Runpeng Deng
Papers
8
Total Citations
157
H-Index
6
About
Runpeng Deng is a leading researcher in the field of robotic precision engineering, specializing in the prediction, quantification, and compensation of robot pose errors to enhance machining quality. His major contributions include pioneering methods that integrate uncertainty quantification, online prediction, and physics-informed frameworks to address error-motion correlations in robotic systems. Deng’s work has garnered significant attention, with his most-cited paper, “Quantification of uncertainty in robot pose errors and calibration of reliable compensation values” (2024), accumulating 44 citations, followed closely by his online prediction and compensation method (32 citations) and active semi-supervised transfer learning approach (30 citations). Notably, he developed the CME-EPC framework, which embeds coarse mechanisms for error prediction across multi-condition tasks, and introduced sparse knowledge embedded configuration optimization to improve machining quality. His recent advances include spatial-temporal feature fusion and physics-informed error prediction, demonstrating a trajectory toward intelligent, data-driven robotic systems. Deng’s research is highly impactful for students and researchers in robotics, manufacturing, and control systems, offering practical solutions for reducing errors in automated machining processes.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8