# US 11,893,004 B2 · Anomaly detection in multidimensional sensor data

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

- Number: US 11,893,004 B2
- Document ID: US11893004B2
- Status: Granted
- Kind: B2
- Application number: 17/003,088
- Filed: 2020-08-26
- Published: 2022-03-03
- Granted: 2024-02-06
- Earliest claimed: 2020-08-26
- Assignees: Ford Global Technologies, LLC
- Applicants: Ford Global Technologies, LLC
- Inventors: Gaurav Pandey; Brian George Buss; Dimitar Petrov Filev
- Web page: https://patentgrep.com/patent/US11893004B2

## CPC

- G01S 17/89: for mapping or imaging
- G06F 16/2365: {Ensuring data consistency and integrity}
- G01D 3/032: affecting incoming signal, e.g. by averaging; gating undesired signals
- G01S 7/40: Means for monitoring or calibrating
- G01S 13/865: {Combination of radar systems with lidar systems}
- G01S 13/867: {Combination of radar systems with cameras}
- G01S 13/931: of land vehicles
- G01S 17/931: of land vehicles
- G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)}
- G05D 1/0223: {involving speed control of the vehicle (vehicle fittings for automatically controlling, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator B60K31/00)}
- G05D 1/228: Command input arrangements located on-board unmanned vehicles
- G05D 1/65: Following a desired speed profile
- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G05D 1/0246: {using a video camera in combination with image processing means}
- G05D 1/0257: {using a radar (radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931)}
- G05D 1/027: {comprising intertial navigation means, e.g. azimuth detector (inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165)}
- G05D 1/0278: {using satellite positioning signals, e.g. GPS}
- G05D 1/229: Command input data, e.g. waypoints
- G05D 1/247: using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
- G05D 1/248: generated by satellites, e.g. GPS
- G05D 1/249: from positioning sensors located off-board the vehicle, e.g. from cameras
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G01D: MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

## Abstract

A computer includes a processor and a memory storing instructions executable by the processor to receive a time series of vectors from a sensor, determine a weighted moving mean of the vectors, determine an inverse covariance matrix of the vectors, receive a current vector from the sensor, determine a squared Mahalanobis distance between the current vector and the weighted moving mean, and output an indicator of an anomaly with the sensor in response to the squared Mahalanobis distance exceeding a threshold. The squared Mahalanobis distance is determined by using the inverse covariance matrix.

## Claims

### Claim 1

A computer comprising a processor and a memory storing instructions executable by the processor to:
receive a time series of vectors from a sensor of a vehicle;
determine a weighted moving mean of the vectors over at least a portion of the time series;
determine an inverse covariance matrix of the vectors;
receive a current vector from the sensor;
determine a squared Mahalanobis distance between the current vector and the weighted moving mean, wherein the squared Mahalanobis distance is determined by using the inverse covariance matrix;
output an indicator of an anomaly with the sensor in response to the squared Mahalanobis distance exceeding a threshold; and
operate the vehicle based on the time series of vectors without the indicator of the anomaly and not based on the time series of vectors with the indicator of the anomaly.

### Claim 2 (depends on 1)

The computer of claim 1, wherein
the sensor is a first sensor; and
the instructions further include to run a Kalman filter on vectors from a plurality of sensors including the first sensor, and to prevent the Kalman filter from receiving the vectors from the first sensor in response to outputting the indicator of the anomaly.

### Claim 3 (depends on 2)

The computer of claim 2, wherein running the Kalman filter includes, when the Kalman filter is prevented from receiving the vectors from the first sensor, performing an iteration of the Kalman filter with a prediction step and without a measurement step.

### Claim 4 (depends on 2)

The computer of claim 2, wherein the vectors describe at least one of motion, position, and orientation of the vehicle relative to an external environment.

### Claim 5 (depends on 4)

The computer of claim 4, wherein the instructions further include to operate at least one of a propulsion, brake system, or steering system of the vehicle based on an output of the Kalman filter.

### Claim 6 (depends on 1)

The computer of claim 1, wherein the inverse covariance matrix is weighted favoring recency of the vectors.

### Claim 7 (depends on 6)

The computer of claim 6, wherein the inverse covariance matrix includes exponentially decreasing weights.

### Claim 8 (depends on 1)

The computer of claim 1, wherein the weighted moving mean includes exponentially decreasing weights.

### Claim 9 (depends on 1)

The computer of claim 1, wherein the sensor is one of a global positioning system sensor, an accelerometer, a gyroscope, a radar, a camera, or a LIDAR.

### Claim 10 (depends on 1)

The computer of claim 1, wherein the threshold is a value chosen from a chi-square distribution.

### Claim 11

A method comprising:
receiving a time series of vectors from a sensor of a vehicle;
determining a weighted moving mean of the vectors over at least a portion of the time series;
determining an inverse covariance matrix of the vectors;
receiving a current vector from the sensor;
determining a squared Mahalanobis distance between the current vector and the weighted moving mean, wherein the squared Mahalanobis distance is determined by using the inverse covariance matrix;
outputting an indicator of an anomaly with the sensor in response to the squared Mahalanobis distance exceeding a threshold; and
operating the vehicle based on the time series of vectors without the indicator of the anomaly and not based on the time series of vectors with the indicator of the anomaly.

### Claim 12 (depends on 11)

The method of claim 11, wherein the sensor is a first sensor, the method further comprising running a Kalman filter on vectors from a plurality of sensors including the first sensor, and preventing the Kalman filter from receiving the vectors from the first sensor in response to outputting the indicator of the anomaly.

### Claim 13 (depends on 12)

The method of claim 12, wherein running the Kalman filter includes, when the Kalman filter is prevented from receiving the vectors from the first sensor, performing an iteration of the Kalman filter with a prediction step and without a measurement step.

### Claim 14 (depends on 12)

The method of claim 12, wherein the vectors describe at least one of motion, position, and orientation of the vehicle relative to an external environment.

### Claim 15 (depends on 14)

The method of claim 14, further comprising operating at least one of a propulsion, brake system, and steering system of the vehicle based on an output of the Kalman filter.

### Claim 16 (depends on 11)

The method of claim 11, wherein the inverse covariance matrix is weighted favoring recency of the vectors.

### Claim 17 (depends on 16)

The method of claim 16, wherein the inverse covariance matrix includes exponentially decreasing weights.

### Claim 18 (depends on 11)

The method of claim 11, wherein the weighted moving mean includes exponentially decreasing weights.

### Claim 19 (depends on 11)

The method of claim 11, wherein the sensor is one of a global positioning system sensor, an accelerometer, a gyroscope, a radar, a camera, or a LIDAR.

### Claim 20 (depends on 11)

The method of claim 11, wherein the threshold is a value chosen from a chi-square distribution.