An Immersive Investment Game to Study Human-Robot Trust

Abstract

As robots become more advanced and capable, developing trust is an important factor of human-robot interaction and cooperation. However, as multiple environmental and social factors can influence trust, it is important to develop more elaborate scenarios and methods to measure human-robot trust. A widely used measurement of trust in social science is the investment game. In this study, we propose a scaled-up, immersive, science fiction Human-Robot Interaction (HRI) scenario for intrinsic motivation on human-robot collaboration, built upon the investment game and aimed at adapting the investment game for human-robot trust. For this purpose, we utilize two Neuro-Inspired COmpanion (NICO) - robots and a projected scenery. We investigate the applicability of our space mission experiment design to measure trust and the impact of non-verbal communication. We observe a correlation of 0.43 (p=0.02) between self-assessed trust and trust measured from the game, and a positive impact of non-verbal communication on trust (p=0.0008) and robot perception for anthropomorphism (p=0.007) and animacy (p=0.00002). We conclude that our scenario is an appropriate method to measure trust in human-robot interaction and also to study how non-verbal communication influences a human’s trust in robots.

What’s on Your Mind, NICO?

“…The studies reported below by Kerzel et al [28] and Churamani et al [9] are concerned with displaying and learning emotions, an important prerequisite for communicating non-verbal explanations when viewed through the lens of the XHRI framework. In [71], the effects of nonverbal communication on trust, a main driver for explainable AI research in HRI, are examined. The work summarized in [6] combine verbal utterances and non-verbal cues to Fig.…”

“…Non-verbal Communication in a Cooperative Scenario: Zörner et al [71] analyzed the influence of non-verbal communication in developing trust with a robot in a cooperative scenario. In the fictional experimental scenario, two NICO robots offer information and advice to the user who has to assign (fictional) limited resources to the different actions suggested by the two robots as a measurement of trust.…”

An Immersive Human-Robot Interactive Game Framework Based on Deep Learning for Children’s Concentration Training

“…YOLOv5 is the latest and the most lightweight version of the previous YOLO algorithms and uses the PyTorch framework instead of the Darknet framework. An overview of YOLOv5 is shown in Figure 1 [ 24 ], and Table 1 summarizes the comparison between the architectures of the YOLOv3, YOLOv4, and YOLOv5 algorithms [ 29 ]. The head and neural network type are the same for all of the algorithms, whereas the backbone, neck, and loss function are different.…”

“…The technology of human–robot interaction has gradually been applied to the field of education [ 23 , 24 , 25 , 30 , 31 ]. Logan found that children were more attracted to electronic products and could concentrate and maintain their attention for longer [ 25 ].…”

“…Thus, natural interaction and real-time performance are two key issues in relation to the application of HRI games in concentration training. Experiments have shown that this new HRI game scenario is beneficial for concentration training, and there are thus two questions that need to be explored regarding natural relationships and reaction time [ 22 , 23 , 24 , 25 ]: Does the gesture recognition-based immersive HRI game scenario realize the goal of unconstrained concentration training? Are the contents of the immersive HRI game suitable for children’s concentration training, such as for visual short-time memory and response time?…”