vladimirmodylevskii/tomato-harvest-final-v1_20260525_185957

该数据集是一个用于机器人学领域的机器人操作数据集，由LeRobot工具创建。数据集包含20个训练片段，总计6686帧数据，涉及机器人动作控制（如肩部、肘部、手腕和夹爪的位置信息）和观测状态（包括前视和顶部两个视角的视频图像，分辨率为480x640，帧率为30fps，使用AV1编码）。数据特征还包括时间戳、帧索引、片段索引等，机器人类型为so_follower，适用于机器人模仿学习或控制任务。

This dataset is a robotics manipulation dataset created using the LeRobot tool. It contains 20 training episodes with a total of 6686 frames, covering robot actions (e.g., positions of shoulder, elbow, wrist, and gripper) and observation states (including front and top view video images at 480x640 resolution, 30fps, encoded with AV1). Features also include timestamps, frame indices, episode indices, etc. The robot type is so_follower, suitable for imitation learning or control tasks in robotics.