软件工具 / 开源

Robotics-Object-Pose-Estimation · Unity-Technologies

完整的端到端演示，其中我们在Unity中收集训练数据并使用该数据来训练深度神经网络以预测立方体的姿态。然后将该模型部署在...

perception geometry

Robotics-Object-Pose-Estimation · Unity-Technologies 资源页面截图 — 资源截图·抓获 2026-10-09 ·目视审查

概述

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a…<br><br>Publisher purpose：A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.<br><br>Inspect installation instructions, supported versions, examples and interfaces in the source. This directory does not claim the software has been installed or tested on your robot.

项目信息

维护者: Unity-Technologies
主要语言: Python
存储库代码许可证: Apache-2.0
模型重量许可证: 未记录
数据集许可: 未记录
硬件设计许可证: 未记录
维护: 未存档在最后记录的元数据中
最后观察到的存储库推送: 2022-04-13

代码许可不会自动涵盖模型权重、数据集或硬件设计。未记录的许可证详细信息需要与发布者确认。

文档部分

Object Pose Estimation Demo
<a name="link-part-1">[Part 1：Create Unity Scene with Imported URDF](Documentation/1_set_up_the_scene.md)</a>
<a name="link-part-2">[Part 2：Setup the Scene for Data Collection](Documentation/2_set_up_the_data_collection_scene.md)</a>
<a name="link-part-3">[Part 3：Data Collection and Model Training](Documentation/3_data_collection_model_training.md)</a>
<a name="link-part-4">[Part 4：Pick-and-Place](Documentation/4_pick_and_place.md)</a>
Support