Velocity-based relevance filter

1. A vehicle system comprising:

one or more sensors;

one or more processors; and

memory storing processor-executable instructions that, when executed by the one or more processors, configure the vehicle system to:

receive sensor data from the one or more sensors;

identify, at a first time, an object at a first location in an environment based at least in part on the sensor data;

determine, at the first time, a first speed associated with a vehicle operating in the environment;

determine, at a second time, a planned second speed associated with the vehicle operating in the environment;

generate a relevance polygon associated with a planned path of the vehicle through the environment, the relevance polygon having a first width determined based at least in part on the first speed and a second width determined based at least in part on the planned second speed;

determine that the first location of the object is outside a first boundary of the relevance polygon;

determine, based at least in part on determining that the first location of the object is outside the first boundary, that the object is irrelevant to the vehicle at the first time; and

control the vehicle based on exclusion of data associated with the object at the first time based at least in part on determining that the object is irrelevant to the vehicle.

2. The vehicle system of claim 1 , wherein the relevance polygon comprises a first relevance polygon associated with the first speed and a second relevance polygon associated with the planned second speed.

3. The vehicle system of claim 2 , wherein:

the first relevance polygon comprises at least two of:

a first width, a first length or a first height;

the second relevance polygon comprises at least two of:

a second width, a second length or a second height;

the planned second speed is greater than the first speed; and

at least one of:

the second width is greater than the first width;

the second length is greater than the first length; or

the second height is greater than the first height.

4. The vehicle system of claim 1 , wherein the object is a first object and the processor-executable instructions further configure the vehicle to:

identify a second object at a second location in the environment based at least in part on the sensor data, wherein the second object is at least partially occluded by the first object;

determine that the second object is outside of the first boundary associated with the relevance polygon;

modify the relevance polygon to obtain a modified relevance polygon that includes the second location based at least in part on the second object being at least partially occluded by the first object;

determine that the second object is relevant to the vehicle based at least in part on the second location being associated with the modified relevance polygon; and

control the vehicle based on data associated with the second object.

5. A method comprising:

determining, at a first time, a first speed associated with a vehicle operating in an environment;

determining an acceleration associated with the vehicle operating in the environment;

determining, at a second time, a planned second speed associated with the vehicle operating in the environment;

generating a relevance polygon associated with the vehicle, wherein the relevance polygon extends a first extent along a planned path in a direction the vehicle is traveling and a second extent normal to the planned path, the first extent determined based at least in part on the first speed and the second extent varying along the planned path based at least in part on the planned second speed and the acceleration associated with the vehicle; receiving sensor data from one or more sensors;

identifying an object at a location in the environment based at least in part on the sensor data; and

determining that the object is relevant to the vehicle based at least in part on the location of the object being associated with the relevance polygon.

6. The method of claim 5 , further comprising:

controlling the vehicle based on inclusion of data associated with the object.

7. The method of claim 5 , wherein the speed is a first speed of the vehicle at a first time and the relevance polygon is a first relevance polygon, the method further comprising:

determining a second speed associated with the vehicle at a second time; and

generating a second relevance polygon based at least in part on the second speed.

8. The method of claim 7 , wherein

the first relevance polygon defines a first area,

the second relevance polygon defines a second area;

the second speed is less than the first speed; and

the second area is less than the first area.

9. The method of claim 5 , wherein the object is a first object located at a first location, the method further comprising:

identifying a second object at a second location in the environment based at least in part on the sensor data;

determining that the second location is outside of a boundary associated with the relevance polygon;

determining that the second object is irrelevant to the vehicle; and

controlling the vehicle based on exclusion of data associated with the second object.

10. The method of claim 5 , wherein the object is a first object located at a first location, the method further comprising:

determining a second object at a second location in the environment based at least in part on the sensor data, wherein the second object is at least partially occluded by the first object;

determining that the second object is outside of a boundary associated with the relevance polygon; and

modifying the relevance polygon to obtain a modified relevance polygon that includes the second location based at least in part on the second object being at least partially occluded by the first object.

11. The method of claim 5 , wherein:

the relevance polygon is defined by a minimum size if the speed is less than or equal to a threshold speed.

12. The method of claim 5 , further comprising:

receiving map data associated with the environment,

wherein the relevance polygon is further based at least in part on the map data.

13. The method of claim 5 , the method further comprising:

determining an object type associated with the object,

wherein the relevance polygon is further based at least in part on the object type.

14. The method of claim 5 , wherein the relevance polygon is further defined by a third extent extending along the planned path in a direction opposite the direction of the vehicle,

the third extent is determined based at least in part on the speed, and

the third extent differs from the first extent.

15. One or more non-transitory computer-readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform operations comprising:

determining, at a first time, a first speed associated with a vehicle operating in an environment;

determining an acceleration of the vehicle operating in the environment;

determining, at a second time, a planned second speed associated with the vehicle operating in the environment;

determining a region proximate the vehicle, wherein the region extends a first extent along a planned path in a direction the vehicle is traveling and a second extent normal to the planned path, the first extent determined based at least in part on the first speed and the second extent varying along the planned path based at least in part on the planned second speed and the acceleration associated with the vehicle;

receiving sensor data from one or more sensors;

identifying an object at a location in an environment based at least in part on the sensor data; and

determining that the object is relevant to the vehicle based at least in part on the location of the object being associated with the region.

16. The one or more non-transitory computer-readable media of claim 15 , wherein the region comprises a polygon, the operations further comprising:

controlling the vehicle based on inclusion of data associated with the object.

17. The one or more non-transitory computer-readable media of claim 15 , wherein the object is a first object at a first location, the operations further comprising:

generating a representation of the environment based at least in part on the sensor data;

determining, based at least in part on the representation, a second object at a second location in the environment, wherein the second object is at least partially occluded by the first object;

determining that the second object is outside of a boundary associated with the region;

modifying the region to obtain a modified relevance polygon that includes the second location based at least in part on the second object being at least partially occluded by the first object; and

controlling the vehicle based on inclusion of data associated with the second object.

18. The one or more non-transitory computer-readable media of claim 15 , wherein:

the region has a size greater than or equal to a minimum size.

19. The method of claim 14 , wherein a width of the relevance polygon is further based at least in part on a planned maneuver of the vehicle.