Space extrapolation for robot task performance

A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to:

• identify, based on a gesture of an operator detected in vision data captured by one or more vision sensors, an approximation of a discrete space within an environment, wherein the approximation is identified by projecting a plurality of vectors to a plurality of points on a surface in the environment;
• define, based on the plurality of points, the discrete space within the environment;
• identify a plurality of objects that are co-present within the discrete space, wherein the plurality of objects are to be manipulated by a robot;
• and
• operate the robot to manipulate the identified plurality of objects.

A method implemented using one or more processors, comprising:

• identifying, based on a gesture of an operator detected in vision data captured by one or more vision sensors, an approximation of a discrete space within an environment, wherein the approximation is identified by projecting a plurality of vectors to a plurality of points on a surface in the environment;
• defining, based on the plurality of points, the discrete space within the environment;
• identifying a plurality of objects that are co-present within the discrete space, wherein the plurality of objects are to be manipulated by a robot;
• and
• operating the robot to manipulate the identified plurality of objects.