Oliver Kroemer

About

Oliver Kroemer is a prominent robotics researcher whose work sits at the intersection of robot learning, tactile sensing, and manipulation. Based at Carnegie Mellon University, he has made foundational contributions to how robots acquire and execute complex motor skills, interact with humans, and perceive their environments through touch. Kroemer's early work on robot learning established influential frameworks for skill acquisition, including his widely cited research on striking movements in robot table tennis (404 citations) and combining active learning with reactive grasping control (156 citations). His development of interaction primitives for human-robot cooperation (200 citations) and probabilistic movement primitives (192 citations) significantly advanced how robots can adapt to and collaborate with human partners in dynamic settings. A recurring theme in his research is tactile perception — from learning dynamic tactile sensing (108 citations) to developing soft magnetic skin for continuous deformation sensing (134 citations). His comprehensive review of tactile information has become a go-to reference in the field, accumulating 312 citations. Kroemer has also shaped the broader research agenda through his influential reviews of robot learning for manipulation (collectively approaching 260 citations), and his work on hierarchical skill learning for multi-phase manipulation tasks continues to inspire new approaches to complex robotic problem-solving.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning to select and generalize striking movements in robot table tennis

   404 citations · 2013
2. 2
   A Review of Tactile Information: Perception and Action Through Touch

   312 citations · 2020
3. 3
   Interaction primitives for human-robot cooperation tasks

   200 citations · 2014
4. 4
   Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks

   192 citations · 2016
5. 5
   A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

   162 citations · 2021
6. 6
   Combining active learning and reactive control for robot grasping

   156 citations · 2010
7. 7
   Soft Magnetic Skin for Continuous Deformation Sensing

   134 citations · 2019
8. 8
   Towards learning hierarchical skills for multi-phase manipulation tasks

   109 citations · 2015
9. 9
   Learning Dynamic Tactile Sensing With Robust Vision-Based Training

   108 citations · 2011
10. 10
    A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

    97 citations · 2019

Key Collaborators

Contact & Links