mbodiai/ABB_PandG_20250331_215847

该数据集包含了观察数据、动作数据、状态数据和奖励数据。观察数据由图像和字符串类型的指令、提示组成。动作数据包含姿态（由x、y、z、roll、pitch、yaw六个浮点数表示）、抓握力度（浮点数）和机械臂夹持器的力量（整型）。状态数据由两个摄像头视角的图像、深度信息、世界中的物体信息以及机械臂夹持器的姿态序列组成。奖励数据为浮点型。数据集分为训练集，共有7个样本。数据集的总大小为74190111字节，下载大小为43154107字节。

The dataset consists of observation data, action data, state data, and reward data. Observation data includes images and string-type instructions and prompts. Action data contains pose (represented by six floats: x, y, z, roll, pitch, yaw), grip strength (float), and gripper force (int). State data comprises images from two camera perspectives, depth information, objects in the world, and a sequence of the gripper pose. Reward data is of float type. The dataset is split into a training set with 7 samples. The total size of the dataset is 74190111 bytes, and the download size is 43154107 bytes.