Manos Papagelis
Papers
2
Total Citations
23
H-Index
2
About
Manos Papagelis is a leading researcher in artificial intelligence, robotics, and spatial data science, with a focus on scene understanding and trajectory prediction. His work bridges computer vision and deep learning to solve critical challenges in autonomous navigation and human movement analytics. In his 2019 paper on scene classification for indoor robots, Papagelis pioneered the use of context-based word embeddings to improve classification accuracy in complex environments, a foundational contribution that has garnered 15 citations and influenced subsequent robotics research. More recently, his 2025 work, "TrajLearn: Trajectory Prediction Learning using Deep Generative Models," introduces a novel deep learning framework for estimating future paths from historical movement data. This paper, with 8 citations in its first year, demonstrates his ability to advance state-of-the-art methods in trajectory prediction, benefiting fields from autonomous vehicles to crowd analytics. Papagelis’s research is characterized by its practical impact, combining rigorous theoretical foundations with real-world applications. His work continues to shape how machines perceive and predict dynamic environments, making him a notable figure in AI-driven spatial intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2TrajLearn: Trajectory Prediction Learning using Deep Generative Models8 citations · 2025