Papers

6

Total Citations

110

H-Index

5

About

Yufeng Chi is a robotics researcher whose work spans the intersection of legged locomotion, multi-robot coordination, and hardware-software co-design for intelligent systems. His most impactful contributions focus on enabling dynamic, real-world behaviors in quadrupedal robots—most notably, a reinforcement learning framework that transforms a quadruped into a soccer goalkeeper, capable of highly dynamic locomotion and precise ball interception (36 citations). He has also advanced collaborative manipulation by developing control strategies for multiple quadrupeds to tow cable-slung loads through narrow spaces, demonstrating real-time collision avoidance and reconfigurable teamwork (35 citations). Beyond locomotion, Chi has contributed to hardware accessibility with the Berkeley Humanoid Lite, an open-source, 3D-printed humanoid robot designed to lower barriers in humanoid research. His work extends into custom silicon for robotics and AI, including the NeCTAr SoC for efficient transformer inference and the MAVERIC heterogeneous robotics SoC, which achieves 72 FPS at just 10 mJ per frame. With a publication record that bridges control theory, embedded systems, and environmental sensing—including a data-filling method for satellite aerosol measurements—Chi exemplifies a modern roboticist whose impact is felt from the chip to the field.

Research Focus

Key Achievements

5
H-Index
6
Papers
110
Total Citations
18
Avg Citations/Paper
🏆 Most Cited Paper
Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning
36 citations · 2023
📈 Most Prolific Year: 2025 (2 Papers)
🤝 Key Collaborators: 52
🏛 Institutions: University of California, Berkeley, Chinese Academy of Sciences

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago