Adaptive predictor apparatus and methods

• US 10,155,310 B2
• Filed: 09/18/2017
• Issued: 12/18/2018
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Brain Corporation
• Original Assignee: Brain Corporation
• Inventors: Izhikevich, Eugene, Sinyavskiy, Oleg, Passot, Jean-Baptiste
• Primary Examiner(s): Jen, Ian
• Application Number:
  US15/707,985
• Publication Number:
  US 20180126550A1
• Time in Patent Office: 456 Days
• CPC Class Codes: B25J 9/161 Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
• CPC Class Codes: B25J 9/163 learning, adaptive, model based, rule based expert control
• CPC Class Codes: G05B 2219/39292 Neural brain based controller based on simplified model of vertebrate nervous system
• CPC Class Codes: G05B 2219/39298 Trajectory learning
• CPC Class Codes: G05B 2219/40499 Reinforcement learning algorithm
• CPC Class Codes: G05D 1/0221 involving a learning process
• 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

Apparatus and methods for training and operating of robotic devices. Robotic controller may comprise a predictor apparatus configured to generate motor control output. The predictor may be operable in accordance with a learning process based on a teaching signal comprising the control output. An adaptive controller block may provide control output that may be combined with the predicted control output. The predictor learning process may be configured to learn the combined control signal. Predictor training may comprise a plurality of trials. During initial trial, the control output may be capable of causing a robot to perform a task. During intermediate trials, individual contributions from the controller block and the predictor may be inadequate for the task. Upon learning, the control knowledge may be transferred to the predictor so as to enable task execution in absence of subsequent inputs from the controller. Control output and/or predictor output may comprise multi-channel signals.

Claims

1. A system for minimizing error along a path, comprising:

a memory having computer readable instructions stored thereon; and

a first processor of one or more processors configured to execute the computer readable instructions to;

receive one or more first signals, the one or more first signals including output channels of N-dimensions, the one or more first signals corresponding to information stored in a look-up table for one or more inputs generated by one or more sensors;

receive one or more second signals, the one or more second signals including input channels of M-dimensions different from the N-dimensions; and

output one or more third signals, the one or more third signals including a combination of each one of the one or more first signals with each one of the one or more second signals, the one or more third signals including an output channel of a single dimension.

2. The system of claim 1, wherein the look-up table includes at least one of (i) a numerical value that corresponds to a distance between a device and an obstacle along the path and (ii) a numerical value that corresponds a turn angle for the device relative to a course along the path.

3. The system of claim 1, wherein the look-up table includes one or more counters, where each of the one or more counters corresponds to the one or more inputs generated by the one or more sensors.

4. The system of claim 1, further comprising a second processor of the one or more processors, where the second processor is configured to execute the computer readable instructions to:

generate the one or more first signals received by the first processor;

increment one or more counters in the look-up table if the one or more inputs corresponds to the one or more counters is not modified; and

decrement the one or more counters in the look-up table if the one or more inputs corresponds to the one or more counters is modified by a user input.

5. The system of claim 1, wherein the one or more first signals includes low-level commands and high-level commands based on the one or more inputs generated by the one or more sensors.

6. The system of claim 5, wherein the first processor is further configured to execute the computer readable instructions to receive the low-level commands such that either (i) one or more wheels of the device are rotated by a desired angle or (ii) a motor current of the device is modified.

7. The system of claim 5, wherein the first processor is further configured to execute the computer readable instructions to receive the high-level commands such that either (i) the device approaches an object along the path or (ii) the device avoids the object along the path.

8. A non-transitory computer readable medium having computer readable instructions stored thereon, that when executed by at least processor cause the at least one processor to:

receive one or more first signals, the one or more first signals including output channels of N-dimensions, the one or more first signals corresponding to information stored in a look-up table for one or more inputs generated by one or more sensors;

receive one or more second signals, the one or more second signals including input channels of M-dimensions different from the N-dimensions; and

output one or more third signals, the one or more third signals including a combination of each one of the one or more first signals with each one of the one or more second signals, the one or more third signals including an output channel of a single dimension.

9. The non-transitory computer readable medium of claim 8, wherein the look-up table includes at least one of (i) a numerical value that corresponds to a distance between a device and an obstacle along the path and (ii) a numerical value that corresponds a turn angle for the device relative to a course along the path.

10. The non-transitory computer readable medium of claim 8, wherein the look-up table includes one or more counters, where each of the one or more counters corresponds to the one or more inputs generated by the one or more sensors.

11. The non-transitory computer readable medium of claim 8, wherein the at least one processor is further configured to execute the computer readable instructions to increment one or more counters in the look-up table if the one or more inputs corresponds corresponding to the one or more counters is not modified, and decrement the one or more counters in the look-up table if the one or more inputs corresponds to the one or more counters is modified by a user input.

12. The non-transitory computer readable medium of claim 8, wherein the one or more first signals includes low-level commands and high-level commands based on the one or more inputs generated by the one or more sensors.

13. The non-transitory computer readable medium of claim 12, wherein the at least one processor is further configured to execute the computer readable instructions to receive the low-level commands such that either (i) one or more wheels of the device are rotated by a desired angle or (ii) a motor current of the device is modified.

14. The non-transitory computer readable medium of claim 12, wherein the at least one processor is further configured to execute the computer readable instructions to receive the high-level commands such that either (i) the device approaches an object along the path or (ii) the device avoids the object along the path.

15. A method for minimizing error along a path, comprising:

receiving one or more first signals, the one or more first signals including output channels of N-dimensions, the one or more first signals corresponding to information stored in a look-up table for one or more inputs generated by one or more sensors;

receiving one or more second signals, the one or more second signals including input channels of M-dimensions different from the N-dimensions; and

outputting one or more third signals, the outputting of the one or more third signals including combining each one of the one or more first signals with each one of the one or more second signals, the one or more third signals including an output channel of a single dimension.

16. The method of claim 15, wherein the look-up table includes storing at least one of (i) a numerical value that corresponds to distance between a device and an obstacle along the path and (ii) a numerical value that corresponds a turn angle for the device relative to a course along the path.

17. The method of claim 15, wherein the look-up table includes storing one or more counters, each of the one or more counters corresponds to the one or more inputs generated by the one or more sensors.

18. The method of claim 15, further comprising:

incrementing one or more counters in the look-up table if the one or more inputs corresponds to the one or more counters is not modified; and

decrementing the one or more counters in the look-up table if the one or more inputs corresponds to the one or more counters is modified by a user input.

19. The method of claim 15, wherein the receiving of the one or more first signals includes receiving low-level commands and high-level commands based on the one or more inputs generated by the one or more sensors.

20. The method of claim 19, further comprising:

receiving the low-level commands such that either (i) rotating one or more wheels of the device by a desired angle or (ii) modifying a motor current of the device.