Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for positioning a radio signal receiver at a first location within a three dimensional space; positioning a transmitter at a second location within the three dimensional space; transmitting a transmission signal from the transmitter to the radio signal receiver; processing, using a machine-learning network, one or more parameters of the transmission signal received at the radio signal receiver; in response to the processing, obtaining, from the machine-learning network, a prediction corresponding to a direction of arrival of the transmission signal transmitted by the transmitter; computing an error term by comparing the prediction to a set of ground truths; and updating the machine-learning network based on the error term.

The present invention relates to systems and methods for measuring signal strength emitted by a wireless portable device to determine the location of the wireless portable device. The wireless portable device may be located within a designated geographical location, premise or facility. The measurement involves two levels of transmissions. A first level involves a user's wireless portable device receiving signals from a plurality of beacons in the vicinity. The second level involves transmission of repeater signals from a mesh network. The payload of these signals, which may include a duress signal, includes the strength of the received beacon signals, so that when the duress signal is received by a controller, the signal strengths of both levels/types of transmissions can be determined. This two-level collection of signals is then processed by a neural network which have been previously trained to classify the signal collections into precise locations.

Certain aspects of the present disclosure provide methods, apparatus, and systems for predicting a location of a device in a spatial environment using a machine learning model. An example method generally includes measuring a plurality of signals received from a network entity at a device. A channel state information (CSI) measurement is generated from the measured plurality of signals. Generally, the CSI measurement includes a multipath component. Positions of one or more anchors in a spatial environment are identified based on a machine learning model trained to identify the positions of the one or more anchors based on the CSI measurement. A location of the device is estimated based on the identified positions of the one or more anchors.

Disclosed herein are an apparatus and method for precise positioning based on deep learning. The method performed by the apparatus includes setting a collection location and a collection environment, collecting wireless signal data based on the collection location and the collection environment, generating a magnitude map image for training from the wireless signal data, and generating a positioning DB model by learning the image characteristics of the magnitude map image for training through deep-learning-based training.

In one embodiment, a method includes accessing a place-entities graph comprising a plurality of place-entity nodes, in which each place-entity node representing a place-entity corresponding to a particular geographic location, and identifying a place-entity cluster within the place-entities graph. The place-entity cluster comprises a plurality of place-entity nodes corresponding to a plurality of place-entities corresponding to the same geographic location. The method includes accessing embeddings representing the plurality of place-entities corresponding to the place-entity cluster. Each embedding is a point in a d-dimensional embedding space. The method includes calculating, using a machine-learning model, a cluster-quality score of the place-entity cluster based on the embeddings. The cluster-quality score represents a probability that the place-entities correspond to a valid geographic location. The method further includes identifying the place-entities as corresponding to an invalid geographic location based on a determining that the cluster-quality score is less than a threshold cluster-quality score.

Provided are a system and method of an advanced dynamic multi lead technology utilizing Ultra Wideband and other sensors to improve position accuracy and data sharing among devices. The system and method use a high calculation process to enhance the position and sharing technology, focusing on representative devices as lead devices. The remaining devices act passively to locate their coordinate positions using the lead devices as a reference and as a medium to share resources.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first wireless communication device may determine, based at least in part on a first model, an estimated position of the first wireless communication device. The first wireless communication device may determine, based at least in part on a second model, an estimated direction for transmission of a packet to a second wireless communication device. The first wireless communication device may determine, based at least in part on a third model, an estimated transmit power for transmission of the packet. The first wireless communication device may determine, using a neural network, a narrow beam based at least in part on the estimated position, the estimated direction, and the estimated transmit power. The first wireless communication device may transmit the packet on the narrow beam to the second wireless communication device. Numerous other aspects are provided.

A geolocationing system and method for providing awareness in a multi-space environment, such as a hospitality environment or educational environment, are presented. In one embodiment of the geolocationing system, a vertical and horizontal array of gateway devices is provided. Each gateway device includes a gateway device identification providing an accurately-known fixed location within the multi-space environment. Each gateway device includes a wireless transceiver that receives a beacon signal from a proximate wireless-enabled personal locator device. The gateway devices, in turn, send gateway signals to a server, which determines estimated location of the wireless-enabled personal location device with angle of arrival modeling.

A method of passive location of radar transmitters implemented by at least two ESM stations, the radars having a quasi-constant scanning speed in the course of the transit over the set comprising at least two ESM stations, each of the ESM stations being able to intercept the transmission lobes of radar transmitters and to estimate their lobe transit times (LTT) and at least one station being able to estimate the angle of arrival α of the transmission lobes, the location of the radar transmitters being performed by testing the intersection between an iso-LTTD curve passing through at least the two ESM stations and a sighting straight line passing through the ESM station having measured the angle of arrival and of azimuth equal to the measured angle of arrival α.

A mobile device can identify its physical location without explicit knowledge of physical coordinates, but instead using sensor measurements dependence on distance, e.g., signal strength from a Wi-Fi router. Sensor measurements can be used to determine the mobile device is at a same physical location as a previous measurement. For example, numerous measurements of sensor values can form data points that are clustered in sensor space, where a cluster of data points in sensor space corresponds to a physical cluster of physical positions in physical space. A current physical location of the mobile device can be determined by identifying which cluster of sensor positions the current measurements correspond. To identify the cluster of sensor positions, a probability can be determined for each cluster based on a sensor distance between the current measurement and a representative data point of the cluster and a kernel function.