mbodiai/ABB_PandG_20250401_151749

该数据集包含机器人执行任务时的观察数据、动作、状态和奖励等信息。观察数据中包含图像和文本指令，动作数据包括机械臂的姿态、抓握力度和夹爪力等信息。状态数据则包括不同摄像头的图像、深度信息和世界中的物体信息，以及夹爪的姿态。此外，每个步骤还伴有奖励值和元数据信息，如剧集索引和步骤索引。数据集分为训练集，共有9个示例，总大小约为92.13MB。

The dataset includes observations, actions, states, and rewards of a robot performing tasks. Observation data contain images and text instructions, action data include the robot arms pose, grip strength, and gripper force. State data cover images from different cameras, depth information, objects in the world, and the grippers pose. Each step is also accompanied by a reward value and metadata such as episode index and step index. The dataset is split into a training set with 9 examples, totaling approximately 92.13MB.