Map selection for vehicle pose system
Various examples are directed to systems and methods for locating a vehicle. A pose state estimator may access a previous position for the vehicle at a first time, wherein the previous position is on a first sub-map of a plurality of sub-maps. The pose state estimator may receive from a first localizer a first position estimate for the vehicle at a second time after the first time. The first position estimate may be on a second sub-map of the plurality of sub-maps. The pose state estimator may send to a second localizer a sub-map change message indicating the second sub-map.
1 . A system for localizing a vehicle, the system comprising:
a vehicle computing system comprising a processor and data storage, wherein the vehicle computing system is programmed to execute operations comprising:
accessing a first position estimate for the vehicle generated by a first vehicle position generator executed by the vehicle computing system, wherein the first position estimate is generated by matching a first subset of sensor data to map data;
accessing a second position estimate for the vehicle generated by a second vehicle position generator executed by the vehicle computing system, wherein the second position estimate is generated by matching a second subset of sensor data that is different from the first subset of sensor data to the map data;
determining a pose for the vehicle based at least in part on the first position estimate, the second position estimate, and a plurality of motion sensor outputs; and
moving the vehicle using at least one vehicle control, the moving of the vehicle being based at least in part on the pose for the vehicle.
2 . The system of claim 1 , the matching of the first subset of sensor data to the map data comprising matching at least a portion of the first subset of sensor data to a first object indicated by the map data.
3 . The system of claim 1 , the matching of the second subset of sensor data to the map data comprising matching at least a portion of the second subset of sensor data to at least a portion of a ground surface described by the map data.
4 . The system of claim 1 , the first position estimate being on a first map area of a plurality of map areas and the second position estimate being on a second map area of the plurality of map areas, the operations further comprising:
selecting the second map area; and
sending, to the first vehicle position generator, a map area message indicating that the second map area is to be used for a future position estimate.
5 . The system of claim 4 , the operations further comprising:
generating, by the first vehicle position generator, the first position estimate using at least a portion of the map data associated with the first map area;
receiving, by the first vehicle position generator, the map area message; and
after receiving the map area message, generating, by the first vehicle position generator, an additional position estimate using map data associated with the second map area.
6 . The system of claim 4 , the operations further comprising:
accessing a first additional position estimate for the vehicle generated by the first vehicle position generator, the first additional position estimate being on the second map area;
accessing a second additional position estimate for the vehicle generated by the second vehicle position generator, the second additional position estimate being on an additional map area different than the second map area;
selecting, by the vehicle computing system, the second map area based at least in part on a confidence of the first additional position estimate and a confidence of the second additional position estimate; and
sending, to the second vehicle position generator, a second map area message indicating that the second map area is to be used for a future position estimate.
7 . The system of claim 4 , wherein the selecting of the second map area is based at least in part on a confidence of the first position estimate and a confidence of the second position estimate.
8 . A method for localizing a vehicle, the method comprising:
accessing, by a vehicle computing system, a first position estimate for the vehicle generated by a first vehicle position generator executed by the vehicle computing system, wherein the first position estimate is generated by matching a first subset of sensor data to map data;
accessing, by the vehicle computing system, a second position estimate for the vehicle generated by a second vehicle position generator executed by the vehicle computing system, wherein the second position estimate is generated by matching a second subset of sensor data that is different from the first subset of sensor data to the map data;
determining, by the vehicle computing system, a pose for the vehicle based at least in part on the first position estimate, the second position estimate, and a plurality of motion sensor outputs; and
moving the vehicle using at least one vehicle control, the moving of the vehicle being based at least in part on the pose for the vehicle.
9 . The method of claim 8 , the matching of the first subset of sensor data to the map data comprising matching at least a portion of the first subset of sensor data to a first object indicated by the map data.
10 . The method of claim 8 , the matching of the second subset of sensor data to the map data comprising matching at least a portion of the second subset of sensor data to at least a portion of a ground surface described by the map data.
11 . The method of claim 8 , the first position estimate being on a first map area of a plurality of map areas and the second position estimate being on a second map area of the plurality of map areas, the method further comprising:
selecting the second map area; and
sending, to the first vehicle position generator, a map area message indicating that the second map area is to be used for a future position estimate.
12 . The method of claim 11 , further comprising:
generating, by the first vehicle position generator, the first position estimate using at least a portion of the map data associated with the first map area;
receiving, by the first vehicle position generator, the map area message; and
after receiving the map area message, generating, by the first vehicle position generator, an additional position estimate using map data associated with the second map area.
13 . The method of claim 11 , further comprising:
accessing a first additional position estimate for the vehicle generated by the first vehicle position generator, the first additional position estimate being on the second map area;
accessing a second additional position estimate for the vehicle generated by the second vehicle position generator, the second additional position estimate being on an additional map area different than the second map area;
selecting, by the vehicle computing system, the second map area based at least in part on a confidence of the first additional position estimate and a confidence of the second additional position estimate; and
sending, to the second vehicle position generator, a second map area message indicating that the second map area is to be used for a future position estimate.
14 . The method of claim 11 , wherein the selecting of the second map area is based at least in part on a confidence of the first position estimate and a confidence of the second position estimate.
15 . A non-transitory machine-readable medium comprising instructions thereon that, when executed by at least one processor of a vehicle computing system, because the vehicle computing system to execute operations comprising:
accessing a first position estimate for the vehicle generated by a first vehicle position generator executed by the vehicle computing system, wherein the first position estimate is generated by matching a first subset of sensor data to map data;
accessing a second position estimate for the vehicle generated by a second vehicle position generator executed by the vehicle computing system, wherein the second position estimate is generated by matching a second subset of sensor data that is different from the first subset of sensor data to the map data;
determining a pose for the vehicle based at least in part on the first position estimate, the second position estimate, and a plurality of motion sensor outputs; and
moving the vehicle using at least one vehicle control, the moving of the vehicle being based at least in part on the pose for the vehicle.
16 . The non-transitory machine-readable medium of claim 15 , the matching of the first subset of sensor data to the map data comprising matching at least a portion of the first subset of sensor data to a first object indicated by the map data.
17 . The non-transitory machine-readable medium of claim 15 , the matching of the second subset of sensor data to the map data comprising matching at least a portion of the second subset of sensor data to at least a portion of a ground surface described by the map data.
18 . The non-transitory machine-readable medium of claim 15 , the first position estimate being on a first map area of a plurality of map areas and the second position estimate being on a second map area of the plurality of map areas, the operations further comprising:
selecting the second map area; and
sending, to the first vehicle position generator, a map area message indicating that the second map area is to be used for a future position estimate.
19 . The non-transitory machine-readable medium of claim 18 , the operations further comprising:
generating, by the first vehicle position generator, the first position estimate using at least a portion of the map data associated with the first map area;
receiving, by the first vehicle position generator, the map area message; and
after receiving the map area message, generating, by the first vehicle position generator, an additional position estimate using map data associated with the second map area.
20 . The non-transitory machine-readable medium of claim 18 , the operations further comprising:
accessing a first additional position estimate for the vehicle generated by the first vehicle position generator, the first additional position estimate being on the second map area;
accessing a second additional position estimate for the vehicle generated by the second vehicle position generator, the second additional position estimate being on an additional map area different than the second map area;
selecting, by the vehicle computing system, the second map area based at least in part on a confidence of the first additional position estimate and a confidence of the second additional position estimate; and
sending, to the second vehicle position generator, a second map area message indicating that the second map area is to be used for a future position estimate.