Pith. sign in

REVIEW 19 cited by

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

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 2405.19620 v2 pith:C3A3ASST submitted 2024-05-30 cs.CV

Wenchao Sun , Xuewu Lin , Yining Shi , Chuang Zhang , Haoran Wu , Sifa Zheng This is my paper · ORCID
classification cs.CV
keywords planningsparsesparsedrivedesigndrivingend-to-endautonomousmodule
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end paradigms unify multi-tasks into a fully differentiable framework, allowing for optimization in a planning-oriented spirit. Despite the great potential of end-to-end paradigms, both the performance and efficiency of existing methods are not satisfactory, particularly in terms of planning safety. We attribute this to the computationally expensive BEV (bird's eye view) features and the straightforward design for prediction and planning. To this end, we explore the sparse representation and review the task design for end-to-end autonomous driving, proposing a new paradigm named SparseDrive. Concretely, SparseDrive consists of a symmetric sparse perception module and a parallel motion planner. The sparse perception module unifies detection, tracking and online mapping with a symmetric model architecture, learning a fully sparse representation of the driving scene. For motion prediction and planning, we review the great similarity between these two tasks, leading to a parallel design for motion planner. Based on this parallel design, which models planning as a multi-modal problem, we propose a hierarchical planning selection strategy , which incorporates a collision-aware rescore module, to select a rational and safe trajectory as the final planning output. With such effective designs, SparseDrive surpasses previous state-of-the-arts by a large margin in performance of all tasks, while achieving much higher training and inference efficiency. Code will be avaliable at https://github.com/swc-17/SparseDrive for facilitating future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 19 Pith papers

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

  1. Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

    cs.AI 2026-08 conditional novelty 7.0 of 10

    Hiding future trajectory information until after a driving model forms its decision reduces rationalization and improves verifiable autonomous-driving reasoning in the proposed AD-MCQ and DEFT-RLVR framework.

  2. PRISM: Privileged Probabilistic Latent Supervision for End-to-End Autonomous Driving Motion Planning

    cs.RO 2026-08 reject novelty 6.0 of 10

    PRISM regularizes intermediate planning latents with a CVAE-style ELBO objective using ground-truth future paths, claiming an 8% L2 planning error reduction over deterministic baselines on nuScenes.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

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

    cs.RO 2026-01 unverdicted novelty 6.0 of 10

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

  5. IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model

    cs.AI 2025-08 conditional novelty 6.0 of 10

    IRL-VLA fine-tunes a vision-language-action driving policy with PPO against a learned reward world model trained on NAVSIM's EPDMS metrics, reaching 74.9 EPDMS on navhard-real.

  6. DriveCamSim: Generalizable Camera Simulation via Explicit Camera Modeling for Autonomous Driving

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DriveCamSim uses explicit 3D-aware attention to generate multi-view driving video under new camera parameters and frame rates, trained on 2Hz nuScenes data.

  7. 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.

  8. iPad: Iterative Proposal-centric End-to-End Autonomous Driving

    cs.CV 2025-05 conditional novelty 6.0 of 10

    iPad achieves top NAVSIM and Bench2Drive driving scores by iteratively refining sparse candidate trajectories with proposal-anchored attention over camera images.

  9. DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model

    cs.RO 2025-08 conditional novelty 5.0 of 10

    A distillation framework with a ground-truth-annotation teacher, RL status optimization, and generative distribution interaction improves end-to-end planning collisions and closed-loop scores.

  10. GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GEMINUS reports state-of-the-art closed-loop driving scores on Bench2Drive with a monocular camera by routing each situation to either a global expert or a scene-specialized expert based on scenario confidence.

  11. ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

    cs.RO 2025-07 conditional novelty 5.0 of 10

    ReAL-AD combines VLM-generated strategy and tactical commands with a two-stage trajectory decoder, cutting open-loop L2 error and collision rate by about a third on nuScenes and Bench2Drive.

  12. World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

    cs.CV 2025-07 conditional novelty 5.0 of 10

    World4Drive couples multiple driving intentions with a latent world model to generate, score, and select trajectories, reporting state-of-the-art perception-free planning on nuScenes and NavSim.

  13. RoCA: Robust Cross-Domain End-to-End Autonomous Driving

    cs.CV 2025-06 conditional novelty 5.0 of 10

    RoCA, a Gaussian-process codebook over ego and agent tokens, improves cross-domain generalization and adaptation of end-to-end autonomous driving models without extra inference cost.

  14. CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Driving

    cs.RO 2025-05 conditional novelty 5.0 of 10

    CogAD reports state-of-the-art open-loop and closed-loop planning results by combining hierarchical scene-to-instance perception with intent-to-trajectory planning and dual-level uncertainty.

  15. SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving

    cs.CV 2025-05 conditional novelty 5.0 of 10

    SOLVE couples a vision-language model and an end-to-end planner via a shared encoder and a trajectory chain-of-thought, reporting small but state-of-the-art open-loop planning gains on nuScenes.

  16. Challenger: Affordable Adversarial Driving Video Generation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A framework for automatic generation of photorealistic adversarial driving videos, shown to sharply increase collision rates of end-to-end autonomous driving models.

  17. A Survey on Vision-Language-Action Models for Autonomous Driving

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A survey organizes vision-language-action models for autonomous driving into four stages, compares over 20 systems, and catalogs datasets, benchmarks, and open challenges.

  18. DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving

    cs.AI 2025-05 conditional novelty 4.0 of 10

    DiffVLA integrates VLM guidance, hybrid sparse-dense BEV perception, and a truncated diffusion policy to achieve 45.0 PDMS on the NAVSIM v2 benchmark.

  19. Generative AI for Autonomous Driving: A Review

    cs.CV 2025-05 conditional novelty 2.0 of 10

    A review of generative models (VAEs, GANs, diffusion, transformers, LLMs) applied to map generation, scenario generation, trajectory prediction, and motion planning for autonomous driving.

Pith tools