mbodiai/ABB_PandG_20250402_143340

该数据集包含了机器人执行任务时的观察、动作、状态和奖励等信息。观察部分包括图像和文本指令，动作部分包括机器人的姿态、抓取力度和夹爪力度等，状态部分包括双摄像头图像、深度信息和环境中的物体信息，奖励部分为执行动作后的奖励值。此外，还包含了索引等元数据信息。数据集分为训练集，共有8个示例。

The dataset includes observations, actions, states, and rewards for robot task execution. The observation part consists of images and text instructions, the action part includes robot poses, grasping force, and gripper force, the state part includes dual camera images, depth information, and objects in the environment, the reward part is the reward value after performing actions, and metadata such as indices are also included. The dataset is split into a training set with a total of 8 examples.