Quantitative analysis of robot gesticulation behavior

TL;DR

This paper introduces a quantitative framework for evaluating robot gesture generation methods, combining statistical analyses and a novel distance metric to assess fidelity and originality.

Contribution

It proposes a comprehensive quantitative approach, including a new Fréchet Gesture Distance, for objectively comparing gesture generation models.

Findings

The methods effectively differentiate between gesture fidelity and originality.

The proposed Fréchet Gesture Distance correlates with qualitative assessments.

Quantitative analysis provides a robust alternative to visual evaluation.

Abstract

Social robot capabilities, such as talking gestures, are best produced using data driven approaches to avoid being repetitive and to show trustworthiness. However, there is a lack of robust quantitative methods that allow to compare such methods beyond visual evaluation. In this paper a quantitative analysis is performed that compares two Generative Adversarial Networks based gesture generation approaches. The aim is to measure characteristics such as fidelity to the original training data, but at the same time keep track of the degree of originality of the produced gestures. Principal Coordinate Analysis and procrustes statistics are performed and a new Fr\'echet Gesture Distance is proposed by adapting the Fr\'echet Inception Distance to gestures. These three techniques are taken together to asses the fidelity/originality of the generated gestures.