Samuel T. Wauthier

Ghent University, Ghent University Hospital

Papers

Total Citations

H-Index

About

Samuel T. Wauthier is a leading researcher at the intersection of computational neuroscience and artificial intelligence, with a primary focus on **active inference** and its application to autonomous systems. His work bridges the gap between theoretical models of biological cognition and practical robotic control. Wauthier’s major contribution lies in developing **generative state space models** that enable artificial agents to perceive, learn, and act by minimizing surprise—a principle derived from the free-energy principle in neuroscience. His most cited paper, “Learning Generative State Space Models for Active Inference” (2020, 39 citations), provides a foundational framework for implementing active inference in artificial agents, demonstrating how they can build internal models to drive goal-directed behavior. In a subsequent applied work, “Deep Active Inference for Autonomous Robot Navigation” (2020, 7 citations), he extends these concepts to real-world robotics, showing how deep neural networks can enable robots to navigate complex environments using only sensory input and prior beliefs. Wauthier’s research is notable for making active inference computationally tractable, offering a principled alternative to reinforcement learning. His work has been influential in both the active inference community and among researchers seeking biologically plausible AI, with his papers serving as key references for those building next-generation autonomous agents.