Autonomous vehicle lane boundary detection systems and methods
Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain rasterized LIDAR data associated with a surrounding environment of an autonomous vehicle. The rasterized LIDAR data can include LIDAR image data that is rasterized from a LIDAR point cloud. The computing system can access data indicative of a machine-learned lane boundary detection model. The computing system can input the rasterized LIDAR data associated with the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model. The computing system can obtain an output from the machine-learned lane boundary detection model. The output can be indicative of one or more lane boundaries within the surrounding environment of the autonomous vehicle.
1. A computing system, comprising:
one or more processors; and
one or more tangible, non-transitory, computer readable media that collectively store instructions that when executed by the one or more processors cause the computing system to perform operations comprising:
obtaining rasterized LIDAR data associated with a surrounding environment of an autonomous vehicle, wherein the rasterized LIDAR data comprises LIDAR image data that is rasterized from a LIDAR point cloud,
wherein the rasterized LIDAR data comprises one or more spatial locations, and wherein each of the one or more spatial locations comprises a first channel representing a height of at least one pixel, a second channel representing a brightness level of the at least one pixel, and a third channel representing a total number of points, the at least one pixel being associated with a lane marking on a ground of a travel way;
accessing data indicative of a machine-learned lane boundary detection model;
inputting the rasterized LIDAR data associated with the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model; and
obtaining an output from the machine-learned lane boundary detection model, wherein the output is indicative of one or more lane boundaries within the surrounding environment of the autonomous vehicle, wherein the one or more lane boundaries comprises the lane marking on the ground of the travel way.
2. The computing system of claim 1 , wherein the rasterized LIDAR data is indicative of a two-dimensional overhead view depicting at least a portion of the surrounding environment.
3. The computing system of claim 1 , further comprising:
obtaining camera image data associated with the surrounding environment of the autonomous vehicle; and
generating overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the rasterized LIDAR data and the camera image data.
4. The computing system of claim 3 , further comprising:
inputting the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model,
wherein the output from the machine-learned lane boundary detection model is based on the rasterized LIDAR data and the overhead image data.
5. The computing system of claim 1 , wherein the machine-learned lane boundary detection model comprises a convolutional neural network.
6. The computing system of claim 1 , wherein the operations further comprise:
providing, for storage in a memory onboard the autonomous vehicle, the output indicative of the one or more lane boundaries within the surrounding environment of the autonomous vehicle.
7. The computing system of claim 1 , wherein the operations further comprise:
perceiving an object within the one or more lane boundaries;
predicted a motion trajectory of the object based at least in part on the one or more lane boundaries, wherein predicting the motion trajectory of the object comprises predicting that the object will stay within the one or more lane boundaries;
planning a motion of the autonomous vehicle based at least in part on the motion trajectory of the object, wherein the motion comprises at least one of traveling behind the object within the one or more lane boundaries or passing the object by moving the autonomous vehicle outside of the one or more lane boundaries.
8. A computer-implemented method of detecting lane boundaries, the method comprising:
obtaining, by a computing system comprising one or more computing devices, LIDAR data associated with a surrounding environment of an autonomous vehicle, wherein the LIDAR data is indicative of a LIDAR point cloud associated with the surrounding environment of the autonomous vehicle;
generating, by the computing system, rasterized LIDAR data based at least in part on the LIDAR data associated with the surrounding environment of the autonomous vehicle,
wherein the rasterized LIDAR data comprises one or more spatial locations and wherein each of the one or more spatial locations comprises a first channel representing a height of at least one pixel, a second channel representing a brightness level of the at least one pixel, and a third channel representing a total number of points, the at least one pixel being associated with a lane marking on a ground of a travel way; and
determining, by the computing system, one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the rasterized LIDAR data and a machine-learned lane boundary detection model, wherein the one or more lane boundaries comprises the lane marking on the ground of the travel way.
9. The computer-implemented method of claim 8 , wherein generating, by the computing system, the rasterized LIDAR data based at least in part on the LIDAR data associated with the surrounding environment of the autonomous vehicle comprises:
rasterizing, by the computing system, the LIDAR point cloud associated with the surrounding environment of the autonomous vehicle into a two-dimensional overhead view image depicting at least a portion of the surrounding environment.
10. The computer-implemented method of claim 8 , wherein determining, by the computing system, the one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the rasterized LIDAR data and the machine-learned lane boundary detection model comprises:
accessing, by the computing system, data indicative of the machine-learned lane boundary detection model;
inputting, by the computing system, the rasterized LIDAR data associated with the surrounding environment of the autonomous vehicle into the machine-learned boundary detection model; and
obtaining, by the computing system, an output from the machine-learned lane boundary detection model, wherein the output is indicative of the one or more lane boundaries within the surrounding environment of the autonomous vehicle.
11. The computer-implemented method of claim 10 , further comprising:
inputting, by the computing system, overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model.
12. The computer-implemented method of claim 10 , wherein the machine-learned lane boundary detection model comprises a convolutional neural network.
13. The computer-implemented method of claim 8 , further comprising:
initiating, by the computing system, a performance of one or more vehicle actions by the autonomous vehicle based at least in part on the one or more lane boundaries.
14. The computer-implemented method of claim 13 , wherein the one or more vehicle actions comprise determining a location of the autonomous vehicle within a travel lane based at least in part on the one or more lane boundaries.
15. The computer-implemented method of claim 13 , wherein the one or more vehicle actions comprise planning a motion of the autonomous vehicle based at least in part on the one or more lane boundaries.
16. The computer-implemented method of claim 13 , wherein the one or more vehicle actions comprise perceiving an object within the surrounding environment of the autonomous vehicle based at least in part on the one or more lane boundaries.
17. The computer-implemented method of claim 12 , wherein the one or more vehicle actions comprise predicting a motion trajectory of an object within the surrounding environment of the autonomous vehicle based at least in part on the one or more lane boundaries.
18. An autonomous vehicle, comprising:
a machine-learned lane boundary detection model;
one or more processors; and
one or more tangible, non-transitory, computer readable media that collectively store instructions that when executed by the one or more processors cause the autonomous vehicle to perform operations comprising:
obtaining rasterized LIDAR data associated with a surrounding environment of an autonomous vehicle, wherein the rasterized LIDAR data comprises LIDAR image data that is rasterized from a LIDAR point cloud,
wherein the rasterized LIDAR data comprises one or more spatial locations, and wherein each of the one or more spatial locations comprises a first channel representing a height of at least one pixel, a second channel representing a brightness level of the at least one pixel, and a third channel representing a total number of points, the at least one pixel being associated with a lane marking on a ground of a travel way;
inputting the rasterized LIDAR data associated with the surrounding environment of the autonomous vehicle into the machine-learned lane boundary detection model; and
obtaining an output from the machine-learned lane boundary detection model, wherein the output is indicative of one or more lane boundaries within the surrounding environment of the autonomous vehicle, wherein the one or more lane boundaries comprises the lane marking on the ground of the travel way.
19. The autonomous vehicle of claim 18 , wherein the one or more lane boundaries are located within a highway on which the autonomous vehicle is located.
20. The autonomous vehicle of claim 18 , wherein the autonomous vehicle is an autonomous truck.