Driver assistance apparatus and driver assistance method

1. An apparatus for assisting driving of a host vehicle, the apparatus comprising:

a camera mounted to the host vehicle and having a field of view outside of the host vehicle, the camera configured to obtain front image data; and

a controller configured to:

process the front image data, and

obtain collision time with a surrounding host vehicle and weather information based on the image data,

estimate a road friction coefficient based on the weather information,

determine whether a collision with surrounding host vehicle is avoidable by changing a driving direction of the host vehicle,

based determining that the collision with the surrounding host vehicle is unavoidable, control a braking device provided in the host vehicle to start braking at a first braking time point determined based on the collision time and the road friction coefficient.

2. The apparatus of claim 1 , wherein the controller is configured to start second braking at a second braking time point and start third braking at a third braking time point based on the weather information.

3. The apparatus of claim 1 , wherein the controller is configured to learn a road friction coefficient according to the weather information by deep learning.

4. The apparatus of claim 3 , further comprising:

a storage configured to store a learning result of braking situation,

wherein the controller is configured to determine the road friction coefficient based on the learning result stored in the storage when it is determined that communication of a transceiver of the host vehicle to obtain the road friction coefficient from a base station is impossible, and determine the first braking time point based on the determined friction coefficient.

5. The apparatus of claim 4 , wherein the controller is configured to change the first braking time point when it is determined that the road friction coefficient is less than a preset value.

6. A method for assisting driving of a host vehicle, the method comprising:

obtaining front image data by a camera mounted to the host vehicle and having a field of view outside of the host vehicle;

processing the front image data

estimating a road friction coefficient based on the weather information;

obtaining collision time with a surrounding host vehicle and weather information based on the processed image data;

determining whether a collision with surrounding host vehicle is avoidable by changing a driving direction of the host vehicle;

based determining that the collision with the surrounding host vehicle is unavoidable, controlling a braking device provided in the host vehicle to start braking at a first braking time point determined based on the collision time and the road friction coefficient.

7. The method of claim 6 , wherein the controlling comprises:

starting third braking at a third braking time point based on the weather information.

8. The method of claim 6 , wherein the controlling comprises:

learning a road friction coefficient according to the weather information by deep learning.

9. The method of claim 8 , further comprising:

storing the learning result, and

wherein the controlling comprises:

determining the road friction coefficient based on the learning result when it is determined that communication to obtain the road friction coefficient from a base station is impossible; and

determining the first braking time point based on the determined road friction coefficient.

10. The method of claim 9 , wherein the controlling comprises:

changing the first braking time point when it is determined that the road friction coefficient is less than a preset value.

11. A system for assisting driving of a host vehicle, the system comprising:

a camera mounted to the host vehicle and having a field of view outside of the host vehicle, the camera configured to obtain front image data;

a transceiver configured to communicate with a host vehicle to Everything (V2X) communication base station to receive, from the base station, information related to driving the host vehicle according to weather; and

a controller configured to:

process the front image data, and

obtain collision time with a surrounding host vehicle and weather information based on the information received from the base station and the image data, and

determining whether a collision with surrounding host vehicle is avoidable by changing a driving direction of the host vehicle;

based determining that the collision with the surrounding host vehicle is unavoidable, control a braking device provided in the host vehicle to start braking at a first braking time point determined based on the collision time and a road friction coefficient.

12. The system of claim 11 , wherein the controller is configured to start second braking at a second braking time point and start third braking at a third braking time point based on the weather information.

13. The system of claim 11 , further comprising:

a storage configured to store a learning result of braking situation; and

wherein the controller is configured to learn the braking situation according to the weather information and the road friction coefficient by deep learning, determine the road friction coefficient based on the learning result stored in the storage when it is determined that communication of the transceiver to receive, from the base station, the information related to driving the host vehicle according to weather is impossible, and determine the first braking time point based on the determined road friction coefficient.

14. The system of claim 13 , wherein the controller is configured to change the first braking time point when it is determined that the road friction coefficient is less than a preset value.