Papers
7
Total Citations
57
H-Index
5
About
Qingfeng Yao is a pioneering robotics researcher whose work centers on advancing quadrupedal locomotion and legged mobile manipulation through the integration of deep reinforcement learning and optimal control. His major contributions include developing hierarchical terrain-aware control systems that enable quadruped robots to navigate complex environments by combining perception with motion planning, and creating imitation learning frameworks that allow robots to learn natural gait patterns from animal videos. Yao has also made significant strides in amphibious robotics, designing learning-based adaptive propulsion control that enables quadrupeds to seamlessly transition between terrestrial and aquatic locomotion. His work on disturbance predictive control for legged manipulators—quadruped robots equipped with robotic arms—has established new paradigms for adaptive manipulation in unstructured environments. With multiple papers accumulating 10-11 citations each, Yao’s research has garnered attention for its practical impact on real-world robotics challenges. Notably, he contributed to the Real Robot Challenge, a cloud-based robotics competition that democratizes access to dexterous manipulation research platforms. His innovative approaches to combining learning-based control with classical robotics continue to push the boundaries of what legged robots can achieve in dynamic, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7Real Robot Challenge: A Robotics Competition in the Cloud2 citations · 2021