End-to-end autonomous driving: Challenges and frontiers

L Chen, P Wu, K Chitta, B Jaeger… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …

Maptrv2: An end-to-end framework for online vectorized hd map construction

B Liao, S Chen, Y Zhang, B Jiang, Q Zhang… - International Journal of …, 2024 - Springer
High-definition (HD) map provides abundant and precise static environmental information of
the driving scene, serving as a fundamental and indispensable component for planning in …

Sledge: Synthesizing driving environments with generative models and rule-based traffic

K Chitta, D Dauner, A Geiger - European Conference on Computer Vision, 2025 - Springer
SLEDGE is the first generative simulator for vehicle motion planning trained on real-world
driving logs. Its core component is a learned model that is able to generate agent bounding …

Fully sparse 3d occupancy prediction

H Liu, Y Chen, H Wang, Z Yang, T Li, J Zeng… - … on Computer Vision, 2025 - Springer
Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically
construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering high …

Enhancing vectorized map perception with historical rasterized maps

X Zhang, G Liu, Z Liu, N Xu, Y Liu, J Zhao - European Conference on …, 2025 - Springer
In autonomous driving, there is growing interest in end-to-end online vectorized map
perception in bird's-eye-view (BEV) space, with an expectation that it could replace …

Lanemapnet: Lane network recognization and hd map construction using curve region aware temporal bird's-eye-view perception

T Zhu, J Leng, J Zhong, Z Zhang… - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
The construction of local HD (High Definition) Map and Lane Network with onboard sensors
is critical for autonomous vechicles and facilitates downstream tasks. In contrast to previous …

Topomaskv2: Enhanced instance-mask-based formulation for the road topology problem

M Kalfaoglu, HI Ozturk, O Kilinc, A Temizel - arXiv preprint arXiv …, 2024 - arxiv.org
Recently, the centerline has become a popular representation of lanes due to its advantages
in solving the road topology problem. To enhance centerline prediction, we have developed …

Priormapnet: Enhancing online vectorized hd map construction with priors

R Wang, X Lu, X Liu, X Zou, T Cao, Y Li - arXiv preprint arXiv:2408.08802, 2024 - arxiv.org
Online vectorized High-Definition (HD) map construction is crucial for subsequent prediction
and planning tasks in autonomous driving. Following MapTR paradigm, recent works have …

LaneCMKT: Boosting Monocular 3D Lane Detection with Cross-Modal Knowledge Transfer

R Zhao, H Wang, W Cai - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
Detecting 3D lane lines from monocular images is garnering increasing attention in the
Autonomous Driving (AD) area due to its cost-effective edge. However, current monocular …

Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression

S Huang, Z Shen, Z Huang, Y Liao… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
In this paper, we focus on the challenging task of monocular 3D lane detection. Previous
methods typically adopt inverse perspective mapping (IPM) to transform the Front-Viewed …