Inference of affordances and active motor control in simulated agents

Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience perspective. Based on the theory, we introduce an output-probabilistic,...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neurorobotics Vol. 16; p. 881673
Main Authors: Scholz, Fedor, Gumbsch, Christian, Otte, Sebastian, Butz, Martin V.
Format: Journal Article
Language:English
Published: Lausanne Frontiers Research Foundation 11.08.2022
Frontiers Media S.A
Subjects:
active inference
affordances
Computational neuroscience
Control theory
Energy
Free energy
free energy principle
goal-directed control
Homeostasis
Information processing
Markov analysis
model-predictive control
Motor task performance
Nervous system
Neural networks
Neuroscience
Prediction models
Sensorimotor system
simulation
ISSN:1662-5218, 1662-5218
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience perspective. Based on the theory, we introduce an output-probabilistic, temporally predictive, modular artificial neural network architecture, which processes sensorimotor information, infers behavior-relevant aspects of its world, and invokes highly flexible, goal-directed behavior. We show that our architecture, which is trained end-to-end to minimize an approximation of free energy, develops latent states that can be interpreted as affordance maps. That is, the emerging latent states signal which actions lead to which effects dependent on the local context. In combination with active inference, we show that flexible, goal-directed behavior can be invoked, incorporating the emerging affordance maps. As a result, our simulated agent flexibly steers through continuous spaces, avoids collisions with obstacles, and prefers pathways that lead to the goal with high certainty. Additionally, we show that the learned agent is highly suitable for zero-shot generalization across environments: After training the agent in a handful of fixed environments with obstacles and other terrains affecting its behavior, it performs similarly well in procedurally generated environments containing different amounts of obstacles and terrains of various sizes at different locations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Edited by: Mario Senden, Maastricht University, Netherlands
Reviewed by: Jean Daunizeau, INSERM U1127 Institut du Cerveau et de la Moelle épinière (ICM), France; Stefan J. Kiebel, Technical University Dresden, Germany
ISSN:1662-5218
1662-5218
DOI:10.3389/fnbot.2022.881673