Torsten Koller
Papers
1
Total Citations
33
H-Index
1
About
Torsten Koller is a leading researcher in human-aware robot navigation and socially compliant autonomous systems. His most-cited work, "Learning Human-Aware Robot Navigation from Physical Interaction via Inverse Reinforcement Learning" (2020, 33 citations), addresses a critical challenge in robotics: how autonomous systems—like indoor delivery robots—can navigate dynamic environments while respecting human social norms. Koller’s key contribution lies in using inverse reinforcement learning to enable robots to learn socially compliant behaviors directly from physical human-robot interaction, rather than relying on pre-programmed rules. This approach allows robots to adapt to nuanced human cues, improving safety and comfort in shared spaces. His research bridges the gap between machine learning and human-robot interaction, with implications for service robotics, healthcare, and smart infrastructure. By focusing on real-time adaptation and human-centered design, Koller’s work has influenced how robots perceive and respond to human presence, making autonomous navigation more intuitive and trustworthy. His findings are foundational for developing robots that can seamlessly integrate into human environments, reducing friction and enhancing collaboration.
Research Focus
Key Achievements
Top Papers
- 1