aiqbench analysis
This paper applies adaptive robust Markov decision processes to autonomous surveillance drones, updating a set of possible adversary models as new observations arrive. The method is primarily control and optimization theory, but it is a sequential decision-making approach with Bayesian-style belief refinement, which is core machine learning territory. Readers should note that the results come from simulated experiments on defined threat models, so real-world performance under adversarial conditions is still unproven.
Bayesian Ambiguity Contraction-based Adaptive Robust Markov Decision Processes for Adversarial Surveillance Missions
arXiv:2512.01660v2 Announce Type: replace-cross Abstract: Collaborative Combat Aircraft (CCAs) are envisioned to enable autonomous Intelligence, Surveillance, and Reconnaissance (ISR) missions in contested environments, where adversaries may act strategically to deceive or evade detection. These missions pose challenges due to model uncertainty and the need for safe, real-time decision-making. Robust Markov Decision Processes (RMDPs) provide worst-case guarantees but are limited by static ambiguity sets that capture initial uncertainty without adapting to new observations. This paper presents an adaptive RMDP framework tailored to ISR missions with CCAs. We introduce a mission-specific formulation in which the CCA alternates between movement and sensing states. Adversarial uncertainty is represented by finite threat prototypes defining observation, exposure, and state-action transition models. Our approach incrementally refines policies by eliminating inconsistent threat models, allowing the CCA to move from worst-case protection toward more efficient mission policies while maintaining robustness. We establish fixed point stability, agreement with nominal planning as credible sets identify the true node-specific threat prototypes, and a conservative expected value guarantee while those prototypes remain credible. Experiments under Gaussian and non-Gaussian threat models across diverse network topologies show higher mission rewards and fewer exposure events compared to nominal and static robust planners.
Abstract:Collaborative Combat Aircraft (CCAs) are envisioned to enable autonomous Intelligence, Surveillance, and Reconnaissance (ISR) missions in contested environments, where adversaries may act strategically to deceive or evade detection. These missions pose challenges due to model uncertainty and the need for safe, real-time decision-making. Robust Markov Decision Processes (RMDPs) provide worst-case guarantees but are limited by static ambiguity sets that capture initial uncertainty without adapting to new observations. This paper presents an adaptive RMDP framework tailored to ISR missions with CCAs. We introduce a mission-specific formulation in which the CCA alternates between movement and sensing states. Adversarial uncertainty is represented by finite threat prototypes defining observation, exposure, and state-action transition models. Our approach incrementally refines policies by eliminating inconsistent threat models, allowing the CCA to move from worst-case protection toward more efficient mission policies while maintaining robustness. We establish fixed point stability, agreement with nominal planning as credible sets identify the true node-specific threat prototypes, and a conservative expected value guarantee while those prototypes remain credible. Experiments under Gaussian and non-Gaussian threat models across diverse network topologies show higher mission rewards and fewer exposure events compared to nominal and static robust planners.
Optimization and Control (math.OC); Machine Learning (cs.LG); Systems and Control (eess.SY)
arXiv:2512.01660 [math.OC]
(or arXiv:2512.01660v2 [math.OC] for this version)
https://doi.org/10.48550/arXiv.2512.01660 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.2514/1.G009808 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 301 words