Papers
3
Total Citations
93
H-Index
3
About
Thomas Cederborg is a pioneering researcher at the intersection of robotics, imitation learning, and cognitive science, with a focus on how machines can acquire complex, context-dependent skills from human demonstration. His most influential work, "Incremental local online Gaussian Mixture Regression for imitation learning of multiple tasks" (2010, 81 citations), introduced a powerful, easy-to-tune regression technique that enables robots to learn incrementally and online across varied motor tasks—a foundational contribution to adaptive robotic learning. Cederborg’s research uniquely bridges robotics and language acquisition, as seen in his 2013 paper on the "Gavagai problem," where he draws structural parallels between learning sensorimotor skills and resolving ambiguities in language learning. His 2011 work further explores imitation of internal cognitive operations, pushing beyond observable motor patterns to model unobservable linguistic and cognitive structures. By framing these challenges within a unified research program, Cederborg has opened novel pathways for developing robots that learn not just movements, but the underlying cognitive rules of human communication and task execution.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3