Papers
2
Total Citations
13
H-Index
2
About
Runyu Ma’s research sits at the intersection of robotics, reinforcement learning, and large language models, with a focus on enabling intelligent, adaptive control in complex environments. In their 2023 work, Ma introduced a hybrid force-magnetic control scheme for steering flexible medical devices—a novel approach that combines physical force sensing with magnetic actuation to improve precision in minimally invasive procedures. This paper has already garnered 8 citations, signaling its relevance to the medical robotics community. More recently, Ma proposed ExploRLLM, a framework that leverages large language models to guide exploration in reinforcement learning for robot manipulation. By addressing the notorious sample inefficiency and convergence challenges in RL, this 2025 work demonstrates how foundation models can provide structured priors for exploration, achieving more reliable learning in high-dimensional spaces. With 5 citations in its first year, ExploRLLM is quickly gaining traction. Ma’s work bridges the gap between classical control theory and modern AI, offering practical solutions for both surgical robotics and autonomous manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2