Massimiliano Patacchiola
Papers
12
Total Citations
547
H-Index
10
About
Massimiliano Patacchiola is a multidisciplinary researcher whose work spans computer vision, human-robot interaction, developmental robotics, and machine learning. He is perhaps best known for his influential 2017 paper on head pose estimation using Convolutional Neural Networks and adaptive gradient methods, which has accumulated over 200 citations and remains a key reference in real-world visual perception research. A significant thread of his scholarship addresses how robots develop and model trust, with his developmental cognitive architectures for trust and Theory of Mind in humanoid robots drawing considerable attention — collectively earning well over 150 citations across multiple publications. His work explores how artificial agents can distinguish reliable from unreliable informants and adapt accordingly, a challenge central to deploying robots in real-world social settings. Patacchiola has also made notable contributions to human-robot cooperation dynamics, anthropomorphism, and reinforcement learning for autonomous UAV landing using sim-to-real transfer techniques. His research consistently bridges cognitive science and engineering, offering both theoretical frameworks and practical implementations. With a citation record reflecting sustained influence across diverse subfields, Patacchiola stands as an inventive voice in socially intelligent and perceptually capable robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Generalisation of Anthropomorphic Stereotype29 citations · 2019
- 7Investigating cooperation with robotic peers26 citations · 2019
- 8A developmental Bayesian model of trust in artificial cognitive systems21 citations · 2016
- 9
- 10Do Humans Imitate Robots?13 citations · 2020