John Yao
Papers
2
Total Citations
41
H-Index
2
About
John Yao is a roboticist whose research centers on autonomous exploration, perceptual modeling, and aerial robot navigation in challenging, real-world environments. His most influential work, "Real-Time Information-Theoretic Exploration with Gaussian Mixture Model Maps" (2019, 36 citations), introduces a novel framework that uses Gaussian mixture models (GMMs) for high-fidelity perceptual mapping. By exploiting the compactness of GMM distributions, Yao enables efficient information sharing in communications-constrained settings, advancing state-of-the-art exploration for multi-robot teams. This contribution is critical for applications like search-and-rescue or environmental monitoring, where bandwidth is limited but high-resolution perception is essential. Yao also investigates the impact of wind on small aerial robots, as seen in his 2017 study on surface-proximal flight performance, which models how turbulence affects stability and control. Though early in his career, his work bridges theoretical information theory and practical robotics, offering scalable solutions for autonomous systems. Yao’s research is particularly relevant for students and engineers developing resilient, perception-driven robots for dynamic, unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Real-Time Information-Theoretic Exploration with Gaussian Mixture Model Maps36 citations · 2019
- 2