mbodiai/ABB_PandG_20250401_135906

该数据集包含机器人执行的观察、动作和状态等信息。具体特征包括：图像、指令、提示信息、动作（包括姿态、抓取力度和夹爪力度）、状态（包括相机前后视图的图像和深度信息、世界中的物体以及夹爪姿态）、奖励值和元数据（包括剧集索引和步骤索引）。数据集分为训练集，共有8个示例，大小为84095775字节。

The dataset includes observations, actions, and states of robot executions. Specific features include: images, instructions, prompt information, actions (including pose, grasp strength, and gripper force), state (including images and depth information from front and rear cameras, objects in the world, and gripper pose), reward values, and metadata (including episode index and step index). The dataset is split into a training set with a total of 8 examples, sized at 84095775 bytes.