arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04564cs.ROcs.CV
收藏

基于视觉提示的越野制图推理使用多模态大语言模型

Visual Prompt Based Reasoning for Offroad Mapping using Multimodal LLMs

Khalifa University(哈利法大学)

Abdelmoamen Nasser, Yousef Baba'a, Murad Mebrahtu, Nadya Abdel Madjid, Jorge Dias, Majid Khonji

AI总结:

本文提出一种零样本方法,利用SAM2进行环境分割和多模态大语言模型(VLM)进行可行驶区域推理,通过整合分割图像和原始图像实现越野制图推理,无需专门地形模型。

摘要:

传统越野自主方法依赖于单独的模型进行地形分类、高度估计和滑动或坡度条件量化。使用多个模型需要分别训练每个组件,具有任务特定的数据集,并进行微调。在本文中,我们提出了一种零样本方法,利用SAM2进行环境分割和视觉语言模型(VLM)进行可行驶区域推理。我们的方法将原始图像和带有数字标签的分割图像传递给VLM,然后提示VLM识别由这些数字标签表示的可行驶区域。结合规划和控制模块,这种统一框架消除了对显式地形特定模型的需求,转而依赖VLM的内在推理能力。我们的方法在高分辨率分割数据集上超过了现有可训练模型,并在我们的Isaac Sim越野环境中实现了完整的导航栈。

英文摘要:

Traditional approaches to off-road autonomy rely on separate models for terrain classification, height estimation, and quantifying slip or slope conditions. Utilizing several models requires training each component separately, having task specific datasets, and fine-tuning. In this work, we present a zero-shot approach leveraging SAM2 for environment segmentation and a vision-language model (VLM) to reason about drivable areas. Our approach involves passing to the VLM both the original image and the segmented image annotated with numeric labels for each mask. The VLM is then prompted to identify which regions, represented by these numeric labels, are drivable. Combined with planning and control modules, this unified framework eliminates the need for explicit terrain-specific models and relies instead on the inherent reasoning capabilities of the VLM. Our approach surpasses state-of-the-art trainable models on high resolution segmentation datasets and enables full stack navigation in our Isaac Sim offroad environment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑