HouseExpo
收藏资源简介:
HouseExpo数据集是由香港中文大学电子工程系创建的大型2D室内布局数据集,包含35,126个人工设计的2D房屋蓝图,总计252,550个房间,涵盖从单间工作室到多房间住宅的多样化结构。数据集通过PseudoSLAM模拟平台加速数据生成过程,提高训练效率。该数据集主要用于支持深度学习技术在移动机器人任务中的应用,如自主探索和避障,旨在通过模拟和真实世界实验验证数据集的有效性。
The HouseExpo dataset is a large-scale 2D indoor layout dataset created by the Department of Electronic Engineering, The Chinese University of Hong Kong. It contains 35,126 manually designed 2D house blueprints, totaling 252,550 rooms, covering diverse structures ranging from single-room studios to multi-room residences. The dataset leverages the PseudoSLAM simulation platform to accelerate the data generation process and improve training efficiency. This dataset is primarily designed to support the application of deep learning technologies in mobile robotics tasks such as autonomous exploration and obstacle avoidance, aiming to validate the effectiveness of the dataset through both simulation and real-world experiments.

- 1HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots香港中文大学 · 2020年



