MAP: End-to-End Autonomous Driving with Map-Assisted Planning

2025-09-17

AI Summary

Existing end-to-end autonomous driving methods underutilize online semantic maps, limiting trajectory planning accuracy and safety. This paper proposes MAP, the first framework to deeply fuse online map features with ego-vehicle state for end-to-end trainable trajectory planning. Its core contributions are: (1) a Map Enhancement Module enabling robust segmentation feature extraction and online spatial mapping; (2) an Ego-Guided Planning Module incorporating state-aware attention; and (3) a State-Based Dynamic Weight Adapter explicitly modeling the heterogeneous contribution of map information to planning. Evaluated on DAIR-V2X-seq-SPD, MAP reduces L2 error by 16.6%, decreases yaw rate by 56.2%, and achieves a 44.5% overall performance gain. It also ranks first in the CVPR 2025 Autonomous Driving Challenge, outperforming the runner-up by 39.5%.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

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

In recent years, end-to-end autonomous driving has attracted increasing attention for its ability to jointly model perception, prediction, and planning within a unified framework. However, most existing approaches underutilize the online mapping module, leaving its potential to enhance trajectory planning largely untapped. This paper proposes MAP (Map-Assisted Planning), a novel map-assisted end-to-end trajectory planning framework. MAP explicitly integrates segmentation-based map features and the current ego status through a Plan-enhancing Online Mapping module, an Ego-status-guided Planning module, and a Weight Adapter based on current ego status. Experiments conducted on the DAIR-V2X-seq-SPD dataset demonstrate that the proposed method achieves a 16.6% reduction in L2 displacement error, a 56.2% reduction in off-road rate, and a 44.5% improvement in overall score compared to the UniV2X baseline, even without post-processing. Furthermore, it achieves top ranking in Track 2 of the End-to-End Autonomous Driving through V2X Cooperation Challenge of MEIS Workshop @CVPR2025, outperforming the second-best model by 39.5% in terms of overall score. These results highlight the effectiveness of explicitly leveraging semantic map features in planning and suggest new directions for improving structure design in end-to-end autonomous driving systems. Our code is available at https://gitee.com/kymkym/map.git

Problem

• Integrates map features for trajectory planning
• Reduces displacement and off-road errors
• Enhances end-to-end autonomous driving performance

Innovation

• Map-assisted end-to-end trajectory planning framework
• Plan-enhancing Online Mapping module integration
• Ego-status-guided Planning with Weight Adapter