Malte Mosbach
Papers
2
Total Citations
17
H-Index
2
About
Malte Mosbach is a robotics researcher focused on advancing dexterous manipulation and interactive grasping for humanoid robots. His work tackles the high-dimensional challenges of anthropomorphic robot hands, aiming to enable skillful, closed-loop manipulation in unstructured real-world environments. Mosbach’s most-cited paper, “Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations” (2022, 11 citations), introduces GPU-accelerated simulation and expert demonstrations to speed up learning of complex manipulation tasks. Complementing this, his second most-cited work, “Efficient Representations of Object Geometry for Reinforcement Learning of Interactive Grasping Policies” (2022, 6 citations), addresses the challenge of generalizing grasping policies to novel objects by leveraging efficient geometric representations. Together, these contributions highlight Mosbach’s impact in bridging simulation and real-world robotics, with his citation counts reflecting growing interest in his methods. His research is particularly notable for its focus on interactive, human-like manipulation—a critical step toward deploying humanoid robots in everyday settings. For students and researchers, Mosbach’s work offers practical insights into combining reinforcement learning, simulation, and geometric reasoning to solve foundational robotics problems.
Research Focus
Key Achievements
Top Papers
- 1
- 2