Reinforcement Learning for Joint Detection and Mapping Using Dynamic UAV Networks

Abstract

Dynamic radar networks, usually composed of flying unmanned aerial vehicles (UAVs), have recently attracted great interest for time-critical applications, such as searchand-rescue operations, involving reliable detection of multiple targets and situational awareness through environment radio mapping. Unfortunately, the time available for detection is often limited, and in most settings, there are no reliable models of the environment, which should be learned quickly. One possibility to guarantee short learning time is to enhance cooperation among UAVs. For example, they can share information for properly navigating the environment if they have a common goal. Alternatively, in case of multiple and different goals or tasks, they can exchange their available information to fitly assign tasks (e.g., targets) to each network agent. In this paper, we consider ad-hoc approaches for task assignment and a multiagent reinforcement learning (RL) algorithm that allow the UAVs to learn a suitable navigation policy to explore an unknown environment while maximizing the accuracy in detecting targets. The obtained results demonstrate that cooperation at different levels accelerates the learning process and brings benefits in accomplishing the team's goals.

UAV Detection Using Reinforcement Learning

“…RF-based detection is a promising approach that plays a crucial role in accurately identifying objects by analyzing the RF signals in the communication medium. UAV dynamic radar networks (DRN) and RF sensors were utilized to facilitate target detection and mapping [ 21 ]. To enable UAV agents to detect objects with the greatest degree of accuracy and to improve their map reconstruction, they developed a multi-agent RL framework.…”

“…Reinforcement learning (RL) is a subset of ML algorithms that investigates how agents should behave in a particular situation to achieve a certain goal or obtain the maximum rewards [ 19 ]. Effective traditional UAV detection approaches include radar systems [ 20 , 21 ], visual surveillance [ 22 , 23 ], radio frequency (RF) signals [ 24 , 25 , 26 ], and acoustic sensors [ 27 ]. According to [ 28 ], radio waves are used by radar systems to identify objects in the airspace.…”