Computational Design of a Low-Visibility UAV Using a Human-Aligned Perceptual Metric

2026-05-11

AI Summary

This study addresses the high visual conspicuity of drones during high-speed flight by proposing Phantom Twist, a single-rotor configuration that leverages motion blur induced by rapid rotation to reduce visual salience. For the first time in low-observability drone design, the perceptual consistency metric LPIPS is integrated into a two-stage automated design framework that jointly considers rigid-body dynamics, aerodynamic constraints, and multi-objective optimization. This approach optimizes the layout of critical components to minimize perceptual visibility while preserving flight stability and controllability. Experimental validation with a physical prototype demonstrates that the proposed design achieves significantly enhanced visual stealth compared to conventional quadrotors, without compromising flight dynamic performance.

Abstract

We introduce Phantom Twist, a type of single-propeller UAV designed to achieve low visibility through high-speed spinning and the exploitation of motion blur. We develop a two-stage automated design pipeline that optimizes the placement of functional components including batteries, control PCB, motor-propeller assembly, and counterweights. The pipeline minimizes visibility as measured by a human-aligned perceptual metric (LPIPS) while strictly satisfying inertial and aerodynamic constraints required for stable flight. We validate this approach through fabrication and flight testing of multiple prototypes. These tests confirm that our pipeline produces stable, controllable designs and that the optimized UAV exhibits significantly reduced visual perceptibility compared to conventional quadcopters.

Problem

• low-visibility UAV
• human-aligned perceptual metric
• motion blur
• visual perceptibility
• UAV design

Innovation

• low-visibility UAV
• human-aligned perceptual metric
• motion blur
• automated design pipeline
• LPIPS