Yaonan Gu

Papers

Total Citations

H-Index

About

Yaonan Gu is a robotics researcher whose work focuses on advancing legged robot locomotion, particularly in the areas of state estimation and motion planning for challenging environments. His major contributions include a novel data-driven approach to leg odometry that uses a Long Short-Term Memory (LSTM) Recurrent Neural Network to learn and correct biases in foot contact detection, directly addressing the drift problem that plagues traditional methods. This work, published in 2024, has already garnered 3 citations, signaling its early impact on the field. Gu has also developed a workspace-based motion planner for quadrupedal robots navigating rough terrain, offering a computationally efficient and conceptually straightforward alternative to more complex planning algorithms. This 2023 publication has received 2 citations, further establishing his reputation for creating practical, implementable solutions. By combining deep learning with classical robotics challenges, Gu is helping to make legged robots more reliable and autonomous in real-world, unstructured environments—a critical step toward their deployment in search-and-rescue, inspection, and exploration missions.