电子学报2025，Vol.53Issue(7)：2418-2427,10.DOI:10.12263/DZXB.20241022
基于时空注意力Transformer的自动驾驶运动规划方法
A Motion Planning Method for Autonomous Driving Based on Spatiotemporal Attention Transformer
摘要
Abstract
The static and dynamic agents,road structures,and interactions among various elements in driving scenari-os are typically complex and rapidly change across time and space.Consequently,motion prediction for autonomous vehi-cles remains a challenging task,especially with the open problem of efficiently representing and integrating multi-modal scene information,including road conditions,various agent states,and historical interaction information.Current approach-es often rely on independently designed modules to process each modality in parallel.However,this approach tends to result in limited system flexibility,challenging adjustments,and,frequently,high computational redundancy,which reduces over-all system efficiency.Furthermore,decoding the spatiotemporal information from autonomous driving scenarios to generate safe driving commands is inherently challenging.This paper proposes an autonomous driving motion planning method based on a spatiotemporal attention Transformer,comprising a phased multi-modal scene encoder and a spatiotemporal fu-sion decoder.This model progressively constructs a multi-modal scene representation and predicts the future safe trajectory of the autonomous vehicle under spatiotemporal fusion.The proposed approach establishes a new baseline on the large-scale nuScenes autonomous driving dataset,achieving competitive results.关键词
自动驾驶运动预测/分阶段多模态编码器/时空融合解码器/Transformer/全新基线Key words
autonomous driving motion prediction/phased multimodal encoder/spatiotemporal fusion decoder/transformer/new baseline分类
信息技术与安全科学引用本文复制引用
袁丁,李源,孟羽倩,张弘,杨一帆..基于时空注意力Transformer的自动驾驶运动规划方法[J].电子学报,2025,53(7):2418-2427,10.基金项目
国家自然科学基金(No.62002005,No.61972015) National Natural Science Foundation of China(No.62002005,No.61972015) （No.62002005,No.61972015）
