Haodong Huang
Papers
5
Total Citations
25
H-Index
3
About
Haodong Huang is at the forefront of humanoid robotics, pioneering the integration of large language models (LLMs) and reinforcement learning (RL) to solve one of the field’s most complex challenges: locomotion control. His research fuses the precision of dynamics-based control with the adaptability of learning-based methods, achieving both precise gait planning and high robustness in bipedal locomotion. In his highly cited 2024 work, Huang demonstrated how LLMs can replace manually designed reward functions in RL, dramatically reducing the resource intensity of training humanoid robots to walk, run, and even perform continuous jumping gaits. His comprehensive review of learning-based locomotion control methods (2025) has already become a key reference for researchers seeking robust frameworks for embodied intelligence. With over 25 citations across his recent publications, Huang’s impact is rapidly growing. Notably, he has also extended his expertise to industrial robotics, developing a swarm learning-based diagnostic algorithm for harmonic reducers that preserves data privacy across factories. Huang’s work is shaping the next generation of agile, intelligent humanoids—bridging the gap between theoretical control and real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5