Markus Thom
Papers
1
Total Citations
14
H-Index
1
About
Markus Thom is a researcher whose work sits at the intersection of robotics, autonomous systems, and probabilistic sensor fusion. His primary research focus is on environment perception for robotic and automotive applications, with a particular emphasis on dynamic occupancy grid mapping. Thom’s most notable contribution is his development of a random finite set (RFS) approach for dynamic occupancy grid maps, published in 2018. This work advances the well-established grid mapping paradigm by applying Bayesian filtering to recursively estimate the occupancy state of each cell in a robot’s environment, enabling real-time, robust perception in dynamic scenes. The paper has garnered 14 citations, reflecting its relevance to researchers working on autonomous navigation and perception. Thom’s approach addresses a critical challenge in robotics: how to reliably model and update a robot’s understanding of its surroundings as both the robot and objects in the environment move. By bridging theoretical rigor with practical real-time implementation, his work has contributed to safer and more efficient autonomous systems. For students and researchers in robotics or autonomous driving, Thom’s research offers a compelling example of how advanced probabilistic methods can be translated into deployable solutions.
Research Focus
Key Achievements
Top Papers
- 1