Martin Seidel

Otto-von-Guericke University Magdeburg, Fraunhofer Institute for Factory Operation and Automation

Papers

Total Citations

H-Index

About

Martin Seidel is a robotics researcher whose work focuses on bridging the gap between simulation and real-world deployment, particularly for autonomous outdoor robots. His key research areas include sim-to-real transfer for reinforcement learning, autonomous navigation on pedestrian infrastructure, and the use of open geospatial data for robotics. Seidel’s most notable contribution is his pioneering application of OpenStreetMap data for outdoor robotic systems, demonstrating how freely available map data can enable delivery and transport robots to navigate footpaths and cycle tracks safely—a critical step toward practical, cost-efficient autonomous logistics. His 2019 paper on this topic has garnered 6 citations and laid foundational groundwork for integrating crowd-sourced mapping into robotic navigation. More recently, his 2024 study on sim-to-real transfer for robotics tasks, with 5 citations, systematically addresses the challenges of deploying reinforcement learning policies trained in simulation to physical robots, highlighting safety and sample efficiency concerns. This work is particularly valuable for researchers seeking to move beyond purely simulated environments. Seidel’s contributions are shaping the future of autonomous mobile robotics, making him a key figure in outdoor robotic navigation and sim-to-real methodologies.