Robot gesture generation
AssigneeMicrosoft Technology Licensing, LLC
InventorsKatsushi Ikeuchi, Mona Soliman Habib
Life of this patent
Estimating the term…
Abstract
A method and apparatus for robot gesture generation is described. Generally speaking, a concept corresponding to a utterance to be spoken by a robot is determined (204). After a concept is determined or selected, a symbolic representation of a gesture that corresponds to the determined concept is retrieved from a predetermined gesture library (206). Subsequently, the symbolic representation is provided to cause the robot to perform the gesture (208). In such way, a more natural, comprehensive and effective communication between human and robots may be achieved.
Claims20
A method, performed by a processing unit, for robot gesture generation, comprising:
- determining a concept (C1, C2, . . . , CN) corresponding to an utterance to be spoken by a robot:
- retrieving, from a predetermined gesture library, a symbolic representation (SR1, SR2, . . . , SRN) of a gesture that corresponds to the determined concept (C1, C2, . . . , CN);
- providing the symbolic representation (SR1, SR2, . . . , SRN) to cause the robot to perform the gesture.
An apparatus for robot gesture generation, comprising:
- a processing unit;
- and
- a memory coupled to the processing unit and storing instructions for execution by the processing unit, the instructions, when executed by the processing unit, causing the apparatus to:
- determine a concept (C1, C2, . . . , CN) corresponding to a received utterance to be spoken by a robot;
- retrieve, from a predetermined gesture library, a symbolic representation (SR1, SR2, . . . , SRN) of a gesture that corresponds to the determined concept (C1, C2, . . . , CN);
- and
- provide the symbolic representation (SR1, SR2, . . . , SRN) to causing the robot to perform the gesture.
A computer program product for storage of a solid-state drive, the computer program product being tangibly stored on a non-transient computer-readable medium and comprising machine-executable instructions, the machine-executable instructions, when executed, causing a machine to:
- determine a concept (C1, C2, . . . , CN) corresponding to a received utterance to be spoken by the robot;
- retrieve, from predetermined gesture library, a symbolic representation (SR1, SR2, . . . , SRN) of a gesture that corresponds to the determined concept (C1, C2, . . . , CN);
- and
- provide the symbolic representation (SR1, SR2, . . . , SRN) to cause the robot to perform the gesture.
Dependencies are inferred from the claim text.