# US 2023/0406347 A1 · Preception and prediction based driving

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

- Number: US 2023/0406347 A1
- Document ID: US20230406347A1
- Status: Published application
- Kind: A1
- Application number: 18/459,416
- Filed: 2023-08-31
- Published: 2023-12-21
- Earliest claimed: 2023-05-09
- Assignees: Autobrains Technologies Ltd
- Applicants: Autobrains Technologies Ltd
- Inventors: Igal Raichelgauz
- Web page: https://patentgrep.com/patent/US20230406347A1

## CPC

- B60W 60/001: {Planning or execution of driving tasks}
- B60W 50/0097: {Predicting future conditions}
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- B60W 2300/36: Cycles; Motorcycles; Scooters
- B60W 2510/0638: Engine speed
- B60W 2554/4044: Direction of movement, e.g. backwards
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for managing a group of narrow artificial intelligence (AI) agents for at least partially autonomous driving, the method includes (i) obtaining, by a prediction circuit, a stream of metadata segments generated at multiple points in time and associated with a selection of one or more sub-groups of the group of narrow AI agents; wherein the metadata segments are selected out of (a) selected narrow AI agent identifiers, and (b) multiple multi-domain identifier, the multiple multi-domain identifier are indicative of multiple instances of multi-domain information about elements affecting a vehicle in relation to the multiple points in time; wherein a multi-domain identifier generated at a given point of time of the multiple points in time is a combination of class signatures that are indicative of classes of elements of a multi-domain information associated with the given point in time; (ii) finding, by the prediction circuit, a segment of the stream that is a predictor to a receiving of a next cluster identifier at a future point in time; and (iii) automatically predicting, when finding the predictor, at least one of: (c) future metadata segments to be received during the future point of time, or (d) a future sub-group of narrow AI agents to be selected at the future point of time.

## Claims

### Claim 1

A method for managing a group of narrow artificial intelligence (AI) agents for at least partially autonomous driving, the method comprises:
obtaining, by a prediction circuit, a stream of metadata segments generated at multiple points in time and associated with a selection of one or more sub-groups of the group of narrow AI agents; wherein the metadata segments are selected out of (a) selected narrow AI agent identifiers, and (b) multiple multi-domain identifier, the multiple multi-domain identifier are indicative of multiple instances of multi-domain information about elements affecting a vehicle in relation to the multiple points in time; wherein a multi-domain identifier generated at a given point of time of the multiple points in time is a combination of class signatures that are indicative of classes of elements of a multi-domain information associated with the given point in time;
finding, by the prediction circuit, a segment of the stream that is a predictor to a receiving of a next cluster identifier at a future point in time; and
automatically predicting, when finding the predictor, at least one of:
(a) future metadata segments to be received during the future point of time;
(b) a future sub-group of narrow AI agents to be selected at the future point of time.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the future sub-group of narrow AI agents is associated with a future sub-group of skills.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the automatically predicting triggers a predicting of a next state of the vehicle at the next point of time.

### Claim 4 (depends on 3)

The method according to claim 3, comprising triggering a determination of a response to the next state of the vehicle.

### Claim 5 (depends on 3)

The method according to claim 3, comprising determining a response to the next state of the vehicle.

### Claim 6 (depends on 1)

The method according to claim 1, comprising evaluating an accuracy of the predictor.

### Claim 7 (depends on 1)

The method according to claim 1, comprising searching, in at least the stream of metadata segments, for a new predictor.

### Claim 8 (depends on 1)

The method according to claim 1, comprising predicting, based on the predictor, selected perception modules out of multiple perception modules, to be utilized during the future point in time.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the automatically predicting of the future metadata segments triggers an execution of a driving related operation at a point in time that does not exceed the future point of time.

### Claim 10 (depends on 9)

The method according to claim 9, wherein the driving related operation involves changing a speed of the vehicle.

### Claim 11 (depends on 9)

The method according to claim 9, wherein the driving related operation involves changing a direction of the vehicle.

### Claim 12

A non-transitory computer readable medium for managing a group of narrow artificial intelligence (AI) agents for at least partially autonomous driving, the non-transitory computer readable medium stores instructions for:
obtaining, by a prediction circuit, a stream of metadata segments generated at multiple points in time and associated with a selection of one or more sub-groups of the group of narrow AI agents; wherein the metadata segments are selected out of (a) selected narrow AI agent identifiers, and (b) multiple multi-domain identifier, the multiple multi-domain identifier are indicative of multiple instances of multi-domain information about elements affecting a vehicle in relation to the multiple points in time; wherein a multi-domain identifier generated at a given point of time of the multiple points in time is a combination of class signatures that are indicative of classes of elements of a multi-domain information associated with the given point in time;
finding, by the prediction circuit, a segment of the stream that is a predictor to a receiving of a next cluster identifier at a future point in time; and
automatically predicting, when finding the predictor, at least one of:
(a) future metadata segments to be received during the future point of time;
(b) a future sub-group of narrow AI agents to be selected at the future point of time.

### Claim 13 (depends on 12)

The non-transitory computer readable medium according to claim 12, wherein the future sub-group of narrow AI agents is associated with a future sub-group of skills.

### Claim 14 (depends on 12)

The non-transitory computer readable medium according to claim 12, wherein the automatically predicting triggers a predicting of a next state of the vehicle at the next point of time.

### Claim 15 (depends on 14)

The non-transitory computer readable medium according to claim 14, comprising triggering a determination of a response to the next state of the vehicle.

### Claim 16 (depends on 14)

The non-transitory computer readable medium according to claim 14, comprising determining a response to the next state of the vehicle.

### Claim 17 (depends on 12)

The non-transitory computer readable medium according to claim 12, comprising evaluating an accuracy of the predictor.

### Claim 18 (depends on 12)

The non-transitory computer readable medium according to claim 12, comprising searching, in at least the stream of metadata segments, for a new predictor.

### Claim 19 (depends on 12)

The non-transitory computer readable medium according to claim 12, comprising predicting, based on the predictor, selected perception modules out of multiple perception modules, to be utilized during the future point in time.

### Claim 20 (depends on 12)

The non-transitory computer readable medium according to claim 12, wherein the automatically predicting of the future metadata segments triggers an execution of a driving related operation at a point in time that does not exceed the future point of time.
