Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
This work addresses surveillance-evasion scenarios for applications like security or robotics, but it is incremental as it builds on existing methods by integrating learning with formal guarantees.
The paper tackles the problem of optimizing visibility while maintaining surveillance guarantees in a two-player game, achieving an efficient approach by combining formal methods for correctness with machine learning for scalability.
This paper studies a two-player game with a quantitative surveillance requirement on an adversarial target moving in a discrete state space and a secondary objective to maximize short-term visibility of the environment. We impose the surveillance requirement as a temporal logic constraint.We then use a greedy approach to determine vantage points that optimize a notion of information gain, namely, the number of newly-seen states. By using a convolutional neural network trained on a class of environments, we can efficiently approximate the information gain at each potential vantage point.Subsequent vantage points are chosen such that moving to that location will not jeopardize the surveillance requirement, regardless of any future action chosen by the target. Our method combines guarantees of correctness from formal methods with the scalability of machine learning to provide an efficient approach for surveillance-constrained visibility optimization.