Lukas Rummelhard
Papers
2
Total Citations
5
H-Index
2
About
Lukas Rummelhard is a leading researcher in autonomous navigation and perception, specializing in dynamic environment modeling for robotics and automotive applications. His work bridges the critical gap between perception and safe navigation in complex, unstructured, and uncertain settings. Rummelhard’s major contributions include developing a cross-prediction, hidden-state-augmented approach for Dynamic Occupancy Grid filtering, which enables accurate tracking of spatial occupancy at a sub-object level—a significant advancement over traditional static grid mapping. This work, cited 3 times, provides a robust framework for understanding dynamic scenes. He further extended this research to collision avoidance with his work on predictive collision detection, transforming probabilistic occupancy grids into versatile tools for real-world navigation. This paper, with 2 citations, addresses the challenge of integrating perception and planning under uncertainty, a problem rarely tackled holistically. Rummelhard’s innovative methods are foundational for autonomous vehicles and mobile robots operating in unpredictable environments, offering practical solutions for safety-critical applications. His research continues to shape how robots perceive and interact with dynamic surroundings, making him a key figure in advancing autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2