Search for: All records

Development of responsive automation necessitates a framework for studying human-automation interactions in a broad range of operating conditions. This study uses a novel experiment design involving multiple binary perturbations in different stimuli to elicit measurable changes in cognitive factors that affect human-decision making during conditionally-automated (SAE Level 3) driving: trust in automation, mental workload, self-confidence, and risk perception. To infer changes in these factors, psychophysiological metrics such as heart rate variability and galvanic skin response, behavioral metrics such as eye gaze and reliance on automation, and self-reports were collected. Findings from statistical tests revealed significant changes, particularly in psychophysiological and behavioral metrics, for some treatments. However, other treatments did not elicit a significant change, highlighting the complexities of a between-subject experiment design with variations in multiple independent variables. Findings also underscore the importance of collecting heterogeneous human data to infer changes in cognitive factors during interactions with automation. 

Robots working collaboratively can share observations with others to improve team performance, but communication bandwidth is limited. Recognizing this, an agent must decide which observations to communicate to best serve the team. Accurately estimating the value of a single communication is expensive; finding an optimal combination of observations to put in the message is intractable. In this paper, we present OCBC, an algorithm for Optimizing Communication under Bandwidth Constraints. OCBC uses forward simulation to evaluate communications and applies a bandit-based combinatorial optimization algorithm to select what to include in a message. We evaluate OCBC’s performance in a simulated multi-robot navigation task. We show that OCBC achieves better task performance than a state-of-the-art method while communicating up to an order of magnitude less.