Mind Your Manners! A Dataset and A Continual Learning Approach for Assessing Social Appropriateness of Robot Actions

Abstract

To date, endowing robots with an ability to assess social appropriateness of their actions has not been possible. This has been mainly due to (i) the lack of relevant and labelled data, and (ii) the lack of formulations of this as a lifelong learning problem. In this paper, we address these two issues. We first introduce the Socially Appropriate Domestic Robot Actions dataset (MANNERS-DB), which contains appropriateness labels of robot actions annotated by humans. To be able to control but vary the configurations of the scenes and the social settings, MANNERS-DB has been created utilising a simulation environment by uniformly sampling relevant contextual attributes. Secondly, we train and evaluate a baseline Bayesian Neural Network (BNN) that estimates social appropriateness of actions in the MANNERS-DB. Finally, we formulate learning social appropriateness of actions as a continual learning problem using the uncertainty of the BNN parameters. The experimental results show that the social appropriateness of robot actions can be predicted with a satisfactory level of precision. Our work takes robots one step closer to a human-like understanding of (social) appropriateness of actions, with respect to the social context they operate in. To facilitate reproducibility and further progress in this area, the MANNERS-DB, the trained models and the relevant code will be made publicly available.

Learning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback

“…To learn socially appropriate robot behaviours, most current approaches use static datasets, created using crowd-sourced labelling platforms, that provide common consensus annotations on what is considered socially appropriate. Tjomsland et al [19] proposed the MANNERS-DB consisting of 3D scenes created in Unity, where the appropriateness of robot actions in each scene was labelled on a 5-point Likert scale, ranging from very inappropriate to very appropriate using a crowd-sourced labelling platform. Similarly, Gao et al [20] trained an agent to learn socially appropriate approach behaviour using a 3D simulated environment in Unity.…”