Abstract: In one embodiment, a method includes determining a fleet-level objective for a vehicle associated with instructing the vehicle to travel a route according to route criteria based on the fleet-level objective. The method includes receiving a ride request from a ride requestor associated with ride criteria including a pick-up location and a drop-off location. The method includes determining that the ride requestor is a passenger for the vehicle to satisfy the fleet-level objective contingent on modifications to the ride criteria. The method includes providing incentives to the ride requestor contingent on acceptance of the modifications to the ride criteria. The method includes, after receiving the acceptance of the modifications to the ride criteria, modifying the ride criteria in accordance with the route criteria. The method includes instructing the vehicle to transport the ride requestor based on the modified ride criteria so as to fulfill the fleet-level objective.

Abstract: In particular embodiments, a computing system may determine a predicted amount of ride requests for a plurality of collectively-managed vehicles and determine an availability of the collectively-managed vehicles to satisfy the predicted amount of ride requests. Subsequent to determining that the availability fails to satisfy one or more predetermined criteria for servicing the predicted amount of ride requests, the system may determine status information associated with the collectively-managed vehicles and determine, based on at least the status information, one or more minimum services for servicing one or more vehicles among the plurality of collectively-managed vehicles at one or more service centers such that the availability satisfies the one or more predetermined criteria. The system may instruct the one or more vehicles that are to receive the one or more minimum services to travel to the one or more service centers to be serviced.

Abstract: In particular embodiments, a computing system may determine a predicted amount of ride requests for a plurality of collectively-managed vehicles and determine an availability of the collectively-managed vehicles to satisfy the predicted amount of ride requests. Subsequent to determining that the availability fails to satisfy one or more predetermined criteria for servicing the predicted amount of ride requests, the system may determine status information associated with the collectively-managed vehicles and determine, based on at least the status information, one or more minimum services for servicing one or more vehicles among the plurality of collectively-managed vehicles at one or more service centers such that the availability satisfies the one or more predetermined criteria. The system may instruct the one or more vehicles that are to receive the one or more minimum services to travel to the one or more service centers to be serviced.

Abstract: In one embodiment, a method includes determining a fleet-level objective for a vehicle associated with instructing the vehicle to travel a route according to route criteria based on the fleet-level objective. The method includes receiving a ride request from a ride requestor associated with ride criteria including a pick-up location and a drop-off location. The method includes determining that the ride requestor is a passenger for the vehicle to satisfy the fleet-level objective contingent on modifications to the ride criteria. The method includes providing incentives to the ride requestor contingent on acceptance of the modifications to the ride criteria. The method includes, after receiving the acceptance of the modifications to the ride criteria, modifying the ride criteria in accordance with the route criteria. The method includes instructing the vehicle to transport the ride requestor based on the modified ride criteria so as to fulfill the fleet-level objective.

Abstract: In particular embodiments, a computing system may determine a predicted amount of ride requests for a plurality of collectively-managed vehicles and determine an availability of the collectively-managed vehicles to satisfy the predicted amount of ride requests. Subsequent to determining that the availability fails to satisfy one or more predetermined criteria for servicing the predicted amount of ride requests, the system may determine status information associated with the collectively-managed vehicles and determine, based on at least the status information, one or more minimum services for servicing one or more vehicles among the plurality of collectively-managed vehicles at one or more service centers such that the availability satisfies the one or more predetermined criteria. The system may instruct the one or more vehicles that are to receive the one or more minimum services to travel to the one or more service centers to be serviced.

Abstract: In one embodiment, a method includes a computing system receiving information from an autonomous vehicle (AV). Based on the received information, the system may identify a target objective, with an associated target destination, for the AV and determine that the AV is able to transport passengers while furthering the target objective. The system may receive multiple ride requests from ride requestors, respectively. Each of the ride requests is associated with an origination location and a destination location. The system may match the AV with one of the ride requests based on a location of the AV, the target destination of the target objective, and the origination location and destination location associated with the ride request. The system may instruct the AV to perform a transportation task from the origination location to the destination location associated with the ride request, and drive to the target destination after completing the transportation task.

Abstract: In particular embodiments, a computing system may generate a prediction of requests for autonomous vehicles in a fleet of collectively managed autonomous vehicles based on a current condition and a future event, the prediction including a predicted request level and a predicted duration of the request level. The system may receive status information from fleet vehicles and identify a vehicle in need of service. The system may receive status information from service centers and identify a service center to service the vehicle. The system may determine a time at which to service the vehicle at the identified service center based on the generated prediction of requests, schedule the vehicle for service at the identified service center at the determined time, and instruct the vehicle to drive to the service center to be serviced at the determined time. In particular embodiments, the prediction of requests may be generated using machine learning.

Abstract: In one embodiment, a method includes a computing system receiving information from an autonomous vehicle (AV). Based on the received information, the system may identify a target objective, with an associated target destination, for the AV and determine that the AV is able to transport passengers while furthering the target objective. The system may receive multiple ride requests from ride requestors, respectively. Each of the ride requests is associated with an origination location and a destination location. The system may match the AV with one of the ride requests based on a location of the AV, the target destination of the target objective, and the origination location and destination location associated with the ride request. The system may instruct the AV to perform a transportation task from the origination location to the destination location associated with the ride request, and drive to the target destination after completing the transportation task.

Abstract: In particular embodiments, a computing system may receive an indication of an impaired sensor component from a first autonomous vehicle. The system may identify a sensor type of the impaired sensor component and determine a suitable service center for servicing the sensor type based on one or more criteria. The system may identify a second autonomous vehicle. The second autonomous vehicle has a functional sensor component of the sensor type. The system may send instructions to the second autonomous vehicle to drive to a location of the first autonomous vehicle and share sensor data from the functional sensor component with the first autonomous vehicle. The first autonomous vehicle may be instructed to drive to the service center location using sensor data of the second autonomous vehicle. The second autonomous vehicle may be instructed to drive to the service center location with the first autonomous vehicle.

Abstract: In particular embodiments, a computing system may generate a prediction of requests for autonomous vehicles in a fleet of collectively managed autonomous vehicles based on a current condition and a future event, the prediction including a predicted request level and a predicted duration of the request level. The system may receive status information from fleet vehicles and identify a vehicle in need of service. The system may receive status information from service centers and identify a service center to service the vehicle. The system may determine a time at which to service the vehicle at the identified service center based on the generated prediction of requests, schedule the vehicle for service at the identified service center at the determined time, and instruct the vehicle to drive to the service center to be serviced at the determined time. In particular embodiments, the prediction of requests may be generated using machine learning.