18th ICCRTS Learned Tactics for Asset Allocation Topics

Tactics can be developed in a number of different ways. Rules can be created based on a theory of operations as has been done in the development of tactical decision aids for a considerable time. But these tools can behave poorly in unanticipated scenarios and can require significant design effort. In this paper, an existing machine learning approach for training geographically based agents learns tactics for the placement of surveillance assets. These results serve as a potential benchmark to compare against other methods. While there are many approaches possible, there are currently few ways of directly comparing these methods for the military environment. It would be advantageous to have a common set of benchmark scenarios that could evaluate different strategies with respect to each other. This paper presents such a problem, simulated data, and solution. In this domain a limited number of surveillance assets must autonomously coordinate to detect several types of vessels, so that they can be intercepted. The results show that a machine learning approach is able to consistently locate opposing vessels, even in the presence of noise, but more importantly provides a performance baseline and guide for developing future benchmark problems.