The University of Southampton
University of Southampton Institutional Repository

MapDiffusion: generative diffusion for vectorized online HD map construction and uncertainty estimation in autonomous driving

MapDiffusion: generative diffusion for vectorized online HD map construction and uncertainty estimation in autonomous driving
MapDiffusion: generative diffusion for vectorized online HD map construction and uncertainty estimation in autonomous driving
Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird’s Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from the latent BEV grid. However, traditional map construction models provide deterministic point estimates, failing to capture uncertainty and the inherent ambiguities of real-world environments, such as occlusions and missing lane markings. We propose MapDiffusion, a novel generative approach that leverages the diffusion paradigm to learn the full distribution of possible vectorized maps. Instead of predicting a single deterministic output from learned queries, MapDiffusion iteratively refines randomly initialized queries, conditioned on a BEV latent grid, to generate multiple plausible map samples. This allows aggregating samples to improve prediction accuracy and deriving uncertainty estimates that directly correlate with scene ambiguity. Extensive experiments on the nu Scenes dataset demonstrate that MapDiffusion achieves state-of-the-art performance in online map construction, surpassing the baseline by 5% in single-sample performance. We further show that aggregating multiple samples consistently improves performance along the ROC curve, validating the benefit of distribution modeling. Additionally, our uncertainty estimates are significantly higher in occluded areas, reinforcing their value in identifying regions with ambiguous sensor input. By modeling the full map distribution, MapDiffusion enhances the robustness and reliability of online vectorized HD map construction, enabling uncertainty-aware decision-making for autonomous vehicles in complex environments.
Monninger, Thomas
4b9da19d-b0db-44fa-81df-85cfa01bb716
Zhang, Zihan
26d6216a-8a66-4f2a-a76d-fe2326d4a8fc
Mo, Zhipeng
f6ae9cfd-8ac7-4a81-be2b-63a2f8f87c16
Anwar, Md Zafar
6757b332-586c-4dce-9ff2-f740e38a681b
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Ding, Sihao
9418f5ac-b2f1-4ad9-9cd0-fa7190279ceb
Monninger, Thomas
4b9da19d-b0db-44fa-81df-85cfa01bb716
Zhang, Zihan
26d6216a-8a66-4f2a-a76d-fe2326d4a8fc
Mo, Zhipeng
f6ae9cfd-8ac7-4a81-be2b-63a2f8f87c16
Anwar, Md Zafar
6757b332-586c-4dce-9ff2-f740e38a681b
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Ding, Sihao
9418f5ac-b2f1-4ad9-9cd0-fa7190279ceb

Monninger, Thomas, Zhang, Zihan, Mo, Zhipeng, Anwar, Md Zafar, Staab, Steffen and Ding, Sihao (2025) MapDiffusion: generative diffusion for vectorized online HD map construction and uncertainty estimation in autonomous driving. 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, , Hangzhou, China. 19 - 25 Oct 2025. 8 pp . (In Press)

Record type: Conference or Workshop Item (Paper)

Abstract

Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird’s Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from the latent BEV grid. However, traditional map construction models provide deterministic point estimates, failing to capture uncertainty and the inherent ambiguities of real-world environments, such as occlusions and missing lane markings. We propose MapDiffusion, a novel generative approach that leverages the diffusion paradigm to learn the full distribution of possible vectorized maps. Instead of predicting a single deterministic output from learned queries, MapDiffusion iteratively refines randomly initialized queries, conditioned on a BEV latent grid, to generate multiple plausible map samples. This allows aggregating samples to improve prediction accuracy and deriving uncertainty estimates that directly correlate with scene ambiguity. Extensive experiments on the nu Scenes dataset demonstrate that MapDiffusion achieves state-of-the-art performance in online map construction, surpassing the baseline by 5% in single-sample performance. We further show that aggregating multiple samples consistently improves performance along the ROC curve, validating the benefit of distribution modeling. Additionally, our uncertainty estimates are significantly higher in occluded areas, reinforcing their value in identifying regions with ambiguous sensor input. By modeling the full map distribution, MapDiffusion enhances the robustness and reliability of online vectorized HD map construction, enabling uncertainty-aware decision-making for autonomous vehicles in complex environments.

Text
IROS25_2166_FI - Accepted Manuscript
Download (1MB)

More information

Accepted/In Press date: 30 June 2025
Venue - Dates: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, , Hangzhou, China, 2025-10-19 - 2025-10-25

Identifiers

Local EPrints ID: 503989
URI: http://eprints.soton.ac.uk/id/eprint/503989
PURE UUID: fa9f4cdb-613b-4786-8c84-dd95214ca740
ORCID for Steffen Staab: ORCID iD orcid.org/0000-0002-0780-4154

Catalogue record

Date deposited: 21 Aug 2025 05:15
Last modified: 22 Aug 2025 02:13

Export record

Contributors

Author: Thomas Monninger
Author: Zihan Zhang
Author: Zhipeng Mo
Author: Md Zafar Anwar
Author: Steffen Staab ORCID iD
Author: Sihao Ding

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×