Determining lane position of a partially obscured target vehicle
A computing device including processor circuitry. The processor circuitry may perform operations comprising obtaining images representative of features within an environment of a host vehicle; identifying, from the images, a target object partially obscured in the environment; obtaining map data corresponding to the environment of the host vehicle, the map data comprising information of the features within the environment; localizing a position of the partially obscured target object within the environment based on comparing the features in the images to the information of the features obtained from the map data; and identifying a predicted trajectory of the partially obscured target object based on the localized position of the partially obscured target object within the environment.
1. At least one non-transitory machine-readable storage medium comprising instructions, which when executed by processor circuitry of a computing device, cause the processor circuitry to perform operations to:
obtain images representative of landmarks within an environment of a host vehicle;
identify, from the images, a target object partially obscured in the environment, the target object located on one or more lanes of travel of a roadway, wherein the partially obscured target object is a second vehicle;
obtain map data corresponding to the environment of the host vehicle, the map data comprising information of the landmarks within the environment that are located off the lanes of travel of the roadway;
localize a position of the partially obscured target object within the roadway based on comparing the landmarks identified in the images to the landmarks obtained from the map data, each of the compared landmarks being located off the lanes of travel of the roadway, wherein the second vehicle is localized to a lane position of the lanes of travel of the roadway using the landmarks within the environment that are located off the lanes of travel of the roadway; and
identify a predicted trajectory of the partially obscured target object on the roadway based on the localized position of the partially obscured target object within the roadway.
2. The non-transitory machine-readable storage medium of claim 1 , wherein the information of the landmarks obtained from the map data comprises a polynomial representation for each landmark.
3. The non-transitory machine-readable storage medium of claim 2 , wherein the landmarks are located adjacent to the lanes of travel of the roadway, and wherein each of the landmarks has a corresponding polynomial representation.
4. The non-transitory machine-readable storage medium of claim 3 , wherein the landmarks comprise at least one of: traffic signs, traffic lights, or poles.
5. The non-transitory machine-readable storage medium of claim 1 , wherein the predicted trajectory of the partially obscured target object is used for implementing a planned driving action in a host vehicle.
6. The non-transitory machine-readable storage medium of claim 5 , the instructions further to cause the processor circuitry to:
cause a change to a trajectory of the host vehicle based on the predicted trajectory of the partially obscured target object;
wherein the trajectory of the host vehicle represents a planned driving action for accomplishing a navigational goal of the host vehicle.
7. The non-transitory machine-readable storage medium of claim 1 , wherein the images are captured by a multi-camera system of the host vehicle, and wherein each camera of the multi-camera system has a different field of view in the environment.
8. The non-transitory machine-readable storage medium of claim 1 , the instructions further to cause the processor circuitry to obtain additional sensor data from a sensor device of the host vehicle, wherein the position of the partially obscured target object is further identified based on the additional sensor data.
9. The non-transitory machine-readable storage medium of claim 8 , wherein the sensor device includes at least one of a LIDAR system or a RADAR system, and wherein the additional sensor data includes data from the at least one of the LIDAR system or the RADAR system.
10. A computing device, comprising:
at least one interface to receive image data from at least one image capture device, the image data representative of landmarks within an environment of a host vehicle; and
at least one processor configured to perform operations to:
identify, from the image data, a target object partially obscured in the environment, the target object located on one or more lanes of travel of a roadway, wherein the partially obscured target object is a second vehicle;
obtain map data corresponding to the environment of the host vehicle, the map data comprising information of the landmarks within the environment that are located off the lanes of travel of the roadway;
localize a position of the partially obscured target object within the roadway based on comparing the landmarks identified in the image data to the landmarks obtained from the map data, each of the compared landmarks being located off the lanes of travel of the roadway, wherein the second vehicle is localized to a lane position of the lanes of travel of the roadway using the landmarks within the environment that are located off the lanes of travel of the roadway; and
identify a predicted trajectory of the partially obscured target object on the roadway based on the localized position of the partially obscured target object within the roadway.
11. The computing device of claim 10 , wherein the landmarks obtained from the map data comprises a polynomial representation for each landmark.
12. The computing device of claim 11 , wherein the landmarks are located adjacent to the lanes of travel of the roadway, and wherein each of the landmarks has a corresponding polynomial representation.
13. The computing device of claim 12 , wherein the landmarks comprise at least one of: traffic signs, traffic lights, or poles.
14. The computing device of claim 10 , wherein the predicted trajectory of the partially obscured target object is used for implementing a planned driving action in a host vehicle.
15. The computing device of claim 14 , the at least one processor further configured to:
cause a change to a trajectory of the host vehicle based on the predicted trajectory of the partially obscured target object;
wherein the trajectory of the host vehicle represents a planned driving action for accomplishing a navigational goal of the host vehicle.
16. The computing device of claim 10 , wherein the image data is captured by a multi-camera system of the host vehicle, and wherein each camera of the multi-camera system has a different field of view in the environment.
17. The computing device of claim 10 , the at least one interface further to receive additional sensor data from a sensor device of the host vehicle, wherein the position of the partially obscured target object is further identified based on the additional sensor data.
18. The computing device of claim 17 , wherein the sensor device includes at least one of a LIDAR system or a RADAR system, and wherein the additional sensor data includes data from the at least one of the LIDAR system or the RADAR system.