yoohoolala/depth_ai01
收藏资源简介：
该数据集使用LeRobot创建，专注于机器人技术领域，具体针对so101_follower类型的机器人。数据集包含2个完整的情节（episodes），总计576帧数据，覆盖1个任务。数据结构包括动作（action）、观测状态（observation.state）、图像观测（observation.images.intel）等特征，其中动作和状态特征涉及机器人的肩部、肘部、腕部和抓取器的位置控制，图像特征为480x640分辨率的RGB视频，帧率为30fps。数据集适用于机器人控制、模仿学习或强化学习任务，旨在支持机器人行为的研究和开发。
This dataset was created using LeRobot and focuses on the robotics domain, specifically for the so101_follower robot type. It contains 2 complete episodes, totaling 576 frames, and covers 1 task. The data structure includes features such as action, observation.state, and observation.images.intel, where action and state features involve position control of the robots shoulder, elbow, wrist, and gripper, and image features consist of RGB videos with a resolution of 480x640 at 30fps. The dataset is suitable for robot control, imitation learning, or reinforcement learning tasks, aiming to support research and development in robot behavior.
