The Impact of POMDP-Generated Explanations on Trust and Performance in Human-Robot Teams

By Ning Wang, David V. Pynadath, Susan G. Hill. 2016

104 citations recorded by the source corpus.

Researchers have observed that people will more accurately trust an autonomous system, such as a robot, if they have a more accurate understanding of its decision-making process. Studies have shown that hand-crafted explanations can help maintain effective team performance even when the system is less than 100% reliable. However, current explanation algorithms are not sufficient for making a robot's quantitative reasoning (in terms of both uncertainty and conflicting goals) transparent to human teammates. In this work, we develop a novel mechanism for robots to automatically generate explanations of reasoning based on Partially Observable Markov Decision Problems (POMDPs). Within this mechanism, we implement alternate natural-language templates and then measure their differential impact on trust and team performance within an agent-based online test-bed that simulates a human-robot team task. The results demonstrate that the added explanation capability leads to improvement in transparency, trust, and team performance. Furthermore, by observing the different outcomes due to variations in the robot's explanation content, we gain valuable insight that can help lead to refinement of explanation algorithms to further improve human-robot interaction.

Subfields: Artificial Intelligence, Social Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

Citations in the corpus

Improving Robot Controller Transparency Through Autonomous Policy Explanation (2017, background): “Even in situations in which robots’ explanations are neither exhaustive nor precise, the corresponding increase in transparency can improve the decision-making capabilities of collaborators [45, 29, 47].”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, methodology): “n [171] Tag-based [231] Transparency Condence+Sensor Data with Low Robot Ability [237] Decisive Input Values [213] Derived Topic Models and Time Intervals [199] Justication [133] POMDP* Translation [236] Tag-based [231] Persuasiveness Peer Information [84] Peer- and Tag-based [85] Satisfaction Justi”
Trust triggers for multimodal command and control interfaces (2017, background): “why it took a certain route [14, 18] and creation of strategic messages through human-robot interaction [10] with the aim to increase trust.”