Shuai Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shuai Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hongbin Liu
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science Innovation, Chinese Academy of Sciences, Hong Kong, China
4 shared publications - Hao Chen
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Jian Chen
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science Innovation, Chinese Academy of Sciences, Hong Kong, China
2 shared publications - Jian Hu
Beijing University of Technology
2 shared publications - Mingcong Chen
Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, SAR, China
2 shared publications - Zhongkai Zhang
Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science Innovation, Chinese Academy of Sciences, Hong Kong, China
2 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 463
RL-accelerated OSQP for real-time asymmetric corotational beam contact simulation in continuum robots
- 18 September 2026
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 463
Open AccessRL-accelerated OSQP for real-time asymmetric corotational beam contact simulation in continuum robots
- Open Access
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
RL-accelerated OSQP for Real-time Asymmetric Corotational Beam Contact Simulation in Continuum Robots
Real-time simulation of continuum robots within narrow anatomical cavities is crucial for navigating minimally invasive surgeries, yet it remains computationally challenging due to extensive beam-surface multi-point contacts and significant bending deformations. While the corotational finite element method (FEM) effectively captures large nonlinear displacements, its inherent asymmetric stiffness matrix severely impairs the convergence of standard optimization algorithms. To address these challenges, this paper proposes a consistent, implicit 3D corotational beam formulation tailored for real-time dynamic contact simulations. The HHT-α method is employed to predict motion trajectories, effectively mitigating spurious contacts induced by non-convex geometries. The underlying contact problem is formulated into a variational inequality (VI) and resolved using a novel adaptation of the Operator Splitting Quadratic Program (OSQP) algorithm, specifically modified for asymmetric systems. Additionally, reinforcement learning (RL) is integrated to dynamically update the OSQP parameters, significantly accelerating algorithmic convergence. By parallelizing the parameter updates and collision detection on a graphics processing unit (GPU), the proposed framework achieves robust, high-fidelity, real-time simulation of continuum robots in complex environments, such as pulmonary bronchi. Experimental results demonstrate that the proposed algorithm achieves real-time simulation performance without significantly compromising accuracy, reaching 285 FPS in a 200-node simulation of a transbronchial continuum robot.
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRL-accelerated OSQP for Real-time Asymmetric Corotational Beam Contact Simulation in Continuum Robots
Real-time simulation of continuum robots within narrow anatomical cavities is crucial for navigating minimally invasive surgeries, yet it remains computationally challenging due to extensive beam-surface multi-point contacts and significant bending deformations. While the corotational finite element method (FEM) effectively captures large nonlinear displacements, its inherent asymmetric stiffness matrix severely impairs the convergence of standard optimization algorithms. To address these challenges, this paper proposes a consistent, implicit 3D corotational beam formulation tailored for real-time dynamic contact simulations. The HHT-α method is employed to predict motion trajectories, effectively mitigating spurious contacts induced by non-convex geometries. The underlying contact problem is formulated into a variational inequality (VI) and resolved using a novel adaptation of the Operator Splitting Quadratic Program (OSQP) algorithm, specifically modified for asymmetric systems. Additionally, reinforcement learning (RL) is integrated to dynamically update the OSQP parameters, significantly accelerating algorithmic convergence. By parallelizing the parameter updates and collision detection on a graphics processing unit (GPU), the proposed framework achieves robust, high-fidelity, real-time simulation of continuum robots in complex environments, such as pulmonary bronchi. Experimental results demonstrate that the proposed algorithm achieves real-time simulation performance without significantly compromising accuracy, reaching 285 FPS in a 200-node simulation of a transbronchial continuum robot.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 2531-2541
Photoacoustic Triaxial Force Sensing via Integrated Polymer Waveguides for Ultra-Compact Robotic Surgical Instruments
Achieving triaxial tactile force sensing while maintaining miniaturization for robotic-assisted minimally invasive surgery (RMIS) instrument tips remains a significant challenge. Conventional sensing mechanisms struggle to adequately decouple force components and are limited by bulky configurations in space-constrained surgical environments. This article presents a novel triaxial force sensing method enabling precise normal and shear force decoupling within an ultracompact 3-mm diameter design. By leveraging the photoacoustic effect and a strategically patterned light-to-sound transmitter in a polymer elastomer, the sensor captures triaxial forces using a single optical fiber input and acoustic receiver output. Performance validation via modeling, simulation, and experiments demonstrates mean errors of 3.75%, 4.63%, 5.37% for x, y, z axes, respectively. The sensor achieves measurement ranges of 0 to 1.16 N (normal, 39 mN resolution) and $-$0.2 to 0.2 N (shear, 2 mN resolution). Results confirm the method's efficacy in delivering robust triaxial force sensing for RMIS and other space-critical applications.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 2531-2541
Photoacoustic Triaxial Force Sensing via Integrated Polymer Waveguides for Ultra-Compact Robotic Surgical Instruments
Achieving triaxial tactile force sensing while maintaining miniaturization for robotic-assisted minimally invasive surgery (RMIS) instrument tips remains a significant challenge. Conventional sensing mechanisms struggle to adequately decouple force components and are limited by bulky configurations in space-constrained surgical environments. This article presents a novel triaxial force sensing method enabling precise normal and shear force decoupling within an ultracompact 3-mm diameter design. By leveraging the photoacoustic effect and a strategically patterned light-to-sound transmitter in a polymer elastomer, the sensor captures triaxial forces using a single optical fiber input and acoustic receiver output. Performance validation via modeling, simulation, and experiments demonstrates mean errors of 3.75%, 4.63%, 5.37% for x, y, z axes, respectively. The sensor achieves measurement ranges of 0 to 1.16 N (normal, 39 mN resolution) and $-$0.2 to 0.2 N (shear, 2 mN resolution). Results confirm the method's efficacy in delivering robust triaxial force sensing for RMIS and other space-critical applications.
- 5 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (6) , 4504-4513
Controller Design for a Soft Continuum Robot With Concurrent Continuous Rotation
Soft continuum robot arms (CRAs) are potential in narrow confined spaces owing to the high dexterity and compliance, while torsional motion is also anticipated in some scenarios in addition to omnidirectional bending. Most existing designs generate torsional motion either relying on an independent flexible shaft or with only a limited rotation range. This article presented a control scheme for a fully self-rotatable CRA, enabling concurrent rotation along the deformable backbone while positioning the end effector. Shape configuration acts as a bridge between actuation inputs and tip pose, where the bending and rotation motions are decoupled in kinematics. With an optimization-based algorithm and Jacobian-based online correction approach, the position of the tip could be well controlled and could cope with external disturbances. Both simulation and experiments demonstrate the effectiveness of the proposed model. Results indicate that the control scheme is applicable for conventional continuum robot designs and could also perform in-situ rotation, and the motion accuracy reached around $ \text{6}\,\text{mm}$ for the $ \text{120}\,\text{mm}$ length manipulator. A biopsy sampling experiment also demonstrates its potential in medical applications.
- 5 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (6) , 4504-4513
Controller Design for a Soft Continuum Robot With Concurrent Continuous Rotation
Soft continuum robot arms (CRAs) are potential in narrow confined spaces owing to the high dexterity and compliance, while torsional motion is also anticipated in some scenarios in addition to omnidirectional bending. Most existing designs generate torsional motion either relying on an independent flexible shaft or with only a limited rotation range. This article presented a control scheme for a fully self-rotatable CRA, enabling concurrent rotation along the deformable backbone while positioning the end effector. Shape configuration acts as a bridge between actuation inputs and tip pose, where the bending and rotation motions are decoupled in kinematics. With an optimization-based algorithm and Jacobian-based online correction approach, the position of the tip could be well controlled and could cope with external disturbances. Both simulation and experiments demonstrate the effectiveness of the proposed model. Results indicate that the control scheme is applicable for conventional continuum robot designs and could also perform in-situ rotation, and the motion accuracy reached around $ \text{6}\,\text{mm}$ for the $ \text{120}\,\text{mm}$ length manipulator. A biopsy sampling experiment also demonstrates its potential in medical applications.