Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving

• URL: http://arxiv.org/abs/2503.06497v1
• Date: Sun, 09 Mar 2025 07:53:19 GMT
• Title: Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving
• Authors: Enming Zhang, Peizhe Gong, Xingyuan Dai, Yisheng Lv, Qinghai Miao,
• Abstract summary: We propose a novel evaluation method: Safety Cognitive Driving Benchmark (SCD-Bench)<n>To address the large-scale annotation challenge for SCD-Bench, we develop the Autonomous Driving Image-Text.<n>System.<n>Preliminary experimental results indicate that existing open-source models still lack sufficient safety cognition.
• Score: 10.01820885669991
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Assessing the safety of vision-language models (VLMs) in autonomous driving is particularly important; however, existing work mainly focuses on traditional benchmark evaluations. As interactive components within autonomous driving systems, VLMs must maintain strong safety cognition during interactions. From this perspective, 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 Annotation System (ADA) . Additionally, to ensure data quality in SCD-Bench, our dataset undergoes manual refinement by experts with professional knowledge in autonomous driving. We further develop an automated evaluation method based on large language models (LLMs). To verify its effectiveness, we compare its evaluation results with those of expert human evaluations, achieving a consistency rate of 99.74%. Preliminary experimental results indicate that existing open-source models still lack sufficient safety cognition, showing a significant gap compared to GPT-4o. Notably, lightweight models (1B-4B) demonstrate minimal safety cognition. However, since lightweight models are crucial for autonomous driving systems, this presents a significant challenge for integrating VLMs into the field.

Related papers

• Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding [10.242043337117005]
  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. We introduce DVBench, a pioneering benchmark designed to evaluate the performance of VLLMs in understanding safety-critical driving videos.
  arXiv  Detail & Related papers  (2025-04-20T07:50:44Z)
• Uncertainty-Aware Hybrid Machine Learning in Virtual Sensors for Vehicle Sideslip Angle Estimation [12.24021738212853]
  This paper focuses on the development of high-performance virtual sensors to enhance vehicle state estimation for active safety. The proposed Uncertainty-Aware Hybrid Learning architecture integrates a machine learning model with vehicle motion models to estimate Vehicle Sideslip Angle (VSA) directly from onboard sensor data.
  arXiv  Detail & Related papers  (2025-04-08T14:49:58Z)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  Multimodal Large Language Models (MLLMs) can process both visual and textual data.<n>We propose SafeAuto, a novel framework that enhances MLLM-based autonomous driving systems by incorporating both unstructured and structured knowledge.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• 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)<n>We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios.<n>Our evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats.
  arXiv  Detail & Related papers  (2024-12-19T18:59:33Z)
• DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving [1.4104119587524289]
  Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms. These models often sacrifice interpretability, posing significant challenges to trust, safety, and regulatory compliance. We introduce DRIVE, a comprehensive framework designed to improve the dependability and stability of explanations in end-to-end unsupervised driving models.
  arXiv  Detail & Related papers  (2024-09-16T14:40:47Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• 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.<n>We show that using the text-only large language models as judges reveals even better alignment with human preferences than the LVLM judges.<n>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)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective [82.90376711290808]
  This paper explores the integration of Large Language Models (LLMs) into Autonomous Driving systems. LLMs are intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine.
  arXiv  Detail & Related papers  (2023-11-28T03:13:09Z)
• Safety-aware Policy Optimisation for Autonomous Racing [17.10371721305536]
  We introduce Hamilton-Jacobi (HJ) reachability theory into the constrained Markov decision process (CMDP) framework. We demonstrate that the HJ safety value can be learned directly on vision context. We evaluate our method on several benchmark tasks, including Safety Gym and Learn-to-Race (L2R), a recently-released high-fidelity autonomous racing environment.
  arXiv  Detail & Related papers  (2021-10-14T20:15:45Z)

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.