mbodiai/ABB_PandG_20250401_140453

这个数据集包含了机器人执行任务时的观测数据、动作、状态和奖励等信息。具体特征包括：图像（前视和顶视）、指令、提示、姿态（包括x、y、z、roll、pitch、yaw六个维度）、抓取力度、夹爪力度、状态（包括前视和顶视的图像、深度信息、世界中的物体、夹爪姿态）、奖励值以及元数据（包括剧集索引和步索引）。数据集分为训练集，共有7个示例，总大小为73,109,172字节。

The dataset includes observation data, actions, states, and rewards for robot execution tasks. Specific features include: images (front and top view), instructions, prompts, poses (including six dimensions: x, y, z, roll, pitch, yaw), grasp force, gripper force, state (including images, depth information of front and top view, objects in the world, gripper pose), reward value, and metadata (including episode index and step index). The dataset is split into a training set with a total of 7 examples, with a total size of 73,109,172 bytes.