Lyft, Inc.

Maplebear Inc.

Asif Haque

Dor Levi

Jatin Chopra

Snir Kodesh

Limin Shen

Charlie Lin

Zeynep Erkin Baz

Kevin Fan

Yuanyuan Pao

David Tse-Zhou Lu

James Kevin Murphy

Yuanyuan Malek

Sameer Qureshi

Vinay Shet

Ying Liu

Gerard Joyce

Mark Douglas Huyler

Ramesh Rangarajan Sarukkai

Haixun Wang

Xinyu Li

Ze He

Allan Stewart

An online concierge system allows users to order items from a warehouse, which may have multiple warehouse locations. The online concierge system provides a user interface to users for ordering the items, with the user interface providing an indication of whether an item is predicted to be available at the warehouse at different times. To predict availability of an item model at different times, the online concierge system selects data from historical information about availability of items at one or more warehouses based on temporal, geospatial, and socioeconomic information about observations of historical availability of items at warehouses. The online concierge system accounts for distances between observations and a time and geographic location in a feature space to select observations for predicting item availability at the time and the geographic location.

Selecting a warehouse location for displaying an inventory of items to a user of an online concierge system based on predicted availabilities of items at the warehouse over time

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.

Localization based on sensor data

Systems, methods, and non-transitory computer-readable media can determine a road segment. A set of features associated with the road segment can be determined based at least in part on data captured by one or more sensors of a vehicle. A level of similarity between the road segment and each of a set of road segment types can be determined by comparing the set of features to features associated with each of the set of road segment types. The road segment can be classified as a road segment type based on the level of similarity. Scenario information associated with the road segment can be determined based on the classified road segment type.

Road segment similarity determination

Systems, methods, and non-transitory computer-readable media can determine sensor data captured by at least one sensor of a vehicle while navigating a road segment. A plurality of features describing the road segment can be extracted from the sensor data. A map representation of the road segment can be determined based at least in part on the sensor data and the plurality of features extracted from the sensor data, the map representation being determined as the vehicle navigates the road segment. While the map representation of the road segment is being determined, at least one scenario associated with the road segment can be determined based at least in part on the map representation and the plurality of features extracted from the sensor data.

Mapping and determining scenarios for geographic regions

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.

Automatic generation of human-understandable geospatial descriptors

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.

Utilizing artificial neural networks to evaluate routes based on generated route tiles

Systems, methods, and non-transitory computer-readable media can determine a set of features associated with a road segment based at least in part on data captured by one or more sensors of a vehicle. At least one scenario that is associated with the set of features can be determined. The at least one scenario can be associated with the road segment. The associated at least one scenario and the road segment can be maintained in a scenario information database.

Embodiments provide techniques, including systems and methods, for determining an estimated target pickup location for a corresponding transport request at a particular location, such as associated with a particular geohash. A requestor may send a request that is associated with a location that does not reflect the requestor's intent regarding where they would like to be met by the provider (i.e., 'picked up'). GPS inaccuracies may cause the request location to inaccurately indicate where the requestor will be; for example, the request location may be inside a building while the requestor is waiting on a curb around a far side of the building. The target pickup location allows for a requestor and a provider to meet more efficiently, reducing delay for the provider and improving the efficiency of the system by preventing provider system resources from being taken from other service areas and decreasing provider downtime upon matching.

Geohash-related location predictions

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.

Growing community of inventors

Orinda, CA, United States of America

Asif Haque