An information-theoretic on-line update principle for perception-action coupling

TL;DR

This paper introduces an online information-theoretic method for optimizing perception-action coupling in robotic systems, using neural networks and probabilistic models, demonstrated on a simulated robot task.

Contribution

It presents a novel online optimization approach for perception-action channels, integrating neural networks and probabilistic models for bounded optimality.

Findings

Effective online optimization of perception-action channels

Improved task performance in robot simulation

Framework applicable to real-time robotic systems

Abstract

Inspired by findings of sensorimotor coupling in humans and animals, there has recently been a growing interest in the interaction between action and perception in robotic systems [Bogh et al., 2016]. Here we consider perception and action as two serial information channels with limited information-processing capacity. We follow [Genewein et al., 2015] and formulate a constrained optimization problem that maximizes utility under limited information-processing capacity in the two channels. As a solution we obtain an optimal perceptual channel and an optimal action channel that are coupled such that perceptual information is optimized with respect to downstream processing in the action module. The main novelty of this study is that we propose an online optimization procedure to find bounded-optimal perception and action channels in parameterized serial perception-action systems. In particular, we implement the perceptual channel as a multi-layer neural network and the action channel as a multinomial distribution. We illustrate our method in a NAO robot simulator with a simplified cup lifting task.