TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness

Anh Nguyen Trong, Gia-Bao Phan, Minh Tri Huynh, Duc Dung Nguyen
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:638-653, 2025.

Abstract

High-Definition (HD) maps are essential for both Advanced Driver-Assistance Systems (ADAS) and autonomous driving. However, offline HD map construction remains costly and challenging to maintain due to the dynamic nature of real-world environments. Consequently, online HD map generation using onboard sensors has become a key area of research. Despite recent advancements, existing deep learning-based methods often provide inaccurate output even using computationally heavy architectures, limiting their practicality for real-world applications. We introduce TLSD, an efficient end-to-end neural network that generates HD maps, incorporating both topological and geometric road information. To enhance both accuracy and efficiency, we introduce four key innovations: (1) an iterative refinement scheme within the decoder to progressively improve map predictions, (2) a group-wise one-to-many assignment strategy that accelerates training convergence, (3) a graph neural network (GNN) module that integrates lane segment coordinates for improved spatial reasoning, and (4) a distance-aware topological post-processing method that enhances the quality of connectivity outputs. We performed extensive experiments % on the widely used OpenLane-V2 benchmark and showed that TLSD achieves a significant improvement in OLUS score compared to existing methods, setting a new state-of-the-art benchmark, producing accurate HDMaps, and a connectivity graph. In particular, TLSD outperforms previous methods on the lane segment perception task (+3.13 in OLUS) and the lane centerline perception task (+3.20 in OLS), demonstrating superior performance in lane-based HD map generation. In addition, we introduce an efficient version, eTLSD, which incorporates a lightweight ResNet-18 backbone and still achieves competitive results, outperforming previous ResNet-50-based methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-trong25a, title = {TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness}, author = {Trong, Anh Nguyen and Phan, Gia-Bao and Huynh, Minh Tri and Nguyen, Duc Dung}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {638--653}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/trong25a/trong25a.pdf}, url = {https://proceedings.mlr.press/v304/trong25a.html}, abstract = {High-Definition (HD) maps are essential for both Advanced Driver-Assistance Systems (ADAS) and autonomous driving. However, offline HD map construction remains costly and challenging to maintain due to the dynamic nature of real-world environments. Consequently, online HD map generation using onboard sensors has become a key area of research. Despite recent advancements, existing deep learning-based methods often provide inaccurate output even using computationally heavy architectures, limiting their practicality for real-world applications. We introduce TLSD, an efficient end-to-end neural network that generates HD maps, incorporating both topological and geometric road information. To enhance both accuracy and efficiency, we introduce four key innovations: (1) an iterative refinement scheme within the decoder to progressively improve map predictions, (2) a group-wise one-to-many assignment strategy that accelerates training convergence, (3) a graph neural network (GNN) module that integrates lane segment coordinates for improved spatial reasoning, and (4) a distance-aware topological post-processing method that enhances the quality of connectivity outputs. We performed extensive experiments % on the widely used OpenLane-V2 benchmark and showed that TLSD achieves a significant improvement in OLUS score compared to existing methods, setting a new state-of-the-art benchmark, producing accurate HDMaps, and a connectivity graph. In particular, TLSD outperforms previous methods on the lane segment perception task (+3.13 in OLUS) and the lane centerline perception task (+3.20 in OLS), demonstrating superior performance in lane-based HD map generation. In addition, we introduce an efficient version, eTLSD, which incorporates a lightweight ResNet-18 backbone and still achieves competitive results, outperforming previous ResNet-50-based methods.} }
Endnote
%0 Conference Paper %T TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness %A Anh Nguyen Trong %A Gia-Bao Phan %A Minh Tri Huynh %A Duc Dung Nguyen %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-trong25a %I PMLR %P 638--653 %U https://proceedings.mlr.press/v304/trong25a.html %V 304 %X High-Definition (HD) maps are essential for both Advanced Driver-Assistance Systems (ADAS) and autonomous driving. However, offline HD map construction remains costly and challenging to maintain due to the dynamic nature of real-world environments. Consequently, online HD map generation using onboard sensors has become a key area of research. Despite recent advancements, existing deep learning-based methods often provide inaccurate output even using computationally heavy architectures, limiting their practicality for real-world applications. We introduce TLSD, an efficient end-to-end neural network that generates HD maps, incorporating both topological and geometric road information. To enhance both accuracy and efficiency, we introduce four key innovations: (1) an iterative refinement scheme within the decoder to progressively improve map predictions, (2) a group-wise one-to-many assignment strategy that accelerates training convergence, (3) a graph neural network (GNN) module that integrates lane segment coordinates for improved spatial reasoning, and (4) a distance-aware topological post-processing method that enhances the quality of connectivity outputs. We performed extensive experiments % on the widely used OpenLane-V2 benchmark and showed that TLSD achieves a significant improvement in OLUS score compared to existing methods, setting a new state-of-the-art benchmark, producing accurate HDMaps, and a connectivity graph. In particular, TLSD outperforms previous methods on the lane segment perception task (+3.13 in OLUS) and the lane centerline perception task (+3.20 in OLS), demonstrating superior performance in lane-based HD map generation. In addition, we introduce an efficient version, eTLSD, which incorporates a lightweight ResNet-18 backbone and still achieves competitive results, outperforming previous ResNet-50-based methods.
APA
Trong, A.N., Phan, G., Huynh, M.T. & Nguyen, D.D.. (2025). TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:638-653 Available from https://proceedings.mlr.press/v304/trong25a.html.

Related Material