plate_on_platform_20250821_subsampled_noWrist_heatmapGoal

这是一个使用LeRobot创建的机器人控制数据集，包含20个训练片段，总计5748帧数据和60个视频。数据集采集了双手机械臂的多种传感器数据，包括18维的关节状态和动作控制信号、10维的末端执行器位姿信息、720x1280分辨率的深度和彩色图像、500点的夹爪点云数据等。数据以15fps的帧率采集，使用Azure Kinect相机，包含原始彩色图像、对齐的深度图像以及目标夹爪位置在图像上的投影等信息。

This is a robotic control dataset created using LeRobot, containing 20 training segments with a total of 5748 data frames and 60 videos. The dataset collects various sensor data from dual-arm robotic manipulators, including 18-dimensional joint states and action control signals, 10-dimensional end-effector pose information, 720×1280 resolution depth and color images, 500-point gripper point cloud data, and more. The data was acquired at a frame rate of 15 fps using an Azure Kinect camera, and includes raw color images, aligned depth images, as well as the projection of the target gripper position onto the image plane and other related information.