Persistent predictor apparatus and methods for task switching

• US 10,131,052 B1
• Filed: 05/06/2015
• Issued: 11/20/2018
• Est. Priority Date: 10/02/2014
• Status: Active Grant

• Current Assignee: Brain Corporation
• Original Assignee: Brain Corporation
• Inventors: Ibarz Gabardos, Borja, Sinyavskiy, Oleg
• Primary Examiner(s): Cassity, Robert A
• Assistant Examiner(s): Coughlan, Peter D
• Application Number:
  US14/705,487
• Time in Patent Office: 1,294 Days
• CPC Class Codes: B25J 9/0081 with master teach-in means
• CPC Class Codes: B25J 9/1602 characterised by the control system, structure, architecture
• CPC Class Codes: B25J 9/1607 Calculation of inertia, jacobian matrixes and inverses
• 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: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/00 Computing arrangements based on biological models
• 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
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/03 Teaching system
• CPC Class Codes: Y10S 901/09 Closed loop, sensor feedback controls arm movement
• CPC Class Codes: Y10S 901/47 Optical

Abstract

An apparatus and methods for training and/or operating a robotic device to perform a target task autonomously. The target task execution may be configured based on analysis of sensory context by the robot. Target action may comprise execution of two or more mutually exclusive actions for a given context. The robotic device may be operable in accordance with a persistent switching process. For a given sensor input, the switching process may be trained to select one of two or more alternative actions based on a prior action being executed. Switching process operation may comprise assigning priorities to the available tasks based on the sensory context; the task priorities may be modified during training based on input from a trainer. The predicted task priorities may be filtered by a “persistent winner-take-all process configured to switch from a current task to another task based on the priority breaching a switching threshold.

Claims

1. A non-transitory machine-readable storage medium having instructions embodied thereon, the instructions being executable by one or more processors to effectuate training of a learning component configured to operate a robotic apparatus, the instructions configured to, when executed cause the one or more processors to:

provide a first control output, the first control output configured to cause the robotic apparatus to execute a first physical action;

receive a feature occurrence information comprising feedback via a sensor of the robotic apparatus;

cause production of a predicted output comprising a first vector from the learning component based on an occurrence of a feature in the received feature occurrence information, the predicted output configured to automatically cause the robotic apparatus to execute a second physical action based on one or more components of the first vector which is selected from a first range of values between a first value and a second value;

produce a training input indicative of a target physical action, the training input comprises one or more components of a second vector selected from a second range of values between a third and fourth value;

cause a combination of the training input and the predicted output via a combiner to produce a second control output comprising a third vector, the second control output configured to maintain execution of the first physical action by the robotic apparatus or execute the second physical action based on an analysis of one or more components of the third vector which is selected from a third range of values between the first value and the second value;

provide the second control output to the learning component; and

adapt the learning component in accordance with a discrepancy measure between the second control output and the predicted output;

wherein the adaptation of the learning configuration is configured to cause the learning component to produce the second control output upon the occurrence of the feature during execution of the first action.

2. The non-transitory machine-readable storage medium of claim 1, wherein:

a second control output is determined by an overriding combiner component configured to produce;

the second control output corresponding to the training input when the training input comprises a non-trivial indication; and

the second control output corresponding to the predicted output when the training input comprises a trivial indication.

3. The non-transitory machine-readable storage medium of claim 2, wherein the non-trivial indication comprises a non-zero signal.

4. The non-transitory machine-readable storage medium of claim 2, wherein the trivial indication comprises a zero-valued signal.

5. The non-transitory machine-readable storage medium of claim 1, wherein:

a second control output is characterized by an active state configured to automatically cause the robotic apparatus to execute the second physical action; and

an inactive state configured to be ignored by the robotic apparatus; and

the second control output is effectuated by the combiner, the combiner being operable in accordance with a state-persistent process characterized by a threshold, the process configured to;

produce the active state of the second control output when a combination of the training input and the predicted output breaches the threshold; and

produce the inactive state of the second control output when the combination of the training input and the predicted output does not breach the threshold.

6. The non-transitory machine-readable storage medium of claim 5, wherein:

the active state comprises a positive value; and

the inactive state comprises a negative value.

7. The non-transitory machine-readable storage medium of claim 5, wherein:

the predicted output comprises the first vector, the first vector comprised of a first component configured to activate the first physical action, and a second component configured to activate the second physical action;

the training input comprises the second vector, the second vector being comprised of a plurality of components;

the second control output comprises the third vector being comprised of a plurality of components; and

the threshold of the state-persistent process is performed on a component-by component basis.

8. The non-transitory machine-readable storage medium of claim 7, wherein a sum of the plurality of components of the third vector is one.

9. The non-transitory machine-readable storage medium of claim 1, wherein the second control output is generated by an additive combiner component configured to produce the second control output, the additive combiner component configured to generate the combination of the training input and the predicted output when the training input comprises a trivial indication;

and generate the training input when the training input comprises a non-trivial indication.

10. A robotic apparatus comprising:

a sensor interface configured to receive sensor data related to an environment of the robotic apparatus;

an interface configured to receive a training input;

a feature detection component;

an output prediction component in operable communication with the feature detection component and the interface, the output prediction component comprising logic configured to, based on a feature detection indication produced by the feature detection component, to produce a first task activation indication and a second task activation indication; and

a switching component configured to, responsive to the production of the feature detection indication;

evaluate a current active task indication;

based on an occurrence of a first sensory input via the sensor interface during execution of a first physical task by the robotic apparatus, and based on the current active task indication corresponding to a third physical task, provide a first task activation output comprising the first task activation indication, the first task action indication being configured to automatically cause the robotic apparatus to execute the third physical task associated therewith; and

based on the occurrence of the first sensory input via the sensor interface during execution of a second physical task by the robotic apparatus, and based on the current active task indication corresponding to a fourth physical task, provide a second task activation output comprising the second task activation indication, the second task action indication being configured to automatically cause the robotic apparatus to execute the fourth physical task associated therewith, the fourth physical task differing from the third physical task;

wherein;

the third and the fourth physical tasks differ from one another so as to produce outcomes different from one another.

11. The robotic apparatus of claim 10, wherein the first, the second, the third and the fourth physical tasks differ from one another so as to produce outcomes different from one another.

12. The robotic apparatus of claim 10, wherein the first and the second physical tasks differ from one another so as to produce outcomes different from one another.

13. The robotic apparatus of claim 10, further comprising:

a first and second actuator operably coupled to the switching component;

wherein the first task activation output is configured to activate the first actuator; and

the second task activation output is configured to activate the second actuator.

14. The robotic apparatus of claim 13, wherein

the first actuator activation is configured to displace the robotic apparatus from a first coordinate to a second coordinate, and the second actuator activation is configured to displace the robotic apparatus from the first coordinate to a third coordinate substantially different from the second coordinate.

15. The robotic apparatus of claim 13, wherein:

the robotic apparatus is characterized by a state;

the first activation indication is configured to modify a current instance of the state to a first state; and

the second activation indication is configured to modify the current instance of the state to a second state, the second state being different from the first state.

16. The robotic apparatus of claim 15, wherein the state is characterized by a state parameter selected from the group consisting of a position of the robotic apparatus, a characteristic of motion of the robotic apparatus, and an orientation of the robotic apparatus.

17. The robotic apparatus of claim 15, further comprising a first mechanical element and a second mechanical element;

wherein the state is characterized by a state parameter conveying information related to mutual orientation of the first and the second mechanical element.

18. The robotic apparatus of claim 15, further comprising a mechanical element characterized by a dimension of a plurality of possible dimensions;

and

wherein the state comprises a first dimension.