Autonomous vehicle fleet service and system
Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include monitoring a fleet of vehicles, at least one of which is configured to autonomously transit from a first geographic region to a second geographic region, detecting data indicating an event associated with the vehicle having a calculated confidence level, receiving data representing a subset of candidate trajectories responsive to detecting the event, which is associated with a planned path for the vehicle, identifying guidance data to select from one or more of the candidate trajectories as a guided trajectory, receiving data representing a selection of a candidate trajectory, and transmitting the selection of the candidate trajectory as of the guided trajectory to the vehicle.
1. A system, comprising:
a first sensor of a first type configured to sense an environment;
a second sensor of a second type different than the first type, the second sensor configured to sense the environment; and
one or more processors configured to perform operations comprising:
receiving a first signal from the first sensor, the first signal comprising data representing a first sensor measurement of a first three-dimensional position of an object in the environment;
receiving a second signal from the second sensor, the second signal comprising data representing a second sensor measurement of a second three-dimensional position of the object in the environment;
generating fused sensor data comprising data representing the first sensor measurement and the second sensor measurement;
determining, based at least in part on the first signal and the fused sensor data, that the first sensor is miscalibrated;
generating a calibration parameter associated with the first sensor, based at least in part on the second signal and the fused sensor data; and
modifying a parameter of the first sensor based at least in part on the calibration parameter.
2. The system of claim 1 , wherein:
the first sensor comprises one of an image sensor, a LIDAR sensor, a radar sensor, a sonar sensor, an internal sensor, or a location sensor; and
the second sensor comprises a different one of the image sensor, the LIDAR sensor, the radar sensor, the sonar sensor, the internal sensor, or the location sensor.
3. The system of claim 1 , the operations further comprising:
generating an expected sensor measurement associated with the first sensor, wherein:
determining that the first sensor is miscalibrated is further based at least in part on a difference between the expected sensor measurement and the first sensor measurement of the environment, and
generating the calibration parameter associated with the first sensor is further based at least in part on the expected sensor measurement.
4. The system of claim 3 , wherein:
the first sensor comprises a LIDAR sensor; and
the generating the expected sensor measurement is based at least in part on sensor data from one or more additional LIDAR sensors.
5. The system of claim 3 , wherein the generating the expected sensor measurement comprises:
receiving map data indicative of the object in the environment having known properties; and
generating the expected sensor measurement based at least in part on the map data indicative of the object.
6. The system of claim 1 , wherein the first sensor comprises an image sensor, and the modifying the parameter comprises adjusting a focus parameter or a lens parameter of the first sensor.
7. The system of claim 1 , wherein the generating the calibration parameter is further based on at least one of a log file of historical data associated with the first sensor, map data of the environment, or sensor data captured by a sensor external to the system.
8. The system of claim 1 , wherein the system comprises an autonomous vehicle and the operations further comprise:
generating, based at least in part on modifying the parameter, a trajectory; and
controlling the autonomous vehicle, based at least in part on the trajectory, to traverse a portion of the environment.
9. A method implemented at least in part by a system, the method comprising:
receiving a first signal from a first sensor of a first type, the first signal comprising data representing a first sensor measurement of an edge of an object in an environment;
receiving a second signal from a second sensor of a second type different than the first type, the second signal comprising data representing a second sensor measurement of the edge of the object in the environment;
generating fused sensor data comprising data representing the first sensor measurement and the second sensor measurement;
determining, based at least in part on the fused sensor data, that the first sensor is miscalibrated;
generating a calibration parameter associated with the first sensor, based at least in part on the fused sensor data; and
modifying a parameter of the first sensor based at least in part on the calibration parameter.
10. The method of claim 9 , wherein:
generating an expected sensor measurement associated with the first sensor, wherein:
determining that the first sensor is miscalibrated is further based at least in part on the expected sensor measurement and the first sensor measurement of the environment, and
generating the calibration parameter associated with the first sensor is further based at least in part on the expected sensor measurement.
11. The method of claim 10 , wherein:
the first sensor comprises a LIDAR sensor; and
the generating the expected sensor measurement is based at least in part on sensor data from one or more additional LIDAR sensors.
12. The method of claim 10 , wherein the generating the expected sensor measurement comprises:
receiving map data indicative of the object in the environment having known properties; and
generating the expected sensor measurement based at least in part on the map data indicative of the object.
13. The method of claim 9 , wherein the first sensor comprises an image sensor, and modifying the parameter comprises adjusting a focus parameter or a lens parameter of the first sensor.
14. The method of claim 9 , wherein the generating the calibration parameter is further based on at least one of a log file of historical data associated with the first sensor, map data of the environment, or sensor data captured by a sensor external to the system.
15. One or more non-transitory computer readable media having instructions stored thereon which, when executed by one or more processors of a system, cause the system to perform operations comprising:
receiving a first signal from a first sensor of a first type and associated with a first sensor system of a first vehicle, the first signal comprising data representing a first sensor measurement of an environment;
receiving a second signal from a second sensor of a second type and associated with the first sensor system, the second signal comprising data representing a second measurement of the environment;
determining, based at least in part on the first signal and sensor data captured by a second sensor system associated with a second vehicle, that the first sensor is miscalibrated; and
modifying a parameter of the first sensor based at least in part on the second signal and the sensor data captured by the second sensor system.
16. The one or more non-transitory computer readable media of claim 15 , the operations further comprising:
generating an expected sensor measurement associated with the first sensor, wherein:
determining that the first sensor is miscalibrated is further based at least in part on the expected sensor measurement and the first sensor measurement of the environment, and
modifying the parameter is further based at least in part on the expected sensor measurement.
17. The one or more non-transitory computer readable media of claim 16 , wherein:
the first sensor comprises a LIDAR sensor; and
the generating the expected sensor measurement is based at least in part on sensor data from one or more additional LIDAR sensors.
18. The one or more non-transitory computer readable media of claim 16 , wherein the generating the expected sensor measurement comprises:
receiving map data indicative of an object in the environment having known properties; and
generating the expected sensor measurement based at least in part on the map data indicative of the object.
19. The one or more non-transitory computer readable media of claim 15 , wherein the first sensor comprises an image sensor, and modifying the parameter comprises adjusting a focus parameter or a lens parameter of the first sensor.
20. The one or more non-transitory computer readable media of claim 15 , wherein modifying the parameter is further based on at least one of a log file of historical data associated with the first sensor, map data of the environment, or sensor data captured by a sensor external to the system.