Driving · 2026-10-02

A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform

Chengkai Xu, Yiming Cui, Jiaqi Liu, Yicheng Guo, Cheng Qin, Geyuan Zhang, Xinwei Dong, Shiyu Fang, Peng Hang, Jian Sun

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

The authors survey end-to-end autonomous driving training as a “Data-Strategy-Platform” ecosystem. They argue performance depends on (1) data coverage/value and governance, (2) strategies aligning optimization with driving objectives, and (3) platforms enabling scalable, reproducible training and continuous evolution. They review recent advances in data, learning paradigms, and training infrastructure, then outline a vision emphasizing data value, foundation-driven generalization, and integrated training-testing loops.

Why it matters

This survey frames E2E-AD progress as a system-level training problem: data determines what interactions the policy learns, strategy determines how learning aligns with long-horizon safety objectives, and platform determines scalability and lifecycle management. The paper’s taxonomy and cross-layer view are intended to unify how training design choices jointly shape performance, robustness, and deployability.

Method

Propose a Data-Strategy-Platform taxonomy for E2E-AD training: data layer (scenario coverage/governance), strategy layer (learning paradigms), and platform layer (scalability and lifecycle).
Survey recent advances across data-centric pipelines, learning paradigms (IL/RL and generative approaches such as diffusion/MLLM/world models), and training infrastructures, analyzing cross-layer interplay.
Discuss limitations and a forward-looking vision emphasizing shift from data quantity to data value, from isolated optimization to foundation-driven generalization, and from static training to integrated training-testing loops.

Abstract (from arXiv)

Autonomous driving is a cornerstone technology for the future of intelligent transportation, where end-to-end learning has emerged as a transformative paradigm that directly maps multimodal sensory inputs to driving actions through unified differentiable models. While offering advantages, the effectiveness of end-to-end autonomous driving (E2E-AD) is ultimately determined by the quality of its training ecosystem. This paper provides a comprehensive review of training methods and ecosystem for E2E-AD. We introduce a Data-Strategy-Platform taxonomy that conceptualizes training as an interdependent system. The data layer defines what can be learned, the strategy layer governs how learning aligns with driving objectives, and the platform layer supports scalability and continuous evolution. Within this framework, we survey recent advances across data-centric pipelines, learning paradigms, and training infrastructures, and analyze their interplay in shaping model performance, robustness, and deployability. Finally, we reflect on current limitations and articulate a forward-looking vision that emphasizes a shift from data quantity to data value, from isolated optimization to foundation-driven generalization, and from static training to integrated training-testing loops, aiming toward robust, scalable, and trustworthy autonomous driving systems. We maintain a continuously updated repository tracking cutting-edge literature and works at \href{https://github.com/Jiaaqiliu/Awesome-Training-Ecosystem-for-E2E-AD}{Our Project Page}.

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2026-10-01 · Indexed by Pub-AI: 2026-10-02 UTC

preprint