Apple Inc.

Brian Stephen Smith

David Benjamin Millman

Robert William Mayor

Johan Olav Bergerengen

Wei Kong

Jahshan A Bhatti

Vitali Lovich

Benjamin A Detwiler

Margaret H Tam

Ronald Keryuan Huang

Lukas Michael Marti

Lei Wang

Jasvinder Singh

Joseph Ding-Jiu Huang

Ilya K Veygman

Abhinav R Patel

Rob Mayor

Rob Brumley

Ben Detwiler

Described herein are techniques to enable a mobile device to determine a Z-axis coordinate based on altitudes associated with Wi-Fi access points detected in a Wi-Fi scan by the mobile device. One embodiment provides for an electronic device configured to compute a weighted average of Z-axis coordinates associated with detected Wi-Fi access points and determine a Z-axis coordinate for the electronic device based on the weighted average.

Wi-Fi Z-axis positioning

Embodiments are disclosed for a feature-based simultaneous localization and mapping (SLAM) system and method that generates radio maps for environments that are not accessible for surveying. More accurate radio maps are generated for an unsurveyed environment by determining a best estimate of a mobile device state from harvested traced data that maximizes a posterior probability of the mobile device state given measurements, landmarks and loop constraints.

Feature-based slam

An example method includes obtaining a plurality of data items. Each data item includes an indication of a particular location, an indication that a wireless signal from a first access point was observed at that location, and an indication of a time at which the wireless signal from the first access point was observed at that location. The method also includes determining a locational stability of the first access point based on the data items. Determining the locational stability of the first access point includes clustering the plurality of data items into one or more clusters based on the locations indicated in the plurality of data items, determining whether the N most recent data items are associated with a common cluster, and determining whether a time span between the N most recent data items exceeds a threshold period of time.

Managing moving wireless access points in wireless network positioning system

A method comprising: receiving a radio map of an indoor venue using survey data collected by a survey device positioned throughout the venue, the radio map including a boundary; receiving harvest data from a mobile device, wherein at least some of the harvest data are obtained by the mobile device while the mobile device is positioned at locations that are outside of the boundary; determining, based on the harvest data, a trajectory of the mobile device, wherein at least some of the trajectory resides outside of the boundary; identifying one or more locations on or proximate to the trajectory; and extending the radio map using the survey data and the one or more identified locations, wherein the extended radio map is defined at least in part by an extension of the boundary to encompass the one or more identified locations.

Extending a radio map

Methods, program products, and systems for using multiple sensors to determine a location fingerprint are described. A sampling device can measure RF signals detected at a train station of a transit system or a route of the transit system. The sampling device, or a location server receiving the measurements, can filter RF signal measurements using one or more readings from sensors coupled to the sampling device and that are different from RF receivers. The readings can be taken concurrently with the RF signal measurements. These readings, designated as motion cues, can include motion sensor readings, barometer readings, or magnetometer readings. Using the motion cues, the sampling device or location server can distinguish different platforms of a station of the transit system and different levels of the station, or filter out RF signal measurements that may have been inaccurate, e.g., as caused by disturbances from a train entering or leaving a station.

Location fingerprinting for a transit system

Collocated access point (AP) harvest data is combined with accurate location-tagged harvest data to improve access point location estimates and to estimate the location of access points that could not be previously estimated.

Wireless access point location estimation using collocated harvest data

Coarse location estimation for mobile devices is disclosed for detecting mobile device presence at general locations of interest and switching operating modes and services for one or more location context aware applications. In some implementations, sensor data is received from a plurality of data sources at a location. For each data source, a first probability is estimated that the mobile device is at the location based on sensor data from the data sources. A second probability is estimated that the mobile device is not at the location based on sensor data from the data sources. The first and second estimated probabilities are statistically combined to generate a third estimated probability that the mobile device is at the location.

Coarse location estimation for mobile devices

In some implementations, a server device can improve Wi-Fi based location availability for sparse signal locations by augmenting Wi-Fi access point location data with additional Wi-Fi scan data that was collected near the sparse signal locations. The server can receive Wi-Fi access point scans from client devices, determine the locations of the Wi-Fi access points, and generate Wi-Fi access point tiles that include data describing the locations of access points in the geographic areas corresponding to the Wi-Fi access point tiles. After the tiles are generated, the server device can augment the access point tiles by inserting additional Wi-Fi access point scan information into the access point tiles near identified sparse signal locations. The server device can deliver the augmented access point tile data to a client device. The client device can determine the current location of the client device based on the augmented access point tile data.

Wi-Fi based location availability for sparse signal locations

Methods, program products, and systems for building a location fingerprint database for a transit system are described. The transit system can be a subway system including underground train stations and routes where location determination using GPS signals is difficult or impossible. A sampling device can measure signals, e.g., radio frequency (RF) signals detected at the stations or on the routes. A location server can construct a location fingerprint for each of the stations and the routes. Each location fingerprint can represent expected signal measurements by a user device if the user device is located at the respective station or route. The location server can provide the location fingerprint to a user device for the user device to determine a location of the user device within the station or on the route.

Location fingerprinting for transit systems

Methods, program products, and systems for using a location fingerprint database to determine a location of a mobile device are described. A mobile device can use location fingerprint data received from a server to determine a location of the mobile device at the venue. The mobile device can obtain, from a sensor of the mobile device, a vector of sensor readings, each sensor reading can measure an environment variable, e.g., a signal received by the sensor from a signal source. The mobile device can perform a statistical match between the vector and the location fingerprint data. The mobile device can then estimate a current location of the mobile device based on the statistical match.

Modeling connectivity of transit systems

Methods, systems, and computer program product for location transition determination are described. A mobile device can use location fingerprint data and sensor readings to determine a transition of the mobile device into or out of a portion of a venue by using particle filters. When the mobile device determines that the mobile device is located at a first portion of the venue, e.g., on a given floor, the mobile device can introduce candidate locations, or particles, on a second portion of the venue and candidate locations outside of the venue. If estimated locations at the first portion of the venue do not converge, the mobile device can increase weight of the candidate locations that are outside of the first portion of the venue to detect possible transition to the second portion of the venue or to outside of the venue.

Growing community of inventors

Campbell, CA, United States of America

Brian Stephen Smith