Papers
5
Total Citations
167
H-Index
4
About
Torsten Kroeger is a leading researcher in autonomous robotics, with a career spanning foundational motion planning to cutting-edge multi-robot coordination. His work centers on enabling robots to operate safely and efficiently in dynamic, human-populated environments. A key contribution is his "Depth Space Approach for Evaluating Distance to Objects" (118 citations), which provides a computationally efficient method for real-time collision avoidance, critical for safe human-robot interaction. Kroeger also pioneered distributed sensing and prediction for mobile robot motion planning, addressing the challenge of adapting robot behavior to typical human motion patterns—a necessity for social acceptance in crowded spaces. His recent work, "RoboBallet" (2025), pushes boundaries by integrating graph neural networks and reinforcement learning to solve complex multi-robot coordination problems, automating joint task allocation and motion planning in obstacle-rich workspaces. Additionally, his research on sensor-based control (2017) has been instrumental in embedding force, vision, and distance sensors into real-time feedback loops, enabling new applications in assembly and safe collaboration. With over 160 citations, Kroeger’s work continues to shape the future of autonomous, human-aware robotics.
Research Focus
Key Achievements
Top Papers
- 1A Depth Space Approach for Evaluating Distance to Objects118 citations · 2014
- 2Simulation, Modeling, and Programming for Autonomous Robots30 citations · 2014
- 3
- 4
- 5