Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system (e.g., of a vehicle) can generate a first communication associated with an autonomous vehicle. The computing system can provide the first communication to an application programming interface gateway that is remote from the autonomous vehicle. Another computing system can obtain, via an application programming interface gateway, the first communication associated with the autonomous vehicle. The other computing system can determine a first frontend interface of the application programming interface gateway based at least in part on the first communication associated with the autonomous vehicle. The computing system can provide, via the first frontend interface, the first communication associated with the autonomous vehicle to a first system client associated with the first frontend interface.

Abstract: A computer system can determine historical interval data of a freight operator from completed freight service requests associated with the freight operator. Additionally, while the freight operator is fulfilling a current freight service request, the computer system can determine at least a first likely downtime interval for a non-operating activity of the freight operator prior to the freight operator arriving at a pickup location or a destination location of the current freight service request, based on the historical interval data. Also, the computer system can determine an estimated arrival time for the freight operator to arrive at the pickup location or the destination location of the current freight service request, based at least in part on the first likely down time interval. Moreover, the computer system can update a record associated with the freight operator to reflect the estimated arrival time.

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 of using satellite signal strength to determine indoor/outdoor transition points for places are disclosed herein. In some example embodiments, a computer system accesses service data and sensor data for a plurality of requests for a transportation service associated with a place, with the service data comprising pick-up data indicating a pick-up location and drop-off data indicating a drop-off location, and the sensor data comprising satellite signals indicating a pick-up path or a drop-off path, with the satellite signals each having a corresponding signal strength. The computer system determines a transition geographic location for the place based on the signal strengths of the satellite signals.

Abstract: A system can receive, over one or more networks, location data from a computing device of a requesting user, where the location data indicates a current position of the requesting user. The system can determine a rendezvous location for the requesting user prior to the requesting user transmitting a service request to the network computer system. The system may then transmit, over the one or more networks, data corresponding to the rendezvous location to the computing device of the requesting user.

Abstract: Systems and methods for autonomous vehicle state management are provided. An offboard state service can obtain a vehicle command associated with changing an onboard-defined state of an autonomous vehicle. Data indicative of the command can be provided to a computing system onboard the autonomous vehicle. The onboard computing system can initiate a vehicle action in accordance with the command and provide a command response indicative of an updated vehicle status for the onboard-defined state to the state service. In response, the state service can update a current status for the onboard-defined state as represented by a vehicle profile corresponding to the autonomous vehicle. The state service can generate an update event indicative of the vehicle state and the updated current status and publish the update event to a distributed event stream such that a number of devices subscribed to the event stream can receive data indicative of the update event.

Abstract: A computer system identifies a service provider from a plurality of service providers to fulfill a request for a transport service from a user device of a user. The service provider operates a vehicle equipped with an indicator device. The computer system obtains an output configuration associated with the user, monitors location information of a provider device of the service provider, detects a state change of the transport service based on the location information of the provider device, and, in response to detecting the state change, communicates with the provider device to cause the indicator device to display the output configuration of the user.

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: A network system determines dissimilarities between a digital map and trace data of a road network in an area as service providers and service requestors coordinate service using the road network in the area. To determine dissimilarities the network system can determine a suggested route, determine a predicted route, receive executed trace data, and compare the predicted route data to the executed trace data for the suggested route. The network system may aggregate trace data when determining a dissimilarity. The network system can quantify the differences between traces to determine dissimilarities. Quantifications can include, ratios, bounds, and scores. The network system can determine and alternate route if a dissimilarity indicates that the state of a road segment has changed (e.g., from “open” to “closed”). The network system can modify guidance instructions if a dissimilarity indicates that a guidance instruction is misleading.

Abstract: Systems and methods are provided for generating sets of candidates comprising images and places within a threshold geographic proximity based on geographic information associated with each of the plurality of images and geographic information associated with each place. For each set of candidates, the systems and methods generate a similarity score based on a similarity between text extracted from each image and a place name, and the geographic information associated with each image and each place. For each place with an associated image as a potential match, the systems and methods generate a name similarity score based on matching the extracted text of the image to the place name, and store an image as place data associated with a place based on determining that the name similarity score for the extracted text associated with the image is higher than a second predetermined threshold.

Abstract: A network computer service can receive a service request associated with a first service location. Additionally, the network computer service can detect a user action to associate the service request with a second service location. In some examples, the user input can be detected on a user device. In other examples, the second service location can be different from the first service location. Moreover, the network computer service can determine the second service location satisfies a predetermined permissibility criterion for permitting change of the first service location to the second service location. In response to determining the second service location satisfies the predetermined permissibility criterion, the network computer service can transmit an instruction to cause a device to associate the service request with the second service location in place of the first service location.

Abstract: Various examples are directed to routing autonomous vehicles. A processor unit accesses first routing graph modification data and second routing graph modification data. The first routing graph modification data based at least in part on first vehicle capability data describing a first type of autonomous vehicle and the second routing graph modification data based at least in part on second vehicle capability data describing a second type of autonomous vehicle. The processor unit accesses routing graph data describing a plurality of graph elements and generates a first route for a first autonomous vehicle of the first type based at least in part on the first routing graph modification data and the routing graph data. The processor unit also generates a second route for a second autonomous vehicle of the second type based at least in part on the second routing graph modification data and the routing graph data.

Abstract: Various embodiments provide for annotating a geographic map. Display of a geographic map on a client device can be adjusted (e.g., pan over geographic map or adjust zoom level), and a first set of map annotations for the adjusted map is determined, where the first set of map annotations comprises at least one map annotation associated with a transport service opportunity. From the first set of map annotations, a second set of map annotations can be determined based on a map annotation visual hierarchy. For instance, at least a portion of the second set of map annotations can be determined by filtering the first set of map annotations based on a type of transport service opportunity. Subsequently, the second set of map annotations can be presented on the adjusted map on the display.

Abstract: A network system uses Wi-Fi signals or other types of short-range transmissions to determine pickup locations for users receiving services provided via the network system. The network system builds a database of search records mapping pickup locations to signatures of short-range transmission detected by users' client devices when they searched for the pickup locations. By comparing a signature detected by a given user's client device to the signatures in the database, the network system can check for similarities between the short-range transmissions. Responsive to finding a match, the network system predicts that the given user is likely to select a similar pickup location as other users whose client devices detected the signatures corresponding to the match. Accordingly, by leveraging the database, the network system can predict pickup locations without requiring the given user to input a search for a pickup location.

Abstract: The present disclosure is directed to using anomaly data detected in traffic data to efficiently initiate remote assistance sessions. In particular, a computing system can receive, from a computing device associated with a human-driven vehicle, travel data for the human-driven vehicle. The computer system can identify a navigation anomaly associated with the human-driven vehicle based on the travel data. The computer system can generate, based on the identified navigation anomaly, an anomaly entry for storage in an anomaly database, the anomaly entry comprising geofence data describing a geographic area associated with the navigation anomaly. The computer system can determine, based on location data received from an autonomous vehicle and the geofence data, that the autonomous vehicle is entering the geographic area associated with the navigation anomaly. The computer system can initiate a remote assistance session with the autonomous vehicle.

Abstract: A system and method of providing information about a transport service to user devices are described. The system arranges a transport service for a first user and a second user. The system determines first data corresponding to a first route from a location of a driver device of the driver to a first pickup location of the first user and second data corresponding to a second route from the first pickup location to a second pickup location of the second user. A combined route is determined based on the first data and the second data. The system transmits data associated with the first data without transmitting the data corresponding to the combined route to a first user device of the first user, and transmits data corresponding to the combined route to a second user device of the second user.

Abstract: To more realistically represent the real-world, a street-level view depicts a route path and objects that occlude one or more segments of the route path. Such objects can include guardrails, buildings, or any of a variety of other objects as described herein. The street-level view can be implemented in advance to preview travel, during travel, or in other scenarios. The street-level view presents the route path from a viewpoint that can be a current location of a traveler or an arbitrary location.

Abstract: In one aspect, a system for automatically assigning vehicle identifiers for autonomous vehicles can include a registry server computing system configured to perform operations. The operations can include receiving, at the registry server computing system and from a vehicle computing system onboard an autonomous vehicle, data describing the autonomous vehicle and generating, at the registry server computing system, a vehicle identifier for the autonomous vehicle based on the data describing the autonomous vehicle. The vehicle identifier can be different than and distinct from the data describing the autonomous vehicle. The operations can include associating, at the registry server computing system, the data describing the autonomous vehicle with the vehicle identifier for the autonomous vehicle in a vehicle registry. The vehicle registry can include respective vehicle identifiers associated with a plurality of autonomous vehicles.

Abstract: A method of dynamically adjusting access privileges of system identities. A set of access logs associated with a system are analyzed in order to generate a restricted access policy for an over privileged system identity. An initial access policy of the system identity is replaced with the restricted access policy and a continuous monitoring and access management (CMAM) service is initiated. Access logs are collected for a monitoring time window and an access denied error can be extracted from the access logs. The access denied error can be compared to an ignore list and/or the access denied error can be added to the ignore list. Authorization checks can be performed to determine if the action associated with the access denied error is authorized. If the action is authorized, the access policy is adjusted to allow for performance of the action.

Abstract: A distributed computing system uses dynamically calculates a subset size for each of a plurality of load balancers. Each of a plurality of load balancers logs requests from client devices for connections to back-end servers and periodically sends a request report to a traffic aggregator, which aggregates the report requests from the load balancers in the corresponding zone. Each traffic aggregator sends the aggregated request data to a traffic controller, which aggregates the request data to determine a total number of requests received at the system. The total request data is transmitted through each traffic aggregator to each load balancer instance, which calculates a percentage of the total number of requests produced by the load balancer and determines a subset size based on the calculated percentage.