# Hidden Biases of End-to-End Driving Datasets

arXiv: https://arxiv.org/abs/2412.09602 · HTML: https://mlsanity.com/paper/2412.09602/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Placed in

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

## Builds on (most cited first, 30 of 30)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer](https://mlsanity.com/paper/2207.14024/) (2022)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes](https://mlsanity.com/paper/2305.10430/) (2023)
- [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.06242/) (2023)
- [Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research](https://mlsanity.com/paper/2310.08710/) (2023)
- [DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2308.00398/) (2023)
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024)
- [PlanT: Explainable Planning Transformers via Object-Level Representations](https://mlsanity.com/paper/2210.14222/) (2022)
- [Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving](https://mlsanity.com/paper/2403.04133/) (2024)
- [Hidden Biases of End-to-End Driving Models](https://mlsanity.com/paper/2306.07957/) (2023)
- [CarLLaVA: Vision language models for camera-only closed-loop driving](https://mlsanity.com/paper/2406.10165/) (2024)
- [Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)](https://mlsanity.com/paper/2402.16720/) (2024)
- [SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic](https://mlsanity.com/paper/2403.17933/) (2024)
- [LangProp: A code optimization framework using Large Language Models applied to driving](https://mlsanity.com/paper/2401.10314/) (2024)
- [Analysis of a Modular Autonomous Driving Architecture: The Top Submission to CARLA Leaderboard 2.0 Challenge](https://mlsanity.com/paper/2405.01394/) (2024)

## Built on by (most cited first, 30 of 30)

- [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025)
- [SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment](https://mlsanity.com/paper/2503.09594/) (2025)
- [Pseudo-Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.04218/) (2025)
- [Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)](https://mlsanity.com/paper/2505.16394/) (2025)
- [Centaur: Robust End-to-End Autonomous Driving with Test-Time Training](https://mlsanity.com/paper/2503.11650/) (2025)
- [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025)
- [SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving](https://mlsanity.com/paper/2512.10719/) (2025)
- [LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving](https://mlsanity.com/paper/2512.20563/) (2025)
- [Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.09800/) (2025)
- [BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving](https://mlsanity.com/paper/2509.23589/) (2025)
- [Fail2Drive: Benchmarking Closed-Loop Driving Generalization](https://mlsanity.com/paper/2604.08535/) (2026)
- [GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.00034/) (2025)
- [DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving](https://mlsanity.com/paper/2511.17150/) (2025)
- [DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy](https://mlsanity.com/paper/2505.19516/) (2025)
- [ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models](https://mlsanity.com/paper/2506.07725/) (2025)
- [PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving](https://mlsanity.com/paper/2511.07292/) (2025)
- [Learning from Mistakes: Post-Training for Driving VLA with Takeover Data](https://mlsanity.com/paper/2603.14972/) (2026)
- [What Matters for Scalable and Robust Learning in End-to-End Driving Planners?](https://mlsanity.com/paper/2603.15185/) (2026)
- [Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving](https://mlsanity.com/paper/2604.27366/) (2026)
- [Using Ensemble Diffusion to Estimate Uncertainty for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.00560/) (2025)
- [Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces](https://mlsanity.com/paper/2603.14354/) (2026)
- [Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving](https://mlsanity.com/paper/2603.25672/) (2026)
- [DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving](https://mlsanity.com/paper/2511.20720/) (2025)
- [Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling](https://mlsanity.com/paper/2605.13646/) (2026)
- [BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving](https://mlsanity.com/paper/2606.08684/) (2026)
- [UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving](https://mlsanity.com/paper/2606.25736/) (2026)
- [RoG-DAgger: Rollout-Guided Post-Training for End-to-End Driving](https://mlsanity.com/paper/2608.24525/) (2026)
- [Data-Driven Risk Fields for Safer End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.10377/) (2026)
- [Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews](https://mlsanity.com/paper/2609.31191/) (2026)
- [When an Evaluation Rule Writes Training Labels: Measuring Human-Reference Forgiveness in NAVSIM](https://mlsanity.com/paper/2609.33189/) (2026)

## Abstract (arXiv)

End-to-end driving systems have made rapid progress, but have so far not been applied to the challenging new CARLA Leaderboard 2.0. Further, while there is a large body of literature on end-to-end architectures and training strategies, the impact of the training dataset is often overlooked. In this work, we make a first attempt at end-to-end driving for Leaderboard 2.0. Instead of investigating architectures, we systematically analyze the training dataset, leading to new insights: (1) Expert style significantly affects downstream policy performance. (2) In complex data sets, the frames should not be weighted on the basis of simplistic criteria such as class frequencies. (3) Instead, estimating whether a frame changes the target labels compared to previous frames can reduce the size of the dataset without removing important information. By incorporating these findings, our model ranks first and second respectively on the map and sensors tracks of the 2024 CARLA Challenge, and sets a new state-of-the-art on the Bench2Drive test routes. Finally, we uncover a design flaw in the current evaluation metrics and propose a modification for future challenges. Our dataset, code, and pre-trained models are publicly available at https://github.com/autonomousvision/carla_garage.