# End-to-end system architecture

Area: [End-to-end autonomous driving](https://mlsanity.com/driving/index.md). HTML: https://mlsanity.com/driving/end-to-end-system-architecture/

## Key facts

- End-to-end system architecture: 282 papers on arXiv since 2021 (data through 14 Oct 2026).
- 95 of its 282 mapped papers (34%) cite “TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving” (2022, arXiv 2205.15997).
- 68 of its 282 mapped papers (24%) cite “End-to-end Autonomous Driving: Challenges and Frontiers” (2023, arXiv 2306.16927).
- 18 new papers 17 Sep–14 Oct.

## Most cited here

- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022), cited by 95 papers here
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023), cited by 68 papers here
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022), cited by 64 papers here
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024), cited by 62 papers here
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022), cited by 61 papers here
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021), cited by 60 papers here
- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023), cited by 57 papers here
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024), cited by 54 papers here
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024), cited by 53 papers here
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021), cited by 47 papers here

## New (17 Sep–14 Oct)

- [AutoAgent0: An Agentic Runtime for Safe Closed-Loop Driving](https://mlsanity.com/paper/2610.18866/) (2026-10-13)
- [Beyond Planning: Differentiable Control-in-the-loop End-to-End Autonomous Driving](https://mlsanity.com/paper/2610.18167/) (2026-10-13)
- [A Hardware-Partitioned micro-ROS Mini-Vehicle for Operator-Supervised Neural Driving](https://mlsanity.com/paper/2610.15966/) (2026-10-11)
- [FPD-Drive: Future Policy Distillation for End-to-End Autonomous Driving](https://mlsanity.com/paper/2610.13232/) (2026-10-09)
- [SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving](https://mlsanity.com/paper/2610.11583/) (2026-10-08)
- [Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?](https://mlsanity.com/paper/2610.09695/) (2026-10-07)
- [Odyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation Routes](https://mlsanity.com/paper/2610.06469/) (2026-10-05)
- [Autoware in Construction: Gap Analysis and LiDAR Perception Toward Off-Road Autonomous Driving](https://mlsanity.com/paper/2610.04187/) (2026-10-03)
- [Towards Safer Autonomous Driving in an Open World: A Dual-Process Approach](https://mlsanity.com/paper/2610.04088/) (2026-10-02)
- [End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems](https://mlsanity.com/paper/2610.01746/) (2026-10-01)
- [A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform](https://mlsanity.com/paper/2610.00926/) (2026-10-01)
- [When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Driving](https://mlsanity.com/paper/2609.34440/) (2026-09-28)
- [Auditing Latent-Space Monitors for Autonomous Driving](https://mlsanity.com/paper/2609.30557/) (2026-09-24)
- [S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.29813/) (2026-09-24)
- [FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving](https://mlsanity.com/paper/2609.23488/) (2026-09-20)
- [Planning-Aligned Pretraining of BEV Representations with Sparse Action-Conditioned Targets for End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.22868/) (2026-09-19)
- [Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.21486/) (2026-09-18)
- [Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.21470/) (2026-09-18)