Shenghui Liu

Papers

Total Citations

170

H-Index

About

Shenghui Liu is a researcher whose work bridges the frontiers of robotics and soft actuation. His primary contributions lie in advancing visual Simultaneous Localization and Mapping (SLAM) systems and developing novel soft robotic actuators. Liu is best known for his seminal work, "DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features," which has garnered over 148 citations. This paper addresses a critical bottleneck in robot autonomy by replacing traditional, empirically designed feature extraction with deep learning-based methods, resulting in a system that is both more robust and efficient in complex environments. In parallel, Liu explores the domain of soft robotics, as evidenced by his work on "Fascicular module of nylon twisted actuators with large force and variable stiffness." This research introduces a novel actuator design inspired by biological muscle fascicles, achieving a unique combination of high force output and tunable stiffness, which is crucial for adaptive and safe human-robot interaction. Through these contributions, Liu is shaping the future of autonomous navigation and compliant robotic systems, demonstrating a clear impact on both the theoretical foundations and practical applications in his field.