AssistTaxi: A Comprehensive Dataset for Taxiway Analysis and Autonomous Operations
Parth Ganeriwala, Siddhartha Bhattacharyya, Sean Gunther, Brian Kish, Mohammed Abdul Hafeez Khan, Ankur Dhadoti, Natasha Neogi
TL;DR
AssistTaxi addresses the lack of real-world taxiway/runway data for autonomous aviation by introducing a large-scale dataset collected from MLB and X59, comprising approximately 350k frames with coordinate annotations for taxiway and runway scenes. It documents a contour-based labeling approach to annotate taxiway markings, including steps from manual contouring to edge detection, line detection, curve fitting, and pixel-level annotation. The dataset enables benchmarking and safety validation for autonomous taxiing systems, while recognizing that the labeling process is currently manual and would benefit from automation and broader environmental diversity. Future work aims to expand data collection and explore transfer learning to generalize labeling and perception models across more scenarios and conditions.
Abstract
The availability of high-quality datasets play a crucial role in advancing research and development especially, for safety critical and autonomous systems. In this paper, we present AssistTaxi, a comprehensive novel dataset which is a collection of images for runway and taxiway analysis. The dataset comprises of more than 300,000 frames of diverse and carefully collected data, gathered from Melbourne (MLB) and Grant-Valkaria (X59) general aviation airports. The importance of AssistTaxi lies in its potential to advance autonomous operations, enabling researchers and developers to train and evaluate algorithms for efficient and safe taxiing. Researchers can utilize AssistTaxi to benchmark their algorithms, assess performance, and explore novel approaches for runway and taxiway analysis. Addition-ally, the dataset serves as a valuable resource for validating and enhancing existing algorithms, facilitating innovation in autonomous operations for aviation. We also propose an initial approach to label the dataset using a contour based detection and line extraction technique.