Peter Pastor

Papers

Total Citations

H-Index

About

Peter Pastor is a leading researcher in robot learning and human-robot interaction, with a focus on enabling robots to acquire and generalize complex manipulation skills from human demonstration. His seminal work on dynamic movement primitives (DMPs) and associative skill memories, published in 2012 with over 70 citations, introduced a foundational framework for encoding and adapting robot motions. This approach allows robots to learn robust, reusable movement patterns that can be modulated in real time—a key contribution to the field of imitation learning and skill transfer. Pastor’s research has been instrumental in bridging the gap between low-level motor control and high-level task planning, particularly in applications requiring dexterous manipulation and physical human-robot collaboration. His work is widely cited in robotics and machine learning communities, influencing subsequent advances in reinforcement learning for robotics and adaptive control. Beyond his technical contributions, Pastor has been recognized for his interdisciplinary approach, integrating insights from neuroscience and biomechanics to create more intuitive and efficient robot learning systems. His research continues to shape how robots acquire and refine skills, making him a pivotal figure in modern robotics.