Watch from sky: machine-learning-based multi-UAV network for predictive police surveillance

TL;DR

This paper introduces a multi-UAV network framework utilizing machine learning for predictive police surveillance, emphasizing UAV roles in sensing, data handling, and crime prediction to enhance crime deterrence.

Contribution

It proposes a novel multi-UAV framework with ML-based control and dispatching, validated through simulation of UAV dispatching using reinforcement learning.

Findings

Effective UAV dispatching via reinforcement learning

Improved data collection and distribution for surveillance

Potential for enhanced crime deterrence

Abstract

This paper presents the watch-from-sky framework, where multiple unmanned aerial vehicles (UAVs) play four roles, i.e., sensing, data forwarding, computing, and patrolling, for predictive police surveillance. Our framework is promising for crime deterrence because UAVs are useful for collecting and distributing data and have high mobility. Our framework relies on machine learning (ML) technology for controlling and dispatching UAVs and predicting crimes. This paper compares the conceptual model of our framework against the literature. It also reports a simulation of UAV dispatching using reinforcement learning and distributed ML inference over a lossy UAV network.