Inferring Driving Maps by Deep Learning-based Trail Map Extraction

2025-05-15

AI Summary

To address temporal inconsistency, sensor occlusion, poor real-time performance, and limited generalizability in online mapping for autonomous driving, this paper proposes a novel offline high-definition (HD) map construction paradigm leveraging multi-vehicle driver trajectories. For the first time, unstructured trajectories are treated as core semantic cues; a trajectory-aware Transformer architecture is designed to jointly encode ego- and surround-vehicle trajectories, enabling sensor-agnostic, globally consistent map generation. The method supports offline incremental updates, achieving high accuracy and deployment efficiency while significantly improving generalizability. Evaluated on two benchmark datasets, it outperforms state-of-the-art online mapping approaches—demonstrating superior robustness to unseen scenarios and heterogeneous sensor configurations—and enables lightweight map distribution.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

High-definition (HD) maps offer extensive and accurate environmental information about the driving scene, making them a crucial and essential element for planning within autonomous driving systems. To avoid extensive efforts from manual labeling, methods for automating the map creation have emerged. Recent trends have moved from offline mapping to online mapping, ensuring availability and actuality of the utilized maps. While the performance has increased in recent years, online mapping still faces challenges regarding temporal consistency, sensor occlusion, runtime, and generalization. We propose a novel offline mapping approach that integrates trails - informal routes used by drivers - into the map creation process. Our method aggregates trail data from the ego vehicle and other traffic participants to construct a comprehensive global map using transformer-based deep learning models. Unlike traditional offline mapping, our approach enables continuous updates while remaining sensor-agnostic, facilitating efficient data transfer. Our method demonstrates superior performance compared to state-of-the-art online mapping approaches, achieving improved generalization to previously unseen environments and sensor configurations. We validate our approach on two benchmark datasets, highlighting its robustness and applicability in autonomous driving systems.

Problem

• Automating HD map creation to reduce manual labeling efforts
• Addressing challenges in online mapping like temporal consistency and occlusion
• Integrating trail data for comprehensive and continuously updatable offline maps

Innovation

• Uses transformer-based deep learning models
• Integrates trail data from multiple vehicles
• Enables continuous updates and sensor-agnostic