Method, apparatus and system for augmenting three-dimensional mapping aided (3DMA) positioning

Abstract

A method, apparatus, and system for three-dimensional mapping aided positioning of a receiver includes receiving at the receiver radio signals from a transmitters, determining, from the radio signals, an estimate of at least one of a receiver position or a time of reception of the radio signals using motion compensated correlation, evaluating the determined estimate of the at least one receiver position or the time of reception and information of the signal environment and properties of the received radio signals using a trained, augmented 3DMA neural network, and determining using the trained, augmented 3DMA neural network, a position of the receiver. The augmented 3DMA neural network is trained such that the position of the receiver can determined by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the received radio signals.

Description

METHOD, APPARATUS AND SYSTEM FOR AUGMENTING THREE- DIMENSIONAL MAPPING AIDED (3DMA) POSITIONINGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims benefit of and priority to U.S. Provisional Patent Application Serial No. 63 / 608,926 filed December 12, 2023, which is herein incorporated by reference in its entirety.BACKGROUNDField

[0002] Embodiments of the present principles generally relate to positioning devices such as global navigation satellite system (GNSS) receivers and, in particular, to a method, apparatus, and system for augmenting three-dimensional mapping aided (3DMA) positioning.Description of the Related Art

[0003] Positioning signal receivers (i.e. , positioning devices) such as receivers for global satellite navigation systems (GNSS) signals have become ubiquitous in mobile devices. A GNSS receiver (e.g., receivers for GPS, GLONASS, GALILEO, BEIDOU, etc. satellite signals or a combination thereof) receive signals from satellites, process the received signals and determine the position of the receiver from information contained in the received signals. The typical accuracy of a consumer receiver without the assistance of an inertial measurement unit (IMU) can range from 5 to 50m, with positioning outputs provided at rates of 1 to 10 Hz. To provide inertial navigation in a typical mobile device, an IMU typically comprises a magnetometer, a gyroscope and an accelerometer, i.e., traditional IMU sensors. The signals from these three sensors (typically, MEMS-based sensors) are used to augment the GNSS receiver’s positioning computation such that the receiver may output positions at a higher rate (e.g. the IMU sampling rate which is typically 100 to 1000 Hz) and maintain meterlevel accuracy during short periods where GNSS signals are unavailable or are of low quality. However, that additional accuracy comes with a substantial cost of the IMU sensors and additional computational complexity.

[0004] To complicate matters, when a GNSS receiver is used within a city (i.e., in a so-called urban canyon), signals from the satellites are attenuated and / or reflected by nearby buildings. This interference causes substantial errors in the position computation even when an IMU is used. To address such issues, some GNSS receivers utilize 3DMA positioning, where a three-dimensional map (model) of the surrounding buildings is used to predict the path length of reflected signals, compensate for the path length and use the path length compensated signals in the positioning solution. In this manner, the reflected signals can be used to generate a more accurate position. 3DMA positioning may also exploit a technique known as shadow matching, in which the three-dimensional building model is used to generate maps of signal availability and areas of shadow (i.e. areas where a signal is blocked) at different times of day as GNSS satellites rise and set with respect to the local horizon. A receiver may then estimate its live position by matching the signals it is receiving with the current signal availability map. However, both of the described implementations of 3DMA are prone to significant positioning errors, in particular due to the frequent misidentification of reflected signals and the difficulty of making accurate ranging measurements in the presence of multipath interference.

[0005] In a further enhancement, a neural network uses a 3DMA cityscape model to learn the reflected signal environment at various true positions. Thereafter, a GNSS receiver uses the neural network to predict information about the signal environment, such as, which signals are available, which signals are direct, which signals are reflected, and the path length for the reflected signals at an approximate location. The approximate location, however, can be an inaccurate GNSS receiver calculated position or a position estimated by an IMU or both.

[0006] Therefore, there is a need to address the technical problem of inaccurate GNSS receiver calculated position, and inaccurate IMU estimated position, or both by providing a technical solution including at least a method, apparatus and system for augmenting 3DMA GNSS positioning models with additional information to enhance the position computation.SUMMARY

[0007] Embodiments of the present principles generally relate to methods, apparatuses, and systems for augmenting 3DMA positioning by training and using an augmented 3DMA neural network with a radio signal receiver that uses motion compensated signal processing.

[0008] Various features and advantages of the present principles may be appreciated from a review of the following detailed description of the present disclosure, along with the accompanying figures.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] So that the manner in which the above recited features of the present principles can be understood in detail, a more particular description of the principles, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments in accordance with the present principles and are therefore not to be considered limiting of its scope, for the principles may admit to other equally effective embodiments.

[0010] FIG. 1 depicts a communication environment in which an augmented 3DMA neural network of the present principles can be implemented to determine a position of a radio signal receiver in accordance with at least one embodiment of the present principles;

[0011] FIG. 2 depicts a functional block diagram of a radio signal receiver in accordance with at least one embodiment of the present principles;

[0012] FIG. 3 depicts a high-level block diagram of a computing device that can be implemented as a 3DMA neural network module 224 of the receiver 104 of FIGs. 1 and 2 in accordance with at least one embodiment of the present principles;

[0013] FIG. 4 depicts a flow diagram of a method of training the augmented 3DMA neural network in accordance with at least one embodiment of the present principles; and

[0014] FIG. 5 depicts a flow diagram of a method of operating the receiver to use the augmented 3DMA neural network to accurately determine a position of the receiver in accordance with at least one embodiment of the present principles.

[0015] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. The figures are not drawn to scale and may be simplified for clarity. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.DETAILED DESCRIPTION

[0016] Embodiments of the present principles generally relate to methods, apparatuses and systems for augmenting 3DMA positioning by training and using an augmented 3DMA neural network with a radio signal receiver that uses motion compensated signal processing. It should be understood however, that there is no intent to limit the concepts of the present principles to the particular forms disclosed. On the contrary, the intent is to cover all modifications, equivalents, and alternatives consistent with the present principles and the appended claims. For example, although embodiments of the present principles will be described primarily with respect to 3DMA positioning and 3DMA neural networks, embodiments of the present principles can be implemented with substantially any neural networks for aiding other types of positioning.

[0017] Embodiments of the present principles include at least methods, apparatuses and systems for training and using an augmented 3DMA neural network with a radio signal receiver that uses motion compensated signal processing. Such receivers can be used within positioning devices (e.g., a GNSS receiver). In one exemplary embodiment, at a given true position and time, a 3DMA neural network (or other machine learning techniques) of the present principles can be trained with a catalog of example environments (e.g., street layouts and building models). In accordance with the present principles, a training of a 3DMA neural network of the present principles is further augmented with information determined from a receiverperforming motion compensated correlation (as generated by performing a SUPERCORRELATION technique as described in detail below). The information used to augment the 3DMA neural network training can include, but is not limited to, frequency, frequency rate, signal angle of arrival, and the like, which can be determined by using the SUPERCORRELATION technique. In some embodiments of the present principles, the neural network learns how to infer a likely position (an inference output) using only satellite visibility information (inference input, such as satellite locations in the sky and signal strength received from each satellite) plus the motion compensated correlation information (augmented input, such as frequency, frequency rate and angle of arrival).

[0018] That is, in accordance with embodiments of the present principles, applying an inference input and augmented input information to a 3DMA neural network of the present principles, enables a quick determination of the position of the receiver. The receiver only needs to know its approximate position within a few kilometers and time to within a few minutes in order to correctly place each satellite in the sky (i.e., approximate azimuth and elevation). In essence, in embodiments of the present principles a neural network is performing pattern matching between a learned signal environment and the current pattern being seen by the receiver and input to the augmented 3DMA neural network.

[0019] In positioning solutions, positioning devices utilize encoded digital signals including a deterministic digital code, such as Gold codes, to facilitate signal acquisition. Such a digital code is determined by the receiver and repeatedly broadcast by the transmitter to enable receivers to acquire and process transmitted signals. Using such deterministic codes combined with an accurate motion model of the receiver, embodiments of the present principles enable a receiver to improve its position computation accuracy and / or signal reception. In some embodiments, IMU data can be used to estimate receiver motion. In such embodiments, a technique for improving radio signal reception using receiver motion compensated signal processing is known as SUPERCORRELATION™ and is described in commonly assigned US patent 9,780,829, issued 3 October 2017; US patent 10,321 ,430, issued11 June 2019; US patent 10,816,672, issued 27 October 2020; US patent publication 2020 / 0264317, published 20 August 2020; US patent publication 2020 / 0319347, published 8 October 2020, and US patent publication 2024 / 0045077, published 8 February 2024, which are hereby incorporated herein by reference in their entireties. In such embodiments, a motion model can be derived using IMU data; however, in at least some embodiments of the present principles, the motion model can be derived using only gyroscope data, controller area network (CAN) bus data, visual odometry data, or a combination of data from any of the motion data sources. In addition, in some embodiments, motion information determined by the SUPERCORRELATION™ technique can be provided as feedback to a motion module to correct and / or update the motion model.

[0020] For example, in one embodiment, a radio receiver can be embedded in a moving platform such as, for example, but not limited to, an automobile, motorcycle, airplane, helicopter, drone, bicycle, person (e.g., a person carrying a smartphone, tablet, computer, internet of things (loT) device, etc.), and the like. In operation, at least one signal received by the radio receiver is correlated with at least one locally generated signal to produce at least one correlation result. Afterwards, an augmented neural network of the present principles can be implemented to determine receiver position as described in greater detail below.

[0021] FIG. 1 depicts a communication environment 100 in which an augmented 3DMA neural network of the present principles can be implemented to determine a position of a radio signal receiver 104 in accordance with at least one embodiment of the present principles. In the communication environment 100 of FIG. 1 , a person 102 carrying a receiver 104 is moving on a path (arrow 106) near buildings 108 (e.g., in an urban canyon). While in the urban canyon, the receiver 104 does not have a clear view of the sky and the satellite signals 110 broadcast from a plurality of satellites 112-1 , 112-2, . . . 112-N. Consequently, the receiver 104 does not have a full complement of signals that propagate directly from the satellite 112 to the receiver 104 to use to compute the receiver position. Some of the signals (e.g., reflected signal 114) are reflected from a building 108 (or other object) before the signal reaches thereceiver 104. In the embodiment of FIG. 1 , the receiver 104 uses an augmented 3DMA neural network to determine the receiver position as described in detail below.

[0022] In some embodiments, the receiver 104 of the present principles can be a component (e.g., a GNSS receiver) within user equipment such as mobile phones, tablets, laptop computers, loT devices, and the like. For simplicity of describing the present principles, the device is described herein as a receiver. Those skilled in the art will understand that the receiver can be a standalone receiver or can be a portion or component within user equipment.

[0023] FIG. 2 depicts a functional block diagram of the radio signal receiver 104 of FIG. 1 in accordance with at least one embodiment of the present principles. In the embodiment of FIG. 2, the receiver 104 comprises an antenna 210, a front end 212, a GNSS signal processor 214, motion compensation processor 216, a motion module 218, and a 3DMA neural network module 224. When carried by a person 102 (or other transport platform such as a vehicle), the receiver 104 and the antenna 210 are an indivisible unit in which the antenna 210 moves with the person 102. The SUPERCORRELATION™ technique operates based upon determining a component of motion of the signal receiving antenna that is in the direction of the source of a received signal. Any mention of motion herein refers to the motion of the antenna 210. In most scenarios, the motion of the person 102 is the same as the motion of the antenna 210 and, as such, the following description assumes the motion of the person 102 and antenna 210 are the same.

[0024] In the embodiment of the receiver 104 of FIG. 2, the receiver’s front end 212 downconverts, filters, and samples (digitizes) the received signals in a manner that is well-known to those skilled in the art. The output of the receiver front end 212 is a digital signal containing data. In the embodiment of FIG. 2, the deterministic code, e.g., Gold code, is used by the GNSS signal processor 214 to synchronize the receiver 104 to the GNSS transmission.

[0025] The GNSS signal processor 214 of the receiver 104 of FIG. 2 correlates the received code from each satellite with locally generated codes to produce correlationresults. The correlation results are used to determine pseudoranges for each satellite and the pseudoranges are processed to ultimately compute a receiver position. The motion compensation processor 216 of the receiver 104 performs the SUPERCORRELATION™ processing to provide signals (phasor sequences) to phase adjust the correlation results, such that the coherent integration period is extended, e.g., extended to one or more seconds. In the SUPERCORRELATION™ process, the phasor sequence is a time sequence of phase offsets in which each phasor in the sequence adjusts the phase of a signal sample. The adjustment can be performed by adjusting the phase of each sample of the received signals, the locally generated signals, and / or the correlation results themselves. The least computationally intensive adjustment process adjusts the phase of the correlation results.

[0026] In the embodiment of FIG. 2, the motion module 218 of the receiver 104 generates receiver motion information that is used by the motion compensation processor 216 to generate phasor sequences that are used to motion compensate the correlation results. The phasor sequences comprise a sequence of phase offsets to be made over time (e.g., across a received signal) to compensate for phase changes that occur over time due to movement of the receiver. In some embodiments, the motion module 218 uses the GNSS signal processor 214 and / or an IMU 222 to generate motion information for the motion compensation processor 216. The motion information can comprise a prediction of receiver velocity and heading. Alternatively or in addition, in some embodiments the motion module 218 can comprise an IMU 222 to provide orientation information for the motion model. The motion compensation processor 216 can provide motion estimation correction information along path 220 to the motion module 218. As such, the motion compensation processor 216 can provide corrective feedback to the motion module 218.

[0027] In the embodiment of FIG. 2, the 3DMA neural network module 224 is coupled to the GNSS processor 214 and the motion compensation processor 216. As is described in detail below, the 3DMA neural network module 224 relies upon a trained augmented 3DMA neural network 226 that has been trained with at least GNSS signal information, street maps, 3D building models (i.e., cityscapes), signalavailability maps and motion compensated correlation information (e.g., frequency, frequency rate and signal angle of arrival). The GNSS processor 214 provides information such as the general location of the receiver (e.g., within a couple of kilometers of the true position), current GNSS signal information, and the current motion compensated correlation information to the 3DMA neural network module 224. From this input, the trained, augmented 3DMA neural network 226 infers a current position of the receiver 104 in accordance with the present principles. The inferred position can be provided to the GNSS processor 214 to be used as an updated position estimate for further GNSS signal processing. In some embodiments, the described process (GNSS signal processing aided by SUPERCORRELATION) can be iterated to determine an accurate position and time.

[0028] FIG. 3 depicts a high-level block diagram of a computing device that can be implemented as a 3DMA neural network module 224 of the receiver 104 of FIGs. 1 and 2 in accordance with at least one embodiment of the present principles. In some embodiments, the functionality of a 3DMA neural network module 224 of the present principles can be performed remotely on a server. In such an embodiment, the receiver 104 communicates wirelessly with the server and position inferences are remotely computed. Alternatively or in addition, in some embodiments, the 3DMA neural network module 224 can comprise a component within the receiver 104. The 3DMA neural network module 224 of FIG. 3 comprises at least one processor 300, support circuits 302 and memory 304. The at least one processor 300 can be any form of processor or combination of processors including, but not limited to, central processing units, microprocessors, microcontrollers, field programmable gate arrays, graphics processing units, digital signal processors, and the like. The support circuits 302 can include well-known circuits and devices facilitating functionality of the processor(s). The support circuits 302 can include one or more of, or a combination of, power supplies, clock circuits, analog to digital converters, communications circuits, cache, displays, and / or the like. The support circuits 302 form an interface between the processor 300 and both the motion compensation processor 216 and GNSS signal processor 214.

[0029] In the embodiment of FIG. 3, the memory 304 comprises one or more forms of non-transitory computer readable media including one or more of, or any combination of, read-only memory or random-access memory. The memory 304 stores software and data including, for example, augmented 3DMA neural network software 306 and data 308. The data 308 comprises a receiver position estimate 310, motion hypotheses 312, time 324, SUPERCORRELATION™ (SC) related data 334 and various additional data used to perform the 3DMA neural network processing of the present principles. In some embodiments, the data 308 can include augmented 3DMA neural network training data 314, including GNSS signals 316, GNSS satellite positions 318, building maps 320, street maps 322, augmentation data 326 (e.g., frequency 328, frequency rate 330 and angle of arrival 332) and the like. The neural network software 316, when executed by the one or more processors 300, becomes a trained neural network 226 of, for example, FIG. 2 that is capable of using input data to infer a position of the receiver. In embodiments of the present principles, the operation of the neural network software 306 functions as the neural network 226 of the rapid initialization module 224 of FIG. 2. An embodiment of the training of the neural network is described with reference to at least FIG. 4 below and use of the trained neural network is described with reference to at least FIG. 5 below.

[0030] FIG. 4 depicts a flow diagram of a method 400 of training the augmented 3DMA neural network 226 in accordance with at least one embodiment of the present principles. In some embodiments, the neural network can be installed in the mobile device (receiver 104) and initially trained in the field. Alternatively or in addition, in some embodiment, the training of the neural network can be performed on a server and, afterwards, the trained neural network can be installed onto a receiver of the present principles on, for example, a mobile device. In other embodiments, the trained neural network can be located on a server and remotely accessed by a receiver of the present principles, on, for example, the mobile device via wireless communications (e.g., WIFI, cellular, etc.) when applicable and in accordance with the present principles.

[0031] In the embodiment of FIG. 4, the method 400 begins at 402 and proceeds to 404 where the neural network software is executed to form a neural network. At 406, training data is applied to the neural network. In some embodiments, the training data can include, but is not limited to, GNSS signals, GNSS satellite positions, building maps, street maps, time of day, as well as augmentation data including, but not limited to, frequency, frequency rate and signal angle of arrival. In some embodiments, the GNSS signals contain the signal strengths for satellite transmissions of GNSS satellites that are above the horizon at a particular location and time of day on Earth. The building maps of the present principles can include three-dimensional maps of the cityscape environment at a particular location and street maps can include two- dimensional maps of roadways proximate a particular location. In such embodiments, the augmented 3DMA neural network can be trained with regional data representing buildings, streets, and visible satellite signal information covering a region of Earth (e.g., a particular city). Alternatively, in some embodiments, the regional data can represent the entire world. In some embodiments, the augmentation data can be generated by a GNSS reference receiver that uses the SUPERCORRELATION™ technique. The result of training the augmented 3DMA neural network in accordance with the present principles can be a network that contains information defining a GNSS signal environment related to any location or time augmented with augmentation data from the SUPERCORRELATION™ process.

[0032] In some embodiments of the present principles, to generate the GNSS signal training data, a reference receiver can be used to log visible satellites and their transmission signal strength at various locations and times of day (e.g., every few meters and / or every few seconds). Such data forms a signal signature during training for each location and time. In such embodiments, the reference receiver can utilize the SUPERCORRELATION™ process to determine at least motion compensated correlation data as augmentation data and outputs the augmentation data to be used as part of the training data. Training the neural network with this augmented information as well as street and building map in accordance with the present principles produces an augmented 3DMA neural network with the knowledge of the signal environment at any location and time. Such knowledge enables the trainedneural network to use currently determined signal information that is generated by the receiver to rapidly infer the position of the receiver. That is, the augmented 3DMA neural network of the present principles is performing pattern matching between learned augmented signal environment patterns and a current pattern being captured by the receiver. As the receiver moves, the augmented 3DMA neural network of the present principles infers a new position of the receiver (further described below with reference to FIG. 5).

[0033] Once an initial amount of training data is applied to the neural network, the method 400 queries at 408 whether the training is to continue. If the query is affirmatively answered, the method 400 returns to 406 to continue applying additional training data. If the query is negatively answered, the method 400 proceeds to 410 and ends. The augmented 3DMA neural network is then trained and ready for use.

[0034] FIG. 5 depicts a flow diagram of a method 500 of operation of the receiver in accordance with at least one embodiment of the present principles. The method 500 can be implemented in software, hardware or a combination of both (e.g., using the GNSS processor 214, the motion compensation processor 216 and the 3DMA neural network module 224 of FIG. 2).

[0035] The method 500 begins at 502 and proceeds to 504 where signals are received at a receiver from at least one remote source (e.g., transmitters such as the GNSS satellites 112 of FIG. 1 ) in a manner as described with respect to FIG. 1 . Each received signal comprises a synchronization or acquisition code, e.g., a Gold code, extracted from the radio frequency (RF) signal received at the antenna. The RF signal is then downconverted and the digital code is sampled. The method 500 can then proceed to 506.

[0036] At 506, motion compensation correlation is performed on the received signals. For example, in some embodiments, the correlation results converge on an optimal value and the search space can be narrowed for subsequent correlation result processing. For example, the method defines a search space defining frequency and frequency rate hypotheses related to the receiver motion. Once a preferred hypothesisis determined, the next received signal is tested with hypotheses that are near to or identical to the prior preferred hypothesis.

[0037] In embodiments of the present principles, SUPERCORRELATION™ is performed using the motion hypotheses (i.e., frequency and frequency rate hypotheses) and the received signals. During this process, the SUPERCORRELATION™ procedure generates a plurality of phasor sequence hypotheses related to the motion information. These hypotheses comprise a plurality of local signals representing code phase estimates. Each phasor sequence hypothesis comprises a phase estimate that varies with motion parameters of the receiver. The signal processing correlates a local code encoded in a local signal with a code encoded in the received RF signal. The phasor sequence hypotheses are used to adjust, at a sub-wavelength accuracy, the carrier phase of the local code. Such adjustment or compensation may be performed by adjusting a local oscillator signal, the received signal(s), or the correlation result. The signals and / or correlation results comprise complex signal samples having in-phase (I) and quadrature phase (Q) components. The method applies each phase offset in the phasor sequence to a corresponding complex sample in the signals and / or correlation results. For each received signal, the process correlates the received signals with a set (plurality) of phasor sequence hypotheses containing estimates of a phase offset necessary to accurately correlate the received signals.

[0038] The motion estimates are typically hypotheses of the motion in a direction of interest such as in the direction of the satellite that transmitted the received signal, e.g., along the signal propagation path. At initialization, the direction of interest may be unknown or inaccurately estimated. Consequently, the augmented 3DMA neural network module is used to identify a position of the receiver. A comparison of correlation results over the various hypotheses enables the method 500 to narrow the search space when processing subsequently received signals. Consequently, subsequent compensation is performed over a narrow search space.

[0039] In some embodiments, if a signal from a given satellite was received previously, the set of hypotheses for the newly received signal include a group ofphasor sequence hypotheses using the expected Doppler and Doppler rate and / or last Doppler and last Doppler rate used in receiving the prior signal from that particular satellite. The hypotheses values may be centered around the last values used or the last values used additionally offset by a prediction of further offset based on the expected receiver motion. The method 500 correlates each received signal with that signal’s set of hypotheses. The hypotheses are used as parameters to form the phase-compensated phasors to phase compensate the correlation process. As such, the phase compensation can be applied to the received signals, the local frequency source (e.g., an oscillator), or the correlation result values. The result of the correlation process is a plurality of phase-compensated correlation results - one phase- compensated correlation result value for each hypothesis for each received signal.

[0040] The correlation results are processed to find the “best” or optimal result for each received signal. In one embodiment, a joint correlation output is produced as a function (e.g., summation) of the plurality of correlation results resulting from all the hypotheses and received transmitter signals. The joint correlation output can be a single value or a plurality of values that represent the parameter hypotheses (preferred hypotheses) that provide an optimal or best correlation output. In general, a cost function is applied to each set of correlation values for each received signal to find the optimal correlation output corresponding to a preferred hypothesis or hypotheses.

[0041] For example, assuming all other receiver parameters are known except receiver motion direction, hypotheses are tested with various phasor sequences that compensate for phase changes due to each direction hypothesis. The correct phasor sequence hypothesis that represents the accurate direction estimate will produce the highest correlation result magnitude for a given received signal. By processing the received signals from different satellites, the correlation results will converge upon hypotheses representing the true receiver motion / direction. The method 500 can proceed to 508.

[0042] At 508, at least one of an estimate of at least one of a receiver position or a time of reception of the received radio signals is accessed / determined using themotion compensated correlation results. For example, in some embodiments, the motion compensated correlation results can be used with a positioning solution (e.g., using range to each satellite transmitter) to generate an estimated position of the receiver and, in some embodiments, an estimated time of reception of a radio signal received by the receiver. The method 500 can proceed to 510.

[0043] At 510, information of at least one of the signal environment and properties of the received radio signals is determ ined / accessed and augmentation information is determined using the motion compensated correlation results. The method can proceed to 512.

[0044] At 512, the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information is applied to / evaluate using a trained augmented 3DMA neural network of the present principles, which in some embodiments can be trained according to the method 400 of FIG. 4 described above. The method 500 can proceed to 514.

[0045] At 514, the augmented 3DMA neural network determ ined / outputs a receiver position. The method 500 can then end at 516.

[0046] In some embodiments of the present principles, the determined receiver position can be used in additional signal processing, for example, to identify line-of- sight (LOS) and non-line-of-sight (NLOS) signals, which can be used in a navigation solution.

[0047] In some embodiments, a computer-implemented method of training a neural network for augmented, three-dimensional mapping aided (3DMA) positioning includes collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters, creating a first training set comprising the information regarding the signal environment and the respective information regarding each of the radio signals received by the receiver, training the neural network in a firststage using the first training set, collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver, creating a second training set comprising the respective augmentation information regarding the determined motion compensated correlation signals, and training the neural network in a second stage using the second training set.

[0048] In some embodiments, a computer-implemented method of training a neural network for augmented, three-dimensional mapping aided (3DMA) positioning includes collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters, collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver, creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information, and training the neural network using the training set.

[0049] In some embodiments, the information regarding the signal environment and the radio signals comprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

[0050] In some embodiments, the augmentation information regarding motion compensated correlation signals comprises at least one of an estimated position of the receiver, frequency of the received radio signals, frequency rate of the received radio signals, or angle of arrival of the received radio signals.

[0051] In some embodiments, the augmentation information regarding motion compensated correlation signals is determined using a SUPERCORRELATION technique.

[0052] In some embodiments, the method further includes after the training of the neural network, applying the trained neural network to radio signals received by the receiver to determine a position of the receiver by matching at least one of learned signal environment information or a learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver.

[0053] In some embodiments, an apparatus for training a neural network for augmented, three-dimensional mapping aided (3DMA) positioning includes at least one processor and a memory accessible to the processor, the memory having stored therein at least one of programs or instructions, that when executed by the processor configure the apparatus to collect information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters, collect respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver, create a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information, and train the neural network using the training set.

[0054] In some embodiments, the apparatus is further configured to apply the trained neural network to radio signals received by the receiver to determine a position of the receiver by matching at least one of learned signal environment information or a learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver.

[0055] In some embodiments, the apparatus comprises at least one of a server remote from the receiver or an integrated component of the receiver.

[0056] In some embodiments, a method for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver includes receiving, at the receiver in a signal environment, radio signals from a plurality of transmitters, determining, fromthe received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals using motion compensated correlation, determining information of at least one of the signal environment and properties of the received radio signals and determining augmentation information using the motion compensated correlation, evaluating the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using an augmented 3DMA neural network that is trained using a computer-implemented method including collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters, collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver, creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information, and training the neural network using the training set. The method further includes determining, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

[0057] In some embodiments, the motion compensated correlation for determining, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals is performed using a SUPERCORRELATION technique.

[0058] In some embodiments, the evaluated information of at least one of the signal environment and properties of the received radio signals comprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

[0059] In some embodiments, the position of the receiver is determined by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motioncompensation information determined from the radio signals received by the receiver from the plurality of transmitters.

[0060] In some embodiments, an apparatus for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver includes at least one processor and a memory accessible to the processor, the memory having stored therein at least one of programs or instructions that when executed by the processor configures the apparatus to receive, at the receiver in a signal environment, radio signals from a plurality of transmitters, determine, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals using motion compensated correlation, determine information of at least one of the signal environment and properties of the received radio signals and determine augmentation information using the motion compensated correlation, evaluate the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using a trained augmented 3DMA neural network that is trained as described above, and determine, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

[0061] In some embodiments, the apparatus is further configured to determine the position of the receiver by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver from the plurality of transmitters.

[0062] In some embodiments, a system for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver includes at least one transmitter, an augmented 3DMA neural network, and a receiver comprising at least one processor and a memory accessible to the processor. In some embodiments the memory has stored therein at least one of programs or instructions which when executed by the processor configures the receiver to receive, at the receiver in a signal environment, radio signals from the at least one transmitter, determine, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of thereceived radio signals using motion compensated correlation, determine information of at least one of the signal environment and properties of the received radio signals and determine augmentation information using the motion compensated correlation, evaluate the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using an augmented 3DMA neural network that is trained according to any of the methods described herein. In some embodiments, the apparatus is further configured to determine, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

[0063] Those skilled in the art will appreciate that, while various items are illustrated as being stored in memory or on storage while being used, these items or portions of them can be transferred between memory and other storage devices for purposes of memory management and data integrity. Alternatively, in other embodiments some or all of the software components can execute in memory on another device and communicate with the illustrated computer system via intercomputer communication. Some or all of the system components or data structures can also be stored (e.g., as instructions or structured data) on a computer-accessible medium or a portable article to be read by an appropriate drive, various examples of which are described above. In some embodiments, instructions stored on a computer- accessible medium separate can be transmitted to a computing device via transmission media or signals such as electrical, electromagnetic, or digital signals, conveyed via a communication medium such as a network and / or a wireless link. Various embodiments can further include receiving, sending or storing instructions and / or data implemented in accordance with the foregoing description upon a computer-accessible medium or via a communication medium. In general, a computer-accessible medium can include a storage medium or memory medium such as magnetic or optical media, e.g., disk or DVD / CD-ROM, volatile or non-volatile media such as RAM (e.g., SDRAM, DDR, RDRAM, SRAM, and the like), ROM, and the like.

[0064] The methods and processes described herein may be implemented in software, hardware, or a combination thereof, in different embodiments. In addition, the order of methods can be changed, and various elements can be added, reordered, combined, omitted or otherwise modified. All examples described herein are presented in a non-limiting manner. Various modifications and changes can be made as would be obvious to a person skilled in the art having benefit of this disclosure. Realizations in accordance with embodiments have been described in the context of particular embodiments. These embodiments are meant to be illustrative and not limiting. Many variations, modifications, additions, and improvements are possible. Accordingly, plural instances can be provided for components described herein as a single instance. Boundaries between various components, operations and data stores are somewhat arbitrary, and particular operations are illustrated in the context of specific illustrative configurations. Other allocations of functionality are envisioned and can fall within the scope of claims that follow. Structures and functionality presented as discrete components in the example configurations can be implemented as a combined structure or component. These and other variations, modifications, additions, and improvements can fall within the scope of embodiments as defined in the claims that follow.

[0065] In the foregoing description, numerous specific details, examples, and scenarios are set forth in order to provide a more thorough understanding of the present disclosure. It will be appreciated, however, that embodiments of the disclosure can be practiced without such specific details. Further, such examples and scenarios are provided for illustration, and are not intended to limit the disclosure in any way. Those of ordinary skill in the art, with the included descriptions, should be able to implement appropriate functionality without undue experimentation.

[0066] References in the specification to “an embodiment,” etc., indicate that the embodiment described can include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described inconnection with an embodiment, it is believed to be within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly indicated.

[0067] Embodiments in accordance with the disclosure can be implemented in hardware, firmware, software, or any combination thereof. Embodiments can also be implemented as instructions stored using one or more machine-readable media, which may be read and executed by one or more processors. A machine-readable medium can include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device or a “virtual machine” running on one or more computing devices). For example, a machine-readable medium can include any suitable form of volatile or non-volatile memory.

[0068] In addition, the various operations, processes, and methods disclosed herein can be embodied in a machine-readable medium and / or a machine accessible medium / storage device compatible with a data processing system (e.g., a computer system), and can be performed in any order (e.g., including using means for achieving the various operations). Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. In some embodiments, the machine-readable medium can be a non-transitory form of machine-readable medium / storage device.

[0069] Modules, data structures, and the like defined herein are defined as such for ease of discussion and are not intended to imply that any specific implementation details are required. For example, any of the described modules and / or data structures can be combined or divided into sub-modules, sub-processes or other units of computer code or data as can be required by a particular design or implementation.

[0070] In the drawings, specific arrangements or orderings of schematic elements can be shown for ease of description. However, the specific ordering or arrangement of such elements is not meant to imply that a particular order or sequence of processing, or separation of processes, is required in all embodiments. In general, schematic elements used to represent instruction blocks or modules can beimplemented using any suitable form of machine-readable instruction, and each such instruction can be implemented using any suitable programming language, library, application-programming interface (API), and / or other software development tools or frameworks. Similarly, schematic elements used to represent data or information can be implemented using any suitable electronic arrangement or data structure. Further, some connections, relationships or associations between elements can be simplified or not shown in the drawings so as not to obscure the disclosure.

[0071] While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.

Claims

Claims:1 . A computer-implemented method of training a neural network for augmented, three-dimensional mapping aided (3DMA) positioning, comprising: collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters; collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver; creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information; and training the neural network using the training set.

2. The computer-implemented method of claim 1 , wherein the information regarding the signal environment and the radio signals comprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

3. The computer-implemented method of any of claims 1 or 2, wherein the augmentation information regarding motion compensated correlation signals comprises at least one of an estimated position of the receiver, frequency of the received radio signals, frequency rate of the received radio signals, or angle of arrival of the received radio signals.

4. The computer-implemented method of claim 1 , wherein the augmentation information regarding motion compensated correlation signals is determined using a SUPERCORRELATION technique.

5. The computer-implemented method of any of claims 1 , 2 or 4, further comprising: after the training of the neural network, applying the trained neural network to radio signals received by the receiver to determine a position of the receiver by matching at least one of learned signal environment information or a learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver.

6. An apparatus for training a neural network for augmented, three-dimensional mapping aided (3DMA) positioning, comprising: at least one processor; and a memory accessible to the processor, the memory having stored therein at least one of programs or instructions executable by the processor to configure the apparatus to: collect information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters; collect respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver; create a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information; and train the neural network using the training set.

7. The apparatus of claim 6, wherein the apparatus is further configured to: apply the trained neural network to radio signals received by the receiver to determine a position of the receiver by matching at least one of learned signal environment information or a learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver.

8. The apparatus of any of claims 6 or 7, wherein the apparatus comprises at least one of a server remote from the receiver or an integrated component of the receiver.

9. A method for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver, comprising: receiving, at the receiver in a signal environment, radio signals from a plurality of transmitters; determining, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals using motion compensated correlation; determining information of at least one of the signal environment and properties of the received radio signals and determining augmentation information using the motion compensated correlation; evaluating the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using an augmented 3DMA neural network that is trained using a computer-implemented method comprising: collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters; collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver; creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information; and training the neural network using the training set; anddetermining, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

10. The method of claim 9, wherein the motion compensated correlation for determining, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals is performed using a SUPERCORRELATION technique.11 . The method of any of claims 9 or 10, wherein the evaluated information of at least one of the signal environment and properties of the received radio signals comprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

12. The method of any of claims 9 or 10, wherein the position of the receiver is determined by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver from the plurality of transmitters.

13. An apparatus for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver, comprising: at least one processor; and a memory accessible to the processor, the memory having stored therein at least one of programs or instructions executable by the processor to configure the apparatus to: receive, at the receiver in a signal environment, radio signals from a plurality of transmitters; determine, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals using motion compensated correlation;determine information of at least one of the signal environment and properties of the received radio signals and determining augmentation information using the motion compensated correlation; evaluate the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using an augmented 3DMA neural network that is trained using a computer- implemented method comprising: collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters; collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver; creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information; and training the neural network using the training set; and determine, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

14. The apparatus of claim 13, wherein the apparatus is further configured to: determine the position of the receiver by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver from the plurality of transmitters.

15. The apparatus of any of claims 13 or 14, wherein the evaluated information of at least one of the signal environment and properties of the received radio signalscomprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

16. A system for augmented, three-dimensional mapping aided (3DMA) positioning of a receiver, comprising: at least one transmitter; an augmented 3DMA neural network; and a receiver comprising at least one processor and a memory accessible to the processor, the memory having stored therein at least one of programs or instructions executable by the processor to configure the receiver to: receive, at the receiver in a signal environment, radio signals from the at least one transmitter; determine, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals using motion compensated correlation; determine information of at least one of the signal environment and properties of the received radio signals and determine augmentation information using the motion compensated correlation; evaluate the determined estimate of the at least one receiver position or the time of reception and information of at least one of the signal environment and properties of the received radio signals and the augmentation information using an augmented 3DMA neural network that is trained using a computer- implemented method comprising: collecting information regarding a signal environment and respective information regarding each radio signal received by a receiver in the signal environment from a plurality of transmitters; collecting respective augmentation information regarding motion compensated correlation signals determined for each of the received radio signals using motion information of the receiver;creating a training set comprising the information regarding the signal environment, the respective information regarding each of the radio signals received by the receiver, and the augmentation information; and training the neural network using the training set; and determine, from the evaluation by the trained, augmented 3DMA neural network, a position of the receiver.

17. The system of claim 16, wherein the receiver is further configured to: determine the position of the receiver by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver from the plurality of transmitters.

18. The system of any of claims 16 or 17, wherein the motion compensated correlation for determining, from the received radio signals, an estimate of at least one of a receiver position or a time of reception of the received radio signals is performed using a SUPERCORRELATION technique.

19. The system of any of claims 16 or 17, wherein the evaluated information of at least one of the signal environment and properties of the received radio signals comprises at least one of street layouts, building models, signal availability maps, time of day the radio signals were received, transmitter locations in the sky, or signal strength of signals received from each transmitter.

20. The system of any of claims 16 or 17, wherein the position of the receiver is determined by matching at least one of learned signal environment information or learned motion compensation information with signal environment information or motion compensation information determined from the radio signals received by the receiver from the plurality of transmitters.

Images