SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving

• DOI: 10.48550/arxiv.2404.06892
• Publication Date: 2024-01-01
• Authors: Zhang, Diankun; Wang, Guoan; Zhu, Runwen; Zhao, Jianbo; Chen, Xiwu; Zhang, Siyu; Gong, Jiahao; Zhou, Qibin; Zhang, Wenyuan; Wang, Ningzi; Tan, Feiyang; Zhou, Hangning; Xu, Ziyao; Yao, Haotian; Zhang, Chi; Liu, Xiaojun; Di, Xiaoguang; Li, Bin
• Keywords: FOS: Computer and information sciences; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition

End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system. Despite simplicity and clarity, the performance of end-to-end autonomous driving methods on sub-tasks is still far behind the single-task methods. Meanwhile, the widely used dense BEV features in previous end-to-end methods make it costly to extend to more modalities or tasks. In this paper, we propose a Sparse query-centric paradigm for end-to-end Autonomous Driving (SparseAD), where the sparse queries completely represent the whole driving scenario across space, time and tasks without any dense BEV representation. Concretely, we design a unified sparse architecture for perception tasks including detection, tracking, and online mapping. Moreover, we revisit motion prediction and planning, and devise a more justifiable motion planner framework. On the challenging nuScenes dataset, SparseAD achieves SOTA full-task performance among end-to-end methods and significantly narrows the performance gap between end-to-end paradigms and single-task methods. Codes will be released soon.