Visible to the public Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction

TitleFast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction
Publication TypeConference Paper
Year of Publication2019
AuthorsGao, Y., Sibirtseva, E., Castellano, G., Kragic, D.
Conference Name2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Date PublishedNov. 2019
PublisherIEEE
ISBN Number978-1-7281-4004-9
Keywordsadaptation techniques, bi-directional trust, escape room scenario, gradient methods, Human Behavior, human factors, human trust, human-robot interaction, learning (artificial intelligence), meta-learning based adaptation, meta-learning based policy gradient method, meta-reinforcement learning, perceived trustworthiness, pubcrawl, resilience, Resiliency, Robot Trust, robust trust, Service robots, social aspects of automation, socially assistive robotics, statistical adaptation model, trust modelling
Abstract

In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and influenced the dynamics of gaining human's trust. Additionally, participants evaluated that the robot perceived them as more trustworthy during the interactions with the meta-learning based adaptation compared to the previously studied statistical adaptation model.

URLhttps://ieeexplore.ieee.org/document/8967924
DOI10.1109/IROS40897.2019.8967924
Citation Keygao_fast_2019