Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving

TL;DR

This paper introduces SMERF, a lightweight map-prior-based model that enhances lane-topology prediction for autonomous driving by integrating structured road metadata and design manual priors, improving detection and association accuracy.

Contribution

The paper presents a novel approach combining natural language encoded road conventions with map data to improve lane-topology prediction in complex environments.

Findings

Improved lane and traffic element detection accuracy.

Enhanced generalization to diverse topologies and conditions.

Effective integration of structured road metadata and priors.

Abstract

Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this information often follows conventions encoded in natural language, through design codes that reflect the road structure and road names that capture the road functionality. We augment this information in a lightweight manner to SMERF, a map-prior-based online lane-topology prediction model, by combining structured road metadata from OSM maps and lane-width priors from Road design manuals with the road centerline encodings. We evaluate our method on two geo-diverse complex intersection scenarios. Our method shows improvement in both lane and traffic element detection and their association. We report results using four topology-aware metrics to comprehensively assess the model performance. These results demonstrate the ability of our approach to generalize and scale to diverse topologies and conditions.