Marie Ossenkopf

Papers

Total Citations

H-Index

About

Marie Ossenkopf is a robotics researcher whose work bridges the critical gap between autonomous exploration and safe manipulation in constrained environments. Her primary research areas include multi-agent active SLAM, reinforcement learning for robotics, and optimal mechanical design for robotic manipulation. Her most influential contribution is the development of a long-horizon Active SLAM system for multi-agent coordinated exploration, which enables teams of autonomous agents to efficiently map unknown environments while maintaining bounded estimation uncertainties—a foundational challenge in field robotics. This work has garnered 11 citations and is cited as a key reference in multi-robot exploration literature. Ossenkopf has also advanced reinforcement learning for industrial manipulators, addressing the critical safety problem of dangerous exploration by proposing policy search algorithm extensions that allow robots to learn in physically constrained environments without direct obstacle perception. Additionally, her work on optimal wheel positioning for ball handling demonstrates a practical engineering contribution to robotic manipulation. Through these contributions, Ossenkopf has established herself as a researcher tackling fundamental challenges in autonomous systems, from coordinated exploration to safe learning and mechanical optimization.