Pith. sign in

REVIEW 27 cited by

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

Not yet reviewed by Pith; the record is open.

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 2503.07656 v2 pith:L4IGSFN2 submitted 2025-03-07 cs.LG cs.CVcs.RO

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

classification cs.LG cs.CVcs.RO
keywords taskautonomousdrivetransformerdrivinge2e-adqueriessystembenchmark
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

End-to-end autonomous driving (E2E-AD) has emerged as a trend in the field of autonomous driving, promising a data-driven, scalable approach to system design. However, existing E2E-AD methods usually adopt the sequential paradigm of perception-prediction-planning, which leads to cumulative errors and training instability. The manual ordering of tasks also limits the system`s ability to leverage synergies between tasks (for example, planning-aware perception and game-theoretic interactive prediction and planning). Moreover, the dense BEV representation adopted by existing methods brings computational challenges for long-range perception and long-term temporal fusion. To address these challenges, we present DriveTransformer, a simplified E2E-AD framework for the ease of scaling up, characterized by three key features: Task Parallelism (All agent, map, and planning queries direct interact with each other at each block), Sparse Representation (Task queries direct interact with raw sensor features), and Streaming Processing (Task queries are stored and passed as history information). As a result, the new framework is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention, which significantly reduces the complexity of system and leads to better training stability. DriveTransformer achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 27 Pith papers

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

  1. Decaying Turbulence and the Riemann Hypothesis: The number theory behind the infinite-time singularity

    hep-th 2026-04 unverdicted novelty 8.0

    Freely decaying incompressible turbulence possesses a universal Euler-ensemble attractor whose continuum Mellin spectrum is controlled by the non-trivial zeros of the Riemann zeta function, producing an infinite-time ...

  2. Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving

    cs.RO 2026-04 unverdicted novelty 7.0

    The SNG framework and SNG-VLA model enable end-to-end driving systems to better incorporate global navigation for state-of-the-art route following without auxiliary perception losses.

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

    cs.LG 2026-03 conditional novelty 7.0

    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.

  4. ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

    cs.CV 2025-06 unverdicted novelty 7.0

    ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks.

  5. Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving

    cs.CV 2026-07 conditional novelty 6.0

    LCS steers a VLA driving model's latent features toward command-specific centroids to improve command following at roughly half the inference cost of two-pass CFG.

  6. MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

    cs.CV 2026-07 conditional novelty 6.0

    Block-wise Modal Joint Attention over image, LiDAR, and diffusion action tokens yields 88.9 PDMS / 88.4 EPDMS on NAVSIM without anchors or auxiliary supervision.

  7. GeoWorldAD: Geometry World Action Model for Autonomous Driving

    cs.RO 2026-07 conditional novelty 6.0

    Grounding an autonomous-driving action model in ego-aligned multi-scale 3D geometry and latent future-geometry tokens improves NAVSIM closed-loop PDMS/EPDMS over prior geometry- and world-model-based planners.

  8. BeyondSight: Object Permanence for End-to-End Autonomous Driving

    cs.RO 2026-07 conditional novelty 6.0

    A sparse-query end-to-end driving model that maintains persistent actor hypotheses across full occlusions, plus a nuScenes extension that supervises and evaluates unobservable actors, cuts planning L2 error and raises...

  9. AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning

    cs.RO 2026-07 conditional novelty 6.0

    Trajectory-pattern anchors bridge VLA reasoning and continuous residual flow, yielding 77.28% success rate on Bench2Drive closed-loop driving.

  10. UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 6.0

    UniTeD unifies perception and planning in autonomous driving via shared temporal diffusion with TTM and ARS modules, reporting SOTA results on benchmarks.

  11. VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 6.0

    VLGA introduces geometry as a fourth modality in VLA models via pointmap regression loss, reporting SOTA open-loop and closed-loop driving metrics on nuScenes and Bench2Drive.

  12. CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 6.0

    CLAP reduces planning error on challenging driving scenarios by 24% on NAVSIM using contrastive latent-space prompt optimization on frozen VLA models with no regression on normal frames.

  13. OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models

    cs.CV 2026-04 unverdicted novelty 6.0

    OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.

  14. LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving

    cs.CV 2026-04 unverdicted novelty 6.0

    LMGenDrive unifies LLM-based multimodal understanding with generative world models to output both future driving videos and control signals for end-to-end closed-loop autonomous driving.

  15. Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models

    cs.CV 2026-04 unverdicted novelty 6.0

    Orion-Lite uses latent feature distillation and trajectory supervision to create a vision-only model that surpasses its LLM-based teacher on closed-loop Bench2Drive evaluation, achieving a new SOTA driving score of 80.6.

  16. Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving

    cs.CV 2026-02 conditional novelty 6.0

    Person2Drive adds a 50-driver closed-loop CARLA dataset, MMDSS/KL style metrics, and a head-only fine-tuning method that shifts an end-to-end driving policy toward a target driver's style.

  17. Driving Like Yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving

    cs.CV 2026-02 unverdicted novelty 6.0

    Person2Drive is a new benchmark that generates personalized driving datasets via simulation, quantifies styles with MMD and KL metrics, and adapts E2E-AD models using a style reward framework.

  18. AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

    cs.RO 2026-01 conditional novelty 6.0

    Conditioning speed planning on the predicted path and relabeling synthetic cut-ins yields SOTA Bench2Drive scores (DS 89.07, SR 73.18%).

  19. AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

    cs.RO 2026-01 unverdicted novelty 6.0

    A cascaded end-to-end driving model conditions longitudinal planning on the lateral path via anchor-based regression and path-conditioned 1D displacement prediction, achieving SOTA driving score of 89.07 and 73.18% su...

  20. CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving

    cs.RO 2026-07 conditional novelty 5.5

    Residual waypoint RL around a frozen VLA prior, scaled via heterogeneous CARLA/H100 infrastructure, raises closed-loop driving score and success rate on longest6 v2 and Bench2Drive.

  21. Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

    cs.RO 2026-05 unverdicted novelty 5.0

    CaAD adds ego-centric joint-causal modeling and causality-aware policy alignment to end-to-end driving, reporting Driving Score 87.53 and Success Rate 71.81 on Bench2Drive plus PDMS 91.1 on NAVSIM.

  22. Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

    cs.RO 2026-05 unverdicted novelty 5.0

    CaAD adds ego-centric joint-causal modeling and causality-aware policy alignment to end-to-end driving, reporting Driving Score 87.53 and PDMS 91.1 on Bench2Drive and NAVSIM.

  23. Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation

    cs.AI 2026-05 unverdicted novelty 5.0

    Redesigning Alpamayo 1 to single-reasoning and optimizing diffusion action generation cuts inference latency by 69.23% while preserving trajectory diversity and prediction quality.

  24. UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving

    cs.CV 2026-01 conditional novelty 5.0

    A unified VLM for autonomous driving that couples trajectory planning with future-frame image generation improves open- and closed-loop planning metrics on Bench2Drive and nuScenes.

  25. DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving

    cs.CV 2025-07 unverdicted novelty 5.0

    DIVER uses RL-guided diffusion to produce diverse feasible trajectories from one ground-truth path, addressing mode collapse in imitation learning for autonomous driving.

  26. Do Open-Loop Metrics Predict Closed-Loop Driving? A Cross-Benchmark Correlation Study of NAVSIM and Bench2Drive

    cs.RO 2026-04 conditional novelty 4.0

    Cross-benchmark analysis of 8 methods shows NAVSIM PDM Score correlates with Bench2Drive Driving Score at Spearman ρ=0.90, with Ego Progress as the strongest single predictor and a simpler 3-metric formula matching th...

  27. Decaying Turbulence and the Riemann Hypothesis: The number theory behind the infinite-time singularity

    hep-th 2026-04 unverdicted novelty 3.0

    Decaying turbulence converges to an Euler ensemble attractor whose statistics are governed by an arithmetic structure from the Farey sequence of coprime fractions.