Abstract
This paper considers the problem of path planning for a team of unmanned aerial vehicles performing surveillance near a friendly base. The unmanned aerial vehicles do not possess sensors with automated target recognition capability and, thus, rely on communicating with unattended ground sensors placed on roads to detect and image potential intruders. The problem is motivated by persistent intelligence, surveillance, reconnaissance and base defense missions. The problem is formulated and shown to be intractable. A heuristic algorithm to coordinate the unmanned aerial vehicles during surveillance and pursuit is presented. Revisit deadlines are used to schedule the vehicles' paths nominally. The algorithm uses detections from the sensors to predict intruders' locations and selects the vehicles' paths by minimizing a linear combination of missed deadlines and the probability of not intercepting intruders. An analysis of the algorithm's completeness and complexity is then provided. The effectiveness of the heuristic is illustrated through simulations in a variety of scenarios.
Highlights
A team of small unmanned aerial vehicles (UAVs) is tasked with patrolling a network of roads near a friendly base
The UAVs are equipped with a long-range communication device, which enables communication with a central authority, and a short-range communication device, which enables the UAVs to query the status of a unattended ground sensors (UGSs) directly below
This equation consists of a sum over all of the UAVs, where j indicates the UAV index. αj is only one when UAV j is loitering over a UGS during the step, in which case, the probability of an intruder passing the node where the UAV is located during the time window of the step is added
Summary
A team of small unmanned aerial vehicles (UAVs) is tasked with patrolling a network of roads near a friendly base. This work is motivated by base defense scenarios within the Talisman Saber biennial U.S./Australian military exercise [2], where UAVs are tasked with obtaining intelligence (e.g., location and imagery) about intruders. In these base defense scenarios, the UAVs have limited onboard processing capabilities and, cannot autonomously detect intruders; the UAVs rely on UGSs for intruder detection, pursuit and interception [3]. The objective is to generate paths for the UAVs (i.e., select waypoints in real time) that satisfy the revisit constraints of UGSs and capture images of intruders before the latter reach the base (i.e., maximize the likelihood of a UAV and intruder being at the same location). The capture of an image of the intruder is achieved when a UGS that a UAV is loitering (as directed by the heuristic) detects an intruder
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
