Device for classifying road surface and system for controlling terrain mode of vehicle using the same
A device for identifying a road surface includes: storage for storing a deep learning-based road surface model; and a controller configured to identify a type of a road surface on which a vehicle is currently traveling, using the road surface model. The device for identifying a road surface can identify a type of a road surface on which the vehicle is traveling based on deep learning and control the terrain mode of the vehicle based on the identified type of the road surface. The type of the road surface on which the vehicle is traveling may be identified with a high accuracy and an optimal terrain mode may be set, thereby improving not only travel stability but also riding comfort of the vehicle.
1. A device for identifying a road surface, the device comprising:
a storage for storing a road surface model in which deep learning is completed by a ratio of energy for each frequency band of a vehicle signal, and a road surface state value; and
a controller configured to identify a type of a road surface on which a vehicle is currently traveling, using the road surface model.
2. The device of claim 1 , wherein the controller is configured to:
obtain a vehicle signal through a vehicle network,
convert the vehicle signal into a frequency domain signal and then calculate a ratio of energy for each frequency band of the frequency domain signal,
calculate a road surface state value based on the vehicle signal, and
identify a type of a road surface corresponding to the ratio of the energy for each frequency band and the road surface state value based on the road surface model.
3. The device of claim 2 , wherein the controller is configured to:
sequentially store vehicle signals for a reference time obtained from the vehicle network in a buffer, and
sequentially overwrite storage spaces having previous vehicle signals in an order of a storage space having an oldest vehicle signal and a storage space of a next oldest vehicle signal, when the buffer is completely full.
4. The device of claim 2 , wherein the controller is configured to divide the frequency domain signal into a plurality of frequency bands having different sizes.
5. The device of claim 4 , wherein the controller is configured to set a size of a low frequency band to be larger than a size of a high frequency band.
6. The device of claim 2 , wherein the controller is configured to calculate, as the road surface state value, at least one of a braking smoothness, a handling smoothness, a degree of acceleration compared to user's willingness to accelerate, a roughness of the road surface, a setting value based on whether an Electronic Stability Control (ESC) is involved, a sum of a slip amount of a Front-Left (FL) wheel, a sum of a slip amount of a Front-Right (FR) wheel, a sum of a slip amount of a Rear-Left (RL) wheel, or a sum of a slip amount of a (Rear-Right) RR wheel.
7. The device of claim 2 , wherein the controller is configured to remove a road surface maintained within a reference time from road surfaces identified based on the road surface model.
8. The device of claim 1 , wherein the type of the road surface includes at least one of a normal, a sand, a mud, or a snow.
9. A system for controlling a terrain mode of a vehicle, the system comprising:
a road surface classification device configured to identify a type of a road surface on which the vehicle is currently traveling, using a road surface model; and
a control device configured to set the terrain mode of the vehicle based on the type of the road surface identified by the road surface classification device,
wherein the road surface model is a model in which deep learning is completed by a ratio of energy for each frequency band of a vehicle signal, and a road surface state value.
10. The system of claim 9 , wherein the control device is configured to maintain a current terrain mode even when the type of the road surface is changed when a speed of the vehicle exceeds a first reference speed.
11. The system of claim 9 , wherein the control device is configured to maintain a current terrain mode even when the type of the road surface is changed when a speed of the vehicle is equal to or less than a second reference speed.
12. The system of claim 9 , wherein the control device is configured to maintain a current terrain mode when an abnormality occurs in the road surface classification device.
13. The system of claim 9 , wherein the control device is configured to maintain a current terrain mode of the vehicle when at least one of a situation where travel is unusual, a situation where an environment is unusual, a situation where the road surface is unusual, or a situation where the vehicle is unusual occurs.
14. The system of claim 9 , wherein the road surface classification device is configured to:
obtain a vehicle signal through a vehicle network,
convert the vehicle signal into a frequency domain signal and then calculate a ratio of energy for each frequency band of the frequency domain signal,
calculate a road surface state value based on the vehicle signal, and
identify a type of a road surface corresponding to the ratio of the energy for each frequency band and the road surface state value based on the road surface model.
15. The system of claim 14 , wherein the road surface classification device is configured to:
sequentially store vehicle signals for a reference time obtained from the vehicle network in a buffer, and
sequentially overwrite storage spaces having previous vehicle signals in an order of a storage space having an oldest vehicle signal and a storage space of a next oldest vehicle signal, when the buffer is completely full.
16. The system of claim 14 , wherein the road surface classification device is configured to divide the frequency domain signal into a plurality of frequency bands having different sizes.
17. The system of claim 16 , wherein the road surface classification device is configured to set a size of a low frequency band to be larger than a size of a high frequency band.
18. The system of claim 14 , wherein the road surface classification device is configured to calculate, as the road surface state value, at least one of a braking smoothness, a handling smoothness, a degree of acceleration compared to user's willingness to accelerate, a roughness of the road surface, a setting value based on whether an Electronic Stability Control (ESC) is involved, a sum of a slip amount of a Front-Left (FL) wheel, a sum of a slip amount of a Front-Right (FR) wheel, a sum of a slip amount of a Rear-Left (RL) wheel, or a sum of a slip amount of a Rear-Right (RR) wheel.
19. The system of claim 14 , wherein the road surface classification device is configured to remove a road surface maintained within a reference time among road surfaces identified based on the road surface model.
20. The system of claim 9 , wherein the type of the road surface includes at least one of a normal, a sand, a mud, or a snow.