Abstract: In one embodiment, a method includes receiving a sequence of location data points associated with a vehicle from a first source and a sequence of motion data points associated with the vehicle from a second source. The method includes determining a first turn angle of the vehicle based on at least one location data point in the sequence of location data points associated with the first source. The method includes determining that an additional location data point in the sequence of location data points is inaccurate. The method includes determining a second turn angle of the vehicle by using at least one motion data point in the sequence of motion data points corresponding to the additional location data point that is inaccurate. The method includes determining a turn trajectory of the vehicle by using at least the first turn angle and the second turn angle.

Abstract: A client device is configured to (i) based on initial sensor data and a road network graph maintained on the client device, determine a set of particles corresponding to the road network graph, each particle including a (a) trajectory along the road network graph, (b) position and velocity, and (c) probability, (ii) identify a particle with a highest probability, (iii) based on the identified particle, determine the location of the client device in the road network graph, (iv) after receiving new sensor data, extend the trajectory of each particle, (v) based on the new sensor data, update, for each particle (a) the position and velocity and (b) the probability, (vi) identify a particle from the second updated set of particles with a highest probability, and (vii) based on the identified particle, determine the updated location of the client device in the road network graph.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for identifying traffic control features based on telemetry patterns within digital image representations of vehicle telemetry information. The disclosed systems can generate a digital image representation based on collected telemetry information to represent the frequency of different speed-location combinations for transportation vehicles passing through a traffic area. The disclosed systems can also apply a convolutional neural network to analyze the digital image representation and generate a predicted classification of a type of traffic control feature that corresponds to the digital image representation of vehicle telemetry information. The disclosed systems further train the convolutional neural network to determine traffic control features based on training data.

Abstract: This disclosure describes a vehicle-motion-analysis system that can align axes for a provider device and a corresponding transportation vehicle based on the provider device's location and motion data as a basis for generating driving-event scores for particular driving events. In particular, the disclosed systems can generate axes-rotation parameters that align axes of a provider device with axes of a transportation vehicle. In addition, the disclosed systems can identify motion paths, motion patterns, or other driving behaviors that occur during particular driving events. Further, the disclosed systems can generate driving-event scores for such driving events and can customize a graphical user interface based on the driving-event scores to reflect a provider rating and/or a location rating.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for identifying traffic control features based on telemetry patterns within digital image representations of vehicle telemetry information. The disclosed systems can generate a digital image representation based on collected telemetry information to represent the frequency of different speed-location combinations for transportation vehicles passing through a traffic area. The disclosed systems can also apply a convolutional neural network to analyze the digital image representation and generate a predicted classification of a type of traffic control feature that corresponds to the digital image representation of vehicle telemetry information. The disclosed systems further train the convolutional neural network to determine traffic control features based on training data.

Abstract: A disclosed method may include receiving geographic coordinates of a location at which two parties are to rendezvous, generating a human-understandable geospatial descriptor for the request location, and sending the descriptor to respective devices of the two parties for presentation to the two parties. Generating the human-understandable geospatial descriptor may include identifying a human-visible feature in the vicinity of the request location that is labeled within available map data, selecting, based on a descriptor generation model, a reference expression relative to the identified feature, and applying a grammar-based constructor to the label and the selected reference expression to form the human-understandable geospatial descriptor. The model may be tuned using machine learning. The two parties may include a ride requestor and a ride provider in a ridesharing service. The identified feature may be a point of interest, landmark, street name, intersection, marker, or structure.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that generate route tiles reflecting both GPS locations and map-matched locations for regions along a route traveled by a client device associated with a transportation vehicle. For example, in some implementations, the disclosed systems use an artificial neural network to analyze the route tiles and determine route-accuracy metrics indicating GPS locations or map-matched locations for particular regions along the route. The disclosed systems can then use the route-accuracy metrics to facilitate transport of requestors by, for example, determining a distance of the route or a location of a client device associated with a transportation vehicle.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for identifying traffic control features based on telemetry patterns within digital image representations of vehicle telemetry information. The disclosed systems can generate a digital image representation based on collected telemetry information to represent the frequency of different speed-location combinations for transportation vehicles passing through a traffic area. The disclosed systems can also apply a convolutional neural network to analyze the digital image representation and generate a predicted classification of a type of traffic control feature that corresponds to the digital image representation of vehicle telemetry information. The disclosed systems further train the convolutional neural network to determine traffic control features based on training data.

Abstract: In one embodiment, a method includes receiving a sequence of location data points associated with a vehicle from a first source and a sequence of motion data points associated with the vehicle from a second source. The method includes determining a first turn angle of the vehicle based on at least one location data point in the sequence of location data points associated with the first source. The method includes determining that an additional location data point in the sequence of location data points is inaccurate. The method includes determining a second turn angle of the vehicle by using at least one motion data point in the sequence of motion data points corresponding to the additional location data point that is inaccurate. The method includes determining a turn trajectory of the vehicle by using at least the first turn angle and the second turn angle.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for identifying traffic control features based on telemetry patterns within digital image representations of vehicle telemetry information. The disclosed systems can generate a digital image representation based on collected telemetry information to represent the frequency of different speed-location combinations for transportation vehicles passing through a traffic area. The disclosed systems can also apply a convolutional neural network to analyze the digital image representation and generate a predicted classification of a type of traffic control feature that corresponds to the digital image representation of vehicle telemetry information. The disclosed systems further train the convolutional neural network to determine traffic control features based on training data.

Abstract: The disclosed computer-implemented method may include providing and making use of uncertain ETA information. Inaccurate ETA information may result in ride cancellations, poor experience on the part of transportation requestors and providers, and reduced transportation network efficiency. Errors in ETA estimates may be introduced in various ways, including inaccurate starting location data for providers, variable delays in provider navigation readiness, providers failing to react in time to take expected routes to newly assigned destinations, and driving conditions en route. By estimating both the likelihood various scenarios that impact ETA and the impact of these scenarios on arrival time, the method may provide information about the uncertainty of ETA information. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a method includes receiving a sequence of location points and motion data associated with a mobile computing device. The method further includes generating, based on the motion data, a motion-data trace of a path and calculating, for each location point, a distance between the location point and a point on the motion-data trace of the path. The method further includes determining that the distance associated with at least one location point exceeds a threshold distance. The method further includes generating an estimated path traveled by the mobile computing device using (1) the point on the motion-data trace of the path used for calculating the distance associated with each of the at least one location point and (2) the received location point for each of the sequence of location points whose associated distance is at or within the threshold distance.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that generate route tiles reflecting both GPS locations and map-matched locations for regions along a route traveled by a client device associated with a transportation vehicle. For example, in some implementations, the disclosed systems use an artificial neural network to analyze the route tiles and determine route-accuracy metrics indicating GPS locations or map-matched locations for particular regions along the route. The disclosed systems can then use the route-accuracy metrics to facilitate transport of requestors by, for example, determining a distance of the route or a location of a client device associated with a transportation vehicle.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that generate route tiles reflecting both GPS locations and map-matched locations for regions along a route traveled by a client device associated with a transportation vehicle. For example, in some implementations, the disclosed systems use an artificial neural network to analyze the route tiles and determine route-accuracy metrics indicating GPS locations or map-matched locations for particular regions along the route. The disclosed systems can then use the route-accuracy metrics to facilitate transport of requestors by, for example, determining a distance of the route or a location of a client device associated with a transportation vehicle.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that generate route tiles reflecting both GPS locations and map-matched locations for regions along a route traveled by a client device associated with a transportation vehicle. For example, in some implementations, the disclosed systems use an artificial neural network to analyze the route tiles and determine route-accuracy metrics indicating GPS locations or map-matched locations for particular regions along the route. The disclosed systems can then use the route-accuracy metrics to facilitate transport of requestors by, for example, determining a distance of the route or a location of a client device associated with a transportation vehicle.

Abstract: Embodiments provide techniques, including systems and methods, for determining projected locations for providers to better match providers in response to a transport request. Providers may be matched to a requestor based not only on a current location of the provider with respect to a request location, with a projected location of the provider that accounts for timing delays in processing transport requests, communication networks, etc. As such, projecting the projected location of the provider allows the dynamic transportation matching system to be matched more efficiently, reducing delay for the provider and requestor, and improving the efficiency of the system by preventing provider system resources from being taken from other service areas and decreasing provider inefficient rerouting upon matching.