Method and system for topology detection

1 . A vehicle computing system, comprising:

a memory storing computer instructions;

a data storage device storing data associated with operation of a vehicle including data captured by at least a first sensor; and

a processor communicatively coupled with the memory to execute the instructions and, during operation of the vehicle, capable of:

receiving an image of a first lane of a road, the image being captured by the first sensor;

defining the first lane as a set of N ordered points, wherein N is defined based on at least one of a current operating state of the vehicle, a current environment surrounding the vehicle, or any combination thereof;

representing the first lane, for each of the N ordered points, as an ordered sequence of a plurality of predefined lane components, the plurality of predefined lane components comprising a continuing lane component, a merging lane component, and a splitting lane component, each predefined lane component corresponding to a different structural portion of the first lane such that the ordered sequence of the plurality of predefined lane components in combination define a geometry of the first lane;

generating images based on the representation of the first lane, where each image represents one of the predefined lane components for one of the N ordered points; and

combining the generated images to generate a topology representation for the first lane.

2 . The vehicle computing system of claim 1 , wherein each lane of the road is represented by a set of predefined lane line geometries defined by the ordered sequence of the plurality of predefined lane components.

3 . The vehicle computing system of claim 2 , wherein each lane line geometry in the set of predefined lane line geometries is fully defined by an ordered combination of the predefined lane components.

4 . The vehicle computing system of claim 3 , where the set of predefined lane line geometries includes a plurality of lane line geometries defined by a combination of C of the predefined lane components, where C is equal to at least 3 lane components and (N×C) images are generated based on associating one or more of the lane components with one or more of the N ordered points, wherein at least one of the plurality of lane line geometries is a merging lane component followed by a splitting lane component within the ordered sequence.

5 . The vehicle computing system of claim 1 , wherein the first sensor is a camera onboard the vehicle.

6 . The vehicle computing system of claim 1 , wherein the processor is further capable of:

receiving an image of a second lane of the road, the image of the second lane being captured by the first sensor;

defining the second lane as a set of N ordered points;

representing the second lane, for each of the N ordered points, as a second ordered sequence of a second plurality of predefined lane components, the second plurality of predefined lane components comprising the continuing lane component, the merging lane component, and the splitting lane component, such that the second ordered sequence of the second plurality of predefined lane components in combination define a geometry of the second lane;

generating images based on the representation of the first second lane, where each image represents one of the predefined lane components for one of the N ordered points for the second lane;

combining the generated images for the second lane to generate a topology representation for the second lane; and

combining the generated topology representation for the second lane and the generated topology representation for the first lane to generate a complete topology representation for the road including the first lane and the second lane.

7 . A method comprising:

receiving an image of a first lane of a road, the image being captured by a first sensor of a vehicle;

defining the first lane as a set of N ordered points, wherein N is defined based on at least one of a current operating state of the vehicle, a current environment surrounding the vehicle, or any combination thereof;

representing the first lane, for each of the N ordered points, as an ordered sequence of a plurality of predefined lane components, the plurality of predefined lane components comprising a continuing lane component, a merging lane component, and a splitting lane component, each predefined lane component corresponding to a different structural portion of the first lane such that the ordered sequence of the plurality of predefined lane components in combination define a geometry of the first lane;

generating images based on the representation of the first lane, where each image represents predefined lane components for one of the N ordered points; and

combining the generated images to generate a topology representation for the first lane.

8 . The method of claim 7 , wherein each lane of the road is represented by a set of predefined lane line geometries defined by the ordered sequence of the plurality of predefined lane components.

9 . The method of claim 8 , wherein each lane line geometry in the set of predefined lane line geometries is fully defined by an ordered combination of the predefined lane components.

10 . The method of claim 9 , where the set of predefined lane line geometries includes a plurality of lane line geometries defined by a combination of C of the predefined lane components, where C is equal to at least 3 lane components and (N×C) images are generated based on associating one or more of the lane components with one or more of the N ordered points, wherein at least one of the plurality of lane line geometries is a merging lane component followed by a splitting lane component within the ordered sequence.

11 . The method of claim 7 , wherein the first sensor is a camera onboard the vehicle.

12 . The method of claim 7 , further comprising:

receiving an image of a second lane of the road, the image of the second lane being captured by the first sensor;

defining the second lane as a set of N ordered points;

representing the second lane, for each of the N ordered points, as a second ordered sequence of a second plurality of predefined lane components, the second plurality of predefined lane components comprising the continuing lane component, the merging lane component, and the splitting lane component, such that the second ordered sequence of the second plurality of predefined lane components in combination define a geometry of the second lane;

generating images based on the representation of the second lane, where each image represents one of the predefined lane components for one of the N ordered points for the second lane;

combining the generated images for the second lane to generate a topology representation for the second lane; and

combining the generated topology representation for the second lane and the generated topology representation for the first lane to generate a complete topology representation for the road including the first lane and the second lane.

13 . A non-transitory medium having processor-executable instructions stored thereon, the medium comprising:

instructions to receive an image of a first lane of a road, the image being captured by a first sensor of a vehicle;

instructions to define the first lane as a set of N ordered points, wherein Nis defined based on at least one of a current operating state of the vehicle, a current environment surrounding the vehicle, or any combination thereof;

instructions to represent the first lane, for each of the N ordered points, as an ordered sequence of a plurality of predefined lane components, the plurality of predefined lane components comprising a continuing lane component, a merging lane component, and a splitting lane component, each predefined lane component corresponding to a different structural portion of the first lane such that the ordered sequence of the plurality of predefined lane components in combination define a geometry of the first lane;

instructions to generate images based on the representation of the first lane, where each image represents one of the predefined lane components for one of the N ordered points; and

instructions to combine the generated images to generate a topology representation for the first lane.

14 . The non-transitory medium of claim 13 , wherein each lane of the road is represented by a set of predefined lane line geometries defined by the ordered sequence of the plurality of predefined lane components.

15 . The non-transitory medium of claim 14 , wherein each lane line geometry in the set of predefined lane line geometries is fully defined by an ordered combination of the predefined lane components, where the set of predefined lane line geometries includes a plurality of lane line geometries defined by a combination of C of the predefined lane components, where C is equal to at least 3 lane components and (N×C) images are generated based on associating one or more of the lane components with one or more of the N ordered points, wherein at least one of the plurality of lane line geometries is a merging lane component followed by a splitting lane component within the ordered sequence.

16 . The non-transitory medium of claim 13 , wherein the first sensor is a camera onboard the vehicle.

17 . The non-transitory medium of claim 13 , further comprising:

instructions to receive an image of a second lane of the road, the image of the second lane being captured by the first sensor;

instructions to define the second lane as a set of N ordered points;

instructions to represent the second lane, for each of the N ordered points, as a second ordered sequence of a second plurality of predefined lane components, the second plurality of predefined lane components comprising the continuing lane component, the merging lane component, and the splitting lane component, such that the second ordered sequence of the second plurality of predefined lane components in combination define a geometry of the second lane;

instructions to generate images based on the representation of the second lane, where each image represents one of the predefined lane components for one of the N ordered points for the second lane;

instructions to combine the generated images for the second lane to generate a topology representation for the second lane; and

instructions to combine the generated topology representation for the second lane and the generated topology representation for the first lane to generate a complete topology representation for the road including the first lane and the second lane.