{"slug": "drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models", "title": "DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models", "summary": "Researchers introduced DriveJudge, a driving evaluation agent that combines rule-grounded evaluation with Vision-Language Model (VLM) reasoning to assess autonomous driving in a context-aware and interpretable manner. DriveJudge outperforms existing metrics like EPDMS and DriveCritic on driving quality classification and trajectory preference selection tasks, setting a new standard for driving evaluation.", "body_md": "arXiv:2606.17362v1 Announce Type: new\nAbstract: Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical grounding. To evaluate driving in a manner that is both interpretable and context-aware, we introduce DriveJudge. DriveJudge is a driving evaluation agent that combines rule-grounded evaluation with Vision-Language Model (VLM) reasoning and selectively invokes physically-grounded deterministic rule functions after interpreting the environmental context. To train and evaluate DriveJudge, we curate a large-scale dataset of 33,577 challenging driving samples with human annotations on whether the driving behavior is reasonable in the given scenario. With this dataset, we address the underexplored problem of driving metric evaluation, and introduce two human-aligned benchmark tasks: Driving Quality Classification and Trajectory Preference Selection. DriveJudge outperforms EPDMS for driving quality classification by 21.23 AUC, and the recent VLM-based DriveCritic for trajectory preference selection by 6.5%, setting a new standard for interpretable and precise driving evaluation.", "url": "https://wpnews.pro/news/drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models", "canonical_source": "https://arxiv.org/abs/2606.17362", "published_at": "2026-06-17 04:00:00+00:00", "updated_at": "2026-06-17 04:26:06.204155+00:00", "lang": "en", "topics": ["autonomous-vehicles", "computer-vision", "natural-language-processing", "ai-research", "ai-products"], "entities": ["DriveJudge", "EPDMS", "DriveCritic", "Vision-Language Model", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models", "markdown": "https://wpnews.pro/news/drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models.md", "text": "https://wpnews.pro/news/drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models.txt", "jsonld": "https://wpnews.pro/news/drivejudge-rethinking-autonomous-driving-evaluation-with-vision-language-models.jsonld"}}