Effects of Reliance Support on Team Performance by Advising and Adaptive Autonomy

Abstract

Problems with estimating trust in information sources are common in time constraining and ambiguous situations and often lead to a decrease of team performance. Humans lack the resources to track the integrity of information and thus tend to over- or under-rely on advice from support systems. Two types of adaptive team support have been developed and evaluated that are intended to support human-computer teams in estimating trust appropriately and making appropriate reliance decisions thereof. The first adaptive system (graphical support) supports by communicating the estimated degree of over- or under-trust. The second system (adaptive autonomy) takes over a reliance decision when this estimation exceeds a certain threshold. The two types of support were implemented in a multi-agent environment where human operators and Unmanned Aerial Vehicles (UAVs) work together on a target classification task. We evaluated the two support types in terms of team performance, satisfaction and effectiveness and obtained promising results.