Jan Mundo
Papers
1
Total Citations
40
H-Index
1
About
Jan Mundo is a leading researcher in robot learning and movement generation, with a focus on data-driven approaches that enable robots to acquire and generalize complex motor skills. Their key research areas include movement primitives (MPs), learning from demonstrations, and robot reinforcement learning. Mundo’s major contribution lies in developing methods to extract low-dimensional control variables from high-dimensional movement data, making it easier for robots to adapt learned skills across related tasks. Their seminal 2015 paper, “Extracting low-dimensional control variables for movement primitives,” has garnered 40 citations and is widely recognized for advancing the efficiency and scalability of movement primitive frameworks. This work has been instrumental in reducing the complexity of policy search in reinforcement learning, allowing robots to transfer skills with minimal retraining. Mundo’s research bridges the gap between theoretical control and practical robotics, with applications ranging from industrial automation to assistive robotics. Their contributions have been cited by leading labs worldwide, underscoring their impact on the field. For students and researchers, Mundo’s work offers a compelling entry point into the intersection of machine learning and robotic control, demonstrating how dimensionality reduction can unlock more versatile, autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Extracting low-dimensional control variables for movement primitives40 citations · 2015