Uber Technologies, Inc.

Dinesh Ramasamy

Upamanyu Madhow

Daniel Iland

Brent Evans Hamby

Juthika Kiran Dabholkar

Brandon Iles

William J Salisbury

Anson Chu

Andrew T Irish

Theodore Russell Sumers

Andrew Joseph Beinstein

Vivek Sankaravadivel

Hemabh Shekar

Brent Hamby

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.

Geographic positioning using short-range transmissions

A network system, such as a transport management system, infers movement and a location of a vehicle associated with a transportation service using sensor data from a provider client device and a wireless device mounted in a fixed position in the vehicle. Before or during a transportation service, the provider client device transmits sensor data to the network system for use in detecting the occurrence of one or more specified events, such as a sudden deceleration or a harsh turn. The network system fuses the received sensor data to infer the movement of the vehicle along forward, lateral, and vertical axes and implements an event detector by analyzing movement of the vehicle in the forward direction. Fused sensor data received from the wireless device is used to validate the detected movement and to determine a position of the vehicle.

Inferring vehicle location and movement using sensor data fusion

A network system, such as a transport management system, efficiently allocates resources by monitoring the geospatial and topological locations of a rider responsive to receiving a trip request. A trip management module matches a rider with an available driver based in part on an comparison of the estimated times of arrival of the rider and the driver at the pickup location. A client positioning module monitors the rider's progress through nodes and edges in a topological graph associated with the origin location based on radio signatures received at the rider client device. A client ETA module calculates a rider ETA based on the rider's rate of travel through the origin location represented by nodes in the topological graph. Responsive to determining that the rider ETA and the driver ETA vary by over a threshold amount of time, the trip management module matches the rider with a second available driver.

Determining a topological location of a client device using received radio signatures

Growing community of inventors

Mountain View, CA, United States of America

Dinesh Ramasamy