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

2021/04/19 by Annabi, Louis, Pitti, Alexandre, Quoy, Mathias · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2104.09163

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.

Cited by

• CERNet: Class-Embedding Predictive-Coding RNN for Unified Robot Motion, Recognition, and Confidence Estimation

Related

• Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning
• AFA-PredNet: The action modulation within predictive coding
• A Neural Active Inference Model of Perceptual-Motor Learning
• Predictive Processing in Cognitive Robotics: a Review
• Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems