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

TL;DR

SparseAD introduces a sparse, query-centric framework for end-to-end autonomous driving, replacing dense BEV features, leading to improved multi-task performance and better scalability across perception, prediction, and planning tasks.

Contribution

It proposes a unified sparse architecture for perception, motion prediction, and planning, significantly enhancing end-to-end autonomous driving performance over dense methods.

Findings

Achieves state-of-the-art full-task performance on nuScenes

Reduces the performance gap between end-to-end and single-task methods

Demonstrates efficiency and scalability of sparse query-centric paradigm

Abstract

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.