A device implementing a system for estimating device location includes at least one processor configured to receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite, and receive a set of parameters associated with the estimated position. The processor is further configured to apply the set of parameters and the estimated position to a machine learning model, the machine learning model having been trained based at least on a position of a receiving device relative to the GNSS satellite. The processor is further configured to provide the estimated position and an output of the machine learning model to a Kalman filter, and provide an estimated device location based on an output of the Kalman filter.

A method of localization using bearing from environmental features includes receiving an estimated location of a global navigation satellite system (GNSS) receiver associated with a user and a corresponding bearing for the GNSS receiver. The method also includes identifying one or more environmental features about the estimated location of the GNSS receiver. The method further includes determining whether an orientation of a respective environmental feature of the one or more environmental features correlates to the corresponding bearing for the GNSS receiver. When the orientation of the respective environmental feature correlates to the corresponding bearing for the GNSS receiver, the method includes generating an updated bearing for the GNSS receiver or locational system that matches the orientation of the respective environmental feature.

A position estimation unit (2) comprising a first transceiver device (3) and a processing unit (10) that is arranged to repeatedly calculate time-of-flight (TOF) for radio signals (x.sub.1, x.sub.2, x.sub.3, x.sub.4, x.sub.5, x.sub.6) sent pair-wise between two transceivers among the first transceiver device (3) and at least two other transceiver devices (7, 8, 9); calculate possible positions for the transceiver devices (3, 7, 8, 9), which results in possible positions for each transceiver device (3, 7, 8, 9); and perform Multidimensional scaling (MDS) calculation in order to obtain relative positions of the transceiver devices (3, 7, 8, 9) in a present coordinate system. After two initial MDS calculations, between every two consecutive MDS calculations, the processing unit (10) is arranged to repeatedly perform a processing procedure comprising translation, scaling and rotation of present coordinate system such that a corrected present coordinate system is acquired. The processing procedure is arranged to determine the corrected present coordinate system such that a smallest change for the relative positions of the transceiver devices (3, 7, 8, 9) between the consecutive MDS calculations is obtained.

A method for controlling an aerial vehicle includes determining a direction in which the aerial vehicle is traveling; determining, with reference to a table, an altitude range which corresponds to the determined direction and within which the aerial vehicle is caused to fly, the table indicating correspondences between directions in which the aerial vehicle is traveling and altitude ranges within which the aerial vehicle is to fly; obtaining, from an altimeter, a first altitude, which is a current altitude, at which the aerial vehicle is flying; determining whether the first altitude is included in the determined altitude range; and if it is determined that the first altitude is not included in the determined altitude range, changing an altitude at which the aerial vehicle is caused to fly from the first altitude to a second altitude included in the determined altitude range.

Some embodiments of the invention relate to methods carried out by an NSS receiver and/or a processing entity capable of receiving data therefrom, for estimating parameters derived from NSS signals. An estimator is operated, which uses state variables and computes the values thereof based on delta observables computed for a previous epoch. Previous residuals are obtained from the estimator, each previous residual being associated with a delta observable computed for the previous epoch. The previous residuals are then adjusted using a back-residual coefficient. Delta observables for a current epoch are computed. For each of at least some of the delta observables, the delta observable computed for the current epoch is corrected using the adjusted previous residual associated with the delta observable. The estimator is then operated for the current epoch at least based on the corrected delta observables.

A method for estimating the pressure measurement bias of a barometric sensor in a wireless terminal. A location engine using the method generates an enhanced estimate of the measurement bias. The location engine generates the enhanced estimate based in part on relatively coarse estimates of the elevation of the wireless terminal. Each coarse estimate of elevation is often generated from noisy measurements, such as measurements of signals transmitted by Global Positioning System (GPS) satellites, and has an associated uncertainty. The location engine accounts for the uncertainty in these estimates of elevation by applying an optimal estimation technique, such as Kalman filtering, and by compensating for environment-related effects. Compensating Includes filtering across a plurality of lateral locations and imposing a lower bound of bias uncertainty at the lateral locations. Once the location engine generates the enhanced estimate of measurement bias, it can generate improved estimates of elevation of the wireless terminal.

An apparatus and method for providing an improved heading estimate of a mobile device in a vehicle is presented. First, the mobile device determines if it is mounted in a cradle attached to the vehicle; if so, inertia sensor data may be valid. While in a mounted stated, the mobile device determines whether it has been rotated in the cradle; if so, inertia sensor data may no longer be reliable and a recalibration to determine a new relative orientation between the vehicle and the mobile device is needed. If the mobile device is mounted and not recently rotated, heading data from multiple sensors (e.g., GPS, gyroscope, accelerometer) may be computed and combined to form the improved heading estimate. This improved heading estimate may be used to form an improved velocity estimate. The improved heading estimate may also be used to compute a bias to correct a gyroscope.

A navigation system includes a GPS reception unit receiving a GPS signal, an observation unit observing observables including a GPS vehicle position based on the received GPS signal, and an estimation unit estimating state quantities concerning the present location based on the observables and on the Kalman filter, the estimation unit calculates prediction values of the state quantities and errors of the prediction values, calculates estimation values of the state quantities and errors of the estimation values, based on the prediction values, the errors of the prediction values and errors of the observables observed, and, when calculating the estimation values and the errors of the estimation values, assigns a weight based on a period from a first timing to a second timing in which the GPS signal received in the first timing is not reflected in observation of the GPS vehicle position, to an error of the GPS vehicle position.

Systems and methods of using sensor data for coordinate prediction are disclosed herein. In some example embodiments, for a place, a computer system accesses corresponding service data comprising pick-up data and drop-off data for requests, and accesses corresponding sensor data indicating at least one path of mobile devices of the requesters of the requests, with the at least one path comprising at least one of a pick-up path ending at the pick-up location indicated by the pick-up data and a drop-off path beginning at the drop-off location indicated by the drop-off data. In some example embodiments, the computer system generates at least one predicted geographic location using the paths indicated by the sensor data, and stores the at least one predicted geographic location in a database in association with an identification of the place.

A method of compensating a position of an object by using a Global Navigation Satellite System (GNSS) processor is provided. The method includes generating a compensated position associated with a target satellite at a compensation target time based on a pseudo range between the object and the target satellite at the compensation target time, generating a displacement vector of the object based on the compensated position at the compensation target time and a previous position of the object at a previous time that is prior to the compensation target time, determining a weight for the compensated position associated with the target satellite based on a velocity vector at the compensation target time and the displacement vector, and compensating a predicted position of the object according to the weight and the compensated position.