Hiroki Sawada

Okinawa Institute of Science and Technology Graduate University

Papers

Total Citations

H-Index

About

Hiroki Sawada is a pioneering researcher at the intersection of cognitive robotics and computational neuroscience, whose work centers on the free-energy principle and its application to human-robot interaction. His most influential contribution, the development of the PV-RNN (Predictive Variational Recurrent Neural Network) model, has fundamentally advanced our understanding of how robots can engage in kinaesthetic interactions that mirror human social dynamics. By grounding robotic behavior in the free-energy principle—a theoretical framework for understanding perception, action, and learning—Sawada has demonstrated that robots can exhibit top-down expectations and bottom-up sensory integration, enabling more natural, adaptive, and intuitive physical collaboration with humans. His 2024 study on human-robot kinaesthetic interactions, already garnering 5 citations, represents a significant step toward machines that can anticipate and respond to human movement in real time. Sawada’s work bridges the gap between theoretical neuroscience and practical robotics, offering a roadmap for creating socially intelligent machines. His research is essential reading for students and scholars interested in embodied cognition, predictive processing, and the future of human-robot collaboration.