Apparatus and method for recognizing driving lane based on multiple sensors
An apparatus for recognizing a driving lane based on multiple sensors is provided. The apparatus includes a first sensor configured to calculate road information, a second sensor configured to calculate moving obstacle information, a third sensor configured to calculate movement information of a vehicle, and a controller configured to remove the moving obstacle information from the road information to extract only road boundary data, accumulate the road boundary data to calculate a plurality of candidate location information on the vehicle based on the movement information, and select final candidate location information from the plurality of candidate location information.
1. An apparatus for recognizing a driving lane of a vehicle based on multiple sensors that are located on the vehicle, the apparatus comprising:
a first sensor configured to calculate road information, wherein the road information includes at least road boundaries;
a second sensor configured to calculate moving obstacle information;
a third sensor configured to calculate movement information of the vehicle; and
a controller configured to remove the moving obstacle information from the road information to extract only road boundary data, accumulate the road boundary data to calculate pieces of candidate location information on the vehicle on the basis of the movement information, and select one among the pieces of candidate location information as final candidate location information,
wherein the pieces of candidate location information are calculated using driving lane information of the vehicle obtained using a fourth sensor or precision map lane information which is set in advance on the basis of current vehicle location information.
2. The apparatus of claim 1 , wherein the controller is configured to:
extract the road boundary data from a plurality of previous frames using the movement information and accumulated in a current frame.
3. The apparatus of claim 2 , wherein the controller is configured to:
when a number of previous frames is greater than a preset value, remove one farthest previous frame and add one current frame to keep an accumulated number of frames constant.
4. The apparatus of claim 3 , wherein the controller is configured to:
set variably the accumulated number of frames according to a vehicle speed or a movement distance of the vehicle.
5. The apparatus of claim 1 , wherein the pieces of candidate location information are calculated based on a grid formed by dividing a predetermined region of interest placed on a map road boundary of the precision map lane information at regular intervals.
6. The apparatus of claim 5 , wherein the controller is configured to:
form the grid with a plurality of lateral directions and a plurality of transverse directions; and
set the plurality of lateral directions and the plurality of transverse directions as a plurality of transverse candidate location information and a plurality of lateral candidate location information.
7. The apparatus of claim 5 , wherein the controller is configured to:
form the grid with a plurality of heading angles;
generate the plurality of heading angles by dividing the region of interest at regular intervals based on a center point of the vehicle; and
set the plurality of heading angles as candidate heading angle information.
8. The apparatus of claim 7 , wherein the controller is configured to:
obtain the plurality of candidate location information by multiplying the plurality of lateral location information, the plurality of transverse location information, and the plurality of heading angle location information.
9. The apparatus of claim 1 , wherein the pieces of candidate location information consist of only of a preset number of pieces of transverse candidate location information based on the transverse direction in consideration of a location error of the vehicle.
10. The apparatus of claim 9 , wherein the controller is configured to:
determine a location of the vehicle present within one road boundary according to a ratio of a lateral offset calculated between a driving lane and a center of the vehicle.
11. The apparatus of claim 10 , wherein the controller is configured to:
determine a preset number of transverse candidate location information for each lane according to the ratio of the lateral offset based on a lane position and the number of lanes which are identified in a region of interest preset in the precision map lane information.
12. The apparatus of claim 10 , wherein the controller is configured to:
calculate a heading angle of each of a preset number of transverse candidate location information using a difference value between a first average of a heading angle of a left lane and a heading angle of a right lane in front of the vehicle, which are recognized through the second sensor, and a second average of a heading angle of the left lane and a heading angle of the right lane of a preset number of transverse candidate location information which are calculated through the precision map lane information.
13. The apparatus of claim 1 , wherein the controller matches precision map road boundary information searched on the basis of the pieces of candidate location information with the accumulated road boundary data to assign a matching degree score to each of the pieces of candidate location information and select a lane of the final candidate location information, to which a highest matching degree score is assigned, as the driving lane.
14. The apparatus of claim 13 , wherein the controller is configured to:
convert the precision map road boundary information and the accumulated road boundary data into a coordinate system including Y-axis coordinates and X-axis coordinates; and
compare values of the X-axis coordinates based on an index of the Y-axis coordinates to calculate the matching degree score.
15. The apparatus of claim 14 , wherein:
the matching degree score is calculated using the number of data points located in the vicinity of the precision map road boundary information; and
the data points are generated by the first sensor, and the number of data points are the number of left points, the number of right points, and the number of points between the road boundaries on the basis of the precision map road boundary information.
16. The apparatus of claim 1 , wherein the first sensor includes a distance sensor, the second sensor includes a vision sensor, the third sensor includes a motion sensor, and the fourth sensor includes a global positioning system (GPS) sensor or an image sensor.
17. The apparatus of claim 16 , wherein the controller is configured to:
apply a preset invalid determination condition to the final candidate location information to determine whether the final candidate location information is valid.
18. The apparatus of claim 17 , wherein the invalid determination condition includes any of a comparison condition whether the matching degree score of the final candidate location information is less than a preset first matching degree, a comparison condition whether a residual amount of the distance sensor present in the driving lane is greater than a preset second matching degree in the final candidate location information, and a determination condition whether a left lane direction and a right lane direction are parallel according to a difference between the left lane direction and the right lane direction in the final candidate location information, and whether the vehicle deviates from a road width by comparing a difference between a lateral offset of the left lane and a lateral offset of the right lane based on the center of the vehicle with a preset road width.
19. A method of recognizing a driving lane of a vehicle based on multiple sensors that are located on the vehicle, the method comprising:
a first information calculation operation of calculating, by a first sensor and a second sensor, road information and moving obstacle information, wherein the road information includes at least road boundaries;
a second information calculation operation of calculating, by a third sensor, movement information of the vehicle; and
a selection operation of removing, by a controller, the moving obstacle information from the road information to extract only road boundary data, accumulating the road boundary data to calculate pieces of candidate location information on the vehicle on the basis of the movement information, and selecting one among the pieces of candidate location information as final candidate location information,
wherein the pieces of candidate location information are calculated using driving lane information of the vehicle obtained using a fourth sensor or precision map lane information which is set in advance on the basis of current vehicle location information.