用于商业办公场景的三维场景数据
收藏资源简介：
本数据集专为开发和训练在商业办公环境中工作的服务机器人（如接待、巡检、递送机器人）与智能化应用而设计，旨在提升其在结构化办公环境中的自主导航、人机共存、空间管理与任务执行能力。该数据集高度还原了现代商业办公空间的典型环境。场景包含开放式办公区（由大量标准工位、隔断组成）、独立办公室、会议室、茶水间及走廊等。模型细节涵盖办公桌、办公椅、电脑（台式机、笔记本）、显示器、键盘、鼠标、文件柜、打印机等常见办公资产，并模拟了多种办公布局风格（如灵活工位、固定部门布局）。环境同时考虑了动态元素，如临时放置的箱子和可移动的办公椅，以训练机器人应对真实办公环境的复杂性和不确定性本算法旨在处理三维模型，通过一系列步骤实现模型的分割、实例重组及格式转换，以生成新的实例模型，用于场景渲染和机器人训练等应用。 1.模型分割：本步骤接收任意初始三维模型作为输入，三维模型包括位置、尺寸、材质、顶点信息、法相信息、面片信息字段，运用拓扑连通性聚类算法将该组合模型拆分为多个面片组（face group），获取模型类型字段。此步骤有效提取模型的结构特征，有助于后续的实例重组。 2.模型实例重组：在此步骤中，对三维模型的位置、尺寸、材质、顶点信息、法相信息、面片信息字段进行分割，再利用Qwen-VL-Max和GroundingDino算法对分割后的部件进行组合，形成独立的模型实例，并获取其中的标签字段。标签字段能够使每个模型实例能够基于原模型的结构和信息进行识别和应用。 3.模型格式转换：本步骤将拆分获得的实例模型及其对应的材质信息转换为OpenUSD格式，并获取其中的碰撞体设置信息字段和动画约束信息字段，以使模型能够在场景中动起来。 通过以上步骤，将原本数据库中的模型进行重组，生成新的实例模型，并被组装成一个完整的场景，以满足场景渲染、机器人训练等多个应用需求。
This dataset is designed for the development and training of service robots operating in commercial office environments (e.g., reception, patrol and delivery robots) and intelligent applications, aiming to enhance their capabilities of autonomous navigation, human-robot coexistence, space management and task execution in structured office environments. This dataset highly faithfully reproduces typical environments of modern commercial office spaces. The scenarios include open-plan office areas (composed of numerous standard workstations and partitions), private offices, conference rooms, break rooms, corridors and other common spaces. The model details cover common office assets such as desks, office chairs, computers (desktops and laptops), monitors, keyboards, mice, filing cabinets and printers, and simulate multiple office layout styles (e.g., hot-desking setups and fixed departmental layouts). The environment also considers dynamic elements, such as temporarily placed boxes and movable office chairs, to train robots to cope with the complexity and uncertainty of real office environments. This algorithm is designed to process 3D models, and generate new instance models for applications such as scene rendering and robot training through a series of steps including model segmentation, instance recombination and format conversion. 1. Model Segmentation: This step takes any initial 3D model as input. The 3D model includes fields such as position, size, material, vertex information, normal information and face information. A topological connectivity clustering algorithm is used to split the combined model into multiple face groups, and obtain the model type field. This step effectively extracts the structural features of the model, which facilitates subsequent instance recombination. 2. Model Instance Recombination: In this step, the fields of position, size, material, vertex information, normal information and face information of the 3D model are split, and then the split components are combined using the Qwen-VL-Max and GroundingDino algorithms to form independent model instances, and the label field is obtained. The label field enables each model instance to be recognized and applied based on the structure and information of the original model. 3. Model Format Conversion: This step converts the split instance models and their corresponding material information into the OpenUSD format, and obtains the collider configuration information field and animation constraint information field to enable the models to move within the scene. Through the above steps, the models originally stored in the database are recombined to generate new instance models, which are then assembled into a complete scene to meet multiple application requirements such as scene rendering and robot training.
