# US 2023/0276122 A1 · Adaptive system for autonomous machine learning and control in wearable augmented reality and virtual reality visual aids

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0276122 A1
- Document ID: US20230276122A1
- Status: Published application
- Kind: A1
- Application number: 18/069,506
- Filed: 2022-12-21
- Published: 2023-08-31
- Earliest claimed: 2018-03-06
- Assignees: Eyedaptic, Inc.
- Applicants: Eyedaptic, Inc.
- Inventors: David A. WATOLA; Jay E. CORMIER; Brian KIM
- Web page: https://patentgrep.com/patent/US20230276122A1

## CPC

- G06N 3/08: Learning methods
- G06V 10/764: using classification, e.g. of video objects
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- H04N 23/62: Control of parameters via user interfaces
- H04N 23/64: {Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image}
- H04N 23/681: {Motion detection}
- H04N 23/951: by using two or more images to influence resolution, frame rate or aspect ratio
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Adaptive control systems using augmented and virtual reality systems chimerically integrated with Artificial Intelligence and the like Homunculi fix vision issues with data based and user tuned solutions in real time.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method of presenting images to a user of a visual aid device, comprising the steps of:
capturing real-time video images of a scene with a camera of the visual aid device;
inputting at least one of the real-time video images into a classifier of the visual aid device;
in the classifier, analyzing the at least one of the real-time video images to select a display state template that is appropriate for the scene;
inputting the display state template and at least one of the real-time video images into a machine learning system of the visual aid device;
in the machine learning system, determining if a user-preferred device configuration exists for the scene and, if the user-preferred device configuration exists, modifying the display state template based on the user-preferred device configuration;
applying parameters that accompany the display state template to the real-time video images to produce modified images;
presenting the modified images to the user on a display of the visual aid device.

### Claim 22 (depends on 21)

The method of claim 21, wherein the display state templates are selected from the group consisting of a wide template, an intermediate template, and a close template.

### Claim 23 (depends on 21)

The method of claim 21, wherein applying parameters that accompany the display state template comprises adjusting a magnification of at least a portion of the real-time video images.

### Claim 24 (depends on 21)

The method of claim 21, wherein the display state template comprises a wide display state template and wherein applying parameters that accompany the display state template further comprises applying no magnification to the real-time video images.

### Claim 24 (depends on 21)

The method of claim 21, wherein the display state template comprises an intermediate display state template and wherein applying parameters that accompany the display state template further comprises applying moderate magnification to at least a portion of the real-time video images.

### Claim 25 (depends on 21)

The method of claim 21, wherein the display state template comprises a close display state template and wherein applying parameters that accompany the display state template further comprises applying high magnification to at least a portion of the real-time video images.

### Claim 26 (depends on 25)

The method of claim 25, further comprising applying high magnification over most of the real-time video images.

### Claim 27 (depends on 21)

The method of claim 21, wherein the display state template comprises a central display state template and wherein applying parameters that accompany the display state template further comprises applying increased central magnification to the real-time video images.

### Claim 28 (depends on 27)

The method of claim 27, further comprising tapering the central magnification to neutral at edges of the real-time video images.

### Claim 29 (depends on 21)

The method of claim 21, wherein prior to inputting the selected display state template and at least one of the real-time video images into the machine learning system, the method further comprises training the machine learning system to determine the user-preferred device configuration for a variety of scenes.

### Claim 30 (depends on 29)

The method of claim 29, wherein training the machine learning system further comprises evaluating prior situations in which the user made manual adjustment to settings corresponding to the selected display state template and at least one of the real-time video images.

### Claim 31 (depends on 21)

The method of claim 21, further comprising receiving an input from the user to provide an immediate but temporary learning in a second machine learning system of an association between the scene and the display state template.

### Claim 32 (depends on 31)

The method of claim 31, wherein the input is received by a button on the visual aid device.

### Claim 34 (depends on 21)

The method of claim 21, wherein the classifier identifies individual image features useful for selecting the display state template.

### Claim 35 (depends on 21)

The method of claim 21, further comprising, prior to the presenting step:
evaluating real-time sensor data of the visual aid device with the processor; and
wherein presenting the modified images to the user further comprises presenting the modified images to the user on a display of the visual aid device only if the visual aid device is not being subjected to significant rotation or acceleration.
