Learning Lane Graphs from Aerial Imagery Using Transformers
This addresses the need for robust topological maps in autonomous driving, though it is an incremental application of existing transformer techniques to a new data source.
The paper tackles the problem of generating detailed lane graphs from aerial imagery for autonomous vehicles, introducing a transformer-based method that achieves accurate results on the UrbanLaneGraph dataset.
The robust and safe operation of automated vehicles underscores the critical need for detailed and accurate topological maps. At the heart of this requirement is the construction of lane graphs, which provide essential information on lane connectivity, vital for navigating complex urban environments autonomously. While transformer-based models have been effective in creating map topologies from vehicle-mounted sensor data, their potential for generating such graphs from aerial imagery remains untapped. This work introduces a novel approach to generating successor lane graphs from aerial imagery, utilizing the advanced capabilities of transformer models. We frame successor lane graphs as a collection of maximal length paths and predict them using a Detection Transformer (DETR) architecture. We demonstrate the efficacy of our method through extensive experiments on the diverse and large-scale UrbanLaneGraph dataset, illustrating its accuracy in generating successor lane graphs and highlighting its potential for enhancing autonomous vehicle navigation in complex environments.