Guangzhao Yang
Papers
3
Total Citations
45
H-Index
3
About
Guangzhao Yang is a leading researcher in the intersection of machine learning and robotics, with a primary focus on the control of underactuated legged millirobots. His work addresses the fundamental challenge of enabling small, highly dynamic robots to navigate complex environments despite severe power and size constraints. Yang’s major contribution lies in developing neural network dynamics models that learn directly from image data, allowing millirobots to predict and adapt to their surroundings without hand-engineered controllers. His most-cited paper, “Learning Image-Conditioned Dynamics Models for Control of Underactuated Legged Millirobots” (2018), has garnered 26 citations and demonstrates how learned models can achieve robust locomotion and obstacle scaling. A related 2017 paper (16 citations) further establishes his approach to overcoming underactuation through data-driven control. By replacing traditional control methods with learned dynamics, Yang has opened new pathways for autonomous millirobot operation in search-and-rescue, environmental monitoring, and micro-manipulation. His work is notable for its practical impact, showing that even the smallest robots can be intelligently controlled through advanced learning techniques.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3