Open 7-DoF arm, bimanual-ready, with pilot data-collection packages.
90+ platforms — humanoids, arms, quadrupeds, dexterous hands, and teleoperation kits. Lead time shown on each product.
Hardware-synced demonstrations for VLA and imitation learning. Download in LeRobot, HDF5, or RLDS format.
From first arm on the bench to a policy that survives a real workcell — the Robotics Center pipeline in three steps.
Specifications and integration guide for the tactile and pose-tracking data glove.
Unbox, calibrate, and run your first autonomous walk. Includes ROS 2 bringup and teleop quickstart.
控制策略在训练中未见过的输入上正确执行的能力：新物体、环境、光照条件或任务变化。泛化能力是机器人学习的核心挑战——策略容易过拟合到训练条件。改进泛化能力的技术包括数据增强、域随机化、预训练表示和多样化训练数据。
