Tim Schreiter
Papers
9
Total Citations
56
H-Index
5
About
Tim Schreiter is a researcher specializing in human-robot interaction (HRI), social robot navigation, and multimodal communication in shared human-robot environments. His work sits at the intersection of motion capture, behavioral analysis, and intelligent robotic systems, with a strong emphasis on enabling robots to operate safely and intuitively alongside people. Schreiter's most significant contribution is the development of the THÖR-MAGNI dataset ecosystem — large-scale, richly annotated recordings of human and robot movement in indoor environments — which has become a valuable resource for researchers modeling and predicting human motion (accumulating over 20 citations across related publications). These datasets are notable for their semantic richness, capturing contextual factors such as roles, activities, and interaction dynamics that modern machine learning approaches demand. Beyond data infrastructure, Schreiter has investigated how robots communicate intent to humans, demonstrating the advantages of multimodal over verbal-only communication and examining how anthropomorphism shapes trust in industrial settings. His research on human gaze tracking and mental state attribution further reveals how subtle social cues can transform robot perception and collaborative behavior. More recently, he has explored LLM-enhanced dialogue for more natural HRI and risk-aware navigation in complex logistics environments, reflecting a broad and forward-looking research agenda.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9