LARD 2.0: Enhanced Datasets and Benchmarking for Autonomous Landing Systems

TL;DR

This paper improves datasets and benchmarking methods for autonomous landing systems by expanding data sources, refining operational scenarios, and providing open-source evaluation frameworks.

Contribution

It introduces enhanced datasets with diverse sources, refined operational scenarios, and a benchmarking framework with open-source models for autonomous landing.

Findings

Expanded dataset sources including BingMap and Flight Simulator.

Refined operational scenarios to include multi-runway airports.

Provided baseline models and evaluation framework for object detection.

Abstract

This paper addresses key challenges in the development of autonomous landing systems, focusing on dataset limitations for supervised training of Machine Learning (ML) models for object detection. Our main contributions include: (1) Enhancing dataset diversity, by advocating for the inclusion of new sources such as BingMap aerial images and Flight Simulator, to widen the generation scope of an existing dataset generator used to produce the dataset LARD; (2) Refining the Operational Design Domain (ODD), addressing issues like unrealistic landing scenarios and expanding coverage to multi-runway airports; (3) Benchmarking ML models for autonomous landing systems, introducing a framework for evaluating object detection subtask in a complex multi-instances setting, and providing associated open-source models as a baseline for AI models' performance.