Occlusions, restricted field of view and limited resolution all constrain a robot's ability to
sense its environment from a single observation. In these cases, the robot first needs to …

Scene understanding and decomposition is a crucial challenge for intelligent systems,
whether it is for object manipulation, navigation, or any other task. Although current machine …

We propose an architecture for the open-ended learning and control of embodied agents.
The architecture learns action affordances and forward models based on intrinsic …

We develop a visuomotor model that implements visual search as a focal accuracy-seeking
policy, with the target's position and category drawn independently from a common …

Visual search is an essential cognitive ability, offering a prototypical control problem to be
addressed with Active Inference. Under a Naive Bayes assumption, the maximization of the …

Representing a scene and its constituent objects from raw sensory data is a core ability for
enabling robots to interact with their environment. In this letter, we propose a novel approach …

More than 50% of the sensory receptors in the human body are located in the eyes, and a
significant portion of the cerebral cortex is devoted to interpreting visual information. The …

Decoding the semantic content of images is nowadays dominated by the use of deep
convolutional neural networks (DCNNs), However, their generalization capability is still …

This paper explores the application of active inference and the free energy principle (FEP) to
enable active vision in physical robots, using pixel-level RGB camera observations. By …

Starting from biological systems, we review the interest of active perception for object
recognition in an autonomous system. Foveated vision and control of the eye saccade …