Summaries - Research
Back Decision Theoretic and Algorithmic Foundations for Autonomy in Adversarial Environments
|Division||Graduate School of Operational & Information Sciences|
Royset, Johannes O.
Bassett, Robert L.
Leary, Paul R.
|Sponsor||Office of Naval Research (Navy)|
|Summary||The operation of autonomous agents requires software and hardware which facilitate understanding and responding to complex external environments. To cope with this complexity, researchers and engineers rely on increasingly complex methods for translating sensor data into automated decisions for interaction within the environment, otherwise known as signal detection and classification. In Department of Defense (DoD) applications, autonomous agents often operate in an environment influenced by an adversary, which presents additional challenges. In these adversarial environments, complex methods for onboard decision making can be a liability because their complexity makes it difficult to assess the impact an adversary has on the method's performance. The active or passive influence of an adversary on the environment should not diminish the agent's capabilities. In response to the challenges presented by autonomy in adversarial environments, we propose to develop foundational mathematical and statistical tools for autonomy under adversarial influence. Our cross-disciplinary research team's combined expertise in statistical learning and autonomy, especially with regards to the operational needs of the DoD, make us uniquely qualified to accomplish the proposed research.|
|Publications||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|
|Data||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|