Pith. sign in

REVIEW 5 cited by

Hidden Biases of End-to-End Driving Datasets

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.09602 v2 pith:ACHQ2OUI submitted 2024-12-12 cs.CV cs.AIcs.LGcs.RO

Julian Zimmerlin , Jens Bei{ss}wenger , Bernhard Jaeger , Andreas Geiger , Kashyap Chitta This is my paper
classification cs.CVcs.AIcs.LGcs.RO
keywords datasetend-to-endcarladrivingtrainingarchitecturesfirstframes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

    cs.LG 2026-03 conditional novelty 7.0 of 10

    DeLL combines DPMM dual knowledge spaces with front-door causal adjustment and a non-autoregressive evolutionary decoder to reduce catastrophic forgetting and spurious correlations in lifelong end-to-end autonomous driving.

  2. SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving

    cs.CV 2025-12 conditional novelty 6.0 of 10

    SpaceDrive replaces textual coordinate tokens with shared 3D positional encodings in a VLM driving planner, achieving state-of-the-art open-loop planning on nuScenes and 78.02 Driving Score on Bench2Drive.

  3. Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving

    cs.RO 2025-06 reject novelty 6.0 of 10

    R2SE refines pretrained end-to-end driving policies on hard cases via residual LoRA reinforcement learning and switches between specialist and generalist policies using GPD-based uncertainty.

  4. ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    An asynchronous dual-system architecture forecasts large-model features into the current frame and adds a small-model update to drive in near real time, scoring 69.53 on Bench2Drive at 50 ms.

  5. DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy

    cs.RO 2025-05 conditional novelty 6.0 of 10

    DiffE2E reports state-of-the-art closed-loop driving scores in CARLA and NAVSIM by combining a diffusion trajectory decoder with explicit supervision in a single Transformer decoder.

Pith tools