Improving Online Lane Graph Extraction by Object-Lane Clustering

TL;DR

This paper introduces a novel architecture that enhances online lane graph extraction accuracy by leveraging 3D object detection outputs and object-lane clustering, leading to significant improvements over existing methods.

Contribution

The paper proposes a new learning framework that directly supervises the relationship between objects and lane centerlines using clustering, compatible with any 3D detection method.

Findings

Substantial improvement over state-of-the-art lane graph estimation methods.

Effective use of existing 3D object detection outputs for better lane understanding.

Flexible approach compatible with various detection algorithms.

Abstract

Autonomous driving requires accurate local scene understanding information. To this end, autonomous agents deploy object detection and online BEV lane graph extraction methods as a part of their perception stack. In this work, we propose an architecture and loss formulation to improve the accuracy of local lane graph estimates by using 3D object detection outputs. The proposed method learns to assign the objects to centerlines by considering the centerlines as cluster centers and the objects as data points to be assigned a probability distribution over the cluster centers. This training scheme ensures direct supervision on the relationship between lanes and objects, thus leading to better performance. The proposed method improves lane graph estimation substantially over state-of-the-art methods. The extensive ablations show that our method can achieve significant performance improvements by using the outputs of existing 3D object detection methods. Since our method uses the detection outputs rather than detection method intermediate representations, a single model of our method can use any detection method at test time.