Lane topology, which is usually modeled by a centerline
graph, is essential for high-level autonomous driving. For a high-quality
graph, both topology connectivity and spatial continuity of centerline
segments are critical. However, most of existing approaches pay more
attention to connectivity while neglect the continuity. Such kind of cen-
terline graph usually cause problem to planning of autonomous driving.
To overcome this problem, we present an end-to-end network, CGNet,
with three key modules: 1) Junction Aware Query Enhancement module,
which provides positional prior to accurately predict junction points; 2)
Bézier Space Connection module, which enforces continuity constraints
on any two topologically connected segments in a Bézier space; 3) It-
erative Topology Refinement module, which is a graph-based network
with memory to iteratively refine the predicted topological connectivity.
CGNet achieves state-of-the-art performance on both nuScenes and Ar-
goverse2 datasets
Motivation
Top: A toy example which illustrates the centerline graph and the impact of overlooking the continuity. Bottom: Comparison with MapTR and TopoNet. They predicts inaccurate position of junction points and wrong topology, all leading to the discontinuous path. Our CGNet obtain the continuous path.
Qualitative results
Qualitative comparisons under different weather and lighting conditions on nuScenes. CGNet predicts more accurate position of junction points and correct topology, leading to a more continuous and smooth path.
CGNet
The official implementation of the ECCV 2024 paper: Continuity Preserving Online CenterLine Graph Learning
Abstract
Lane topology, which is usually modeled by a centerline graph, is essential for high-level autonomous driving. For a high-quality graph, both topology connectivity and spatial continuity of centerline segments are critical. However, most of existing approaches pay more attention to connectivity while neglect the continuity. Such kind of cen- terline graph usually cause problem to planning of autonomous driving. To overcome this problem, we present an end-to-end network, CGNet, with three key modules: 1) Junction Aware Query Enhancement module, which provides positional prior to accurately predict junction points; 2) Bézier Space Connection module, which enforces continuity constraints on any two topologically connected segments in a Bézier space; 3) It- erative Topology Refinement module, which is a graph-based network with memory to iteratively refine the predicted topological connectivity. CGNet achieves state-of-the-art performance on both nuScenes and Ar- goverse2 datasets
Motivation
Top: A toy example which illustrates the centerline graph and the impact of overlooking the continuity. Bottom: Comparison with MapTR and TopoNet. They predicts inaccurate position of junction points and wrong topology, all leading to the discontinuous path. Our CGNet obtain the continuous path.
Qualitative results
Usage
Download
Download the pretrained models using these link: pretrained_models.
Installation
Prepare nuScenes data
Train, Test and Visualize
Citation
If you find this work useful for your research, please cite:
Acknowledgements
We would like to thank MapTR, STSU, LaneGNN, OpenLane-V2, TopoNet, VectorMapNet for their great codes!