Real-time reliability assessment method to enhance robustness of data-fusion based vehicle speed estimation
A method for estimating a lateral velocity of a vehicle includes receiving sensor data from a sensor of the vehicle, determining a physics-based longitudinal velocity estimation of the vehicle using a physics-based model and the sensor data, determining a data-driven longitudinal velocity estimation of the vehicle using a first neural network and the sensor data, determining, using a second neural network, which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable to determine a selected longitudinal velocity estimation, determining the lateral velocity of the vehicle using the selected longitudinal velocity estimation, and controlling the vehicle based on the lateral velocity.
1. A method for estimating a lateral velocity of a vehicle, comprising:
receiving sensor data from a sensor of the vehicle;
determining a physics-based longitudinal velocity estimation of the vehicle using a physics-based model and the sensor data;
determining a data-driven longitudinal velocity estimation of the vehicle using a first neural network and the sensor data;
determining, using a second neural network, which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable to determine a selected longitudinal velocity estimation;
determining, in real-time, the lateral velocity of the vehicle using the selected longitudinal velocity estimation; and
controlling the vehicle based on the lateral velocity.
2. The method of claim 1 , wherein the sensor data includes a wheel speed of the vehicle, a longitudinal acceleration of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, a road wheel angle of the vehicle, and a wheel torque of the vehicle, and the first neural network is a recurrent neural network.
3. The method of claim 2 , wherein determining, using the second neural network, which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable includes:
determining, using the second neural network, a reliability of the physics-based longitudinal velocity estimation; and
determining, using the second neural network, a reliability of the data-driven longitudinal velocity estimation.
4. The method of claim 3 , further comprising comparing the reliability of the physics-based longitudinal velocity estimation with the reliability of the data-driven longitudinal velocity estimation to determine which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable.
5. The method of claim 4 , further comprising using a first extended Kalman filter to determine a final longitudinal velocity based on the selected longitudinal velocity estimation.
6. The method of claim 5 , further comprising:
comparing the reliability of the physics-based longitudinal velocity estimation with a predetermined reliability threshold to determine whether the reliability of the physics-based longitudinal velocity estimation is less than the predetermined reliability threshold;
comparing the reliability of the data-driven longitudinal velocity estimation with the predetermined reliability threshold to determine whether the reliability of the data-driven longitudinal velocity estimation is less than the predetermined reliability threshold; and
increasing a covariance of the first extended Kalman filter in response to determining that the reliability of the of the data-driven longitudinal velocity estimation and the reliability of the physics-based longitudinal velocity estimation are both less than the predetermined reliability threshold.
7. The method of claim 6 , further comprising using a second extended Kalman filter to determine the lateral velocity of the vehicle based on the final longitudinal velocity that was previously determined using the first extended Kalman filter.
8. A system estimating a lateral velocity of a vehicle, comprising:
a plurality of sensors, wherein each of the plurality of sensors is configured to generate sensor data;
a controller in communication with the plurality of sensors, wherein the controller is programmed to:
receive the sensor data from the plurality of sensors of the vehicle;
determine a physics-based longitudinal velocity estimation of the vehicle using a physics-based model and the sensor data;
determine a data-driven longitudinal velocity estimation of the vehicle using a first neural network and the sensor data;
determine, using a second neural network, which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable to determine a selected longitudinal velocity estimation;
determine the lateral velocity of the vehicle using the selected longitudinal velocity estimation; and
control the vehicle based on the lateral velocity.
9. The system of claim 8 , wherein the sensor data includes a wheel speed of the vehicle, a longitudinal acceleration of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, a road wheel angle of the vehicle, and a wheel torque of the vehicle, and the first neural network is a recurrent neural network.
10. The system of claim 9 , wherein the controller is programmed to:
determine, using the second neural network, a reliability of the physics-based longitudinal velocity estimation; and
determine, using the second neural network, a reliability of the data-driven longitudinal velocity estimation.
11. The system of claim 10 , wherein the controller is programmed to compare the reliability of the physics-based longitudinal velocity estimation with the reliability of the data-driven longitudinal velocity estimation to determine which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable.
12. The system of claim 11 , wherein the controller is programmed to use a first extended Kalman filter to determine a final longitudinal velocity based on the selected longitudinal velocity estimation.
13. The system of claim 12 , wherein the controller is programmed to:
compare the reliability of the physics-based longitudinal velocity estimation with a predetermined reliability threshold to determine whether the reliability of the physics-based longitudinal velocity estimation is less than the predetermined reliability threshold;
compare the reliability of the data-driven longitudinal velocity estimation with the predetermined reliability threshold to determine whether the reliability of the data-driven longitudinal velocity estimation is less than the predetermined reliability threshold; and
increase a covariance of the first extended Kalman filter in response to determining that the reliability of the data-driven longitudinal velocity estimation and the reliability of the physics-based longitudinal velocity estimation are both less than the predetermined reliability threshold.
14. The system of claim 13 , wherein the controller is programmed to use a second extended Kalman filter to determine the lateral velocity of the vehicle based on the final longitudinal velocity that was previously determined using the first extended Kalman filter.
15. A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions, that when executed by a processor, cause the processor to:
receive sensor data from a plurality of sensors of a vehicle;
determine a physics-based longitudinal velocity estimation of the vehicle using a physics-based model and the sensor data;
determine a data-driven longitudinal velocity estimation of the vehicle using a first neural network and the sensor data;
determine, using a second neural network, which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable to determine a selected longitudinal velocity estimation;
determine a lateral velocity of the vehicle using the selected longitudinal velocity estimation; and
control the vehicle based on the lateral velocity.
16. The tangible, non-transitory, machine-readable medium of claim 15 , wherein the sensor data includes a wheel speed of the vehicle, a longitudinal acceleration of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, a road wheel angle of the vehicle, and a wheel torque of the vehicle, and the first neural network is a recurrent neural network.
17. The tangible, non-transitory, machine-readable medium of claim 16 , wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
determine, using the second neural network, a reliability of the physics-based longitudinal velocity estimation; and
determine, using the second neural network, a reliability of the data-driven longitudinal velocity estimation.
18. The tangible, non-transitory, machine-readable medium of claim 17 , wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to compare the reliability of the physics-based longitudinal velocity estimation with the reliability of the data-driven longitudinal velocity estimation to determine which of the physics-based longitudinal velocity estimation and the data-driven longitudinal velocity estimation is more reliable.
19. The tangible, non-transitory, machine-readable medium of claim 18 , wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to use a first extended Kalman filter to determine a final longitudinal velocity based on the selected longitudinal velocity estimation.
20. The tangible, non-transitory, machine-readable medium of claim 19 , wherein the tangible, non-transitory, machine-readable medium further comprising machine-readable instructions, that when executed by the processor, causes the processor to:
compare the reliability of the physics-based longitudinal velocity estimation with a predetermined reliability threshold to determine whether the reliability of the physics-based longitudinal velocity estimation is less than the predetermined reliability threshold;
compare the reliability of the data-driven longitudinal velocity estimation with the predetermined reliability threshold to determine whether the reliability of the data-driven longitudinal velocity estimation is less than the predetermined reliability threshold; and
increase a covariance of the first extended Kalman filter in response to determining that the reliability of the data-driven longitudinal velocity estimation and the reliability of the physics-based longitudinal velocity estimation are both less than the predetermined reliability threshold.