Lisette1231/eval_20260426_act_pickbreadpot8

该数据集使用LeRobot创建，专注于机器人控制任务，涉及Seeed B601 DM Follower机器人。数据集包含1个任务、1个episode和1782个帧，以30 FPS的速率采集。数据以Parquet文件格式存储，总数据文件大小为100 MB，视频文件大小为200 MB。特征包括7维浮点数的动作和状态观测（如肩部、肘部、腕部等关节位置），以及来自前部和腕部摄像头的图像观测（分辨率480x640，3通道彩色视频）。其他补充信息包括策略动作、干预标志和状态变量。数据集适用于机器人学习和控制研究，支持训练和验证。

This dataset was created using LeRobot and focuses on robotics control tasks, specifically for the Seeed B601 DM Follower robot. It contains 1 task, 1 episode, and 1782 frames, collected at 30 FPS. The data is stored in Parquet format, with a total data file size of 100 MB and video file size of 200 MB. Features include 7-dimensional float32 actions and state observations (e.g., joint positions for shoulder, elbow, wrist), as well as image observations from front and wrist cameras (resolution 480x640, 3-channel color video). Additional complementary information includes policy actions, intervention flags, and state variables. The dataset is suitable for robotics learning and control research, supporting training and validation.