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. Secondly, we train and evaluate a baseline Multi Layer Perceptron and a Bayesian Neural Network (BNN) that estimate social appropriateness of actions in MANNERS-DB. Finally, we formulate learning social appropriateness of actions as a continual learning problem using the uncertainty of Bayesian Neural Network parameters. The experimental results show that the social appropriateness of robot actions can be predicted with a satisfactory level of precision. To facilitate reproducibility and further progress in this area, MANNERS-DB, the trained models and the relevant code are made publicly available at https://github.com/jonastjoms/MANNERS-DB.
Highlights
Determining whether generic robot actions are appropriate or not in a given social context is a relatively less explored area of research. We argue that this is mainly due to the lack of appropriately labeled data related to social appropriateness in robotics
Following the suggestions of Ebrahimi et al (2019), in the Bayesian Neural Network (BNN)-2CL and BNN-16CL models we use 10 Monte Carlos samples to approximate the variational posterior, qθ(ω), and the initial mean of the posterior was sampled from a Gaussian centered at 0 with 0.1 in SD
We conclude that the social appropriateness of robot actions can be predicted with a satisfactory level of precision on the MANNERSDB
Summary
Social robots are required to operate in highly challenging environments populated with complex objects, articulated tools, and complicated social settings involving humans, animals and other robots. To operate successfully in these environments, robots should be able to assess whether an action is socially appropriate in a given context. Determining whether generic robot actions are appropriate or not in a given social context is a relatively less explored area of research. We argue that this is mainly due to the lack of appropriately labeled data related to social appropriateness in robotics. The aforementioned aspects of our work take robots one step closer to a human-like understanding of (social) appropriateness of actions, with respect to the social context they operate in
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
