arXiv：cs.LG（机器学习，全量分类）· Kartik B. Kapse·· 15 小时前AI 评分29
端到端学习 vs. 模块化架构：自动驾驶系统对比洞察
End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems
AI 导读
一篇 arXiv 综述对比了自动驾驶的两大设计范式：端到端学习将原始传感器输入直接映射到驾驶执行器，简洁且适应动态环境，但缺乏透明度、高度依赖大数据集；模块化架构按感知、认知、规划、控制分管道，可解释性和任务优化更强，却面临集成复杂与扩展难题。
正文
Abstract:Autonomous driving systems have become a central focus of intelligent transportation research, with End-to-End Learning and Modular Architectures offering two prominent design paradigms for their implementation. E2E Learning uses deep learning algorithms to map raw sensory inputs directly to driving actuators, providing a streamlined and adaptable solution. while Modular Architectures employ a pipeline-based approach, dividing the system into distinct subsystems for perception, cognition, planning, and control. This paper presents a comprehensive comparative analysis of these paradigms, focusing on their strengths, limitations, and trade-offs to provide insights into their suitability for various autonomous driving applications. The study evaluates key factors such as interpretability, scalability, robustness, and real-world applicability. While End-to-End Learning emphasizes simplicity and adaptability in dynamic environments, it lacks transparency and is highly dependent on large datasets. Conversely, Modular Architectures offer superior interpretability and task-specific optimization, but face challenges related to integration complexity and scalability. To address these limitations, hybrid approaches that combine the strengths of both paradigms have emerged, offering a promising direction for overcoming these challenges. Beyond this comparative synthesis, following work proposes a Four-Dimensional Architecture Selection Framework, comprising twelve binary criteria across safety, operating environment, data/computational resources, and deployment context, and validate it against ten published autonomous driving systems, correctly recommending 7/10 deployed architectures. This work synthesizes existing literature to highlight key trade-offs between the paradigms and identifies hybrid architectures as a promising direction for future research.
| Comments: | 27 pages, 7 figures, 4 tables |
| Subjects: | Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01746 [cs.RO] |
| (or arXiv:2610.01746v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01746 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kartik Balasaheb Kapse [view email]
[v1]
Thu, 1 Oct 2026 14:15:06 UTC (1,414 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org