Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data

TL;DR

This paper presents an automated, scalable method for learning traffic light to lane assignments using motion data and statistical analysis, reducing reliance on manual HD map provisioning.

Contribution

It introduces a novel approach that derives traffic light-lane mappings from motion patterns, including a rejection method with safety considerations and a dataset transformation tool.

Findings

Effective pattern-based assignment detection

Rejection method with statistical hypothesis testing

Public API for Lyft Level 5 dataset

Abstract

Understanding which traffic light controls which lane is crucial to navigate intersections safely. Autonomous vehicles commonly rely on High Definition (HD) maps that contain information about the assignment of traffic lights to lanes. The manual provisioning of this information is tedious, expensive, and not scalable. To remedy these issues, our novel approach derives the assignments from traffic light states and the corresponding motion patterns of vehicle traffic. This works in an automated way and independently of the geometric arrangement. We show the effectiveness of basic statistical approaches for this task by implementing and evaluating a pattern-based contribution method. In addition, our novel rejection method includes accompanying safety considerations by leveraging statistical hypothesis testing. Finally, we propose a dataset transformation to re-purpose available motion prediction datasets for semantic map learning. Our publicly available API for the Lyft Level 5 dataset enables researchers to develop and evaluate their own approaches.