five

Real-World Walking Data

收藏
arXiv2025-09-30 收录
下载链接:
https://antonilo.github.io/vision_locomotion/
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集旨在通过现实世界的经验来训练视觉行走策略,重点是提高适应各种地形的能力。该数据集包含了在多种地形上的行走试验,如楼梯、滑梯和路缘石等,突显了视觉模块在提升运动性能方面的有效性。该数据集规模较小,收集的真实世界数据不足30分钟,其任务是进行视觉行走策略的训练。

This dataset is designed to train visual walking policies using real-world experience, with a primary focus on improving adaptability to various terrains. It includes walking trials conducted on diverse terrain types such as stairs, slides, curbstones and other similar obstacles, which highlights the effectiveness of visual modules in enhancing locomotor performance. This is a small-scale dataset, with the collected real-world data totaling less than 30 minutes, and its core task is the training of visual walking policies.
提供机构:
Authors of the paper
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作