Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racing

TL;DR

This paper presents a lightweight neural network with continual learning for robust gate detection in autonomous drone racing under dynamic lighting conditions, enhancing perception resilience during high-speed flights.

Contribution

It introduces a novel perception technique combining continual learning with a lightweight neural network for reliable gate detection amidst illumination changes.

Findings

Demonstrates robustness of the method under variable lighting conditions

Shows improved detection accuracy in challenging scenarios

Validates effectiveness through comprehensive testing

Abstract

In autonomous and mobile robotics, a principal challenge is resilient real-time environmental perception, particularly in situations characterized by unknown and dynamic elements, as exemplified in the context of autonomous drone racing. This study introduces a perception technique for detecting drone racing gates under illumination variations, which is common during high-speed drone flights. The proposed technique relies upon a lightweight neural network backbone augmented with capabilities for continual learning. The envisaged approach amalgamates predictions of the gates' positional coordinates, distance, and orientation, encapsulating them into a cohesive pose tuple. A comprehensive number of tests serve to underscore the efficacy of this approach in confronting diverse and challenging scenarios, specifically those involving variable lighting conditions. The proposed methodology exhibits notable robustness in the face of illumination variations, thereby substantiating its effectiveness.