhang
RTRuijie Tang
Ruijie Tang
JLJiewen Lai
Jiewen Lai
Hongliang RenHongliang Ren
Hongliang Ren
In the field of natural orifice transluminal endoscopic surgery, there are tasks including retrograde operations. These tasks require endoscopy manipulators to perform retrograde motion in narrow human orifices, along with sufficient compliance to minimize the risk of unintended tissue injury. Aiming for them, a tendon-magnetic coactuation concentric robot (TMCR) is proposed. The tendon-driven continuum manipulator provides a steerable, higher stiffness working channel of the magnetic continuum manipulator. In contrast, the magnetic continuum manipulator equipped with several magnets can bend with different curvature distributions. By combining two manipulators with different approaches of actuation, the proposed TMCR attains greater flexibility and reduces its unreachable workspace. Then, the kinetostatic model considering the gravity influence is established for the first time. The comparison between the motion performance of the TMCR with the current concentric mechanisms is conducted. Results indicate that the TMCR reduces the unreachable cavity (the reachable to unreachable area ratio increases by 71.64$\%$). In addition, the experiment results show that the modeling error of the inner magnetic manipulator is less than 4$\%$ and the 3-D path tracking error of the TMCR is less than 1.1 mm. Finally, a phantom experiment demonstrates that the TMCR can finish different insertion tasks.