Towards Cognitive Robots That People Accept in Their Home

TL;DR

This paper proposes a study to evaluate how end-users perceive and trust cognitive assistive robots that learn on-site in home environments, focusing on different learning modes and their impact on acceptance.

Contribution

It introduces a study design to investigate user attitudes towards adaptive learning robots in home settings, emphasizing trust and acceptance.

Findings

Assess user attitudes towards learning robots in homes

Compare different modes of robot learning and their impact on trust

Evaluate acceptance levels of adaptive versus fully capable robots

Abstract

It is intractable for assistive robots to have all functionalities pre-programmed prior to deployment. Rather, it is more realistic for robots to perform supplemental, on-site learning about user's needs and preferences, and particularities of the environment. This additional learning is especially helpful for care robots that assist with individualized caregiver activities in residential or assisted living facilities. As each care receiver has unique needs and those needs may change over time, robots require the ability to adapt and learn on-site. In this work, we propose the study design to investigate the impacts on end-users of observing robot learning. We will assess user attitudes towards robots that conduct some learning in the home as compared to a baseline condition where the robot is delivered fully capable. We will additionally compare different modes of learning to determine whether some are more likely to instill trust.