Abstract: Systems and methods for detecting and verifying closed places (e.g., claims no longer in business) from trip data are provided. A networked system accesses trip data associated with the POI. The networked system processes the trip data to generate at least two time buckets based on timestamps from the trip data associated with the POI, and calculates trip counts associated with the POI for each of the time buckets. Using a machine learning algorithm and based on the at least two time buckets, the networked system determines that the trip counts show a decline over time that indicates that the POI is likely closed. In response to the determining, the networked system updates a database to indicate the POI is closed.

Abstract: A network computer system receives request data from computing devices of requesting users in a sub-region of a service area. The system further receives location data from computing devices of drivers operating in the sub-region. Based on the request data and the location data, the system determines a service condition for the sub-region. Based on the service condition indicating that the sub-region is in a driver oversupply state, the system transmits a service instruction to computing devices of a plurality of drivers within the sub-region, the service instruction being associated with a target outside the sub-region and a set of progress conditions. The system then periodically determines, for each driver of the plurality of drivers, an estimated time of arrival (ETA) to the target from a current position of the driver to determine whether the driver is satisfying the set of progress conditions of the service instruction.

Abstract: A computer system operates to receive transport service requests from computing devices of requesters within a geographic region. The system matches each transport service request with an available transport provider operating a service vehicle within the geographic region, and determines a location bias for a first transport provider that operates a corresponding vehicle within the geographic region, the location bias being associated with a preferred location of the first transport provider. The system may then match the first transport provider to a transport service request based on (i) the location bias of the first transport provider, and (ii) a destination of the transport service request which, upon fulfilling the transport service request, results in the first transport provider being positioned to arrive at the preferred location within a future time interval.

Abstract: A transport facilitation system can receive a pick-up request from a computing device of a user of a transportation arrangement service, the pick-up request comprising a unique identifier and a pick-up location. Using the unique identifier, the system can perform a lookup in a database for a profile indicating vehicle setup preferences for the user, and select a service vehicle to service the pick-up request. The system can further determine a seat assignment within the service vehicle for the user, and based on the vehicle setup preferences indicated in the profile, the system transmit a set of configuration instructions to the service vehicle, the set of configuration instructions to configure one or more adjustable components of the service vehicle for the user.

Abstract: A computing system can implement pick-up location optimization by receiving trip requests and location data from computing devices of users and determining a specified region in which each requesting user is located. Each region can be associated with a plurality of eligible pickup locations. The computing system can score each of a plurality of eligible pickup locations based, at least in part, on (i) ETAs of vehicles to the pickup locations, and (ii) an amount of reduced time for utilizing each pickup location as opposed to the current location of the requesting user or a pick-up location specified by the requesting user. Based on the scoring, the computing system may then select (i) a trip pickup location to initiate the trip request, and (ii) a selected vehicle from the set of candidate vehicles to service the trip request.

Abstract: A network system receives, from each of a plurality of client devices, a transmission of a scan of signals from signal broadcasting devices. A vector is created from each scan, whereby the vector comprises a received signal strength indicator (RSSI) to each unique signal broadcasting device. Based on the vector created from each scan, the network system determines a probability that the client devices are co-present. The probability is determined based on applying the vectors to a copresence estimation function that uses an angular similarity, a magnitude similarity, and a number of signal broadcasting devices. Based on the probability, the network system triggers a component to perform a corresponding operation.

Abstract: Systems and methods for autonomous vehicle operations are provided. An example computer-implemented method includes obtaining data indicative of vehicle fleet feature(s) associated with an autonomous vehicle fleet. The method includes obtaining data indicative of a vehicle service request associated with a user, the vehicle service request indicating a request for a vehicle service. The method includes determining user feature(s) associated with the user. The method includes determining a compatibility of the user and the autonomous vehicle fleet for the vehicle service based at least in part on the fleet feature(s) and the user feature(s). Determining the compatibility can include predicting how the autonomous vehicle fleet will perform the vehicle service associated with the vehicle service request based at least in part on the fleet's autonomy capabilities. The method includes communicating data associated with the vehicle service request to a computing system associated with the autonomous vehicle fleet.

Abstract: A computing system implementing an application service can receive network data from computing devices of clients of the application service. The system can determine, from the network data, that a network latency for a subset of the computing devices crosses above a latency threshold. Based on determining that the subset of computing devices utilize a common network service provider, the system can transmit a set of configuration signals to the subset of computing devices, which modify a set of default application configurations of the designated application to compensate for the network latency.

Abstract: Examples of the present disclosure describe systems and methods for automated user authentication via phone call. In aspects, user interaction with an application/service may be detected at a user device. Device information for the user device may be provided to a login management service, which may provide access information and a security object for accessing the application/service to the user device. The user device may use the access information to place a call to a service provider. A call detection service may detect the call and collect contact information for the user device and the security object. The contact information and the security object may be provided to the login management service. The login management service may validate the security object and use the contact information to authenticate a user to access the application/service.

Abstract: Systems and methods are disclosed herein for recovering inaccurate or missing base map data for an area while providing riders with incentive to refrain from selecting an alternate transportation service while experiencing increased wait times. A service receives a request for a driver and locates a driver to provide the service. The service determines whether the wait time for the rider exceeds a threshold wait time established by the service. If the service determines that the wait time exceeds the threshold wait time, the service identifies an object within a threshold vicinity of the rider known to have inaccurate or missing base map data. The service transmits a prompt for the rider to capture an image of the object. The service receives a rendering of the captured images from the client device, and activates a function via the client device if the images accurately capture the identified objects included in the prompt.

Abstract: Systems and methods for controlling autonomous vehicles are provided. Assisted autonomy tasks facilitated by operators for a plurality of autonomous vehicles can be tracked in order to generate operator attributes for each of a plurality of operators. The attributes for an operator can be based on tracking one or more respective assisted autonomy tasks facilitated by the operator. The operator attributes can be used to facilitate enhanced remote operations for autonomous vehicles. For example, request parameters can be obtained in response to a request for remote assistance associated with an autonomous vehicle. An operator can be selected to assist with autonomy tasks for the autonomous vehicle based at least in part on the operator attributes for the operator and the request parameters associated with the request. Remote assistance for the first autonomous vehicle can be initiated, facilitated by the first operator in response to the request for remote assistance.

Abstract: Various examples are directed to systems and methods for routing an autonomous vehicle. For example, a system may access temporal data comprising a first temporal data item. The first temporal data item may describe a first roadway condition, a first time, and a first location. The system may also access a routing graph that comprises a plurality of route components and determine that a first route component of the routing graph corresponds to the first location. The system may generate a constrained routing graph at least in part by modifying the first route component based at least in part on the first roadway condition. The system may additionally generate a route for an autonomous vehicle using the constrained routing graph; and cause the autonomous vehicle to begin traversing the route.

Abstract: A network system provides interventions to providers to reduce the likelihood that its users will experience safety incidents. The providers provide service to the users such as transportation. Providers who are safe and have positive interpersonal behavior may be perceived by users as high quality providers. However, other providers may be more prone to cause safety incidents. A machine learning model is trained using features derived from service received by users of the network system. Randomized experiments and trained models predict the effectiveness of various interventions on a provider based on characteristics of the provider and the feedback received for the provider. As interventions are sent to providers, the change in feedback can indicate whether the intervention was effective. By providing messages proactively, the network system may prevent future safety incidents from occurring.

Abstract: Systems and methods are provided for determining a street and segment corresponding to the geographic coordinates for a location and determining a heading and a side of the street for the location. The system and methods further provide for generating a list of places within a predetermined distance from the location, determining a first subset of places of the list of places that are located on the same street as the street corresponding to the geographic coordinates for the location, and generating a second subset of places from the first subset of places, each place of the second subset of places having a same heading and side of the street as the heading and side of the street for the location. The systems and methods further provide for selecting a place of the second subset of places and generating a semantic label for the selected place.

Abstract: Systems and methods for dynamically maintaining and utilizing walking profiles for time estimations in service scheduling are provided. A networked system detects usage of an application on a user device. In response to the detecting, the networked system accesses environmental condition data at a location associated with a user of the user device, whereby the environmental condition data comprises one or more environmental condition affecting the location. The networked system accesses walking pace data from the user device, whereby the walking pace data represents a current walking pace of the user and correlates the walking pace data with the environmental condition data. Using the correlated data, the networked system adjusts a parameter in a walking profile of the user. The walking profile is then used to determine time estimates that are used to schedule services that require walking by a user.

Abstract: Systems and methods for vehicle motion control with interactive object annotation are provided. A method can include obtaining data indicative of a plurality of objects within a surrounding environment of the autonomous vehicle. For example, the plurality of objects can include at least at one problem object encountered by the autonomous vehicle while navigating a planned route. The method can include determining a group of objects of the plurality of objects. For example, the group of objects can include the problem object and one or more other objects in proximity to the problem object. The method can include determining a classification update to be applied to the group of objects. The method can include applying the classification update to the group of objects. The method can include providing data indicative of the classification update for the group of objects to the autonomous vehicle for use in motion planning.

Abstract: Systems and methods for evaluating and deploying fleets of autonomous in operational domains are described. A computing system may obtain data indicative of one or more capabilities of at least one autonomous vehicle, data indicative of vehicle service dynamics in an operational domain over a period of time, and determining a plurality of resource performance parameters respectively for a plurality of autonomous vehicle fleets associated with potential deployment in the operational domain. Each autonomous vehicle fleet can be associated with a different number of autonomous vehicles The resource performance parameter for each autonomous vehicle fleet can be based at least in part on the one or more capabilities of the at least one autonomous vehicle and the vehicle service dynamics in the operational domain. The computing system can initiate an action associated with the operational domain based at least in part on the plurality of resource performance parameters.

Abstract: Systems and methods for improving a search process by providing a visual guided search experience is provided. A networked system determines a location of a user device. A user interface (UI) is presented illustrating a map at a first level view of an area based on the location. The networked system receives, via the UI, a first touch input indicating a zoom selection. In response, the UI shows a second level view of the area that includes a plurality of nodes each representing a point of interest in the area. The second level view is a lower level view than the first level view. The networked system then receives, via the UI, a second touch input selecting a node of the plurality of node. In response to the selecting of the node, navigation information for a selected point of interest corresponding to the selected node is presented.

Abstract: A mechanism is described herein for automatically detecting vulnerability remediations and regressions. A system may receive data indicating that a security alert exists for a specific vulnerability. The system retrieves parameters from the alert and generates (or retrieves) a script or a set of scripts for detecting the vulnerability based on those parameters. The script is executed to determine whether the vulnerability has been remediated or has regressed post remediation. If the system determined that the vulnerability has been remediated, it transmits a request to resolve the security alert. The script is then continually or periodically executed. If the system, through executing the script, determines that the vulnerability has been reintroduced into the environment (e.g., via a code upgrade or a parameter update), it reopens the existing alert indicating that the vulnerability has been reintroduced into the environment.

Abstract: A system for monitoring a vehicle used in providing a service is disclosed. The system detects when the service is complete, and upon detecting that the service is complete, the system determines, from one or more sensors of the vehicle, that an object which should have been removed from the vehicle after completion of the transport service, remains in the vehicle. The system then automatically initiates performance of a remedial action.