Determining parking locations based on multistage filtering
Techniques for determining parking spaces and/or parking trajectories for a vehicle based on multistage filtering are discussed herein. In some examples, a vehicle may navigate to a destination within an environment. The vehicle may receive a set of parking locations and perform filtering operations to determine a subset of the parking locations. For example, the vehicle may use a list of parking characteristics (e.g., conditions) to filter the set of parking spaces. Based on determining the subset of parking spaces, the vehicle may generate a set of candidate trajectories to the subset of parking spaces. The vehicle may determine a subset of the candidate trajectories based on filtering the set of candidate trajectories according to various constraints. Further, the vehicle may determine a cost for the subset of candidate trajectories. Based on the costs, the vehicle may determine a candidate trajectory for the vehicle to follow.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
determining that an autonomous vehicle is within a threshold distance from a destination;
receiving, based at least in part on the autonomous vehicle being within the threshold distance from the destination, a set of parking locations;
identifying parking characteristics associated with the set of parking locations;
determining, based at least in part on the parking characteristics, a subset of parking locations of the set of parking locations, wherein the subset of parking locations satisfy the parking characteristics;
generating a set of trajectories associated with at least one of the subset of parking locations;
determining a cost associated with an individual trajectory of the set of trajectories, wherein determining the cost associated with the individual trajectory comprises determining a subset of trajectories of the set of trajectories based at least in part on a constraint, and wherein the constraint comprises at least one of:
a steering limitation of the autonomous vehicle,
an acceleration limitation of the autonomous vehicle,
a velocity limitation of the autonomous vehicle, or
a predicted intersection with an object;
determining, based at least in part on the cost, a candidate trajectory of the subset of trajectories; and
controlling the autonomous vehicle based at least in part on the candidate trajectory.
2. The system of claim 1 , wherein the parking characteristics for a parking location of the set of parking locations comprise at least one of:
an availability of the parking location,
a first distance between the parking location and the autonomous vehicle meeting or exceeding a first threshold,
a second distance between the parking location and the autonomous vehicle being at or below second threshold,
a side of a road of the parking location, or
a type of parking space of the parking location.
3. The system of claim 1 , wherein generating the set of trajectories is based at least in part on:
generating an initial trajectory to a second parking location;
generating, based at least in part on the initial trajectory, a second candidate trajectory to the second parking location; and
generating, based at least in part on the initial trajectory, a third candidate trajectory to the second parking location, wherein the second candidate trajectory is different than the third candidate trajectory.
4. The system of claim 1 , wherein determining the subset of parking locations comprises:
determining an additional cost associated with a second parking location of the set of parking locations, wherein the additional cost is determined based at least in part on the parking characteristics; and
determining that the additional cost associated with the second parking location meets or exceeds a threshold value; and
determining, based at least in part on the additional cost meeting or exceeding the threshold value, that the second parking location satisfies the parking characteristics.
5. One or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
determining that a vehicle is within a threshold distance from a destination;
receiving, based at least in part on the vehicle being within the threshold distance from the destination, a set of parking locations;
identifying parking characteristics associated with the set of parking locations;
determining, based at least in part on the parking characteristics, a subset of parking locations of the set of parking locations;
generating a set of trajectories associated with a parking location of the subset of parking locations; and
controlling a vehicle based at least in part on the set of trajectories, wherein controlling the vehicle comprises determining a subset of trajectories of the set of trajectories based at least in part on a constraint, and wherein the constraint comprises at least one of:
a steering limitation of the vehicle,
an acceleration limitation of the vehicle,
a velocity limitation of the vehicle, or
a predicted intersection with an object.
6. The one or more non-transitory computer-readable media of claim 5 , wherein the parking characteristics comprise at least one of:
an availability of a second parking location,
a first distance between the parking location and the vehicle meeting or exceeding a first threshold,
a second distance between the parking location and the vehicle being at or below second threshold,
a side of a road of the second parking location, or
a type of parking space of the second parking location.
7. The one or more non-transitory computer-readable media of claim 5 , wherein the operations for generating the set of trajectories are based at least in part on:
generating an initial trajectory to a second parking location;
generating, based at least in part on the initial trajectory, a second candidate trajectory to the second parking location; and
generating, based at least in part on the initial trajectory, a third candidate trajectory to the second parking location, wherein the second candidate trajectory is different than the third candidate trajectory.
8. The one or more non-transitory computer-readable media of claim 5 , wherein the operations for determining the subset of parking locations comprises:
determining a cost associated with a second parking location of the set of parking locations, wherein the cost is determined based at least in part on the parking characteristics; and
determining that the cost of the second parking location is within a threshold value; and
determining, based at least in part on the cost being within the threshold value, that the second parking location satisfies the parking characteristics.
9. The one or more non-transitory computer-readable media of claim 5 , wherein controlling the vehicle:
determining a cost associated with a candidate trajectory of the set of trajectories; and
determining, based at least in part on the cost, to control the vehicle in accordance with the candidate trajectory.
10. The one or more non-transitory computer-readable media of claim 5 , wherein the threshold distance is based at least at least in part on:
an environment type,
a characteristic of a passenger of the vehicle,
event data, or
historical data.
11. The one or more non-transitory computer-readable media of claim 5 , wherein controlling the vehicle based at least in part on the set of trajectories comprises determining a trajectory of the set of trajectories based at least in part on ranking the set of trajectories.
12. A method comprising:
determining that a vehicle is within a threshold distance from a destination;
receiving, based at least in part on the vehicle being within the threshold distance from the destination, a set of parking locations;
identifying parking characteristics associated with the set of parking locations;
determining, based at least in part on the parking characteristics, a subset of parking locations of the set of parking locations;
generating a set of trajectories associated with a parking location of the subset of parking locations; and
controlling a vehicle based at least in part on the set of trajectories, wherein controlling the vehicle comprises determining a subset of trajectories of the set of trajectories based at least in part on a constraint, and wherein the constraint comprises at least one of:
a steering limitation of the vehicle,
an acceleration limitation of the vehicle,
a velocity limitation of the vehicle, or
a predicted intersection with an object.
13. The method of claim 12 , wherein the parking characteristics comprise at least one of:
an availability of a second parking location,
a first distance between the parking location and the vehicle meeting or exceeding a first threshold,
a second distance between the parking location and the vehicle being at or below second threshold,
a side of a road of the second parking location, or
a type of parking space of the second parking location.
14. The method of claim 12 , wherein generating the set of trajectories is based at least in part on:
generating an initial trajectory to a second parking location;
generating, based at least in part on the initial trajectory, a second candidate trajectory to the second parking location; and
generating, based at least in part on the initial trajectory, a third candidate trajectory to the second parking location, wherein the second candidate trajectory is different than the third candidate trajectory.
15. The method of claim 12 , wherein determining the subset of parking locations comprises:
determining a cost associated with a second parking location of the set of parking locations, wherein the cost is determined based at least in part on the parking characteristics; and
determining that the cost of the second parking location is within a threshold value; and
determining, based at least in part on the cost being within the threshold value, that the second parking location satisfies the parking characteristics.
16. The method of claim 12 , wherein controlling the vehicle:
determining a cost associated with a candidate trajectory of the set of trajectories; and
determining, based at least in part on the cost, to control the vehicle in accordance with the candidate trajectory.
17. The method of claim 12 , wherein the threshold distance is based at least at least in part on:
an environment type,
a characteristic of a passenger of the vehicle,
event data, or
historical data.
18. The system of claim 1 , wherein the set of trajectories includes at least one of acceleration data or steering data of the autonomous vehicle.
19. The one or more non transitory computer readable media of claim 6 , wherein the set of trajectories includes at least one of acceleration data or steering data of the vehicle.
20. The method of claim 12 , wherein the set of trajectories includes at least one of acceleration data or steering data of the vehicle.