Martin Bensch

Leibniz University Hannover

Papers

3

Total Citations

12

H-Index

2

About

Martin Bensch’s research lies at the intersection of continuum robotics, model-based control, and machine learning, with a focus on enabling fast, accurate, and practical manipulation. His major contributions include pioneering the use of Physics-Informed Neural Networks (PINNs) to approximate the static Cosserat rod theory for continuum robots, dramatically reducing computational demands for tasks like path planning. This work, his most cited (8 citations), addresses a critical bottleneck in deploying sophisticated models in real-time applications. Bensch has also advanced trajectory optimization for handling elastically coupled objects, combining reinforcement learning with flatness-based control to suppress oscillations and improve industrial automation performance. Additionally, he developed a novel contact particle filter that uses only proprioceptive sensor data (tendon forces and lengths) to estimate single and multiple simultaneous contacts on tendon-driven continuum robots—a significant leap given the indirect measurement challenges in soft robotics. His work directly tackles the gap between theoretical models and practical deployment, making him a key figure in the push toward more autonomous, sensor-aware continuum robots.

Research Focus

Key Achievements

2
H-Index
3
Papers
12
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
Physics-Informed Neural Networks for Continuum Robots: Towards Fast Approximation of Static Cosserat Rod Theory
8 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Leibniz University Hannover

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago