# US 2004/0019425 A1 · Collision and injury mitigation system using fuzzy cluster tracking

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

- Number: US 2004/0019425 A1
- Document ID: US20040019425A1
- Status: Published application
- Kind: A1
- Application number: 10/201,676
- Filed: 2002-07-23
- Published: 2004-01-29
- Earliest claimed: 2002-07-23
- Assignees: Ford Global Technologies, LLC
- Inventors: Nicholas Zorka; Ka C. Cheok; Manoharprasad K. Rao; Edzko Smid
- Web page: https://patentgrep.com/patent/US20040019425A1

## CPC

- G08G 1/163: {involving continuous checking}
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})

## Abstract

A collision and injury mitigation system (10) for an automotive vehicle (12) is provided. The system (10) includes two or more object detection sensors (15) that detect an object and generate one or more object detection signals. A controller (16) is electrically coupled to the two or more object detection sensors and performs a fuzzy logic technique to classify the object as a real object or a false object in response to the one or more object detection signals. A method for performing the same is also provided.

## Claims

### Claim 1

A collision and injury mitigation system for an automotive vehicle comprising:
two or more object detection sensors detecting an object and generating one or more object detection signals; and
a controller electrically coupled to said two or more object detection sensors performing a fuzzy logic technique to classify said object as a real object or a false object in response to said one or more object detection signals.

### Claim 2 (depends on 1)

A system as in claim 1 wherein performing a fuzzy logic to classify said object comprises performing a clustering method.

### Claim 3 (depends on 1)

A system as in claim 1 further comprises said controller using triangulation in combination with said fuzzy logic to classify said object.

### Claim 4 (depends on 1)

A system as in claim 1 further comprising a filter to track said object relative to the vehicle or an object other than the vehicle.

### Claim 5 (depends on 4)

A system as in claim 4 wherein said filter is a Kalman filter.

### Claim 6 (depends on 1)

A system as in claim 1 wherein said controller in classifying said object determines velocity of said object relative to the vehicle or an object other than the vehicle.

### Claim 7 (depends on 1)

A system as in claim 1 wherein said controller in classifying said object determines direction of travel of said object relative to the vehicle or an object other than the vehicle.

### Claim 8 (depends on 1)

A system as in claim 1 wherein said controller in classifying said object predicts velocity of said object relative to the vehicle or an object other than the vehicle.

### Claim 9 (depends on 1)

A system as in claim 1 wherein said controller in classifying said object predicts direction of travel of said object relative to the vehicle or an object other than the vehicle.

### Claim 10 (depends on 1)

A system as in claim 1 wherein said controller in classifying said object utilizes magnitude of said one or more object detection signals.

### Claim 11 (depends on 1)

A system as in claim 1 further comprising:
a countermeasure electrically coupled to said controller;
said controller activating said countermeasure in response to said object classification.

### Claim 12 (depends on 1)

A system as in claim 1 wherein said controller assesses the threat of said object in response to said object classification.

### Claim 13

A method of classifying an object by a collision and injury mitigation system for an automotive vehicle comprising:
detecting an object and generating one or more object detection signals; and
performing a fuzzy logic technique to classify said detected object as a real object or a false object in response to said one or more object detection signals.

### Claim 14 (depends on 13)

A method as in claim 13 further comprising assessing the threat of said one or more objects in response to said object classification.

### Claim 15 (depends on 13)

A method as in claim 13 further comprising filtering said one or more object detection signals to track said object.

### Claim 16 (depends on 13)

A method as in claim 13 further comprises filtering said one or more object detection signals to predict the future path of said object.

### Claim 17 (depends on 13)

A method as in claim 13 wherein said clustering method comprises using at least one of the following: amplitude information, range rate information, or range information.

### Claim 18

A method of classifying an object by a collision and injury mitigation system for an automotive vehicle comprising:
detecting one or more objects and generating one or more object detection signals;
performing a triangulation technique on said object detection signals and generating an object detection database;
performing a fuzzy logic clustering technique on said object detection database and generating clusters;
filtering said clusters to remove false objects from said object detection database and generating an real object list; and
classifying objects in said real object list.

### Claim 19 (depends on 18)

A method as in claim 18 further comprising determining admissibility of said object detection signals.

### Claim 20 (depends on 18)

A method as in claim 18 further comprising assessing the threat of an object in said real object list.

### Claim 21

A collision and injury mitigation system for an automotive vehicle comprising:
two or more object detection sensors detecting an object and generating one or more object detection signals;
a countermeasure; and
a controller electrically coupled to said two or more object detection sensors performing a triangulation technique and a fuzzy logic technique to generate clusters and filtering said clusters to classify said object as a real object or a false object in response to said one or more object detection signals, said controller activating said countermeasure in response to said object classification.
