# NeuroSymbEAD：用于全向具身自动驾驶的大规模神经符号描述数据集

> 原文链接：https://robotics.hellobike.com/papers/2026-09-15-2609-16919
> 频道：papers | 更新日期：2026-09-15 | 标签：arxiv, cs.RO
> 核心摘要：NeuroSymbEAD在KITTI-360上以自车知识图生成多层文本标注，验证交通场景解释与3D推理基准。

# NeuroSymbEAD：用于全向具身自动驾驶的大规模神经符号描述数据集

::: v-pre
> 原文链接：[NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Driving](https://arxiv.org/abs/2609.16919)（arXiv 2609.16919 · 发布日期：2026-09-15）

**NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Driving**

NeuroSymbEAD在KITTI-360上以自车知识图生成多层文本标注，验证交通场景解释与3D推理基准。

## 核心要点

- 动机是为自动驾驶场景提供可接地语言表示，支持常识和交通/场景理解。
- 方法构建自车中心知识图，标注静动态物体的类别、朝向、方向和距离。
- 在KITTI-360上生成多层文本caption，形成轻量级自车场景地图表示。
- 用预训练grounding与自回归captioning网络评测神经符号和本体caption生成。

**验证范围与局限**：验证范围为KITTI-360上的驾驶场景，并以预训练grounding和自回归captioning网络建立基线。

## 英文摘要 (Abstract)

This paper introduces NeuroSymbEAD, a large-scale neuro-symbolic caption dataset featuring an ego-centric knowledge graph (KG) of static and dynamic objects annotated with classes, categories, heading directions, orientations, and distances from the ego-vehicle. These annotations are used on the KITTI-360 dataset to generate multilevel textual captions representing a lightweight version of an ego-centric scene map. Outdoor scene-map reconstruction, visual recognition, and object grounding establish baselines for driving common sense and traffic/scene understanding. For these purposes, natural language-based grounded captioning of objects and their complex relationships is a widely adopted contextual representation for indoor scene tasks. Neuro-symbolic representations have proven effective in handling structured information for various computer vision and language applications. Our data annotation pipeline allows the generation of varied map segments, populating simulated or real objects within the bounding boxes predicted by any 3D object detection network, and building hierarchical text captions. We benchmark our neuro-symbolic and ontological caption generation using pre-trained grounding and learned auto-regressive captioning networks. By converting 3D driving scenes into structured ego-centric language, NeuroSymbEAD provides a benchmark for vision-language and foundation models for traffic-scene explanation, 3D reasoning, and interpretable autonomous-driving perception.

作者：Muhammad Ahmed Ullah Khan, Mohammed Elamine, Talha Uddin Sheikh, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
:::

## 原始参考来源 (Sources)

- [arXiv 2609.16919：NeuroSymbEAD: A Large Scale Neuro-Symbolic Caption Dataset for Omni-Directional Embodied Autonomous Driving](https://arxiv.org/abs/2609.16919)