知识蒸馏
训练一个较小的学生模型以匹配较大教师模型的输出(软逻辑)。学生学习教师知识的压缩版本。在机器人学中,蒸馏用于:压缩大型VLA模型以实现实时推理,将特权信息教师转移到仅视觉学生,以及创建高效的边缘可部署感知模型。

Open 7-DoF arm, bimanual-ready. Ships from San Francisco with pilot data-collection packages from $2,500.

90+ platforms — humanoids, arms, quadrupeds, dexterous hands, and teleoperation kits. In-stock hardware ships in 48 hours.

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.

Low-latency data-collection glove for dexterous manipulation. From $5,500, ships from San Francisco.

Unbox, calibrate, and run your first autonomous walk. Includes ROS 2 bringup and teleop quickstart.
训练一个较小的学生模型以匹配较大教师模型的输出(软逻辑)。学生学习教师知识的压缩版本。在机器人学中,蒸馏用于:压缩大型VLA模型以实现实时推理,将特权信息教师转移到仅视觉学生,以及创建高效的边缘可部署感知模型。
