In this paper, a human-autonomy interaction approach is presented that enables autonomy to proactively dialogue with human teammates to maintain common understanding of the underlying processes. A class of human-autonomy systems where the role of the autonomy is to assist a human teammate in decision making tasks is considered. The autonomy maintains its knowledge of the processes and the environment in a Bayesian engine, and uses a Bayesian inference framework to provide decision support. Any discrepancy in the knowledge of the process between the autonomy and the human teammate may lead to inefficient decision support. The presented curious partner interaction framework uses a dialogue-based approach to resolve differences between the human and the autonomy. The dialog acts as a feedback mechanism to revise the Bayesian engine representation of the autonomy’s knowledge to establish common ground. An application to military operations is considered where a digital assistant uses the curious partner framework to provide decision support to a commander.

Date Published: 18 May 2017
PDF: 12 pages
Proc. SPIE 10194, Micro- and Nanotechnology Sensors, Systems, and Applications IX, 101941W (18 May 2017); doi: 10.1117/12.2263205

Published in SPIE Proceedings Vol. 10194:
Micro- and Nanotechnology Sensors, Systems, and Applications IX
Thomas George; Achyut K. Dutta; M. Saif Islam, Editor(s)