Survey explains training methods for end-to-end autonomous driving
A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform
RoboticsComputer Vision and Pattern RecognitionMachine Learning
Summary
Autonomous cars need to learn how to drive by processing many types of sensors and deciding what to do. The authors survey how training these car-driving AI systems depends on three key parts: the data used, the training strategies, and the computing platforms. They explain how these parts work together to affect how well the self-driving system performs, stays reliable, and can be improved over time. They also point out current challenges and suggest future directions towards safer and more adaptable autonomous cars.
What this means in practice
- •For autonomous vehicle developers: Use the reviewed training ecosystem insights to improve the effectiveness and robustness of AI driving models through better data, strategies, and infrastructure choices.
- •For robotic system integrators: Adapt training frameworks that coordinate data, learning methods, and computing platforms to build more scalable and maintainable autonomous systems.
A survey. It maps existing work.
Authors
Chengkai Xu, Yiming Cui, Jiaqi Liu, Yicheng Guo, Cheng Qin, Geyuan Zhang, Xinwei Dong, Shiyu Fang, Peng Hang, Jian Sun
Abstract
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}.