A method for determining the self-confidence of autonomous systems is proposed to assist operators inunderstanding the state of unmanned vehicles under control. A sensing-optimization/verification-action(SOVA) model, similar to the perception-cognition-action human informational processing model, has beendeveloped to illustrate how autonomous systems interact with their environment and how areas ofuncertainty affect system performance. LIDAR and GPS were examined for scenarios where sensedsurroundings could be inaccurate, while discrete and probabilistic algorithms were surveyed for situationsthat could result in path planning uncertainty. Likert scales were developed to represent sensor andalgorithm uncertainties, and these scales laid the foundation for the proposed Trust Annunciator Panel(TAP) consisting of a series of uncertainty level indicators (ULIs). The TAP emphasizes the critical role ofhuman judgment and oversight, especially when autonomous systems operate in clustered or dynamicenvironments.
展开▼