A Prototyping Environment for Integrated Artificial Attention Systems

TL;DR

This paper introduces a flexible prototyping environment for integrated artificial attention systems, enabling adaptable testing of attention-guided vision algorithms in robotic applications with diverse inputs and tasks.

Contribution

It presents a novel robotic middleware-based framework that supports development and testing of attention systems across different sources, algorithms, and tasks.

Findings

Supports testing with various input sources

Allows integration of different attention algorithms

Facilitates evaluation in diverse robotic tasks

Abstract

Artificial visual attention systems aim to support technical systems in visual tasks by applying the concepts of selective attention observed in humans and other animals. Such systems are typically evaluated against ground truth obtained from human gaze-data or manually annotated test images. When applied to robotics, the systems are required to be adaptable to the target system. Here, we describe a flexible environment based on a robotic middleware layer allowing the development and testing of attention-guided vision systems. In such a framework, the systems can be tested with input from various sources, different attention algorithms at the core, and diverse subsequent tasks.