Pith. sign in

REVIEW 11 cited by

Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning

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 2506.18234 v1 pith:POBTUW75 submitted 2025-06-23 cs.CV cs.RO

classification cs.CVcs.RO
keywords planningdrive-r1reasoningvlmsmotionautonomousbridgingdirection
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large vision-language models (VLMs) for autonomous driving (AD) are evolving beyond perception and cognition tasks toward motion planning. However, we identify two critical challenges in this direction: (1) VLMs tend to learn shortcuts by relying heavily on history input information, achieving seemingly strong planning results without genuinely understanding the visual inputs; and (2) the chain-ofthought (COT) reasoning processes are always misaligned with the motion planning outcomes, and how to effectively leverage the complex reasoning capability to enhance planning remains largely underexplored. In this paper, we start from a small-scale domain-specific VLM and propose Drive-R1 designed to bridges the scenario reasoning and motion planning for AD. Drive-R1 first undergoes the supervised finetuning on a elaborate dataset containing both long and short COT data. Drive-R1 is encouraged to reason step-by-step from visual input to final planning decisions. Subsequently, Drive-R1 is trained within a reinforcement learning framework that incentivizes the discovery of reasoning paths that are more informative for planning, guided by rewards based on predicted trajectories and meta actions. Experimental evaluations on the nuScenes and DriveLM-nuScenes benchmarks demonstrate that Drive-R1 achieves superior performance compared to existing state-of-the-art VLMs. We believe that Drive-R1 presents a promising direction for bridging reasoning and planning in AD, offering methodological insights for future research and applications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

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

  1. S-GRPO: Unified Post-Training for Large Vision-Language Models

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    S-GRPO unifies SFT and RL for LVLMs via conditional ground-truth injection that supplies a maximal-reward anchor when group exploration fails completely.

  2. Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving

    cs.RO 2026-03 unverdicted novelty 7.0 of 10

    PaIR-Drive runs IL and RL in parallel branches with a tree-structured sampler to reach 91.2 PDMS and 87.9 EPDMS on NAVSIM benchmarks while outperforming sequential RL fine-tuning and correcting some human errors.

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

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  4. Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A learned critic of observation grounding and stepwise coherence, used as dense RL reward, improves VLA planner faithfulness and OOD hazard responsiveness while preserving competitive trajectory accuracy.

  5. Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    The paper fine-tunes Qwen3.5-4B as a driving VLA using serialized decision traces from rule-based planners, reporting reduced ADE and miss rate on a simulator benchmark with camera inputs.

  6. Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    A structured perturbation framework applied to VLA driving models reveals evaluation-dependent visual grounding patterns and uneven dependency across abstraction levels.

  7. Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    Sim2Real-AD enables zero-shot transfer of CARLA-trained VLM-guided RL policies to full-scale vehicles, reporting 75-90% success rates in car-following, obstacle avoidance, and stop-sign scenarios without real-world RL...

  8. Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

    cs.RO 2025-10 conditional novelty 6.0 of 10

    Alpamayo-R1 introduces a VLA model with a Chain of Causation dataset and multi-stage SFT-plus-RL training that reports 12% better planning accuracy and 35% fewer close encounters versus trajectory-only baselines in dr...

  9. DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving

    cs.CV 2026-03 unverdicted novelty 5.0 of 10

    DynFlowDrive models action-conditioned scene transitions via rectified flow in latent space and adds stability-aware trajectory selection, showing gains on nuScenes and NavSim without added inference cost.

  10. S-GRPO: Unified Post-Training for Large Vision-Language Models

    cs.LG 2026-04 conditional novelty 4.0 of 10

    Injecting a max-reward ground-truth answer into a GRPO group whenever all sampled responses fail prevents optimization collapse and matches full fine-tuning's domain scores on three benchmark tasks.

  11. A Survey of Reinforcement Learning for Large Reasoning Models

    cs.CL 2025-09 accept novelty 3.0 of 10

    A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.

Pith tools