Abstract: One of the biggest challenges in robotics is interacting under uncertainty. Unlike robots, humans learn, adapt and perceive their body as a unity when interacting with the world. Here we investigate the suitability of Active inference, a computational model proposed for the brain and governed by the free-energy principle, for robotic body perception and action in a non-simulated environment. We designed and deployed the algorithm on the humanoid iCub showing how our proposed model enabled the robot to have adaptive body perception and to perfor...
(read more)
Topics: 
Artificial intelligence
Machine learning
Computer vision