elements communicate to develop relevant courses of
actions for human-machine systems. We discussed
the algorithms for representation, diagnosis, and
prognosis of context and methods to effectively
communicate it across the data-to-decision process.
We validated our algorithms via the development
of proactive decision support tools across maritime
operations, including ( 1) a multiobjective robust and
adaptive optimization algorithms in the operational
software tool, TMPLAR; ( 2) waterspace interference
identification algorithms embedded in the operational software tool, CONFIDENT; ( 3) dynamic
allocation of surveillance and interdiction assets
for countersmuggling operations via COAST; ( 4) asset
package selection and planning for MOC planning;
and ( 5) machine learning and statistical hypothesis
testing algorithms to infer cognitive context in digit
recall, sequential letter recall, and arithmetic tasks
using eye tracking data (SCOUT; Mishra et al. ).
Our future research directions include practical interactive multiobjective optimization algorithms for resource allocation (for surveillance and
execution) and asset routing, informed by context
(mission, environment, asset, threat, human cognition) and data, featuring adaptive search interfaces (for example, scatter, gather for exploratory
search tasks, baseline web search for lookup-type
query tasks), Q-learning, multigrid methods, feature-based aggregation, rollout, deep reinforcement
learning and approximate policy iteration, and modeling and analysis of cognitive context change
detection in sequential tasks. We plan to use a unified
graph-theoretical framework bringing together concepts from variational free energy optimization in thermodynamics and information theory; approximate
dynamic programming from operations research
and stochastic control; active inference-based perception and action selection from neuroscience;
graphical model inference and bounded rationality from probabilistic inference and cognitive
science; and Feynman–Kac path costs in physics
to mathematically represent, evaluate, and design
complex hybrid team structures.
The authors are thankful to Dr. William Lawless for
his valuable time and excellent suggestions. The
authors would like to thank US Office of Naval
Research and Naval Research Laboratory for support-
ing this research.
2. Sweep width of any sensor is the width a definite range
sensor has to sweep to detect the same number of objects
per unit time in a uniform distribution of search objects. It
is used to evaluate the probability of detection.
Abowd, G. D.; Dey, A. K.; Brown, P. J.; Davies, N.; Smith, M.;
and Steggles, P. 2001. Towards a Better Understanding of
Context and Context-Awareness. In International Sympo-
sium on Handheld and Ubiquitous Computing, 304–7. Berlin:
Alvarez, L.; Pérez-Peña, R.; and Robles, F. 2015. El Faro,
Missing Ship, Has No Sign of Survivors. New York Times
(October 5). www.nytimes.com/2015/10/06/us/el-faro-
Bienkowski, A.; Zhang, L.; Sidoti, D.; and Pattipati, K. R.
2018. Path Planning in an Uncertain Environment Using
Approximate Dynamic Programming Methods. In 21st
International Conference on Information Fusion. Piscataway, NJ:
Bonczek, R. H.; Holsapple, C. W.; and Whinston, A. B. 2014.
Foundations of Decision Support Systems. Boston: Academic Press.
Chapanis, A. 1965. On the Allocation of Functions between
Men and Machines. Occupational Psychology 39( 1): 1–11.
Cummings, M. M. 2014. Man Versus Machine or Man+
Machine? IEEE Intelligent Systems 29( 5): 62–9. doi.org/10.1109/
Fitts, P. M.; Viteles, M.; Barr, N.; Brimhall, D.; Finch, G.;
Gardner, E.; Grether, W.; Kellum, W.; and Stevens, S. 1951.
Human Engineering for an Effective Air-Navigation and Traffic-Control System. Oxford, UK: National Research Council.
Friston, K. 2010. The Free-Energy Principle: A Unified Brain
Theory? Nature Reviews. Neuroscience 11( 2): 127–38. doi.org/
George, D.; Lehrach, W.; Kansky, K.; La’Zaro-Gredilla, M.;
Laan, C.; Marthi, B.; Lou, X. et al. 2017. A Generative Vision
Model That Trains with High Data Efficiency and Breaks
Text-Based CAPTCHAs. Science 358(6368). doi.org/10.1126/
Han, X.; Mishra, M.; Mandal, S.; Bui, H.; Ayala, D. F. M.;
Sidoti, D.; Pattipati, K. R.; and Kleinman, D. L. 2014.
Optimization-Based Decision Support Software for a Team-in-the-Loop Experiment: Multilevel Asset Allocation. IEEE
Transactions on Systems, Man, and Cybernetics. Systems 44( 8):
Hansen, J. A.; Hodyss, D.; Bishop, C. H.; and Campbell, W.
2012. Coupled METOC/ INTEL Risk Assessment. U.S. Patent
13,272,272, filed April 19, 2012.
Horvitz, E. 1999. Principles of Mixed-Initiative User Interfaces.
In Proceedings of the SIGCHI Conference on Human Factors in
Computing Systems, 159–66. New York: ACM.
Kurien, J.; Nayak, P. P.; and Smith, D. E. 2002. Fragment-Based Conformant Planning. In Proceedings of the Sixth
International Conference on Artificial Intelligence Planning and
Scheduling, 153–62. Palo Alto, CA: AAAI Press.
Levchuk, G.; Pattipati, K. R.; Serfaty, D.; Fouse, A.; and
McCormack, R. 2018. Active Inference in Multiagent Systems: Context-Driven Collaboration and Decentralized.
Purpose-Driven Team Adaptation. Paper presented at 2018
AAAI Spring Symposium Series.Stanford, CA, March 26–28.
Levine, S. 2018. Reinforcement Learning and Control as
Probabilistic Inference: Tutorial and Review. arXiv CoRR
abstract:1805.00909. Ithaca, NY: Cornell University Library.
Mannaru, P.; Balasingam, B.; Pattipati, K.; Sibley, C.;
and Coyne, J. T. 2017. Performance Evaluation of the
Gazepoint gp3 Eye Tracking Device Based on Pupil Dilation.
In International Conference on Augmented Cognition, 166–75.
Berlin: Springer. doi.org/10.1007/978-3-319-58628-1_14