Trainable modular robotic apparatus and methods

• US 9,987,743 B2
• Filed: 03/13/2014
• Issued: 06/05/2018
• 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
• Primary Examiner(s): Cook, Jake
• Application Number:
  US14/208,709
• Publication Number:
  US 20150258682A1
• Time in Patent Office: 1,545 Days
• CPC Class Codes: B25J 9/0009 Constructional details, e.g. manipulator supports, bases
• CPC Class Codes: B25J 9/08 characterised by modular constructions
• CPC Class Codes: B25J 9/104 with cables, chains or ribbons
• CPC Class Codes: Y10T 74/20305 Robotic arm
• CPC Class Codes: Y10T 74/20311 including power cable or connector

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 modular robotic apparatus body, comprising:

a first movable element and a second movable element;

at least one sensory interface; and

a mechanical interface configured to effectuate movement of the first and the second movable elements separately based on one or more actuation inputs from a control apparatus when the control apparatus is mated to the modular robotic apparatus body;

wherein the modular robotic apparatus body is configured to mate with the control apparatus via the mechanical interface, the control apparatus comprising a non-transitory computer-readable storage medium having a plurality of instructions thereon, the plurality of instructions being configured to, when executed by a processor apparatus, cause the control apparatus to;

generate an output signal based on a contextual signal obtained via the at least one sensory interface, the output signal being determined by a learning process;

causing an actuation of the modular robotic apparatus body based on the generated output signal;

receive feedback from a trainer via the modular robotic apparatus body when a discrepancy exists between the actuation of the modular robotic apparatus and a target actuation thereof; and

update the learning process based on the feedback from the trainer.

2. The body of claim 1, wherein the mechanical interface is configured to selectively mate with the control apparatus by way of at least one feature on the modular robotic apparatus body.

3. The body of claim 2, wherein the selective mate is facilitated by at least one second feature on the control apparatus, the at least one second feature on the control apparatus being configured to mate directly with the at least one feature on the modular robotic apparatus body.

4. The body of claim 3, wherein the at least one second feature on the control apparatus and the at least one feature on the modular robotic apparatus body comprise complementary first and second components configured to only mate with each other.

5. The body of claim 3, wherein the at least one second feature on the control apparatus and the at least one feature on the modular robotic apparatus body comprise complementary male and female connector components having at least one electrical interface associated therewith.

6. The body of claim 1, wherein the control apparatus comprises the processor apparatus and a plurality of actuators, the control apparatus being disposed in an enclosure configured to be selectively detachable from the modular robotic apparatus body.

7. The body of claim 6, wherein the one or more actuation inputs are each configured to cause mechanical movement of one or more of the plurality of actuators.

8. The body of claim 6, wherein individual ones of the one or more actuation inputs are configured to apply electromagnetic energy by one or more of the plurality of actuators.

9. The body of claim 1, wherein the control apparatus comprises the processor apparatus and a plurality of actuators, the control apparatus being disposed in an enclosure configured to be selectively mated to or unmated from the modular robotic apparatus body.

10. The body of claim 1, wherein the feedback from the trainer is detected via at least one of the first movable element and a second movable element of the modular robotic apparatus body;

and

wherein the control apparatus is further configured to mate with another modular robotic apparatus body, and cause the other modular robotic apparatus body to perform an actuation based on the updated learning process.

11. The body of claim 1, wherein the actuation of the modular robotic apparatus comprises a trajectory thereof, and the target actuation comprises a target trajectory thereof.

12. The body of claim 1, wherein the at least one sensory interface comprises at least one of an optical interface, a thermal sensor, and an auditory sensor.