Systems and methods to adjust autonomous vehicle parameters in response to passenger feedback

1. A computer-implemented method to adjust a vehicle parameter for an autonomous vehicle, the method comprising:

obtaining, by a computing system comprising one or more computing devices, passenger input data descriptive of one or more experiences of one or more passengers associated with one or more autonomous driving sessions, the passenger input data comprising feedback provided by the one or more passengers;

obtaining, by the computing system, one or more vehicle data logs descriptive of vehicle conditions associated with the passenger input data, the one or more vehicle data logs descriptive of vehicle conditions associated with one or more autonomous vehicles during the one or more autonomous driving sessions in which the one or more passengers provided the feedback as passenger input data;

determining, by the computing system using a machine-learned model, an adjusted vehicle parameter of the one or more autonomous vehicles based at least in part on the passenger input data descriptive of the one or more experiences and the associated one or more vehicle data logs descriptive of vehicle conditions; and

implementing, by the computing system, the adjusted vehicle parameter in an operation of the one or more autonomous vehicles.

2. The computer-implemented method of claim 1 , wherein the machine-learned model has been trained based at least in part on training data that comprises previous passenger input data descriptive of passenger experiences and associated vehicle data logs that were previously collected during previous autonomous vehicle driving sessions.

3. The computer-implemented method of claim 2 , wherein the training data includes labels comprising previously adjusted vehicle parameters associated with the previous passenger input data and associated vehicle data logs.

4. The computer-implemented method of claim 1 , wherein determining, by the computing system, the adjusted vehicle parameter of the one or more autonomous vehicles autonomous vehicle based at least in part on the passenger input data descriptive of the one or more experiences and the associated one or more vehicle data logs descriptive of vehicle conditions comprises:

obtaining, by the computing system, data descriptive of the machine-learned model;

inputting, by the computing system, the passenger input data descriptive of the one or more experiences and the associated one or more vehicle data logs descriptive of vehicle conditions into the machine-learned model; and

receiving, by the computing system, data indicative of the adjusted vehicle parameter as an output of the machine-learned model.

5. The computer-implemented method of claim 1 , wherein implementing, by the computing system, the adjusted vehicle parameter in the operation of the one or more autonomous vehicles comprises:

providing, by the computing system, the adjusted vehicle parameter to a computing system on-board the one or more autonomous vehicles.

6. The computer-implemented method of claim 1 , wherein the computing system comprises a computing system on-board the autonomous vehicle.

7. The computer-implemented method of claim 6 , further comprising:

controlling a motion of the autonomous vehicle based at least in part on the adjusted vehicle parameter.

8. The computer-implemented method of claim 1 , wherein the adjusted vehicle parameter comprises adjusted cost data utilized for planning a motion of the autonomous vehicle.

9. The computer-implemented method of claim 1 , wherein the passenger input data indicative of the one or more experiences of the one or more passengers comprises data indicative of a positive or negative experience for one or more of a pick-up event, a drop-off event, or an in-ride event.

10. The computer-implemented method of claim 1 , wherein the one or more vehicle data logs comprise one or more operating parameters of an autonomous vehicle performing a vehicle action associated with the passenger input data indicative of one or more passenger experiences; and

wherein the one or more operating parameters comprise one or more of: a vehicle speed, a vehicle acceleration, a vehicle deceleration, a lateral acceleration, a vehicle location, a vehicle stop duration, a proximity to a pick-up location, a proximity to a drop-off location, or a passenger comfort setting.

11. The computer-implemented method of claim 1 , wherein the one or more vehicle data logs are indicative of one or more conditions associated with an environment of the autonomous vehicle; and

wherein the one or more conditions comprise one or more of: a vehicle traffic condition, a vehicle behavior, a pedestrian behavior, or an object proximate to the autonomous vehicle.

12. The computer-implemented method of claim 1 , wherein the adjusted vehicle parameter is based at least in part on a geographic location.

13. The computer-implemented method of claim 1 , wherein the passenger input data descriptive of the one or more experiences of the one or more passengers associated with the one or more autonomous driving sessions is obtained via a human machine interface device on-board the autonomous vehicle or via a user computing device.

14. The computer-implemented method of claim 1 , wherein the passenger input data descriptive of the one or more experiences of the one or more passengers associated with the one or more autonomous driving sessions is obtained via one or more autonomous vehicle sensors.

15. A computing system comprising:

one or more processors; and

one or more non-transitory computer-readable media that collectively store:

at least one set of passenger input data descriptive of one or more experiences of one or more passengers associated with one or more autonomous driving sessions, the passenger input data comprising feedback provided by the one or more passengers indicative of a positive or negative experience for one or more of a pick-up event, a drop-off event, or an in-ride event; and

at least one vehicle data log descriptive of vehicle conditions associated with the passenger input data descriptive of the one or more experiences of the one or more passengers, the one or more vehicle data logs descriptive of vehicle conditions associated with one or more autonomous vehicles during the one or more autonomous driving sessions in which the one or more passengers provided the feedback as input data, the at least one vehicle data log comprising one or more operating parameters of an autonomous vehicle performing a vehicle action associated with the passenger input data indicative of the one or more passenger experiences or data indicative of one or more conditions associated with an environment of the autonomous vehicle while the autonomous vehicle performed the vehicle action; and

instructions that, when executed by the one or more processors, cause the computing system to:

associate the at least one set of passenger input data descriptive of the one or more experiences of the one or more passengers and the at least one associated vehicle data log with at least one identified operating parameter or identified condition associated with the environment of the autonomous vehicle; and

train a machine-learned model to perform a vehicle parameter adjustment based at least in part on the at least one identified operating parameter or identified condition associated with the environment of the autonomous vehicle.

16. The computing system of claim 15 , wherein the at least one set of passenger input data descriptive of the one or more experiences of the one or more passengers associated with the one or more autonomous driving sessions comprises one or more adjusted vehicle parameter labels associated with the passenger input data and associated vehicle data logs, the one or more adjusted vehicle parameter labels provided by a human reviewer of the passenger input data and associated vehicle data logs.

17. The computing system of claim 15 , wherein the one or more operating parameters comprise one or more of: a vehicle speed, a vehicle acceleration, a vehicle deceleration, a lateral acceleration, a vehicle location, a vehicle stop duration, a proximity to a pick-up location, a proximity to a drop-off location, or a passenger comfort setting.

18. The computing system of claim 15 , wherein the one or more conditions associated with the environment of the autonomous vehicle comprise one or more of: a vehicle traffic condition, a vehicle behavior, a pedestrian behavior, or an object proximate to the autonomous vehicle.

19. The computing system of claim 15 , wherein the adjusted vehicle parameter comprises adjusted cost data utilized for planning a motion of the autonomous vehicle.

20. One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more processors, cause a computing system to perform operations, the operations comprising:

obtaining passenger input data descriptive of one or more passenger experiences of one or more passengers comprising data indicative of a positive or negative experience for one or more of a pick-up event, a drop-off event, or an in-ride event associated with one or more autonomous driving sessions, the passenger input data comprising feedback provided by the one or more passengers;

obtaining one or more vehicle data logs descriptive of vehicle conditions associated with the passenger input data descriptive of the one or more experiences of the one or more passengers, the one or more vehicle data logs descriptive of vehicle conditions associated with one or more autonomous vehicles during the one or more autonomous driving sessions in which the one or more passengers provided the feedback as passenger input data, the one or more vehicle data logs comprising one or more operating parameters of an autonomous vehicle performing a vehicle action associated with the passenger input data indicative of one or more passenger experiences and data indicative of one or more conditions associated with an environment of the autonomous vehicle while the autonomous vehicle performed the vehicle action;

inputting the passenger input data descriptive of the one or more experiences of the one or more passenger and the associated one or more vehicle data logs descriptive of vehicle conditions into a machine-learned model;

receiving data indicative of an adjusted vehicle parameter as an output of the machine-learned model; and

implementing the adjusted vehicle parameter in the operation of an autonomous vehicle.