Pith. sign in

REVIEW 10 cited by

Reinforced Refinement with Self-Aware Expansion for 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 2506.09800 v1 pith:ENOVKCSF submitted 2025-06-11 cs.RO

classification cs.RO
keywords drivinglearningcasesexpansionhardrefinementwhileautonomous
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

End-to-end autonomous driving has emerged as a promising paradigm for directly mapping sensor inputs to planning maneuvers using learning-based modular integrations. However, existing imitation learning (IL)-based models suffer from generalization to hard cases, and a lack of corrective feedback loop under post-deployment. While reinforcement learning (RL) offers a potential solution to tackle hard cases with optimality, it is often hindered by overfitting to specific driving cases, resulting in catastrophic forgetting of generalizable knowledge and sample inefficiency. To overcome these challenges, we propose Reinforced Refinement with Self-aware Expansion (R2SE), a novel learning pipeline that constantly refines hard domain while keeping generalizable driving policy for model-agnostic end-to-end driving systems. Through reinforcement fine-tuning and policy expansion that facilitates continuous improvement, R2SE features three key components: 1) Generalist Pretraining with hard-case allocation trains a generalist imitation learning (IL) driving system while dynamically identifying failure-prone cases for targeted refinement; 2) Residual Reinforced Specialist Fine-tuning optimizes residual corrections using reinforcement learning (RL) to improve performance in hard case domain while preserving global driving knowledge; 3) Self-aware Adapter Expansion dynamically integrates specialist policies back into the generalist model, enhancing continuous performance improvement. Experimental results in closed-loop simulation and real-world datasets demonstrate improvements in generalization, safety, and long-horizon policy robustness over state-of-the-art E2E systems, highlighting the effectiveness of reinforce refinement for scalable autonomous driving.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

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

    cs.CV 2025-06 unverdicted novelty 7.0 of 10

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

  2. MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    MAPLE proposes latent multi-agent rollouts with supervised fine-tuning followed by reinforcement learning using safety, progress, interaction, and diversity rewards to enable scalable closed-loop training for end-to-e...

  3. MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    MAPLE performs closed-loop multi-agent training of VLA driving models entirely in latent space using supervised fine-tuning followed by RL with safety, progress, and diversity rewards, reaching SOTA on Bench2Drive.

  4. Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    E² uses transport-regularized sparse control on learned reverse-time SDEs with topology-driven selection and Topological Anchoring to generate realistic adversarial scenarios, improving collision discovery by 9.01% on...

  5. 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.

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

    cs.CV 2025-12 conditional novelty 6.0 of 10

    SpaceDrive integrates 3D positional encodings derived from depth and ego-states into VLMs, replacing digit tokens to improve spatial reasoning and trajectory regression in autonomous driving.

  7. Optimization-Guided Diffusion for Interactive Scene Generation

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    OMEGA guides diffusion sampling with per-step constrained optimization and game-theoretic adversarial modeling to generate physically valid and interactive driving scenes, raising valid scene ratios from 32% to 72% an...

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

    cs.CV 2025-11 conditional novelty 6.0 of 10

    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 ...

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

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

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

  10. MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

    cs.CV 2025-12 conditional novelty 5.0 of 10

    An autonomous-driving vision-language model that uses online RL over discrete language actions, with a separate action expert mapping decisions to trajectories, reports DS 78.04 and SR 55.09% on Bench2Drive.

Pith tools