Spatially consistent representation of hand motion

A computing device, comprising:

• a logic subsystem;
• and
• a storage subsystem comprising instructions executable by the logic subsystem to:
• receive image data corresponding to an environment;
• recognize a first object in the environment;
• receive a virtual model representing the first object;
• align the virtual model to the first object and maintain such alignment;
• receive a recording of hand motion;
• based on the recording, determine a parametric representation of hand motion relative to the virtual model as aligned with the first object;
• and
• configure the parametric representation of hand motion for display in a coordinate system of the virtual model as aligned to a second object, such that the parametric representation of hand motion relative to the virtual model as aligned to the second object is spatially consistent with the parametric representation of hand motion relative to the virtual model as aligned to the first object, wherein the parametric representation includes a multi-dimensional vector, wherein each dimension of the multi-dimensional vector encodes an articulation of at least one of a plurality of hand joints.

At a robotic device, a method of controlling a robot manipulator, comprising:

• receiving a parametric representation of hand motion determined in a coordinate system of a virtual model aligned to a first object, the virtual model corresponding to the first object;
• receiving image data corresponding to an environment;
• recognizing a second object in the environment;
• aligning the virtual model to the second object;
• and
• based on the parametric representation of hand motion, determining a sequence of actions for performance, relative to the virtual model as aligned to the second object, by a manipulator of the robotic device, where the sequence of actions is spatially consistent with the parametric representation of hand motion relative to the virtual model as aligned to the first object, wherein the parametric representation includes a multi-dimensional vector, wherein each dimension of the multi-dimensional vector encodes an articulation of at least one of a plurality of hand joints.