A multi-UAV deployment method for border patrolling based on Stackelberg game

Abstract

To strengthen border patrol measures, unmanned aerial vehicles (UAVs) are gradually used in many countries to detect illegal entries on borders. However, how to efficiently deploy limited UAVs to patrol on borders of large areas remains challenging. In this paper, we first model the problem of deploying UAVs for border patrol as a Stackelberg game. Two players are considered in this game: The border patrol agency is the leader, who optimizes the patrol path of UAVs to detect the illegal immigrant. The illegal immigrant is the follower, who selects a certain area of the border to pass through at a certain time after observing the leader 's strategy. Second, a compact linear programming problem is proposed to tackle the exponential growth of the number of leader's strategies. Third, a method is proposed to reduce the size of the strategy space of the follower. Then, we provide some theoretic results to present the effect of parameters of the model on leader's utilities. Experimental results demonstrate the positive effect of limited starting and ending areas of UAV's patrolling conditions and multiple patrolling altitudes on the leader 's utility, and show that the proposed solution outperforms two conventional patrol strategies and has strong robustness.

Navigation and Deployment of Solar-Powered Unmanned Aerial Vehicles for Civilian Applications: A Comprehensive Review

“…Some other research studied a similar energy-efficient coverage problem with traditional UAVs, which can guide future research in this area. The paper [106] addresses the efficient deployment of UAVs for border patrol to detect illegal entries. It formulates the problem as a Stackelberg game with two players: the border patrol agency (leader) and the illegal immigrant (follower).…”

Scaling up multi-agent patrolling in urban environments

“…5,6,16,17 In particular, zero-sum Stackelberg games model scenarios in which patrollers must commit to a patrolling strategy that is resistant to attacks even when the intruder is able to learn their strategies perfectly, and have enjoyed wide adoption in adversarial patrolling. 5,[16][17][18] In this work, we also assume that the intruder has access to patrollers' strategies and is able to optimize its attack against them. We expand on previous approaches, however, in two ways.…”

“…Another variety of problem is where the aim is to control a perimeter and deny entrance to intruders. 18,22 In this case, the motion of the patroller is constrained to be along the perimeter. In contrast to these prior works, we consider the fully general case of both patrollers and intruders moving on arbitrarily connected graphs.…”