Papers
4
Total Citations
14
H-Index
3
About
Zechang Wang is a researcher at the intersection of robotics, biomechanics, and medical imaging, whose work advances both human-robot safety and autonomous control. His key contributions span three domains: developing biomechanical response curves for collaborative robot (cobot) collision testing, creating reinforcement learning frameworks robust to time-varying observation delays, and pioneering direct 3D spinal CT reconstruction from 2D X-ray images. His most cited work, "X-CTCANet" (5 citations), introduces a novel deep learning architecture that eliminates the need for traditional CT scanning, potentially reducing radiation exposure and cost in spinal diagnostics. In robotics safety, his biomechanical calibration research (4 citations) directly supports ISO/TS 15066 compliance for power and force limiting cobots, enabling safer human-robot collaboration without safety fences. His recent work on delayed dynamic model scheduled reinforcement learning (3 citations) addresses a critical gap in real-world robotic control by handling unknown, time-varying observation delays. Wang’s research demonstrates a rare ability to bridge theoretical modeling with practical deployment, from medical imaging reconstruction to generalized robot dynamics learning that reduces data collection burdens. His growing citation record reflects the immediate applicability of his work in both clinical and industrial settings.
Research Focus
Key Achievements
Top Papers
- 1X-CTCANet: 3D spinal CT reconstruction directly from 2D X-ray images5 citations · 2024
- 2
- 3
- 4Generalized Robot Dynamics Learning and Gen2Real Transfer2 citations · 2023