mbodiai/ABB_PandG_20250331_222148

该数据集包含了多个特征，如观察（包括图像和字符串类型的指令、提示）、动作（包括姿态、抓取力度和机械臂夹持力度）、状态（包括前后摄像头图像、深度信息、世界中的物体信息和机械臂夹持器的姿态）、奖励值以及元数据（包括剧集索引和步骤索引）。数据集分为训练集，共有6个示例，数据集大小为63733315字节。

The dataset includes multiple features such as observation (including image and string-type instruction, prompt), action (including pose, grasp force, and gripper force), state (including front and rear camera images, depth information, objects in the world, and gripper pose), reward value, and metadata (including episode index and step index). The dataset is split into a training set with a total of 6 examples, and the dataset size is 63733315 bytes.