Aneesha/eval_so101_blueblock_run52

该数据集使用LeRobot工具创建，专门用于机器人学习任务，具体针对跟随者类型的机器人（so_follower）。数据集包含2个episodes，总计552帧，涉及1个任务。数据以parquet格式存储，总大小为100MB，同时包含视频文件，总大小为200MB，帧率为30fps。数据集的特征包括动作数据（6个关节位置：肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕旋转和夹爪位置）、观测状态（与动作相同的关节位置）、观测图像（正面和侧面两个视角的RGB视频，分辨率480x640，3通道）、时间戳、帧索引、集索引、索引和任务索引。这些数据用于训练和评估机器人控制模型，支持从多模态输入中学习动作策略。

This dataset was created using the LeRobot tool and is designed for robotics learning tasks, specifically for a follower type robot (so_follower). It contains 2 episodes, totaling 552 frames, and involves 1 task. The data is stored in parquet format with a total size of 100MB, and includes video files with a total size of 200MB at a frame rate of 30fps. The dataset features include action data (6 joint positions: shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position), observation state (same joint positions as actions), observation images (RGB videos from front and side views, resolution 480x640, 3 channels), timestamp, frame index, episode index, index, and task index. These data are used for training and evaluating robot control models, supporting learning action policies from multimodal inputs.