Back to results
US 11,538,289 B2Granted
Artificial intelligence device mounted on vehicle to perform self-diagnosis, and method for the same
AssigneeLG Electronics Inc.
InventorsJaehong Kim, Heeyeon Choi
Life of this patent
Estimating the term…
Abstract
An artificial intelligence device mounted on a vehicle is provided. A sensing unit acquires a gyroscope sensor value, an acceleration sensor value, a GPS sensor value, and a proximity sensor value. If the acquired data satisfies a predetermined reference value, a processor inputs the acquired sensor values to an artificial intelligence model, acquires whether an impact requiring self-diagnosis occurs and impact direction information as a result value, selects an ECU module to perform self-diagnosis according to the acquired result value, and performs self-diagnosis.
Claims17
An artificial intelligence device mounted on a vehicle, comprising:
- a sensor configured to acquire sensor data based on an impact being applied to the vehicle;
- an output interface configured to output information;
- and
- a processor configured to:
- input data acquired by the sensor to an artificial intelligence model to obtain a result value output by the artificial intelligence model,
- determine whether to perform self-diagnosis and an impact direction according to the result value, and
- based on the self-diagnosis being performed on an engine control unit (ECU) module of the vehicle, control the output interface to output a self-diagnosis result based on the impact direction,
- wherein the sensor comprises a gyroscope sensor, an acceleration sensor, a global positioning system (GPS) sensor, and a proximity sensor, and
- wherein the processor is configured to:
- input data acquired from the gyroscope sensor, the acceleration sensor, and the GPS sensor to the artificial intelligence model (i) based on a value of the proximity sensor being less than or equal to a first reference value, and a value of the gyroscope sensor being greater than or equal to a second reference value, or (ii) based on the value of the proximity sensor being less than or equal to the first reference value, and a value of the acceleration sensor being greater than or equal to a third reference value.
7 more elements
A self-diagnosis method comprising:
- acquiring data from a gyroscope sensor, an acceleration sensor, a global positioning system (GPS) sensor, and a proximate sensor;
- determining, by a processor, whether the data satisfies a predetermined reference value;
- inputting, by the processor, the data to an artificial intelligence model based on the data satisfying the predetermined reference value;
- acquiring a result value output by the artificial intelligence model;
- determining whether to perform self-diagnosis and an impact direction according to the result value;
- performing, by the processor, self-diagnosis on an engine control unit (ECU) module of a vehicle that requires self-diagnosis based on the impact direction;
- and
- outputting, by an output interface, a self-diagnosis result,
- wherein the artificial intelligence model includes a neural network including a weight configured to be adjusted by training using impact information as a result value and sensed values of the GPS sensor, the gyroscope sensor, and the acceleration sensor as an input value,
- wherein the impact information includes information about an impact that does not require the self-diagnosis, information about an impact that requires the self-diagnosis in a first direction, and information about an impact that requires the self-diagnosis in a second direction, and
- wherein inputting the data to the artificial intelligence model comprises:
- inputting the data acquired from the gyroscope sensor, the acceleration sensor, and the GPS sensor to the artificial intelligence model (i) based on a value of the proximity sensor being less than or equal to a first reference value, and the value of the gyroscope sensor being greater than or equal to a second reference value, or (ii) based on the value of the proximity sensor being less than or equal to the first reference value, and the value of the acceleration sensor being greater than or equal to a third reference value.
9 more elements
A non-transitory recording medium having recorded thereon a method for performing self-diagnosis, the method comprising:
- acquiring data from a gyroscope sensor, an acceleration sensor, a global positioning system (GPS) sensor, and a proximate sensor;
- determining, by a processor, whether the data satisfies a predetermined reference value;
- inputting, by the processor, the data to an artificial intelligence model based on the data satisfying the predetermined reference value;
- determining whether to perform self-diagnosis and an impact direction according to a result value output from the artificial intelligence model;
- performing, by the processor, self-diagnosis on an engine control unit (ECU) module of a vehicle that requires self-diagnosis based on the impact direction;
- and
- outputting, by an output interface, a self-diagnosis result,
- wherein the artificial intelligence model includes a neural network including a weight configured to be adjusted by training using impact information as a result value and sensed values of the GPS sensor, the gyroscope sensor, and the acceleration sensor as an input value,
- wherein the impact information includes information about an impact that does not require the self-diagnosis, information about an impact that requires the self-diagnosis in a first direction, and information about an impact that requires self-diagnosis in a second direction,
- wherein inputting the data to the artificial intelligence model comprises:
- inputting the data acquired from the gyroscope sensor, the acceleration sensor, and the GPS sensor to the artificial intelligence model (i) based on a value of the proximity sensor being less than or equal to a first reference value, and the value of the gyroscope sensor being greater than or equal to a second reference value, or (ii) based on the value of the proximity sensor being less than or equal to the first reference value, and the value of the acceleration sensor being greater than or equal to a third reference value.
8 more elements
Dependencies are inferred from the claim text.