Active Inference for Learning and Development in Embodied Neuromorphic Agents

Taking inspiration from humans can help catalyse embodied AI solutions for important real-world applications. Current human-inspired tools include neuromorphic systems and the developmental approach to learning. However, this developmental neurorobotics approach is currently lacking important framew...

Full description

Saved in:
Bibliographic Details
Published in:Entropy (Basel, Switzerland) Switzerland), 2024-07, Vol.26 (7), p.582
Main Authors: Hamburg, Sarah, Jimenez Rodriguez, Alejandro, Htet, Aung, Di Nuovo, Alessandro
Format: Article
Language:English
Subjects:
active inference
Adaptation
Artificial intelligence
Brain research
Cognition & reasoning
Cognitive ability
developmental robotics
Energy efficiency
Free energy
Inference
Learning
Machine learning
Methods
neurorobotics
Reagents
Robotics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Taking inspiration from humans can help catalyse embodied AI solutions for important real-world applications. Current human-inspired tools include neuromorphic systems and the developmental approach to learning. However, this developmental neurorobotics approach is currently lacking important frameworks for human-like computation and learning. We propose that human-like computation is inherently embodied, with its interface to the world being neuromorphic, and its learning processes operating across different timescales. These constraints necessitate a unified framework: active inference, underpinned by the free energy principle (FEP). Herein, we describe theoretical and empirical support for leveraging this framework in embodied neuromorphic agents with autonomous mental development. We additionally outline current implementation approaches (including toolboxes) and challenges, and we provide suggestions for next steps to catalyse this important field.
ISSN:1099-4300
1099-4300
DOI:10.3390/e26070582