Stefan Otte

Papers

Total Citations

H-Index

About

Stefan Otte’s research focuses on autonomous robotic exploration, particularly how machines can physically interact with and learn from their environments. His major contributions center on developing entropy-based strategies that enable robots to systematically discover and manipulate an environment’s degrees of freedom—such as opening doors, drawers, or unlocking mechanisms—without prior knowledge. In his 2014 paper, “Entropy-based strategies for physical exploration of the environment’s degrees of freedom” (18 citations), Otte introduced methods for robots to identify promising interaction points and reveal hidden object properties through pushing and pulling. His 2015 work, “Active exploration of joint dependency structures” (14 citations), advanced this by addressing how robots can learn dependencies between joints, such as understanding that a drawer can only open if a lock is disengaged. These contributions are foundational for creating robots capable of autonomous, adaptive manipulation in unstructured settings. Earlier in his career, Otte contributed to the FUmanoid humanoid robot platform (2010, 3 citations), which competed in RoboCup, showcasing his hands-on work in hardware and software design. With a total of 35 citations across his key works, Otte’s research is a valuable resource for students and researchers in robotics, artificial intelligence, and autonomous systems.