Chengzhi Wu
Papers
3
Total Citations
41
H-Index
3
About
Chengzhi Wu is a researcher at the forefront of robotics and computer vision, specializing in agile production systems for remanufacturing. His work addresses a critical bottleneck in industrial automation: enabling robots to perceive and manipulate end-of-life products with uncertain conditions. Wu’s key contributions lie in simulation-to-reality (sim2real) transfer learning for point cloud segmentation, a technique that allows deep learning models trained on synthetic data to perform reliably on real-world industrial tasks. His most cited paper (2023, 19 citations) demonstrates this approach for autonomous disassembly, tackling the challenge of scarce real-world annotated data. Wu also developed MotorFactory, a Blender add-on for generating large datasets of small electric motors (2022, 15 citations), providing a scalable solution for training machine learning algorithms in remanufacturing environments. His work on agile production systems using learning robots (2022, 7 citations) further explores how flexible, adaptive automation can handle product variability and wear. By bridging the gap between simulation and reality, Wu is paving the way for more resilient, intelligent manufacturing systems that can economically recover valuable components from waste.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3