AniDriveQA:用于带有动物存在的驾驶场景的VQA数据集
Rui Wang1, Ruiqi Wang2, Hao Hu1,3
1The Institute of Computing Technologies, China Academy of Railway Sciences Corporation Ltd., Beijing, China.
Frontiers in robotics and AI
|November 13, 2025
概括
一个新的数据集,AniDriveQA,解决了与动物相遇的自动驾驶方面的挑战. 它揭示了当前视觉语言模型与这些罕见的,安全关键的场景作斗争,突出了需要改进的领域.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 自主系统 自主系统
背景情况:
- 涉及动物的场景为自动驾驶系统带来了独特的,安全关键的挑战.
- 现有的视觉语言数据集往往忽略了这些罕见的,不可预测的"长尾"情况.
研究的目的:
- 介绍AniDriveQA,一个新的视觉问题答案 (VQA) 数据集.
- 评估视觉语言模型 (VLMs),特别是与动物相关的自动驾驶场景.
- 提供一个基准来确定当前VLMs的局限性.
主要方法:
- 使用与动物有关的交通场景的互联网视频构建了一个可扩展的管道.
- 用对象检测和场景分类模型过和注释的场景.
- 使用大型VLM生成多任务VQA标签 (场景描述,动物描述,驾驶建议).
主要成果:
- 采用混合评估方案,将分类准确性和基于LLM的评分结合起来.
- 对开源VLM的实验显示,模型和任务之间存在显著的性能差异.
- AniDriveQA有效地暴露了当前VLM在处理罕见动物场景方面的局限性.
结论:
- AniDriveQA是VLM开发的有价值的诊断基准.
- 数据集强调了需要改进自动驾驶的VLM中的推理,感知和决策.
- 在不可预测的驾驶条件下提高安全性,VLM的进步至关重要.
相关概念视频
Force Classification
2.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.3K
Observational Learning
804
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
804

