mbodiai/ABB_PandG_20250402_120940

这个数据集包含了机器人执行的观察、动作、状态、奖励等信息。观察部分有图像、指令和提示，动作部分包括姿态（x、y、z、roll、pitch、yaw）、抓取力度和夹爪力度，状态部分有相机前后图像、深度信息、世界中的物体和夹爪姿态，还有奖励和元数据（剧集索引和步骤索引）。数据集分为训练集，共有7个示例。

This dataset includes observations, actions, states, and rewards of robot executions. The observation part consists of images, instructions, and prompts, the action part includes pose (x, y, z, roll, pitch, yaw), grasp force, and gripper force, the state part has front and back camera images, depth information, objects in the world, and gripper pose, as well as rewards and metadata (episode index and step index). The dataset is split into a training set with a total of 7 examples.