# US 2024/0394039 A1 · Methods and apparatus for automatically labeling data processing events in autonomous driving vehicles via machine learning

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

- Number: US 2024/0394039 A1
- Document ID: US20240394039A1
- Status: Published application
- Kind: A1
- Application number: 18/793,531
- Filed: 2024-08-02
- Published: 2024-11-28
- Earliest claimed: 2022-01-07
- Assignees: PlusAI, Inc.
- Applicants: PlusAI, Inc.
- Inventors: Gael Gurvan COLAS; Mayank GUPTA; Anurag GANGULI; Timothy P. DALY, JR.
- Web page: https://patentgrep.com/patent/US20240394039A1

## CPC

- G06F 8/65: Updates (security arrangements therefor G06F21/57)
- G06F 8/35: model driven
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In some embodiments, a method comprises receiving, at a processor of an autonomous vehicle and from at least one sensor, sensor data distributed within a time window. A first event being a first event type occurring at a first time in the time window is identified by the processor using a software model based on the sensor data. At least one first attribute associated with the first event is extracted by the processor. A second event being the first event type occurring at a second time in the time window is identified by the processor based on the at least one first attribute. In response to determining that the second event is not yet recognized as being the first event type, a first label for the second event is generated by the processor.

## Claims

### Claim 1

A computer-implemented method comprising:
selecting, by a computing system, a first set of attributes associated with a first event relating to an event type;
determining, by the computing system, a second set of attributes associated with a second event with respect to the first set of attributes; and
without human intervention, generating, by the computing system, a label for the second event to train a machine learning model.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the first set of attributes is a minimum number of attributes selected from a list of predetermined attributes to be considered an occurrence of an event associated with the event type.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the label indicates a false-positive when the second event was previously misidentified or a false-negative when the second event was previously not identified.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein an attribute of the first set of attributes is associated with at least one of a color, shape, size, relative location, absolute location, speed, movement pattern, and unique identifier of an object.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein an attribute of the first set of attributes is associated with at least one of a color, weather, relative location, absolute location, size, shape, unique identifier, curvature, boundaries, and grade of a place.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein an attribute of the first set of attributes is associated with at least one of duration, speed, movement pattern, relative location, and absolute location of an action.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the first set of attributes are extracted based on a second machine learning model.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the event type comprises at least one of a discrepancy between expected movement and actual movement of an object, a driving maneuver, and detection of an object.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, further comprising:
retraining the machine learning model based on the second event and the label.

### Claim 10 (depends on 9)

The computer-implemented method of claim 9, further comprising:
providing data associated with a third event to the retrained machine learning model; and
generating by the retrained machine learning model a label associated with the third event that indicates the event type.

### Claim 11

A system comprising:
at least one processor; and
a memory operably coupled to the at least one processor and storing instructions to cause the at least one processor to perform operations comprising:
selecting a first set of attributes associated with a first event relating to an event type;
determining a second set of attributes associated with a second event with respect to the first set of attributes; and
without human intervention, generating a label for the second event to train a machine learning model.

### Claim 12 (depends on 11)

The system of claim 11, wherein the first set of attributes is a minimum number of attributes selected from a list of predetermined attributes to be considered an occurrence of an event associated with the event type.

### Claim 13 (depends on 11)

The system of claim 11, wherein the label indicates a false-positive when the second event was previously misidentified or a false-negative when the second event was previously not identified.

### Claim 14 (depends on 11)

The system of claim 11, wherein an attribute of the first set of attributes is associated with at least one of a color, shape, size, relative location, absolute location, speed, movement pattern, and unique identifier of an object.

### Claim 15 (depends on 11)

The system of claim 11, wherein an attribute of the first set of attributes is associated with at least one of a color, weather, relative location, absolute location, size, shape, unique identifier, curvature, boundaries, and grade of a place.

### Claim 16

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations comprising:
selecting a first set of attributes associated with a first event relating to an event type;
determining a second set of attributes associated with a second event with respect to the first set of attributes; and
without human intervention, generating a label for the second event to train a machine learning model.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the first set of attributes is a minimum number of attributes selected from a list of predetermined attributes to be considered an occurrence of an event associated with the event type.

### Claim 18 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the label indicates a false-positive when the second event was previously misidentified or a false-negative when the second event was previously not identified.

### Claim 19 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein an attribute of the first set of attributes is associated with at least one of a color, shape, size, relative location, absolute location, speed, movement pattern, and unique identifier of an object.

### Claim 20 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein an attribute of the first set of attributes is associated with at least one of a color, weather, relative location, absolute location, size, shape, unique identifier, curvature, boundaries, and grade of a place.
