Is Your VLM for Autonomous Driving Safety-Ready? A Comprehensive Benchmark for Evaluating External and In-Cabin Risks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909913283821568 |
|---|---|
| author | Meng, Xianhui Zhang, Yuchen Huang, Zhijian Lu, Zheng Ji, Ziling Yin, Yaoyao Zhang, Hongyuan Jiang, Guangfeng Lin, Yandan Chen, Long Ye, Hangjun Zhang, Li Liu, Jun Hao, Xiaoshuai |
| author_facet | Meng, Xianhui Zhang, Yuchen Huang, Zhijian Lu, Zheng Ji, Ziling Yin, Yaoyao Zhang, Hongyuan Jiang, Guangfeng Lin, Yandan Chen, Long Ye, Hangjun Zhang, Li Liu, Jun Hao, Xiaoshuai |
| contents | Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This issue arises from the lack of comprehensive benchmarks that assess both external environmental risks and in-cabin driving behavior safety simultaneously. To bridge this critical gap, we introduce DSBench, the first comprehensive Driving Safety Benchmark designed to assess a VLM's awareness of various safety risks in a unified manner. DSBench encompasses two major categories: external environmental risks and in-cabin driving behavior safety, divided into 10 key categories and a total of 28 sub-categories. This comprehensive evaluation covers a wide range of scenarios, ensuring a thorough assessment of VLMs' performance in safety-critical contexts. Extensive evaluations across various mainstream open-source and closed-source VLMs reveal significant performance degradation under complex safety-critical situations, highlighting urgent safety concerns. To address this, we constructed a large dataset of 98K instances focused on in-cabin and external safety scenarios, showing that fine-tuning on this dataset significantly enhances the safety performance of existing VLMs and paves the way for advancing autonomous driving technology. The benchmark toolkit, code, and model checkpoints will be publicly accessible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14592 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is Your VLM for Autonomous Driving Safety-Ready? A Comprehensive Benchmark for Evaluating External and In-Cabin Risks Meng, Xianhui Zhang, Yuchen Huang, Zhijian Lu, Zheng Ji, Ziling Yin, Yaoyao Zhang, Hongyuan Jiang, Guangfeng Lin, Yandan Chen, Long Ye, Hangjun Zhang, Li Liu, Jun Hao, Xiaoshuai Robotics Artificial Intelligence Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This issue arises from the lack of comprehensive benchmarks that assess both external environmental risks and in-cabin driving behavior safety simultaneously. To bridge this critical gap, we introduce DSBench, the first comprehensive Driving Safety Benchmark designed to assess a VLM's awareness of various safety risks in a unified manner. DSBench encompasses two major categories: external environmental risks and in-cabin driving behavior safety, divided into 10 key categories and a total of 28 sub-categories. This comprehensive evaluation covers a wide range of scenarios, ensuring a thorough assessment of VLMs' performance in safety-critical contexts. Extensive evaluations across various mainstream open-source and closed-source VLMs reveal significant performance degradation under complex safety-critical situations, highlighting urgent safety concerns. To address this, we constructed a large dataset of 98K instances focused on in-cabin and external safety scenarios, showing that fine-tuning on this dataset significantly enhances the safety performance of existing VLMs and paves the way for advancing autonomous driving technology. The benchmark toolkit, code, and model checkpoints will be publicly accessible. |
| title | Is Your VLM for Autonomous Driving Safety-Ready? A Comprehensive Benchmark for Evaluating External and In-Cabin Risks |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2511.14592 |