Papers

4

Total Citations

62

H-Index

4

About

Guanglin Ji is a leading researcher in continuum robotics, with a primary focus on safe and intelligent control for minimally invasive surgical systems. His work uniquely bridges reinforcement learning, model-based control, and real-world deployment. Ji’s major contributions include pioneering the use of shielded multiagent reinforcement learning to ensure safety in continuum manipulators—a critical step for clinical translation. His most cited paper (47 citations) demonstrates how to overcome the nonlinear, hard-to-model behavior of these robots under external forces. More recently, he has advanced the field by integrating the Koopman operator with deep RL to achieve efficient Real2Sim2Real transfer, dramatically reducing the sim-to-real gap for continuum robots under disturbances. Ji has also tackled the practical challenge of dynamic hysteresis compensation in tendon-sheath mechanisms, enabling precise control without distal sensors. His work is highly impactful, with over 60 total citations and growing, and is directly shaping the next generation of flexible surgical robots. Ji’s research is essential reading for anyone interested in combining learning-based control with safety guarantees for soft and continuum robots.

Research Focus

Key Achievements

4
H-Index
4
Papers
62
Total Citations
16
Avg Citations/Paper
🏆 Most Cited Paper
Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning
47 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 12
🏛 Institutions: Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago