A method includes selecting a first machine learning model from a plurality of machine learning models that are trained for use in performing geolocation, wherein the first machine learning model is selected to perform geolocation within a first cell of a plurality of cells of a wireless network, acquiring event data from a plurality of wireless devices within the first cell, grouping the event data into a plurality of records, wherein each record of the plurality of records contains event data that indicates a common wireless device of the plurality of wireless devices, a common cell of the plurality of cells, and a common timestamp, and generating a predicted location of a first wireless device of the plurality of wireless devices, using the first machine learning model, wherein the first machine learning model outputs the predicted location in response to an input of a record of the plurality of records.

A host vehicle position estimation device includes an observation position estimation unit configured to estimate an observation position of the vehicle based on a result of recognition of the target object performed, a prediction position calculation unit configured to calculate a prediction position of the vehicle from a result of estimation of the host vehicle position in the past based on a result of measurement performed by an internal sensor, a host vehicle position estimation unit configured to estimate the host vehicle position based on the observation position and the prediction position. The host vehicle position estimation unit is configured to give more weighting to the prediction position in the estimation of the host vehicle position such that the host vehicle position is estimated to be close to the prediction position if it is determined that a result of estimation of the host vehicle position is unsteady.

A method for kinematic state estimation of a UE connected to a wireless communication network. The method comprises obtaining (S10) of measurement information related to a kinematic measurement concerning the UE. The kinematic measurement is achieved at a measuring time. The kinematic measurement belongs to a set of kinematic measurements. It is further determined (S20) whether the measurement information is consistent with a measurement prediction for the UE valid for the measuring time based on a kinematic state estimation of the UE. The kinematic state estimation is created using kinematic measurements of the set of kinematic measurements. If the measurement information is determined not to be consistent, the measurement information is discarded (S30). If the measurement information is determined to be consistent, the kinematic state estimation of the UE is updated (S31) with the measurement information.

Embodiments for a device locator application are described. In an embodiment, one or more inertial displacement measurement values may be received using the inertial sensor and received camera sensor data, a trajectory based on the one or more inertial displacement measurement values may be determined, a beacon signal from a target wireless device and determine at least one signal strength value from the beacon signal may be received, at least one proximity value to the target wireless device may be estimated based on the at least one signal strength value corresponding to at least one position along the trajectory, and an indicator of the at least one proximity value to the target wireless device may be presented along the trajectory in a user interface.

Systems and methods for mapping location and characteristics about wireless emitters are described. The systems and methods advantageously use correlative receivers for observing the emissions from the wireless emitters without decrypting or decoding information included in the emissions from the wireless emitters to allow for tracking location and emitter class and type in real-time. The real-time geolocation and emitter class information for many receivers in a geographic area can be determined and overlaid on a map, for example.

A tracking device (150) for tracking an asset (110) at a facility is described herein. The tracking device comprises a communication interface (120) configured to communicate with at least one beacon (101-1, 101-2, 101-n) in proximity to the tracking device and an altitude sensor (125). The tracking device is configured to receive, via the communication interface, at least one signal from the at least one beacon, receive, via the altitude sensor, altitude information. The tracking device is configured to transmit, for use in tracking the asset at the facility, information based on the at least one signal and the altitude information.

A method for vehicular self-positioning is executed by a positioning device in a vehicle. The positioning device computes a current estimated position of the vehicle as a function of local motion data obtained from a motion sensor in the vehicle, and operates an RF module in the vehicle to receive a reference signal from one or more base stations in an environment of the vehicle, the respective base station being configured for telecommunication and being part of a 3GPP infrastructure. The positioning device further processes the reference signal to determine measured values of at least one path parameter for a selected set of multipath components, and operates a positioning algorithm, e.g. SLAM, on at least the current estimated position and the measured values to calculate a current output position of the vehicle and position information for an origin of each of the multipath components.

A method, apparatus and computer readable storage medium are provided for determining absolute altitudes of individual floors represented by an indoor map. In the context of a method, location data is obtained representing at least one track of one or more users at least partially in a structure. The location data includes horizontal and vertical location information with the vertical location information representing an absolute altitude. The method also includes obtaining indoor map data representing different floors and indicating structural elements on the floors and determining track sections of the at least one track represented by the location data such that each track section can be assumed to be on a single floor. The method further includes at least partially comparing determined track sections with floors represented by the indoor map data and determining an absolute altitude of at least some of the floors represented by the indoor map data.

A computer implemented method is disclosed for estimating a position of a vehicle. The method comprises obtaining dynamic state information for the vehicle at a first time in a time sequence the dynamic state information comprising position information for the vehicle. The method further comprises receiving, from the vehicle, communication network information for the vehicle at a second time in the time sequence that is after the first time, wherein the communication network information comprises a result of a measurement carried out by the vehicle on a signal exchanged with the communication network. The method further comprises using a trained ML model to estimate a position of the vehicle at the second time in the time sequence on the basis of the obtained dynamic state information and received communication network information.

Also disclosed are a communication network node, a training agent and associated methods.

Systems and methods of collaborative localization for a vehicle are provided. In particular, one or more vehicles that are able to localize themselves with high accuracy may transmit timestamped localization information (i.e. localization packets) to a nearby vehicles which lack high-accuracy localization sensors. Each localization packet may include the location of the transmitting vehicle with respect to a global reference frame. Upon receiving the localization packets, a vehicle may use radiolocation techniques to estimate its location relative to the transmitting vehicle(s). Based on this estimation and the information in the localization packets, the vehicle may then estimate its location with respect to the global reference frame with a high degree of accuracy.