Systems and methods for operating an autonomous vehicle
An example method includes detecting, via sensor data collected from sensors located on the AV, an upcoming object located on a roadway. The method further includes determining, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle. The method further includes mapping the upcoming object to an absolute location with respect to the roadway based on map data that describes upcoming topology of the roadway and a location of the autonomous vehicle. The method further includes associating the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway. The method further includes operating the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located.
1. A method of operating an autonomous vehicle, comprising:
detecting, via sensor data collected from sensors located on the autonomous vehicle, an upcoming object located on a roadway on which the autonomous vehicle is located;
determining, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle;
mapping the upcoming object to an absolute location with respect to the roadway based on (i) map data that describes upcoming topology of the roadway and (ii) a location of the autonomous vehicle within the roadway;
associating the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway;
operating the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located;
determining a width and height of the upcoming object when the autonomous vehicle is a first distance away from the upcoming object; and
determining a length of the upcoming object along a direction of travel of the autonomous vehicle based on movement of the upcoming object and based on a two-dimensional bounding box associated with the determined width and height of the upcoming object when the autonomous vehicle is a second distance away from the upcoming object, wherein the second distance is less than the first distance, wherein the autonomous vehicle is operated further based on the width and the length of the upcoming object.
2. The method of claim 1 , further comprising:
tracking changes to the absolute location of the upcoming object for at least a length of time that the autonomous vehicle is approaching the upcoming object; and
updating the lane associated with the upcoming object based on the tracked changes.
3. The method of claim 1 , further comprising classifying the upcoming object as a static object or a moving object, wherein the autonomous vehicle is operated further based on whether the upcoming object is classified as a static object or a moving object.
4. The method of claim 3 , further comprising, in response to classifying the upcoming object as a moving object, updating the absolute location of the upcoming object at a pre-determined frequency.
5. The method of claim 3 , further comprising:
in response to classifying the upcoming object as a static object, monitoring the upcoming object for movement; and
based on a threshold degree of movement of the upcoming object being detected, re-classifying the upcoming object as a moving object.
6. The method of claim 1 , further comprising associating the upcoming object with a shoulder area of the roadway based on the lane geometry data defining shoulder areas of the roadway.
7. The method of claim 1 , further comprising:
determining a size of the upcoming object from the sensor data; and
based on the lane associated with the upcoming object and the current lane being a same lane, operating the autonomous vehicle with either a lane change operation or a lane bias operation based on the size of the upcoming object.
8. A system for operating an autonomous vehicle, comprising a computer that includes a processor configured to execute instructions to cause the system to:
detect, via sensor data collected from sensors located on the autonomous vehicle, an upcoming object located on a roadway on which the autonomous vehicle is located;
determine, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle;
map the upcoming object to an absolute location with respect to the roadway based on (i) map data that describes upcoming topology of the roadway and (ii) a location of the autonomous vehicle within the roadway;
associate the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway;
operate the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located;
determine a width and height of the upcoming object when the autonomous vehicle is a first distance away from the upcoming object; and
determine a length of the upcoming object along a direction of travel of the autonomous vehicle based on movement of the upcoming object and based on a two-dimensional bounding box associated with the determined width and height of the upcoming object when the autonomous vehicle is a second distance away from the upcoming object, wherein the second distance is less than the first distance, wherein the autonomous vehicle is operated further based on the width and the length of the upcoming object.
9. The system of claim 8 , wherein the processor further causes the system to:
track the upcoming object across successive sensor data collected from the sensors at subsequent points in time; and
update the lane associated with the upcoming object based on the tracking.
10. The system of claim 8 , wherein the processor further causes the system to classify the upcoming object as a vehicular object or a non-vehicular object, wherein the autonomous vehicle is operated further based on whether the upcoming object is classified as a vehicular object or a non-vehicular object.
11. The system of claim 10 , wherein the processor further causes the system to, in response to classifying the upcoming object as a vehicular object, update the absolute location of the upcoming object at a pre-determined frequency.
12. The system of claim 10 , wherein the processor further causes the system to:
in response to classifying the upcoming object as a non-vehicular object, monitor the upcoming object for movement; and
operate the autonomous vehicle to maintain at least a minimum distance away from the upcoming object, wherein the minimum distance corresponds to movement of the upcoming object.
13. The system of claim 8 , wherein the lane associated with the upcoming object includes a shoulder area of the roadway.
14. A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to:
detect, via sensor data collected from sensors located on an autonomous vehicle, an upcoming object located on a roadway on which the autonomous vehicle is located;
determine, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle;
map the upcoming object to an absolute location with respect to the roadway based on (i) map data that describes upcoming topology of the roadway and (ii) a location of the autonomous vehicle within the roadway;
associate the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway;
operate the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located;
determine a width and height of the upcoming object when the autonomous vehicle is a first distance away from the upcoming object; and
determine a length of the upcoming object along a direction of travel of the autonomous vehicle based on movement of the upcoming object and based on a two-dimensional bounding box associated with the determined width and height of the upcoming object when the autonomous vehicle is a second distance away from the upcoming object, wherein the second distance is less than the first distance, wherein the autonomous vehicle is operated further based on the width and the length of the upcoming object.
15. The non-transitory computer readable program storage medium of claim 14 , wherein the code further causes the processor to:
track the upcoming object across other sensor data collected from a different set of sensors located on the autonomous vehicle, wherein the different set of sensors are configured for a different sensing modality than the sensors, wherein the relative distance and the relative direction of the upcoming object is determined further from the other sensor data.
16. The non-transitory computer readable program storage medium of claim 14 , wherein the code further causes the processor to predict a degree of movement of the upcoming object, wherein the autonomous vehicle is operated further based on the predicted degree of movement.
17. The non-transitory computer readable program storage medium of claim 16 , wherein the code further causes the processor to update the absolute location of the upcoming object at a pre-determined frequency that is based on the predicted degree of movement.
18. The non-transitory computer readable program storage medium of claim 14 , wherein at least a portion of the map data is provided by one or more vehicles located at an upcoming portion of the roadway.
19. The non-transitory computer readable program storage medium of claim 14 , wherein the relative distance and the relative direction of the upcoming object is determined using a centroid of a LiDAR point cloud of the sensor data via which the upcoming object is detected.