Manuel Baum

Doctoral researcher

After obtaining his Bachelor’s degree in Cognitive Informatics and his Master’s degree in Intelligent Systems, both at Bielefeld University, Manuel Baum started to work on his  Doctoral degree at the Robotics and Biology Laboratory at TU Berlin and is now also a member of SCIoI. Robots and animals need to solve tasks, but for some tasks the information required is unknown until the agent actually starts to solve a problem, and it needs to be gathered interactively. But which information is actually task-relevant, and how can a robot / animal gather that information? This is the subject of task-directed exploration and interactive perception, which are Manuel’s two main research interests. In the SCIoI project “Intelligent kinematic problem solving”, together with colleagues from Berlin, Oxford and Vienna, Manuel researches how cockatoos and robots can explore, understand and solve complex mechanical puzzles.

SCIoI Publications:

Mengers, V., Battaje, A., Baum, M., & Brock, O. (2023). Combining Motion and Appearance for Robust Probabilistic Object Segmentation in Real Time. ICRA 2023.
Li, X., Baum, M., & Brock, O. (2023). Augmentation Enables One-Shot Generalization In Learning From Demonstration for Contact-Rich Manipulation. IROS 2023.
Baum, M., Schattenhofer, L., Rössler, T., Osuna-Mascaró, A., Auersperg, A., Kacelnik, A., & Brock, O. (2022). Yoking-Based Identification of Learning Behavior in Artificial and Biological Agents. SAB 2022.
Baum, M., Froessl, A., Battaje, A., & Brock, O. (2023). Estimating the Motion of Drawers From Sound. ICRA 2023.
Baum, M., & Brock, O. (2022). “The World Is Its Own Best Model”: Robust Real-World Manipulation Through Online Behavior Selection. ICRA 2022.
Baum, M., & Brock, O. (2021). Achieving Robustness in a Drawer Manipulation Task by using High-level Feedback instead of Planning. DGR Days.