kejia98/brush_table_franka_rlround1

该数据集是一个用于机器人技术研究的多模态数据集，通过本地多模态记录器导出器创建。数据集包含22个训练片段，总计6556帧数据，采样频率为10fps。数据特征包括主次图像（分辨率240x320，3通道）、机器人状态（如末端执行器位置和姿态、夹爪状态）、动作指令、成功标志、时间戳、帧索引、片段索引等。数据集基于Franka机器人平台，适用于机器人控制、强化学习和视觉导航等任务。

This dataset is a multimodal dataset for robotics research, created using a local multimodal recorder exporter. It contains 22 training episodes with a total of 6556 frames, sampled at 10fps. The data features include primary and secondary images (resolution 240x320, 3 channels), robot states (such as end-effector position and orientation, gripper status), action commands, success flags, timestamps, frame indices, episode indices, etc. The dataset is based on the Franka robot platform and is suitable for tasks such as robot control, reinforcement learning, and visual navigation.