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

• URL: http://arxiv.org/abs/2606.08525v2
• Date: Sun, 14 Jun 2026 07:32:19 GMT
• Title: DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving
• Abstract summary: Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving.<n>While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored.<n>We bridge this gap by introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance.
• Score: 17.749010844640388
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation.

Related papers

• DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving [8.267228986831894]
  DriveVer is a lightweight, plug-and-play Test-Time Verifier to enable autonomous driving systems to validate and refine trajectories without costly and heavy training.<n>We show that DriveVer significantly improves the performance of base planning models. Notably, as an extremely compact model with only 34M parameters, DriveVer introduces minimal computational overhead, achieving competitive results.
  arXiv  Detail & Related papers  (2026-07-01T03:50:45Z)
• Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving [79.71689985927625]
  We propose IRR-Drive, an adaptive multimodal reflection framework for autonomous driving.<n>IRR-Drive explicitly models anticipated scene evolution, enabling the model to rigorously self-correct and refine its initial intent.<n>Our method achieves state-of-the-art performance on the benchmark in both PDMS and NAVSIMS.
  arXiv  Detail & Related papers  (2026-06-22T06:53:58Z)
• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine [73.74077186298523]
  CoReVLA is a continual learning framework for autonomous driving.<n>It improves the performance in long-tail scenarios through a dual-stage process of data Collection and behavior Refinement.<n>CoReVLA achieves a Driving Score (DS) of 72.18 and a Success Rate (SR) of 50%, outperforming state-of-the-art methods by 7.96 DS and 15% SR under long-tail, safety-critical scenarios.
  arXiv  Detail & Related papers  (2025-09-19T13:25:56Z)
• AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving [37.260140808367716]
  We propose AutoDrive-R$2$, a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems.<n>We first propose an innovative CoT dataset named nuScenesR$2$-6K for supervised fine-tuning.<n>We then employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework to ensure reliable smoothness and realistic trajectory planning.
  arXiv  Detail & Related papers  (2025-09-02T04:32:24Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model [0.0]
  In this paper, we propose InDRiVE (Intrinsic Disagreement based Reinforcement for Vehicle Exploration) as a model-based Reinforcement Learning framework.<n>By training an ensemble of world models, the agent actively explores high uncertainty regions of environments without task specific feedback.<n> Experimental results in both seen and unseen environments demonstrate that InDRiVE achieves higher success rates and fewer infractions compared to DreamerV2 and DreamerV3 baselines.
  arXiv  Detail & Related papers  (2025-03-07T16:56:00Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• LORD: Large Models based Opposite Reward Design for Autonomous Driving [11.717821043996352]
  We introduce LORD, a novel large models based opposite reward design through undesired linguistic goals. Our proposed framework shows its efficiency in leveraging the power of large pretrained models for achieving safe and enhanced autonomous driving.
  arXiv  Detail & Related papers  (2024-03-27T19:30:06Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving [16.654299927694716]
  We reformulate the learning-to-drive task as obstacle-aware perception and grounding, distribution-aware goal prediction, and model-based planning. Under the CARLA simulator, we report state-of-the-art results on the CARNOVEL benchmark.
  arXiv  Detail & Related papers  (2022-12-16T21:51:51Z)
• Model-based versus Model-free Deep Reinforcement Learning for Autonomous Racing Cars [46.64253693115981]
  This paper investigates how model-based deep reinforcement learning agents generalize to real-world autonomous-vehicle control-tasks. We show that model-based agents capable of learning in imagination, substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization.
  arXiv  Detail & Related papers  (2021-03-08T17:15:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.