Ziwei Lei

Papers

Total Citations

H-Index

About

Ziwei Lei is a researcher at the forefront of medical robotics, specializing in the intersection of machine learning and minimally invasive surgical technologies. Their work focuses on two critical challenges: enabling robots to learn complex manipulation skills from human demonstrations, and developing accurate dynamic models for capsule endoscopy robots. Lei’s most cited paper, "Learning ultrasound scanning skills from human demonstrations" (2022, 12 citations), pioneers a data-driven approach to automate ultrasound procedures, a significant step toward reducing operator dependency and improving diagnostic consistency. Additionally, Lei has made notable contributions to the control of magnet-actuated tethered capsule robots, where friction modeling is essential for precise positioning within the gastrointestinal tract. Their 2022 study on learning friction models for such capsules (3 citations) addresses a key bottleneck in achieving reliable locomotion for diagnostic applications. By integrating learning-based methods with robotic control, Lei’s work enhances the autonomy and accuracy of medical devices, promising safer and more effective interventions. Their research is particularly impactful for students and engineers interested in surgical robotics, reinforcement learning, and the practical deployment of intelligent systems in clinical settings.