Reclaiming saliency: Rhythmic precision-modulated action and perception

Reclaiming saliency: Rhythmic precision-modulated action and perception

Anil Meera, A. (TU Delft Robot Dynamics)
Novicky, Filip (Radboud Universiteit Nijmegen)
Parr, Thomas (University College London (UCL))
Friston, Karl (University College London (UCL))
Lanillos, Pablo (Radboud Universiteit Nijmegen)
Sajid, Noor (University College London (UCL))

2022

Computational models of visual attention in artificial intelligence and robotics have been inspired by the concept of a saliency map. These models account for the mutual information between the (current) visual information and its estimated causes. However, they fail to consider the circular causality between perception and action. In other words, they do not consider where to sample next, given current beliefs. Here, we reclaim salience as an active inference process that relies on two basic principles: uncertainty minimization and rhythmic scheduling. For this, we make a distinction between attention and salience. Briefly, we associate attention with precision control, i.e., the confidence with which beliefs can be updated given sampled sensory data, and salience with uncertainty minimization that underwrites the selection of future sensory data. Using this, we propose a new account of attention based on rhythmic precision-modulation and discuss its potential in robotics, providing numerical experiments that showcase its advantages for state and noise estimation, system identification and action selection for informative path planning

attention
saliency
free-energy principle
active inference
precision
brain-inspired robotics
cognitive robotics

http://resolver.tudelft.nl/uuid:fc2352a9-ad2a-4a53-ac96-be6fd919fba4

https://doi.org/10.3389/fnbot.2022.896229

Frontiers in Neurorobotics, 16

Institutional Repository

journal article

© 2022 A. Anil Meera, Filip Novicky, Thomas Parr, Karl Friston, Pablo Lanillos, Noor Sajid