Trainable modular robotic methods

• US 9,364,950 B2
• Filed: 03/13/2014
• Issued: 06/14/2016
• Est. Priority Date: 03/13/2014
• Status: Active Grant

• Current Assignee: Brain Corporation
• Original Assignee: Brain Corporation
• Inventors: Izhikevich, Eugene, Fisher, Dimitry, Passot, Jean-Baptiste, Hatcher, Heathcliff, Polonichko, Vadim
• Primary Examiner(s): Amin, Bhavesh V
• Application Number:
  US14/209,578
• Publication Number:
  US 20150258679A1
• Time in Patent Office: 824 Days
• Field of Search: 461/75, 446/175
• US Class Current: 1/1
• CPC Class Codes: A63H 29/22 Electric drives power supply through track A63H18/12
• CPC Class Codes: A63H 30/04 using wireless transmission
• CPC Class Codes: B25J 13/00 Controls for manipulators programme controls B25J9/16; control in general G05
• CPC Class Codes: B25J 9/0081 with master teach-in means
• CPC Class Codes: B25J 9/104 with cables, chains or ribbons
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: Y10T 74/20305 Robotic arm
• CPC Class Codes: Y10T 74/20311 including power cable or connector
• CPC Class Codes: Y10T 74/20317 including electric motor

Abstract

Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

Claims

1. A method of animating a robotic apparatus having motive freedom in at least one dimension but no indigenous motive source, comprising:

mating a control module comprising a motive source, at least one haptic learning apparatus, and at least one logic configured to execute a behavioral algorithm to the robotic apparatus such that the motive source is mechanically coupled to a corresponding apparatus of the motive freedom; and

causing the motive source to actuate the corresponding apparatus, thereby causing movement of the robotic apparatus in at least the at least one dimension;

receiving training input from a user training the at least one haptic learning apparatus via at least the robotic apparatus, the at least one haptic learning apparatus being configured to be trained to perform a target task.

2. The method of claim 1, wherein the corresponding apparatus comprises at least one tendon apparatus, and the mechanical coupling comprises a coupling which enables the motive source to vary a tension on the at least one tendon apparatus.

3. The method of claim 2, wherein the mechanical coupling further comprises an electrical coupling.

4. The method of claim 1, wherein the received training input comprises user feedback on one or more assigned tasks to the learning apparatus.

5. The method of claim 1, wherein the motive source comprises an electrical motor-based actuator.

6. The method of claim 1, wherein the motive source comprises a pneumatic- or fluidic-based actuator.

7. A method of providing for cost-efficient ownership and operation of a plurality of robotic apparatus, each of the plurality of robotic apparatus having a different configuration and capability set, the method comprising:

providing a unitary control module configured to interface with each of the plurality of robotic apparatus singularly, the unitary control module configured to learn at least one behavior specific to each of the plurality of robotic apparatus, and thereby control at least one aspect of an operation of each of respective ones of the plurality of robotic apparatus when the unitary control module has been interfaced with respective ones of the plurality of robotic apparatus;

wherein each of the plurality of robotic apparatus is configured to be inoperative without the unitary control module; and

whereby use of the unitary control module with the plurality of robotic apparatus reduces a cost of ownership and operation as compared to use of a dedicated control module for each of the plurality of robotic apparatus.

8. The method of claim 7, wherein the unitary control module is configured to retain each of the at least one learned behavior, and recall each of the at least one learned behavior when interfaced with the respective ones of the plurality of robotic apparatus.

9. The method of claim 8, wherein the recall of the each of the at least one learned behavior for respective ones of the plurality of robotic apparatus is caused at least in part by identifying information that is transmitted from the respective one of the plurality of robotic apparatus to the unitary control module.

10. The method of claim 8, wherein the recall of the each of the at least one learned behavior for respective ones of the plurality of robotic apparatus is caused at least in part through sensing one or more aspects of the configuration of the respective one.

11. The method of claim 10, wherein the unitary control module comprises a plurality of actuator apparatus, and the sensing comprises sensing of a mechanical property associated with one or more of the plurality of actuator apparatus.

12. The method of claim 10, wherein the unitary control module comprises a plurality of actuator apparatus, and the sensing comprises sensing of an electrical property associated with one or more of the plurality of actuator apparatus.

13. A method of operating a plurality of heterogeneous robotic apparatus using a common control module configured to interface with each of the plurality of heterogeneous robotic apparatus singularly, the common control module configured to learn at least one behavior specific to each of the plurality of heterogeneous robotic apparatus, the method comprising:

mating the common control module with a first robotic apparatus;

training the common control module with at least one first behavior relating to the first robotic apparatus to produce a first learned behavior within the common control module;

mating the common control module with a second robotic apparatus different in capability than the first robotic apparatus;

training the common control module with at least one second behavior relating to the second robotic apparatus to produce a second learned behavior within the common control module;

mating the common control module again with the first robotic apparatus; and

performing at least one target task using the first robotic apparatus under control of the common control module and based at least on the first learned behavior.

14. The method of claim 13, wherein the training the common control module with the at least one first behavior comprises downloading data relating to the at least one first behavior via a communications interface of the common control module from a remote entity.

15. The method of claim 14, further comprising:

identifying the first robotic apparatus as a type thereof; and

transmitting information relating to the identified type to the remote entity, the remote entity configured to select the data based at least on the identified type.

16. The method of claim 15, wherein the selection of the data based on the identified type comprises selection of data useful with the identified type of robotic apparatus.

17. The method of claim 14, further comprising:

uniquely identifying the first robotic apparatus; and

transmitting information relating to the unique identification to a remote entity, the remote entity configured to select the data based at least on the unique identification.

18. The method of claim 17, wherein the selection of the data based on at least the unique identification comprises selection of the data useful with only the uniquely identified first robotic apparatus.

19. The method of claim 13, wherein:

the at least one first behavior and the at least one second behavior each comprises a first and second plurality of constituent tasks or behaviors respectively, and the first plurality of constituent tasks or behaviors overlaps with a portion of, but not the entirety of, the second plurality of constituent tasks or behaviors; and

the common control module is configured to identify at least one overlapping constituent task or behavior.