Shangqun Yu
Papers
5
Total Citations
17
H-Index
3
About
Shangqun Yu is a robotics researcher advancing the frontier of dynamic and agile locomotion for humanoid robots. His work sits at the intersection of biomechanics, reinforcement learning, and whole-body control, with a focus on enabling robots to move with human-like fluidity across complex, discrete terrains. Yu’s most influential work, "Learning Generic and Dynamic Locomotion of Humanoids Across Discrete Terrains" (2024, 6 citations), tackles the long-standing challenge of terrain-adaptive motion, bridging the gap between optimization-based methods and reinforcement learning. He is also the lead designer of StaccaToe (2024, 4 citations), a human-scale single-leg robot featuring an actuated toe and co-actuation inspired by human anatomy—a platform that directly mimics the agility of the human leg. Yu’s contributions extend to collision-free locomotion through the integration of Riemannian Motion Policy with whole-body control (2023, 3 citations), and to dynamic sports motions, as seen in his biomechanics-inspired approach to soccer kicking for humanoids (2024, 2 citations). His earlier work on meta-learning parameterized skills (2022, 2 citations) demonstrates a commitment to scalable, transferable skill acquisition. With a growing citation footprint and a design philosophy rooted in biological inspiration, Yu is shaping the next generation of robots that can walk, run, and kick with unprecedented grace and adaptability.
Research Focus
Key Achievements
Top Papers
- 1
- 2StaccaToe: A Single-Leg Robot that Mimics the Human Leg and Toe4 citations · 2024
- 3
- 4A Biomechanics-Inspired Approach to Soccer Kicking for Humanoid Robots2 citations · 2024
- 5Meta-Learning Parameterized Skills2 citations · 2022