Vehicle lane mapping
A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate a first map, based on vehicle sensor data, of a free space on a roadway in which a first vehicle can operate without contacting roadway edges and non-stationary objects on the roadway, the first map including roadway lane markings in an environment around the first vehicle, wherein the non-stationary objects include one or more second vehicles and generate a second map of free space in the environment around the first vehicle by determining B-splines corresponding to first roadway lanes based on the roadway lane markings and the roadway edges included in the first map. The instructions include further instructions to determine second roadway lanes based on determining locations of the non-stationary objects, determine combined roadway lanes based on the first roadway lanes and the second roadway lanes and operate the first vehicle based on the combined roadway lanes.
1. A computer, comprising a processor; and
a memory, the memory including instructions executable by the processor to:
generate a first map, based on vehicle sensor data, of a free space on a roadway in which a first vehicle can operate without contacting roadway edges and non-stationary objects on the roadway, the first map including roadway lane markings in an environment around the first vehicle, wherein the non-stationary objects include one or more second vehicles;
generate a second map of free space in the environment around the first vehicle by determining a first plurality of B-splines defining first roadway lanes based on the roadway lane markings and the roadway edges included in the first map;
determine a second plurality of B-splines defining second roadway lanes based on determining locations of the non-stationary objects;
determine combined roadway lanes by combining the first plurality of B-splines defining the first roadway lanes and the second plurality of B-splines defining the second roadway lanes; and
operate the first vehicle based on the combined roadway lanes.
2. The computer of claim 1 , wherein the first roadway lanes and the second roadway lanes are classified as one or more of a left lane, a right lane, a host lane and a non-relevant lane based on a location of the first vehicle.
3. The computer of claim 1 , wherein the vehicle sensor data includes one or more of video data, lidar data, and radar data.
4. The computer of claim 1 , the instructions including further instructions to determine the B-splines based on knots and controlled points, wherein the knots are points on the B-splines and the controlled points determine a shape of the B-splines between the knots based on third degree polynomial functions.
5. The computer of claim 1 , the instructions including further instructions to determine object tracks based on determining a plurality of locations of the non-stationary objects in data acquired by vehicle sensors at successive time steps.
6. The computer of claim 5 , the instructions including further instructions to determine B-splines corresponding to the second roadway lanes based on the object tracks.
7. The computer of claim 6 , the instructions including further instructions to determine the combined roadway lanes based on combining the B-splines corresponding to the first roadway lanes with the B-splines corresponding to the second roadway lanes.
8. The computer of claim 7 , the instructions including further instructions to include the B-splines corresponding to the second roadway lanes in the combined roadway lanes when the first roadway lanes and the second roadway lanes do not match.
9. The computer of claim 1 , the instructions including further instructions to operate the first vehicle based on determining a steerable path polynomial based on the combined roadway lanes.
10. The computer of claim 9 , the instructions including further instructions to operate the first vehicle on the steerable path polynomial by controlling vehicle powertrain, steering, and brakes.
11. A method, comprising:
generating a first map, based on vehicle sensor data, of a free space on a roadway in which a first vehicle can operate without contacting roadway edges and non-stationary objects on the roadway, the first map including roadway lane markings in an environment around the first vehicle, wherein the non-stationary objects include one or more second vehicles;
generating a second map of free space in the environment around the first vehicle by determining a first plurality of B-splines defining first roadway lanes based on the roadway lane markings and the roadway edges included in the first map;
determining a second plurality of B-splines defining second roadway lanes based on determining locations of the non-stationary objects;
determining combined roadway lanes by combining the first plurality of B-splines defining the first roadway lanes and the second plurality of B-splines defining the second roadway lanes; and
operating the first vehicle based on the combined roadway lanes.
12. The method of claim 11 , wherein the first roadway lanes and the second roadway lanes are classified as one or more of a left lane, a right lane, a host lane and a non-relevant lane based on a location of the first vehicle.
13. The method of claim 11 , wherein the vehicle sensor data includes one or more of video data, lidar data, and radar data.
14. The method of claim 11 , further comprising determining the B-splines based on knots and controlled points, wherein the knots are points on the B-splines and the controlled points determine a shape of the B-splines between the knots based on third degree polynomial functions.
15. The method of claim 11 , further comprising determining object tracks based on determining a plurality of locations of the non-stationary objects in data acquired by vehicle sensors at successive time steps.
16. The method of claim 15 , further comprising determining B-splines corresponding to the second roadway lanes based on the object tracks.
17. The method of claim 16 , further comprising determining the combined roadway lanes based on combining the B-splines corresponding to the first roadway lanes with the B-splines corresponding to the second roadway lanes.
18. The method of claim 17 , further comprising including the B-splines corresponding to the second roadway lanes in the combined roadway lanes when the first roadway lanes and the second roadway lanes do not match.
19. The method of claim 11 , further comprising operating the first vehicle based on determining a steerable path polynomial based on the combined roadway lanes.
20. The method of claim 19 , further comprising operating the first vehicle on the steerable path polynomial by controlling vehicle powertrain, steering, and brakes.