Bidirectional Interaction between Visual and Motor Generative Models using Predictive Coding and Active Inference

TL;DR

This paper presents a neural architecture integrating predictive coding and active inference for bidirectional interaction between visual and motor models, demonstrated on a robotic arm learning to write letters.

Contribution

It introduces a novel neural architecture with bidirectional visual-motor interaction based on predictive coding and active inference frameworks.

Findings

Effective control of a simulated robotic arm in letter reproduction

Bidirectional interaction enhances learning and adaptation

Architecture demonstrates online motor and visual prediction capabilities

Abstract

In this work, we build upon the Active Inference (AIF) and Predictive Coding (PC) frameworks to propose a neural architecture comprising a generative model for sensory prediction, and a distinct generative model for motor trajectories. We highlight how sequences of sensory predictions can act as rails guiding learning, control and online adaptation of motor trajectories. We furthermore inquire the effects of bidirectional interactions between the motor and the visual modules. The architecture is tested on the control of a simulated robotic arm learning to reproduce handwritten letters.