five

Simulated Navigation Scenarios

收藏
arXiv2025-09-30 收录
下载链接:
https://e2map.github.io/
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集包含了三个模拟场景,旨在评估E2Map方法在动态环境中的表现,这些场景分别为危险标志、人墙和动态门。成功定义为机器人按顺序到达所有目标且不发生碰撞,数据集还包含了与基准方法性能比较的详细信息。规模上,每个场景都有十种不同的语言指令。该任务是基于动态环境中的语言指令进行导航。

This dataset contains three simulation scenarios designed to evaluate the performance of the E2Map method in dynamic environments. The three scenarios are hazard sign, human wall, and dynamic door. Success is defined as the robot reaching all targets in sequence without any collisions. The dataset also includes detailed performance comparison information against baseline methods. In terms of scale, each scenario has ten distinct language instructions. The task is navigation based on language instructions in dynamic environments.
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