MambaMap: Online Vectorized HD Map Construction using State Space Model

TL;DR

MambaMap is an efficient online framework that constructs high-definition vectorized maps for autonomous driving by fusing long-range temporal data using a state space model with innovative memory and scanning strategies.

Contribution

It introduces a novel state space model with a memory bank and gating mechanism for efficient long-range temporal feature fusion in HD map construction.

Findings

Outperforms state-of-the-art methods on nuScenes and Argoverse2 datasets.

Achieves higher accuracy and robustness in map prediction.

Ensures robust temporal consistency in dynamic driving environments.

Abstract

High-definition (HD) maps are essential for autonomous driving, as they provide precise road information for downstream tasks. Recent advances highlight the potential of temporal modeling in addressing challenges like occlusions and extended perception range. However, existing methods either fail to fully exploit temporal information or incur substantial computational overhead in handling extended sequences. To tackle these challenges, we propose MambaMap, a novel framework that efficiently fuses long-range temporal features in the state space to construct online vectorized HD maps. Specifically, MambaMap incorporates a memory bank to store and utilize information from historical frames, dynamically updating BEV features and instance queries to improve robustness against noise and occlusions. Moreover, we introduce a gating mechanism in the state space, selectively integrating dependencies of map elements in high computational efficiency. In addition, we design innovative multi-directional and spatial-temporal scanning strategies to enhance feature extraction at both BEV and instance levels. These strategies significantly boost the prediction accuracy of our approach while ensuring robust temporal consistency. Extensive experiments on the nuScenes and Argoverse2 datasets demonstrate that our proposed MambaMap approach outperforms state-of-the-art methods across various splits and perception ranges. Source code will be available at https://github.com/ZiziAmy/MambaMap.