panda_pick_and_place_joint_pos_21

这是一个使用LeRobot创建的机器人领域数据集，专门用于机器人任务。数据集包含10个episodes，总计2817帧和22个视频，以15帧每秒的速率采集。数据以Parquet格式存储，并分为训练集（10个episodes）。数据集的特征包括：来自外部摄像头的图像观测（480x640分辨率，3通道，视频格式）、来自腕部摄像头的图像观测（相同规格）、状态观测（8个浮点数，代表q1到q7关节位置和夹爪状态）、动作（8个浮点数，对应关节和夹爪控制）、时间戳、帧索引、episode索引、索引和任务索引。这些数据适用于机器人学习任务，如模仿学习或强化学习。

This is a robot domain dataset created using LeRobot, specifically designed for robot tasks. The dataset contains 10 episodes, totaling 2817 frames and 22 videos, collected at a rate of 15 frames per second. The data is stored in Parquet format and divided into a training set (10 episodes). The features of the dataset include: image observations from an external camera (480x640 resolution, 3 channels, video format), image observations from a wrist camera (same specifications), state observations (8 floating-point numbers representing q1 to q7 joint positions and gripper status), actions (8 floating-point numbers corresponding to joint and gripper control), timestamps, frame index, episode index, index, and task index. This data is suitable for robot learning tasks such as imitation learning or reinforcement learning.