De-Xing Huang
Papers
2
Total Citations
11
H-Index
2
About
De-Xing Huang is a rising researcher at the forefront of autonomous surgical robotics, with a specialized focus on applying reinforcement learning (RL) to complex, flexible-tool manipulation. His work directly addresses one of the most challenging procedures in interventional cardiology: guidewire delivery during percutaneous coronary intervention. Huang’s major contribution lies in pioneering model-based offline reinforcement learning to enable autonomous guidewire navigation, a task requiring years of human expertise due to the tool’s inherent flexibility and the delicate vascular environment. His 2024 paper on this topic has already garnered 8 citations, signaling its immediate impact on the field. Building on this, Huang further advanced the state of the art by developing a hybrid framework that combines offline and online RL, effectively bridging the gap between simulated training and real-world performance on vascular robotic systems. This dual approach, detailed in his 2023 work, allows for safer, more efficient skill acquisition. By tackling the core challenges of sample efficiency and safety in medical robotics, Huang is laying the groundwork for a future where complex endovascular procedures can be performed with greater precision and autonomy, reducing the burden on specialists and improving patient outcomes.
Research Focus
Key Achievements
Top Papers
- 1
- 2