# US 2026/0303691 A1 · Self-learning system with sensors

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

- Number: US 2026/0303691 A1
- Document ID: US20260303691A1
- Status: Published application
- Kind: A1
- Application number: 19/695,665
- Filed: 2026-06-02
- Published: 2026-10-01
- Earliest claimed: 2020-12-07
- Assignees: Schreder Illuminaçao SA
- Applicants: Schreder Illuminaçao SA
- Inventors: Lourenço BANDEIRA; André GLÓRIA; Michael STEURER
- Web page: https://patentgrep.com/patent/US20260303691A1

## CPC

- H04L 67/125: involving control of end-device applications over a network
- H04L 41/16: using machine learning or artificial intelligence
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A system comprising: at least a first sensor (13a) and a second sensor (13b) arranged at one or more edge devices (10), the first sensor (13a), respectively the second sensor (13b), being configured for obtaining first, respectively second, environmental data (Eda, Edb) related to an event in the vicinity of the one or more edge devices; a first processing means (12a, 22a) configured to process said first environmental data (EDa) in accordance with a first set of rules to generate first processed data (PDa) and a second processing means (12b, 22b) configured to process said second environmental data (EDb) in accordance with a second set of rules to generate second processed data (PDb); a control means (17, 27) configured to control the first and second processing means such that the second processed data (PD2) is used to train the first processing means.

## Claims

### Claim 1

An edge device configured to be arranged in a network with one or more other edge devices, said one or more edge devices being preferably arranged in the vicinity of each other, said edge device comprising:
a plurality of data sources including at least a first sensor configured for obtaining first sensed data related to an event in the vicinity of the one or more edge devices and a second sensor configured for obtaining second sensed data related to an event in the vicinity of the one or more edge devices;
an edge processing means configured to produce first processed data by processing in accordance with a first set of classification and/or prediction rules data based on the first sensed data and to produce second processed data by processing in accordance with a second set of classification and/or prediction rules data based on the second sensed data;
a control means configured to fuse the first and second processed data by decision fusion to obtain a final modelling result.

### Claim 2 (depends on 1)

The edge device of claim 1, wherein the final modelling result comprises at least one of: a classification, an attribute, a prediction.

### Claim 3 (depends on 1)

The edge device of claim 1, wherein the control means is configured for generating first control data to change the first set of classification and/or prediction rules of the edge processing means based on the second processed data and/or for generating second control data to change the second set of classification and/or prediction rules of the edge processing means based on the first processed data.

### Claim 4 (depends on 1)

The edge device of claim 1, wherein the control means is configured for updating the first set of classification and/or prediction rules and/or the second set of classification and/or prediction rules with a new set of rules for new classes and/or subclasses and/or attributes and/or predictions based on the final modelling result of the decision fusion.

### Claim 5 (depends on 1)

The edge device according to claim 1, wherein the edge processing means is configured to state estimate the first sensed data and the second sensed data separately to extract at least one first feature and at least one second feature related to the event, respectively,
wherein the producing of the first processed data comprises processing the at least one first feature and the at least one second feature related to the event separately.

### Claim 6 (depends on 1)

The edge device of claim 1, wherein the plurality of data sources further comprises a third sensor configured for obtaining first sensed data related to an event in the vicinity of the one or more edge devices, wherein the edge processing means is configured to produce the first processed data by processing in accordance with the first set of classification and/or prediction rules data based on the first sensed data and the third sensed data.

### Claim 7 (depends on 6)

The edge device of claim 6, wherein the edge processing means is configured to state estimate the first sensed data and the third sensed data separately to extract at least one first feature and at least one third feature related to the event, respectively,
wherein the edge processing means is configured to group and combine the at least one first feature and the at least one third feature by data association;
wherein the producing of the first processed data comprises processing the result of the data association.

### Claim 8 (depends on 7)

The edge device of claim 7, wherein data association comprises recognizing a similar feature in the at least one first feature and the at least one third feature and/or weighting the at least one first feature and the at least one third feature to obtain a vector of features, wherein preferably a dimension of the vector of features is larger than each of the at least one first feature and at least one third feature.

### Claim 9 (depends on 7)

The edge device of claim 7, wherein the edge processing means is configured to state estimate the second sensed data separately to extract at least one second feature related to the event;
wherein the producing of the second processed data comprises processing the at least one second feature;
wherein the data association comprises grouping and combining the second processed data with the at least one first feature and the at least one third feature.

### Claim 10 (depends on 1)

The edge device of claim 1, wherein decision fusion includes deciding based on a ranking of the first and second set of classification and/or prediction rules.

### Claim 11 (depends on 10)

The edge device of claim 10, wherein the ranking is based on any one of: the number of classes, the number of subclasses, the number of attributes, the accuracy of the attributes, a reliability index derived from environment conditions and historical data.

### Claim 12 (depends on 1)

The edge device of claim 1, further comprising an edge communication means configured to receive data about the event from a central database; wherein the decision fusion further comprises fusing the first and second processed data with the received data.

### Claim 13 (depends on 12)

The edge device according to claim 12, wherein the central database comprises at least one of: a traffic database, a weather database, a regulation database, and an infrastructure database.

### Claim 14 (depends on 12)

The edge device according to claim 12, wherein the control means is configured to adjust measurement settings of the first and/or second sensor based on the received data.

### Claim 15

An edge device configured to be arranged in a network with one or more other edge devices, said one or more edge devices being preferably arranged in the vicinity of each other, said edge device comprising:
a plurality of data sources including at least a first sensor configured for obtaining first sensed data related to an event in the vicinity of the edge device, and a second sensor configured for obtaining second sensed data related to an event in the vicinity of the edge device;
a processing means configured to produce first processed data and second processed data by processing independently in accordance with a first set of classification and/or prediction rules and a second set of classification and/or prediction rules, respectively, data based on the first sensed data and the second sensed data, respectively;
a control means configured to fuse the first and second processed data by decision fusion to obtain a final modelling result.

### Claim 16 (depends on 15)

The edge device according to claim 15, wherein the control means is configured for generating first control data to change the first set of classification and/or prediction rules of the edge processing means based on the second processed data.

### Claim 17 (depends on 15)

The edge device according to claim 15, wherein the edge processing means is configured to state estimate the first sensed data and the second sensed data separately to extract at least one first feature and at least one second feature related to the event, respectively,
wherein the producing of the first processed data and the second processed data comprises processing the at least one first feature and the at least one second feature, respectively.

### Claim 18

An edge device configured to be arranged in a network with one or more other edge devices, said one or more edge devices being preferably arranged in the vicinity of each other, said edge device comprising:
a first plurality of data sources including at least a first sensor configured for obtaining first sensed data related to an event in the vicinity of the one or more edge devices and a second sensor configured for obtaining second sensed data related to an event in the vicinity of the one or more edge devices;
a second plurality of data sources including at least a third sensor configured for obtaining third sensed data related to an event in the vicinity of the one or more edge devices and at least a fourth sensor configured for obtaining fourth sensed data related to an event in the vicinity of the one or more edge devices;
an edge processing means configured to produce first processed data by processing in accordance with a first set of classification and/or prediction rules data based on the sensed data obtained from the first plurality of data sources and to produce second processed data by processing in accordance with a second set of classification and/or prediction rules data based on the sensed data obtained from the second plurality of data sources;
a control means configured to fuse the first and second processed data by decision fusion to obtain a final modelling result.

### Claim 19 (depends on 18)

The edge device of claim 18, wherein the edge processing means is configured to state estimate the first, second, third and fourth sensed data separately to extract at least one first feature, at least one second feature, at least one third feature, and at least one fourth feature related to the event, respectively,
wherein the edge processing means is configured to group and combine the at least one first feature and the at least one second feature by a first data association and to group and combine the at least one third feature and the at least one fourth feature by a second data association;
wherein the producing of the first processed data and the second processed data comprises processing the result of the first data association and the second data association, respectively.

### Claim 20 (depends on 18)

The edge device of claim 18, wherein data association comprises recognizing a similar feature in the at least one first feature and the at least one second feature and/or weighting the at least one first feature and the at least one second feature to obtain a vector of features, wherein preferably a dimension of the vector of features is larger than each of the at least one first feature and at least one second feature.
