SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations

TL;DR

This paper introduces SemVecNet, a modular pipeline that improves the generalization of vector map generation across various sensor configurations in autonomous driving, reducing retraining costs and enhancing adaptability.

Contribution

The paper presents a novel modular pipeline utilizing probabilistic semantic mapping and a BEV semantic map to enhance generalization to different sensor setups.

Findings

Significantly better generalization on unseen sensor configurations.

Outperforms state-of-the-art methods in diverse datasets.

Robust vector map generation with fewer retraining requirements.

Abstract

Vector maps are essential in autonomous driving for tasks like localization and planning, yet their creation and maintenance are notably costly. While recent advances in online vector map generation for autonomous vehicles are promising, current models lack adaptability to different sensor configurations. They tend to overfit to specific sensor poses, leading to decreased performance and higher retraining costs. This limitation hampers their practical use in real-world applications. In response to this challenge, we propose a modular pipeline for vector map generation with improved generalization to sensor configurations. The pipeline leverages probabilistic semantic mapping to generate a bird's-eye-view (BEV) semantic map as an intermediate representation. This intermediate representation is then converted to a vector map using the MapTRv2 decoder. By adopting a BEV semantic map robust to different sensor configurations, our proposed approach significantly improves the generalization performance. We evaluate the model on datasets with sensor configurations not used during training. Our evaluation sets includes larger public datasets, and smaller scale private data collected on our platform. Our model generalizes significantly better than the state-of-the-art methods.