kunhsiang/eval_exp9_sc2var_grasp_the_small_box_20260527-165902
收藏资源简介:
该数据集是一个机器人任务数据集,使用LeRobot工具创建。具体针对so_follower类型的机器人,执行grasp_the_small_box(抓取小盒子)任务。数据集包含一个完整的episode,总共有2423帧数据,以30fps的帧率记录。数据以parquet文件格式存储,并包含对应的mp4视频文件。数据集的特征包括:动作数据(action),表示机器人关节位置(如肩部、肘部、腕部等);观察状态(observation.state),同样为关节位置;以及多个视角的图像观察(observation.images),包括前视(front)、顶部(top)和夹爪(gripper)摄像头,每个图像分辨率为480x640,3通道彩色视频。此外,还包括时间戳(timestamp)、帧索引(frame_index)、episode索引(episode_index)、索引(index)和任务索引(task_index)等元数据。数据集主要用于机器人学习任务,如模仿学习或强化学习。
This dataset is a robotics task dataset created using the LeRobot tool. It specifically targets the so_follower type robot performing the grasp_the_small_box task. The dataset contains one complete episode with a total of 2423 frames recorded at 30fps. The data is stored in parquet file format and includes corresponding mp4 video files. The features of the dataset include: action data representing robot joint positions (e.g., shoulder, elbow, wrist); observation state (observation.state), also for joint positions; and multiple view image observations (observation.images), including front, top, and gripper cameras, each with a resolution of 480x640 and 3-channel color video. Additionally, it includes metadata such as timestamp, frame index, episode index, index, and task index. The dataset is primarily used for robotics learning tasks, such as imitation learning or reinforcement learning.




