Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding

• URL: http://arxiv.org/abs/2504.14526v1
• Date: Sun, 20 Apr 2025 07:50:44 GMT
• Title: Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding
• Authors: Tong Zeng, Longfeng Wu, Liang Shi, Dawei Zhou, Feng Guo,
• Abstract summary: Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering.<n>However, their effectiveness in specialized, safety-critical domains like autonomous driving remains largely unexplored.<n>We introduce DVBench, a pioneering benchmark designed to evaluate the performance of VLLMs in understanding safety-critical driving videos.
• Score: 10.242043337117005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering. However, their effectiveness in specialized, safety-critical domains like autonomous driving remains largely unexplored. Autonomous driving systems require sophisticated scene understanding in complex environments, yet existing multimodal benchmarks primarily focus on normal driving conditions, failing to adequately assess VLLMs' performance in safety-critical scenarios. To address this, we introduce DVBench, a pioneering benchmark designed to evaluate the performance of VLLMs in understanding safety-critical driving videos. Built around a hierarchical ability taxonomy that aligns with widely adopted frameworks for describing driving scenarios used in assessing highly automated driving systems, DVBench features 10,000 multiple-choice questions with human-annotated ground-truth answers, enabling a comprehensive evaluation of VLLMs' capabilities in perception and reasoning. Experiments on 14 SOTA VLLMs, ranging from 0.5B to 72B parameters, reveal significant performance gaps, with no model achieving over 40% accuracy, highlighting critical limitations in understanding complex driving scenarios. To probe adaptability, we fine-tuned selected models using domain-specific data from DVBench, achieving accuracy gains ranging from 5.24 to 10.94 percentage points, with relative improvements of up to 43.59%. This improvement underscores the necessity of targeted adaptation to bridge the gap between general-purpose VLLMs and mission-critical driving applications. DVBench establishes an essential evaluation framework and research roadmap for developing VLLMs that meet the safety and robustness requirements for real-world autonomous systems. We released the benchmark toolbox and the fine-tuned model at: https://github.com/tong-zeng/DVBench.git.

Related papers

• NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving [10.41584658117874]
  We propose NuScenes-SpatialQA, the first large-scale ground-truth-based Question-Answer (QA) benchmark designed to evaluate the spatial understanding and reasoning capabilities of Vision-Language Models (VLMs) in autonomous driving. Built upon the NuScenes dataset, the benchmark is constructed through an automated 3D scene graph generation pipeline and a QA generation pipeline. Using this benchmark, we conduct extensive experiments on diverse VLMs, including both general and spatial-enhanced models, providing the first comprehensive evaluation of their spatial capabilities in autonomous driving.
  arXiv  Detail & Related papers  (2025-04-04T04:43:10Z)
• RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving [10.984203470464687]
  Vision-language models (VLMs) often suffer from limitations such as inadequate spatial perception and hallucination.<n>We propose a retrieval-augmented decision-making (RAD) framework to enhance VLMs' capabilities to reliably generate meta-actions in autonomous driving scenes.<n>We fine-tune VLMs on a dataset derived from the NuScenes dataset to enhance their spatial perception and bird's-eye view image comprehension capabilities.
  arXiv  Detail & Related papers  (2025-03-18T03:25:57Z)
• DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding [76.3876070043663]
  We propose DriveLMM-o1, a dataset and benchmark designed to advance step-wise visual reasoning for autonomous driving.<n>Our benchmark features over 18k VQA examples in the training set and more than 4k in the test set, covering diverse questions on perception, prediction, and planning.<n>Our model achieves a +7.49% gain in final answer accuracy, along with a 3.62% improvement in reasoning score over the previous best open-source model.
  arXiv  Detail & Related papers  (2025-03-13T17:59:01Z)
• Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving [10.01820885669991]
  We propose a novel evaluation method: Safety Cognitive Driving Benchmark (SCD-Bench) To address the large-scale annotation challenge for SCD-Bench, we develop the Autonomous Driving Image-Text. System. Preliminary experimental results indicate that existing open-source models still lack sufficient safety cognition.
  arXiv  Detail & Related papers  (2025-03-09T07:53:19Z)
• CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models [1.6612510324510592]
  CurricuVLM is a novel framework that enables personalized curriculum learning for autonomous driving agents.<n>Our approach exploits Vision-Language Models (VLMs) to analyze agent behavior, identify performance weaknesses, and dynamically generate tailored training scenarios.<n>CurricuVLM outperforms state-of-the-art baselines across both regular and safety-critical scenarios.
  arXiv  Detail & Related papers  (2025-02-21T00:42:40Z)
• Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives [56.528835143531694]
  We introduce DriveBench, a benchmark dataset designed to evaluate Vision-Language Models (VLMs)<n>Our findings reveal that VLMs often generate plausible responses derived from general knowledge or textual cues rather than true visual grounding.<n>We propose refined evaluation metrics that prioritize robust visual grounding and multi-modal understanding.
  arXiv  Detail & Related papers  (2025-01-07T18:59:55Z)
• AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving [106.0319745724181]
  We introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs) We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios. Our evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats.
  arXiv  Detail & Related papers  (2024-12-19T18:59:33Z)
• AutoBench-V: Can Large Vision-Language Models Benchmark Themselves? [65.92331309449015]
  We introduce AutoBench-V, an automated framework for serving evaluation on demand, i.e., benchmarking LVLMs based on specific aspects of model capability.<n>Through an extensive evaluation of nine popular LVLMs across five demanded user inputs, the framework shows effectiveness and reliability.
  arXiv  Detail & Related papers  (2024-10-28T17:55:08Z)
• Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases [102.05741859030951]
  We propose CODA-LM, the first benchmark for the automatic evaluation of LVLMs for self-driving corner cases. We show that using the text-only large language models as judges reveals even better alignment with human preferences than the LVLM judges. Our CODA-VLM performs comparably with GPT-4V, even surpassing GPT-4V by +21.42% on the regional perception task.
  arXiv  Detail & Related papers  (2024-04-16T14:20:55Z)
• Large Language Models as Automated Aligners for benchmarking Vision-Language Models [48.4367174400306]
  Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. Existing evaluation benchmarks, primarily relying on rigid, hand-crafted datasets, face significant limitations in assessing the alignment of these increasingly anthropomorphic models with human intelligence. In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient curation, measuring the alignment betweenVLMs and human intelligence and value through automatic data curation and assessment.
  arXiv  Detail & Related papers  (2023-11-24T16:12:05Z)

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.