Lijia Ding
Papers
1
Total Citations
2
H-Index
1
About
Lijia Ding is a robotics researcher whose work focuses on the intersection of reinforcement learning and bipedal locomotion, particularly the challenge of dynamic balance control. Their most notable contribution is a novel framework for optimal ankle stiffness regulation in humanoid robots, which enables stable balancing in the presence of external disturbances. By applying integral reinforcement learning (IRL) algorithms, Ding developed a data-driven approach that allows bipedal robots to adaptively adjust their posture without relying on precise system models—a significant step toward more resilient humanoid robots. While their foundational 2016 paper on optimal balancing control has garnered 2 citations, its impact lies in laying the groundwork for adaptive, learning-based control strategies in legged robotics. Ding’s work addresses a core problem in humanoid robotics: how to maintain stability under unpredictable forces, a critical requirement for robots operating in human environments. Their research bridges control theory and machine learning, offering practical solutions for real-world deployment of bipedal systems.
Research Focus
Key Achievements
Top Papers
- 1Optimal balancing control of bipedal robots using reinforcement learning2 citations · 2016