Papers
1
Total Citations
2
H-Index
1
About
K. Rosner is a leading researcher in multi-robot systems and learning-based navigation, with a focus on overcoming the sample efficiency challenges that plague Deep Reinforcement Learning (DRL) in complex, dynamic environments. Their most-cited work, "MuRoSim – A Fast and Efficient Multi-Robot Simulation for Learning-based Navigation" (2024), introduces a high-fidelity simulation platform that accelerates the training of DRL agents for multi-robot coordination and dynamic obstacle avoidance. This contribution directly addresses the critical bottleneck of low sample efficiency, enabling more practical deployment of learned navigation policies in real-world scenarios. With 2 citations in its first year, the paper is already shaping the direction of simulation tools for robot learning. Rosner’s work bridges the gap between theoretical DRL advances and scalable, real-world multi-robot applications, making them a key figure in the push toward robust, autonomous swarm systems. Their research is essential reading for students and engineers tackling the intersection of simulation, reinforcement learning, and cooperative robotics.
Research Focus
Key Achievements
Top Papers
- 1