Predictive robotic controller apparatus and methods

• US 10,369,694 B2
• Filed: 04/23/2018
• Issued: 08/06/2019
• Est. Priority Date: 06/14/2013
• Status: Active Grant

• Current Assignee: Brain Corporation
• Original Assignee: Brain Corporation
• Inventors: Laurent, Patryk, Passot, Jean-Baptiste, Sinyavskiy, Oleg, Ponulak, Filip, Ibarz Gabardos, Borja, Izhikevich, Eugene
• Primary Examiner(s): Tran, Khoi H
• Assistant Examiner(s): Peche, Jorge O
• Application Number:
  US15/960,300
• Publication Number:
  US 20180311817A1
• Time in Patent Office: 470 Days
• CPC Class Codes: B25J 9/163 learning, adaptive, model based, rule based expert control
• CPC Class Codes: G05B 2219/39271 Ann artificial neural network, ffw-nn, feedforward neural network
• CPC Class Codes: G05B 2219/39289 Adaptive ann controller
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
• CPC Class Codes: G06N 3/049 Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs

Abstract

Robotic devices may be trained by a user guiding the robot along target action trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control signal based on one or more of the user guidance, sensory input, performance measure, and/or other information. Training may comprise a plurality of trials, wherein for a given context the user and the robot'"'"'s controller may collaborate to develop an association between the context and the target action. Upon developing the association, the adaptive controller may be capable of generating the control signal and/or an action indication prior and/or in lieu of user input. The predictive control functionality attained by the controller may enable autonomous operation of robotic devices obviating a need for continuing user guidance.

Claims

1. A non-transitory computer-readable medium having a plurality of computer readable instructions stored thereon, that when executed by at least one processor, configured the at least one processor to,

determine maneuvering of a device by dividing a desired task to be performed by the device into a hierarchy of tasks, the hierarchy of tasks including at least a first priority level and a second priority level, the first priority level and the second priority level each including a respective sub-set of tasks, wherein each of the respective sub-set of tasks being associated with a weight parameter;

the weight parameter is a value corresponding to the desired task to be performed by the device;

output a signal to at least one actuator on the device based on the determined maneuvering of the device; and

adjust, during a learning trial, the weight parameter associated with at least one of the respective sub-set of tasks based on a teaching input from a user, the teaching input being received in response to the determined maneuvering of the device.

2. The non-transitory computer-readable medium of claim 1, wherein

the weight parameter of at least two tasks in the respective sub-set of tasks in the first priority level is different.

3. The non-transitory computer-readable medium of claim 1, wherein

the weight parameter of at least two tasks in the respective sub-set of tasks in the second priority level are same.

4. The non-transitory computer-readable medium of claim 1, wherein the at least one processor is further configured to execute the computer readable instructions to,

distinguish respective tasks in the respective sub-set of tasks in the first priority level, the respective tasks for the device in the first priority level including at least right turn, left turn, forward movement and backward movement.

5. The non-transitory computer-readable medium of claim 1, wherein the at least one processor is further configured to execute the computer readable instructions to,

distinguish respective tasks in the respective sub-set of tasks in the second priority level, the respective tasks for the device in the second priority level including at least activating first motor and activating second motor.

6. The non-transitory computer-readable medium of claim 2, wherein the at least one processor is further configured to execute the computer readable instructions to,

manipulate the weight parameter of the respective sub-set of tasks in the first priority level based on a determined learning parameter and changes in environment context of the device.

7. A method for maneuvering a device along a path, comprising:

determining maneuvering of a device by dividing a desired task to be performed by the device into a hierarchy of tasks, the hierarchy of tasks including at least a first priority level and a second priority level, the first priority level and the second priority level each including a respective sub-set of tasks, wherein each of the respective sub-set of tasks being associated with a weight parameter;

the weight parameter is a value corresponding to the desired task to be performed by the device, and,

outputting a signal to at least one actuator on the device based on the determined maneuvering of the device, and

adjusting, during a learning trial, the weight parameter associated with at least one of the respective sub-set of tasks based on a teaching input from a user, the teaching input being received in response to the determined maneuvering of the device.

8. The method of claim 7, wherein the weight parameter of at least two tasks in the sub-set of tasks in the first priority level is different.

9. The method of claim 7, wherein the weight parameter of at least two tasks in the sub-set of tasks in the second priority level are same.

10. The method of claim 7, further comprising:

distinguishing respective tasks in the respective sub-set of tasks in the first priority level, the respective tasks for the device in the first priority level including at least right turn, left turn, forward movement and backward movement.

11. The method of claim 7, further comprising:

distinguishing respective tasks in the respective sub-set of tasks in the second priority level, the respective tasks for the device in the second priority level including at least activating first motor and activating second motor.

12. The method of claim 8, further comprising:

manipulating the weight parameter of the respective sub-set of tasks in the first priority level based on a determined learning parameter and changes in environment context of the device.

13. A system for maneuvering a device along a path, comprising:

a memory having computer readable instructions stored thereon;

at least one processor configured to execute the computer readable instructions to,

determine maneuvering of a device by dividing a desired task to be performed by the device into a hierarchy of tasks, the hierarchy of tasks including at least a first priority level and a second priority level, the first priority level and the second priority level each including a respective sub-set of tasks, wherein each of the respective sub-set of tasks being associated with a weight parameter;

the weight parameter is a value corresponding to the desired task to be performed by the device;

output a signal to at least one actuator on the device based on the determined maneuvering of the device, and

adjust, during a learning trial, the weight parameter associated with at least one of the respective sub-set of tasks based on a teaching input from a user, the teaching input being received in response to the determined maneuvering of the device.

14. The system of claim 13, wherein the weight parameter of at least two tasks in the respective sub-set of tasks in the first priority level is different.

15. The system of claim 14, wherein the at least one processor is further configured to execute the computer readable instructions to,

manipulate the weight parameter of the respective sub-set of tasks in the first priority level based on a determined learning parameter and changes in environment context of the device.

16. The system of claim 13, wherein the weight parameter of at least two tasks in the respective sub-set of tasks in the second priority level are same.

17. The system of claim 13, wherein the at least one processor is further configured to execute the computer readable instructions to,

distinguish respective tasks in the respective sub-set of tasks in the first priority level, the respective tasks for the device in the first priority level including at least right turn, left turn, forward movement and backward movement.

18. The system of claim 13, wherein the at least one processor is further configured to execute the computer readable instructions to,

distinguish respective tasks in the respective sub-set of tasks in the second priority level, the respective tasks for the device in the second priority level including at least activating first motor and activating second motor.