Max Robotics — Global Service Robot Directory + US Certification

About

Dorothea Koert is a robotics researcher whose work sits at the intersection of robot learning, motion planning, and human-robot interaction. Her research focuses on enabling robots to acquire, generalize, and adapt skills through human demonstration, making intelligent robotic systems accessible to non-expert users in real-world collaborative settings. Koert's most influential contribution — "Motion Planning Diffusion" (2023, 96 citations) — pioneered the application of diffusion generative models to robot trajectory planning, demonstrating how learned priors over successful motion histories can dramatically accelerate planning for new tasks. This work reflects her broader commitment to data-efficient, generalizable robot learning. Earlier foundational contributions, including demonstration-based trajectory optimization (2016, 51 citations) and probabilistic movement primitives for intention-aware adaptation (2019, 38 citations), established her as a key figure in imitation learning research. Her portfolio extends into human-robot collaboration, teleoperation assistance, interactive reinforcement learning, and even social robotics through expressive facial generation. Notably, her work on guided skill learning with non-experts bridges theoretical machine learning with practical usability, ensuring robots can be taught intuitively in everyday environments. With over 300 cumulative citations, Koert's research meaningfully advances the vision of adaptive, human-centered robotic assistants.