Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning
This addresses the challenge of effective human-robot collaboration for users of autonomous systems like robot assistants, with incremental contributions in applying POMDPs to trust modeling.
The paper tackled the problem of integrating trust into robot decision-making for human-robot collaboration by learning a trust-POMDP model from data, and validated it through experiments with 201 participants in simulation and 20 with a real robot, showing improved team performance over the long term.
Trust in autonomy is essential for effective human-robot collaboration and user adoption of autonomous systems such as robot assistants. This paper introduces a computational model which integrates trust into robot decision-making. Specifically, we learn from data a partially observable Markov decision process (POMDP) with human trust as a latent variable. The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term. We validated the model through human subject experiments on a table-clearing task in simulation (201 participants) and with a real robot (20 participants). In our studies, the robot builds human trust by manipulating low-risk objects first. Interestingly, the robot sometimes fails intentionally in order to modulate human trust and achieve the best team performance. These results show that the trust-POMDP calibrates trust to improve human-robot team performance over the long term. Further, they highlight that maximizing trust alone does not always lead to the best performance.