Abstract: Systems and methods for optimizing issue reporting in a navigation environment are provided. In example embodiments, a networked system causes presentation of a navigation user interface on a user device of a user, whereby the navigation user interface includes a route being navigated and navigation instructions. The networked system also causes presentation of one or more issue icons on the user device, whereby each issue icon represents a different type of issue to be reported. A selection of an issue icon from the one or more issue icons is received by the networked system. In response to receiving the selection of the issue icon, the networked system infers a location associated with the issue. The networked system updates a database with the issue and the inferred location. In some embodiments, the database is updated after the inferred location or the issue is verified.

Abstract: A computing device provides a task user interface that includes a first task for a driver a first location associated with the first task of a transport service. The device determines that a current location of the computing device is within a threshold distance or a threshold estimated travel time from the first location and provides a task panel including information specific to the first task, one or more selectable sub-task features, and a selectable feature that the driver selects to indicate that the first task has been completed. The device can receive a user input corresponding to a selection of the selectable feature and provide a second task of the transport service a second location associated with the second task.

Abstract: A computing system implementing an application service can determine, from a network dataset, that a network latency for a common network service provider crosses an upper latency threshold. Based on this determination, the system can determine a subset of the computing devices that utilize the common network service provider, and transmit a set of configuration signals to the subset of computing devices. The set of configuration signals can modify a set of default application configurations of a designated application to compensate for the network latency.

Abstract: A network system enables a user to record media in connection with a user operating a service application to participate in a transport service. In examples, the network system includes a user computing device on which media is recorded and stored in an unrenderable state. The user can elect to make a media recording submission for a particular service activity (e.g., trip provided or received by user). In response to the media recording submission, the user computing device identifies one or more media files that contain media data which depict the service activity. The identified media foes are transmitted to a service computing system where the media files can be rendered.

Abstract: A network computing system can coordinate on-demand transport serviced by transport providers operating throughout a transport service region. The transport providers can comprise a set of internal autonomous vehicles (AVs) and a set of third-party AVs. The system can receive a transport request from a requesting user of the transport service region, where the transport request indicates a pick-up location and a destination. The system can determine a subset of the transport providers to service the respective transport request, and executing a selection process among the subset of the transport providers to select a transport provider to service the transport request. The system may then transmit a transport assignment to the selected transport provider to cause the selected transport provider to service the transport request.

Abstract: A network system receives a service request sent from a computing device of a user. The service request identifies a service to be provided by a provider and a service request location. In response to receiving the service request, the network system identifies a plurality of candidate locations. The network system selects the location from a plurality of candidate locations according to predetermined criteria including a frequency measurement of each candidate location. The network system replaces the service request location with the selected location. The network system sends the selected location to the computing device. Responsive to receiving an acceptance of the selected location from the computing device, the network system generates navigation instructions for the provider from a current location of the provider to the selected location.

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: Systems and methods of providing a user interface in which map features associated with places are selectively highlighted are disclosed herein. In some example embodiments, a computer system receives a request for a transportation service associated with a place, retrieves an entrance geographic location for the place from a database, with the entrance geographic location being stored in association with the place in the database and representing an entrance for accessing the place, generating route information based on the retrieved entrance geographic location, with the route information indicating a route from an origin geographic location of a computing device of a user to the entrance geographic location of the place, and causing the generated route information to be displayed within a user interface on a computing device of the user.

Abstract: A system computes a timing interval between high-capacity vehicles (HCVs) for each of a plurality of HCV corridors within a geographic region, each respective HCV corridor of the plurality of HCV corridors including a start area. For each respective HCV corridor, the system transmits, via a network communication interface, (i) first data to a first computing device associated with a first HCV, the first data indicating the start area of the respective HCV corridor, and a first start time for the first HCV, and (ii) second data to a second computing device associated with a second HCV, the second data indicating the start area of the respective HCV corridor and a second start time for the second HCV, wherein the first start time for the first HCV and the second start time for the second HCV are based on the computed timing interval for the respective HCV corridor.

Abstract: An online storage system receives a plurality of documents to be stored in a directory. The storage system stores document data from each document in a document database. The storage system generates an entry for each document in an entry table and indexes the documents stored in the directory. The storage system samples a subset of the plurality of documents assigned to the directory in a directory index to determine a sampled subset of the plurality of documents. The storage system indexes the sampled subset in a directory index. The storage system can receive a request, from a client device, to view the indexed documents in the directory. Responsive to the request, the storage system presents the indexed documents in the directory retrieved from the directory index.

Abstract: A system coordinates services between users and providers. The system trains a computer model to predict a user state of a user using data about past services. The prediction is based on data associated with a request submitted by a user. Request data can include current data about the user's behavior and information about the service that is independent of the particular user behavior or characteristics. The user behavior may be compared against the user's prior behavior to determine differences in the user behavior for this request and normal behavior of prior requests. The system can alter the parameters of a service based on the prediction about the state of the user requesting the service.

Abstract: Systems and methods for determining appropriate energy replenishment and controlling autonomous vehicles are provided. An example computer-implemented method can include obtaining one or more energy parameters associated with an autonomous vehicle. The method can include determining a refueling task for the autonomous vehicle based at least in part on the energy parameters associated with the autonomous vehicle. The refueling task comprises a first refueling task that is interruptible by a vehicle service assignment or a second refueling task that is not interruptible by the vehicle service assignment. The method can include communicating data indicative of the refueling task to the autonomous vehicle or to a second computing system that manages the autonomous vehicle. The method can include determining whether the refueling task for the autonomous vehicle has been accepted or rejected.

Abstract: Techniques are provided for determining where to position vehicles for trip optimization or where to map roads for use by autonomous or semi-autonomous vehicles. The techniques include identifying, from historical trip data, common pickup and drop-off points within a geographical area where respective geohashes are used as nodes in the geographical area. A number of trips between respective nodes in the geographical area within a predetermined time frame define edges between respective nodes in the geographic area. The nodes and edges for the geographic area are processed to score each node to identify most active nodes within the geographic area as potential pickup/drop-off zones. The top k potential pickup-drop-off zones are evaluated for suitability as a pickup/drop-off zone, and lane IDs, suitable pickup/drop-off zones, and/or trip lists derived from the historical trip data are provided for use in positioning vehicles or mapping roads.

Abstract: Aspects of the present disclosure include systems, methods, and devices to auction-based on-demand transport selection. A transport request is received from a requesting user of a transport service region. A subset of transport providers to service the transport request are determined from transport providers that service the transport service region. A transport provider is selected to service the transport request based in part on a combination of a proposed cost to service the transport request and a proposed price to be paid in exchange for utilizing one or more pick-up/drop-off zones (PDZs) in servicing the request. The proposed cost to complete the transport request and the proposed price to be paid for utilizing one or more PDZs are specified by the transport provider. A transport assignment is transmitted to the selected transport provider to cause the selected transport provider to service the transport request.

Abstract: A self-driving vehicle implements a deep reinforcement learning based model. The self-driving vehicle comprise one or more sensors configured to capture sensor data of an environment of the self-driving vehicle, a control system configured to navigate the self-driving vehicle, and a controller to determine and provide instructions to the control system. The controller implements a deep reinforcement learning based model that inputs the sensor data captured by the sensors to determine actions to perform by the control system. The model includes an archive storing states reachable by an agent in a training environment, each state stored in the archive is associated with a trajectory for reaching the state. The archive is generated by visiting states stored in the archive and performing actions to explore and find new states. New states are stored in the archive with their trajectories.

Abstract: Various examples described herein are directed to systems and methods for dispatching trips to a plurality of autonomous vehicles. For example, a dispatch system may access trip result data describing a plurality of trips executed by a set of autonomous vehicles of a first vehicle type. The dispatch system may determine a first routing constraint for autonomous vehicles of the first vehicle type using the trip result data and select an autonomous vehicle to execute a first new trip using the first routing constraint. The dispatch system may send a request to execute the first new trip to the selected autonomous vehicle.

Abstract: A trained computer model includes a direct network and an indirect network. The indirect network generates expected weights or an expected weight distribution for the nodes and layers of the direct network. These expected characteristics may be used to regularize training of the direct network weights and encourage the direct network weights towards those expected, or predicted by the indirect network. Alternatively, the expected weight distribution may be used to probabilistically predict the output of the direct network according to the likelihood of different weights or weight sets provided by the expected weight distribution. The output may be generated by sampling weight sets from the distribution and evaluating the sampled weight sets.

Abstract: Systems and methods for displaying corresponding content for vehicle services using a distributed set of electronic devices are provided. For example, a computer-implemented method includes obtaining data associated with a vehicle service instance. The vehicle service instance is associated with a request for a vehicle service for a user. The method includes determining, based on the data associated with the vehicle service instance, a first advertisement content item for a display device positioned on an exterior of a vehicle assigned to the vehicle service instance and a second advertisement content item for a user device associated with the vehicle service instance. The method includes communicating data that initiates the display of the first advertisement content item for the display device positioned on the exterior of the vehicle and data that initiates the display of the second advertisement content item for the user device.

Abstract: A network system is provided that enables a user to record media in connection with a user operating a service application to participate in a transport service. In examples, the network system includes a user computing device on which media is recorded and stored in an unrenderable state. The user can elect to make a media recording submission for a particular service activity (e.g., trip provided or received by user). In response to the media recording submission, the user computing device identifies one or more media files that contain media data which depict the service activity. The identified media files are transmitted to a service computing system where the media files can be rendered.

Abstract: Various embodiments pertain to techniques for proactively delivering navigation options to a user via a mobile device. In various embodiments, one or more navigation options can be determined for the user and delivered to the user's mobile device at a relevant time. Navigation options can be selected based on the user's current location, the user's future plans, the time, and other locally relevant information, such as friends nearby or a nearby favorite location of the user. The navigation options can be delivered to the user's mobile device at a time that the navigation options are relevant.