A radio system is provided which comprises a radio receiver and a processing system, wherein the radio receiver is configured to detect radio signals transmitted from a radio transmitter on a plurality of frequency channels, and to measure respective signal strengths of the radio signals for each of the plurality of frequency channels. The processing system is configured to evaluate a measure of statistical dispersion of the respective signal strengths over the plurality of frequency channels, and to use the measure of statistical dispersion to determine information relating to a proximity of the radio transmitter to the radio receiver.

A method of localizing a mobile body (MB) in a known environment, includes the following steps: a) defining an occupancy grid (G) modeling the environment; b) defining a set of position grids (Π) each position grid being associated to a heading of the mobile body; c) receiving a time series of measurements (z.sub.1, z.sub.2, . . . ) from a distance sensor carried by the mobile body; and d) upon receiving a measurement of the time series, updating the pose probabilities of the position grids as a function of present values of the occupancy probabilities and of the received measurement; wherein step d) is carried out by applying an inverse sensor model to the received measurement, while considering the distance sensor co-located with a detected obstacle and by applying Bayesian fusion to update the pose probabilities of the position grids.

A wireless receiver receives location pilots embedded in received symbols and uses the location pilots to detect the first path for every base station the network has designated for the receiver to use in time of arrival estimation. The receiver preferably applies matching pursuit strategies to offer a robust and reliable identification of a channel impulse response's first path. The receiver may also receive and use estimation pilots as a supplement to the location pilot information in determining time of arrival. The receiver can use metrics characteristic of the channel to improve the robustness and reliability of the identification of a CIR's first path. With the first path identified, the receiver measures the time of arrival for signals from that path and the receiver determines the observed time difference of arrival (OTDOA) to respond to network requests for OTDOA and position determination measurements.

A method for preprocessing data for device operations can include preprocessing measurement data using a machine learning technique, determining, by a Kalman filter and based on (1) the preprocessed measurement data or the measurement data and (2) prediction data from a prediction model predicting a measurement associated with the measurement data, corrected measurement data, and providing the corrected measurement data based on the predicted measurement and the preprocessed measurement data.

Systems, methods, computer program products, and apparatuses to determine, by a neural network based on training data related to wireless signals exchanged by a device and a plurality of wireless access points in an environment, a respective distance between the device and each wireless access point, receive location data related to a respective location of each wireless access point of the plurality of wireless access points, determine a geometric cost of the neural network based on a geometric cost function, the respective distances, and the received location data, and train a plurality of values of the neural network based on a backpropagation and the determined geometric cost.

A vehicle system may include a plurality of wireless transmitters carried by a vehicle and configured to transmit wireless signals, at least one indicator carried by the vehicle, and a portable device moveable relative to the vehicle and configured to receive the wireless signals from the plurality of wireless transmitters. The system may further include a controller carried by the vehicle and configured to wirelessly communicate with the portable device, and determine a predicted zone the portable device is located in adjacent to the vehicle based upon the received wireless signals, with the predicted zone being one of a plurality of different zones adjacent the vehicle having respective vehicle functions associated therewith. The controller may be further configured to cause the at least one indicator to provide an indication that the portable device has entered the predicted zone, and enable the respective vehicle function associated with the predicted zone.

In accordance with a first aspect of the present disclosure, a system is provided for facilitating localizing an external object, the system comprising: a plurality of ultra-wideband (UWB) communication nodes; a controller operatively coupled to said plurality of UWB communication nodes, wherein the controller is configured to: cause at least one of the UWB communication nodes to transmit one or more UWB messages to other UWB communication nodes of said plurality of UWB communication nodes; receive a channel impulse response (CIR) estimate and/or one or more parameters relating to said CIR output by the UWB communication nodes in response to receiving said UWB messages; analyze said CIR estimate and/or said parameters relating to the CIR; select a localization process in dependence on a result of analyzing said CIR estimate and/or said parameters relating to the CIR. In accordance with further aspects of the present disclosure, a corresponding method is conceived, and a computer program for carrying out said method is provided.

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 beam fingerprint-based positioning method, performed by a communication node located in a target space, may include: performing measurements on positioning signals transmitted from at least one reference node through a plurality of directional beams in a beam sweeping scheme; transmitting a result of the measurements to a central node; and receiving information on a position of the communication node from the central node.

A roadside positioning method includes: obtaining positioning information of the user terminal, the positioning information being used for indicating a geographic location of the user terminal; obtaining wireless signal information of the user terminal, the wireless signal information being used for indicating wireless signals acquired by the user terminal at the geographic location; and determining a roadside positioning result of the user terminal based on the positioning information and the wireless signal information, the roadside positioning result being used for indicating a roadside on which the user terminal is located.