Panju Bai
Papers
3
Total Citations
28
H-Index
3
About
Panju Bai is a leading researcher in legged robotics, specializing in reinforcement learning (RL) for agile and adaptive locomotion. Their work tackles the critical challenge of bridging the simulation-to-reality gap, enabling quadruped robots to perform complex, real-world maneuvers. Bai’s major contributions include the development of the Distributional Ensemble Actor-Critic (DEAC) algorithm, which explicitly models and mitigates aleatoric uncertainty from domain randomization—a key innovation that has garnered significant attention (14 citations). They also pioneered Curricular Hindsight Reinforcement Learning (CHRL), a framework that trains end-to-end tracking controllers for high-speed turning, sprinting, and fall recovery in unstructured environments (8 citations). Notably, Bai’s research on dynamic fall recovery control provides robust RL-based strategies for robots to autonomously recover from falls on uneven terrain, a critical capability for real-world deployment (6 citations). Their work is highly cited and recognized for pushing the boundaries of legged robot agility and resilience, offering practical, scalable solutions for autonomous systems operating in the wild.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3