Keivan Amini
Papers
1
Total Citations
3
H-Index
1
About
Keivan Amini is a pioneering researcher at the intersection of cognitive robotics, social interaction, and reinforcement learning. His work fundamentally redefines how robots perceive and act upon their environment by bridging the gap between physical and social affordances. In his highly influential 2024 paper, "A new paradigm to study social and physical affordances as model-based reinforcement learning," Amini introduces a groundbreaking framework that treats social cues—often overlooked in traditional robotics—as learnable, model-based affordances. This paradigm shift allows robots to not only manipulate objects but also interpret and respond to human gestures, expressions, and intentions, enabling more fluid and intuitive human-robot collaboration. With 3 citations in its first year, this work is rapidly gaining traction as a cornerstone for next-generation interactive AI. Amini’s contributions are particularly notable for unifying disparate fields: he demonstrates that the same model-based reinforcement learning mechanisms used for physical tasks can be extended to social contexts, offering a scalable, principled approach to designing robots that learn from and with people. His research promises to transform assistive robotics, autonomous driving, and social AI, making him a key voice in the future of embodied cognition.
Research Focus
Key Achievements
Top Papers
- 1