Christoph Haas
Papers
3
Total Citations
69
H-Index
2
About
Christoph Haas is a leading researcher at the intersection of robotics, machine learning, and surgical automation, with a core focus on enabling gentle, data-efficient robotic manipulation for delicate medical interventions. His most significant contribution is the introduction of **Movement Primitive Diffusion (MPD)**, a novel imitation learning method that combines movement primitives with diffusion models to generate smooth, safe, and high-quality motion policies for robot-assisted surgery (RAS). This work, which has already garnered 48 citations since 2024, directly addresses the critical challenge of achieving both versatility and motion gentleness in surgical robotics. Haas also developed **LapGym**, an open-source reinforcement learning framework specifically designed for robot-assisted laparoscopic surgery, providing a standardized environment that has become a key resource for advancing cognitive assistance and automation in the field. By bridging the gap between data-efficient policy learning and the stringent safety requirements of surgical settings, Haas is paving the way for more autonomous and reliable robotic assistance in the operating room.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3