Shifan Zhu

Papers

Total Citations

H-Index

About

Shifan Zhu is a robotics researcher whose work focuses on pushing the boundaries of legged locomotion and perception, particularly for highly dynamic and agile systems. His research integrates novel hardware design with advanced computer vision, addressing the critical challenges of motion tracking and mechanical agility. Zhu’s major contributions include the development of "StaccaToe," a human-scale, single-leg robot with an actuated toe and a co-actuation configuration inspired by human anatomy, designed to rival the agility of human locomotion. This work, published in 2024, has already garnered 4 citations for its innovative approach to bio-inspired robotics. Complementing this hardware achievement, Zhu proposed a direct sparse visual odometry method that fuses event camera and RGBD data for pose estimation during dynamic locomotion. This method, detailed in his 2023 paper (7 citations), leverages the high temporal resolution of event cameras to eliminate motion blur in agile-legged robots. By combining novel mechanical design with robust, high-speed perception, Zhu is enabling robots to perform acrobatic behaviors previously unattainable, marking a significant step toward truly human-like robotic agility.