SYSTEM AND METHOD FOR AUTOMATICALLY FOLLOWING A LANE WHILE IN A VEHICLE'S AUTONOMOUS DRIVING MODE
Systems and methods for implementing one or more autonomous features for autonomous and semi-autonomous control of one or more vehicles are provided. More specifically, image data may be obtained from an image acquisition device and processed utilizing one or more machine learning models to identify, track, and extract one or more features of the image utilized in decision making processes for providing steering angle and/or acceleration/deceleration input to one or more vehicle controllers. In some instances, techniques may be employed such that the autonomous and semi-autonomous control of a vehicle may change between vehicle follow and lane follow modes. In some instances, at least a portion of the machine learning model may be updated based on one or more conditions.
1 . A method comprising:
receiving image data from an image sensor of a first vehicle, while in an autonomous driving mode;
determining if a portion of the image data includes an edge defining a lane;
determining if a second portion of the edge should be filtered; and
filtering the second portion from the image data to smooth the edge of the lane.
2 . The method of claim 1 , wherein determining if a portion of the image data includes an edge defining a lane comprises applying a machine learning (ML) model to analyze the image for the edge.
3 . The method of claim 2 , wherein the ML model provide a set of two or more points on the lane that define a location of the lane in the image.
4 . The method of claim 3 , wherein determining if a second portion of the edge should be filtered comprises comparing the location of a point to a previous location of an associated point in a previous image.
5 . The method of claim 4 , wherein the location and the previous location deviate by more than a predetermined threshold, filtering out the point as defining the location of the lane.
6 . The method of claim 5 , wherein the two or more points are positioned at predetermined intervals along a vertical axis of the image.
7 . The method of claim 6 , wherein the predetermined threshold is greater for points lower in the image than points higher in the image.
8 . The method of claim 7 , wherein the first vehicle automatically steers between the two or more points defining a first lane and the two or more points defining a second lane.
9 . The method of claim 8 , wherein the first vehicle automatically steers to maintain a path of the first vehicle a predetermined number of pixels from the two or more points defining a first lane.
10 . A system comprising:
a memory;
a processor in communication with the memory, wherein the processor executes instructions stored in the memory, which cause the processor to execute a method, the method comprising:
receiving image data from an image sensor of a first vehicle, while in an autonomous driving mode;
determining if a portion of the image data includes an edge defining a lane;
determining if a second portion of the edge should be filtered; and
filtering the second portion from the image data to smooth the edge of the lane.
11 . The system of claim 10 , wherein determining if a portion of the image data includes an edge defining a lane comprises applying a machine learning (ML) model to analyze the image for the edge, and wherein the ML model provide a set of two or more points on the lane that define a location of the lane in the image.
12 . The system of claim 11 , wherein determining if a second portion of the edge should be filtered comprises comparing the location of a point to a previous location of an associated point in a previous image, and wherein the location and the previous location deviate by more than a predetermined threshold, filtering out the point as defining the location of the lane.
13 . The system of claim 12 , wherein the two or more points are positioned at predetermined intervals along a vertical axis of the image, and wherein the predetermined threshold is greater for points lower in the image than points higher in the image.
14 . The system of claim 11 , wherein the first vehicle automatically steers between the two or more points defining a first lane and the two or more points defining a second lane.
15 . The system of claim 11 , wherein the first vehicle automatically steers to maintain the two or more points defining a first lane a predetermined number of pixels from a center of the image.
16 . A non-transitory computer readable medium having stored thereon instructions, which when executed by a processor cause the processor to execute a method, the method comprising:
receiving image data from an image sensor of a first vehicle, while in an autonomous driving mode;
determining if a portion of the image data includes an edge defining a lane;
determining if a second portion of the edge should be filtered; and
filtering the second portion from the image data to smooth the edge of the lane.
17 . The non-transitory computer readable medium of claim 16 , wherein determining if a portion of the image data includes an edge defining a lane comprises applying a machine learning (ML) model to analyze the image for the edge, and wherein the ML model provide a set of two or more points on the lane that define a location of the lane in the image.
18 . The non-transitory computer readable medium of claim 17 , wherein determining if a second portion of the edge should be filtered comprises comparing the location of a point to a previous location of an associated point in a previous image, and wherein the location and the previous location deviate by more than a predetermined threshold, filtering out the point as defining the location of the lane.
19 . The non-transitory computer readable medium of claim 18 , wherein the two or more points are positioned at predetermined intervals along a vertical axis of the image, and wherein the predetermined threshold is greater for points lower in the image than points higher in the image.
20 . The non-transitory computer readable medium of claim 19 , wherein the first vehicle automatically steers between the two or more points defining a first lane and the two or more points defining a second lane.