pap-final-red-block-100-cutie-combined-master

该数据集使用LeRobot创建，专门针对so_follower机器人类型的机器人学任务。它包含100个episodes，总计32,126帧，以30帧每秒的速率采集。数据以parquet文件格式存储，总数据文件大小为100MB，视频文件大小为200MB。特征包括动作数据（如肩部、肘部、腕部和夹持器的位置）、观察状态（与动作相同的关节位置）、两个摄像头图像（eagle和side视角，分辨率为240x320像素，3通道彩色视频），以及时间戳、帧索引、episode索引等元数据。数据集主要用于训练和评估机器人控制模型，支持从多模态观察中学习动作策略。

This dataset is created using LeRobot and is specifically designed for robotics tasks, particularly for the so_follower robot type. It contains 100 episodes, totaling 32,126 frames, captured at a rate of 30 frames per second. The data is stored in parquet file format, with a total data file size of 100MB and a video file size of 200MB. Features include action data (such as positions of shoulders, elbows, wrists, and grippers), observation states (joint positions identical to actions), two camera images (eagle and side views, with a resolution of 240x320 pixels, 3-channel color video), and metadata such as timestamps, frame indices, and episode indices. The dataset is primarily used for training and evaluating robot control models, supporting the learning of action policies from multimodal observations.