yinongh/real_world_force_image_1_2
收藏资源简介:
该数据集使用LeRobot创建,专注于机器人任务。数据集包含10个episodes、540帧、1个任务和40个视频,数据以parquet格式存储,帧率为30fps,仅提供训练集。特征包括动作数据(9维向量,如delta_x、delta_y、delta_z和delta_rot6d等)和丰富的观测数据,如末端执行器内力、姿态、对齐的插座深度图像、初始插头深度图像、初始手腕点云、手腕相机外参矩阵、手腕深度和RGB图像、Azure Kinect前相机彩色图像、辅助相机左右RGB和深度图像等,支持机器人学习和模拟任务。
This dataset was created using LeRobot and focuses on robotics tasks. It contains 10 episodes, 540 frames, 1 task, and 40 videos, stored in parquet format with a frame rate of 30fps, and includes only a training set. Features include action data (a 9-dimensional vector with elements such as delta_x, delta_y, delta_z, and delta_rot6d) and diverse observation data, such as end-effector internal forces, pose, aligned socket depth images, initial plug depth images, initial wrist point clouds, wrist camera extrinsic matrices, wrist depth and RGB images, Azure Kinect front camera color images, auxiliary camera left RGB and depth images, etc., supporting robot learning and simulation tasks.




