Gaoming Lou
Papers
2
Total Citations
19
H-Index
2
About
Gaoming Lou is at the forefront of soft robotics control, pioneering hybrid approaches that merge physics-based modeling with reinforcement learning (RL) to overcome the inherent challenges of controlling highly deformable, high-degree-of-freedom systems. His most impactful work, "Controlling Soft Robotic Arms Using Hybrid Modelling and Reinforcement Learning" (2024, 17 citations), introduces a novel RL strategy built on a hybrid model that compensates for gravitational effects and modeling inaccuracies, achieving precise control where traditional methods fall short. Building on this, his 2025 paper on "Residual Reinforcement Learning Based on Inverse Kinematic Modeling" (2 citations) tackles the efficiency and accuracy trade-off between interpretable kinematic models and model-free RL, proposing a residual learning framework that significantly improves control performance while reducing sample complexity. Lou’s contributions are critical for advancing soft robotics from lab curiosities to practical, real-world applications in manipulation and human-robot interaction. His work is widely cited by researchers in robotics and control theory, marking him as a rising leader in intelligent, adaptive control for compliant systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2