Che-Wei Chang
Papers
2
Total Citations
56
H-Index
2
About
Che-Wei Chang is a leading researcher in human-robot interaction, specializing in gesture recognition and humanoid robot control. His work focuses on bridging the gap between human motion and robotic imitation, particularly through the use of affordable, accessible sensors like the Microsoft Kinect. Chang’s major contributions lie in developing robust, adaptive algorithms that allow robots to learn and replicate complex human actions in real time. His 2014 paper, "A Kinect-based gesture command control method for human action imitations of humanoid robots" (29 citations), pioneered the use of dynamic time warping (DTW) and hidden Markov models (HMMs) to interpret gestures with high accuracy. He advanced this approach in his 2015 work, "An adaptive hidden Markov model-based gesture recognition approach using Kinect to simplify large-scale video data processing for humanoid robot imitation" (27 citations), which streamlined data processing for more efficient imitation learning. Together, these papers have laid a foundation for intuitive, non-invasive robot training systems, influencing fields from assistive robotics to entertainment. Chang’s research demonstrates how clever algorithm design can make sophisticated robotic control accessible, inspiring new generations of engineers to explore the potential of vision-based human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2