Papers
2
Total Citations
14
H-Index
2
About
Zidong Cao is a researcher advancing the frontiers of robotic perception and autonomous systems, with a primary focus on monocular depth estimation and humanoid robot motion learning. His most impactful work, "SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events" (2024, 11 citations), addresses a critical challenge in autonomous navigation: the degradation of traditional frame-based depth estimation under conditions of motion blur and limited dynamic range. By pioneering a spatial reliability-oriented fusion of standard frames and event-based camera data, Cao’s method achieves robust, fine-grained depth perception essential for self-driving cars and robot navigation. Earlier, he contributed to humanoid robotics through "A multi-stage approach for efficiently learning humanoid robot stand-up behavior" (2014, 3 citations), where he developed a more efficient learning framework that overcomes the time-intensive and expert-dependent limitations of traditional key-frame planning. This work demonstrates his commitment to practical, data-driven solutions for complex robotic behaviors. With his innovative integration of event cameras for depth sensing and efficient learning strategies for locomotion, Cao is shaping the next generation of resilient, perceptive autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2