cf-group-4/cloth_folding_generalized

该数据集是使用LeRobot创建的机器人学数据集，专门用于机器人控制和学习任务。数据集包含249个episodes和350189个frames，涉及一个任务，数据以parquet文件格式存储，视频文件为MP4格式，帧率为30fps。数据集的结构包括以下特征：动作（action），表示机器人的关节位置，如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置；观察状态（observation.state），与动作类似，提供机器人状态信息；前视图像（observation.images.front），分辨率为480x640的RGB视频，用于视觉输入；时间戳（timestamp）、帧索引（frame_index）、episode索引（episode_index）、索引（index）和任务索引（task_index）。数据集适用于机器人模仿学习、强化学习和视觉-动作映射等研究，支持基于状态和图像输入的机器人控制算法开发。This dataset is a robotics dataset created using LeRobot, designed for robot control and learning tasks. It contains 249 episodes and 350189 frames, involving one task, with data stored in parquet files and video files in MP4 format at 30fps. The dataset structure includes the following features: action, representing robot joint positions such as shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions; observation.state, similar to action, providing robot state information; observation.images.front, RGB video with a resolution of 480x640 for visual input; timestamp, frame_index, episode_index, index, and task_index. The dataset is suitable for research in robot imitation learning, reinforcement learning, and vision-action mapping, supporting the development of robot control algorithms based on state and image inputs.