Multi-task trust transfer for human–robot interaction

Abstract

Trust is essential in shaping human interactions with one another and with robots. In this article we investigate how human trust in robot capabilities transfers across multiple tasks. We present a human-subject study of two distinct task domains: a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers. The findings expand our understanding of trust and provide new predictive models of trust evolution and transfer via latent task representations: a rational Bayes model, a data-driven neural network model, and a hybrid model that combines the two. Experiments show that the proposed models outperform prevailing models when predicting trust over unseen tasks and users. These results suggest that (i) task-dependent functional trust models capture human trust in robot capabilities more accurately and (ii) trust transfer across tasks can be inferred to a good degree. The latter enables trust-mediated robot decision-making for fluent human–robot interaction in multi-task settings.

Trust in Robots: Challenges and Opportunities

“…A more general approach is to directly model the human's dynamic trust in the robot. Work in this area has focused on two problems: (i) estimating trust based on observations of the human's behavior [18,27,[57][58][59][60][61][62][63][64] and (ii) utilizing the estimate of trust to guide robot behavior [27,58,[65][66][67][68][69].…”

“…In [ 67 , 69 •], a variant OPTIMo was incorporated into POMDP planning, thus allowing the robot to obtain a policy that reasons over the latent trust of the human user. This Bayesian approach to reasoning about trust has also been explored non-parametrically using Gaussian processes [ 63 ]. Lastly, this framework has also been extended to model a user’s trust in multiple robots [ 62 ], thus paving the way for dynamic trust modeling in multi-agent settings.…”

“…For example, [ 53 ] examined two different aspects of trust—trust in a robot’s intention and trust in a robot’s capability—and demonstrated that these two factors interact to give rise to reliance on the robot. Similarly, [ 63 ] demonstrated that trust can be modeled as a latent function (i.e., an infinite-dimensional model of trust) to incorporate different contexts and showed that this approach could capture how trust transfers across different task environments.…”

Real-Time Estimation of Drivers’ Trust in Automated Driving Systems

“…Robots that execute specific tasks in goaloriented contexts could have their performances measured in sequential time instances that would trigger the the transition of the trust state. For instance, these performance measures could be a success/failure classification, such as pick and place task with a robotic arm [41,44,50]; or a continuous performance evaluation, such as when a follower robot loses track of its leader due to the accumulation of sensor error [37,38].…”

“…Trust is fundamental to effective collaboration between humans and robotic systems [39]. Trust has been studied by the human-robot interaction (HRI) community, especially from researchers who are interested in robotic technologies acceptance and human-robot teams [8,20,39,41,51]. Researchers have been trying to understand the impacts of robots' behaviors on humans' trust evolution over time [42].…”