Confidence Metrics Improve Human-Autonomy Integration

Controls frameworks for human-autonomy integration (HAI) often treat human sources of information as highly reliable [1]. However, data from human sensing are quite variable, both because of human nature and limitations on sensor technologies. This paper focuses on estimating the degree of uncertainty in human sensed data, i.e., developing confidence metrics, and implementing those metrics in a HAI for target recognition. Here we demonstrate that applying such confidence estimates to sensed human data can mitigate effects of variability in human sensing and improve HAI performance.

[1]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[2]  Guillaume Gibert,et al.  xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface , 2009, IEEE Transactions on Biomedical Engineering.

[3]  Claus Bahlmann,et al.  In a Blink of an Eye and a Switch of a Transistor: Cortically Coupled Computer Vision , 2010, Proceedings of the IEEE.

[4]  Translation of EEG-Based Performance Prediction Models to Rapid Serial Visual Presentation Tasks , 2013, HCI.

[5]  Edwin Olson,et al.  Exploration and mapping with autonomous robot teams , 2013, CACM.