LARD 2.0: Enhanced Datasets and Benchmarking for Autonomous Landing Systems
Incremental improvement to dataset and benchmarking for autonomous landing systems, addressing dataset diversity and evaluation gaps.
This paper enhances the LARD dataset for autonomous landing systems by adding new data sources (BingMap, Flight Simulator) and refining the operational design domain, then benchmarks object detection models, providing open-source baselines.
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.