Pith. sign in

REVIEW 19 cited by

Generalized Trajectory Scoring for End-to-end Multimodal Planning

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 2506.06664 v1 pith:FOEICHWP submitted 2025-06-07 cs.RO cs.CV

Generalized Trajectory Scoring for End-to-end Multimodal Planning

classification cs.RO cs.CV
keywords trajectorygtrsend-to-endfine-grainedgeneralizationplanningscoringsets
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

End-to-end multi-modal planning is a promising paradigm in autonomous driving, enabling decision-making with diverse trajectory candidates. A key component is a robust trajectory scorer capable of selecting the optimal trajectory from these candidates. While recent trajectory scorers focus on scoring either large sets of static trajectories or small sets of dynamically generated ones, both approaches face significant limitations in generalization. Static vocabularies provide effective coarse discretization but struggle to make fine-grained adaptation, while dynamic proposals offer detailed precision but fail to capture broader trajectory distributions. To overcome these challenges, we propose GTRS (Generalized Trajectory Scoring), a unified framework for end-to-end multi-modal planning that combines coarse and fine-grained trajectory evaluation. GTRS consists of three complementary innovations: (1) a diffusion-based trajectory generator that produces diverse fine-grained proposals; (2) a vocabulary generalization technique that trains a scorer on super-dense trajectory sets with dropout regularization, enabling its robust inference on smaller subsets; and (3) a sensor augmentation strategy that enhances out-of-domain generalization while incorporating refinement training for critical trajectory discrimination. As the winning solution of the Navsim v2 Challenge, GTRS demonstrates superior performance even with sub-optimal sensor inputs, approaching privileged methods that rely on ground-truth perception. Code will be available at https://github.com/NVlabs/GTRS.

discussion (0)

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

Forward citations

Cited by 19 Pith papers

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

  1. Driving risk emerges from the required two-dimensional joint evasive acceleration

    cs.RO 2026-04 unverdicted novelty 7.0

    Evasive acceleration quantifies driving risk as the minimum 2D constant relative acceleration needed to avoid collision and outperforms time-to-collision on warning timing, discrimination, and information retention ac...

  2. 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.

  3. DRIFT: Drift and Aggregation for Motion Planning

    cs.RO 2026-07 conditional novelty 6.0

    DRIFT achieves 89.6 PDMS and 90.4 EPDMS on NAVSIM navtest by generating proposal features via one-step latent drift and aggregating them label-free.

  4. Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations

    cs.RO 2026-06 unverdicted novelty 6.0

    Derail adversarial perturbations hijack the scoring head in generative E2E driving planners, flipping safe to unsafe trajectory selection with 39-80% score drops and up to 50% collision rates.

  5. FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

    cs.AI 2026-06 unverdicted novelty 6.0

    FlowR2A learns reward-conditioned action distributions via flow-matching decoder to unify dense reward supervision with dynamic proposal generation for multimodal driving planning.

  6. DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    DriveJudge combines VLM reasoning with rule functions on a new 33,577-sample human-annotated dataset, outperforming EPDMS by 21.23 AUC on quality classification and DriveCritic by 6.5% on trajectory preference.

  7. Test-Time Trajectory Optimization for Autonomous Driving

    cs.RO 2026-06 unverdicted novelty 6.0

    TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.

  8. IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving

    cs.RO 2026-05 unverdicted novelty 6.0

    IDOL uses inverse dynamics on adjacent predicted latent futures to extract planning-relevant motion deltas, then optimizes trajectories with a closed-loop refinement step, reporting SOTA results on NAVSIM v1 and v2.

  9. CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning

    cs.RO 2026-05 conditional novelty 6.0

    CLOVER is a closed-loop generator-scorer framework that expands proposal coverage with pseudo-expert trajectories and performs conservative self-distillation to achieve state-of-the-art planning scores on NAVSIM and nuScenes.

  10. DriveFuture: Future-Aware Latent World Models for Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 6.0

    DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.

  11. Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation

    cs.RO 2026-01 conditional novelty 6.0

    SIDP trains a diffusion policy for visual navigation by reward-weighting its own sampled trajectories, improving success rate and cutting inference latency.

  12. SimScale: Learning to Drive via Real-World Simulation at Scale

    cs.CV 2025-11 conditional novelty 6.0

    SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning ...

  13. PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving

    cs.CV 2025-07 unverdicted novelty 6.0

    PRIX presents an efficient camera-only planner with a novel CaRT module that matches larger multimodal models on NavSim and nuScenes while reducing model size and inference time.

  14. HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving

    cs.RO 2026-04 conditional novelty 5.5

    Hierarchical diffusion plus polar structure-preserving expansion and metric-decoupled RL yields SOTA open- and closed-loop planning scores on NAVSIM and HUGSIM.

  15. PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 5.0

    PriorEye augments end-to-end driving models with a dual-memory architecture that stores and gates geospatial visual priors to improve performance and robustness to sensor corruption on NAVSIM-v2.

  16. DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 5.0

    Creates DriveReward dataset with counterfactual annotations and a 1B VLM reward model that outperforms larger VLMs on driving tasks and matches rule-based rewards in RL and trajectory scoring.

  17. CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

    cs.LG 2026-05 unverdicted novelty 5.0

    CRAFT is an on-policy RL fine-tuning framework that decomposes closed-loop policy gradients into a group-normalized counterfactual proxy plus residual correction from interaction events, achieving top closed-loop perf...

  18. RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

    cs.CV 2026-04 unverdicted novelty 5.0

    RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.

  19. CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving

    cs.RO 2026-06 unverdicted novelty 4.0

    CLEAR achieves state-of-the-art PDMS of 93.7 on NAVSIM v1 by combining single-step VAE latent drift with Qwen 3.5-guided adaptive scheduling and trajectory scoring for end-to-end driving.