Systems and methods for locating and mapping buried utility objects using artificial intelligence with local or remote processing

Abstract

This disclosure relates generally to systems and methods for locating and mapping buried utility objects using Artificial Intelligence (AI). In an exemplary embodiment, electromagnetic data related to underground utilities and communication systems is collected and provided to a Deep Learning model to build a training set. New data is then collected and provided to the learning model to enable AI to make a prediction as to the type and location of any existing utilities. This predicted data may be used to create a map which may be stored and / or displayed. In some embodiments, the AI (Deep Learning model) processing may be performed locally in a Utility Locator and / or cable drum-reel, and / or remotely in a wireless device such as a mobile phone, laptop, vehicle, etc., and / or in the Cloud.

Description

SYSTEMS AND METHODS FOR LOCATING AND MAPPING BURIED UTILITY OBJECTS USING ARTIFICIAL INTELLIGENCE WITH LOCAL OR REMOTE PROCESSINGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority under 35 U.S.C. § 119(e) to United States Provisional Patent Application Serial No. 63 / 643,915 entitled SYSTEMS AND METHODS FOR LOCATING AND MAPPING BURIED UTILITY OBIECTS USING ARTIFICIAL INTELLIGENCE WITH LOCAL OR REMOTE PROCESSING, filed May 7, 2024, the content of which is incorporated by reference herein in its entirety for all purposes.FIELD

[0002] This disclosure relates generally to systems and methods for locating and mapping buried utility objects using Artificial Intelligence (Al). More specifically, but not exclusively, this disclosure relates to systems and methods for collecting electromagnetic data related to underground utilities and communication systems and classifying that data using a Deep Learning Learning model in order to locate and map any existing utilities. The Al (Deep Learning model) processing may be performed locally in a Utility Locator or camera, and / or remotely in a wireless device such as a mobile phone, laptop, vehicle, etc., and / or in the Cloud.BACKGROUND

[0003] FIG. 1 illustrates different methods for collecting multifrequency electromagnetic data from buried objects associated with utilities or communication systems, as known in the prior art. Underground objects may include power lines, electrical lines, gas lines, water lines, cableand television lines, and communication lines. Power and electrical lines may be single phase, three phase, passive, active, low or high voltage, and low or high current. Various lines may be publicly or privately owned. Data collected from various underground objects may be single frequency or multifrequency data.

[0004] Collected multifrequency data may be obtained using a Geo-Locating Receiver (GLR), often referred to as a “utility locator device” or “utility locator” or “locator,” or other devices and methods well known in the art. Collected data may form a suite of data which may include, for example, multifrequency electromagnetic data, imaging data, mapping data which may include depth and orientation data, current and voltage data, even and odd harmonics, active and passive signals, spatial relationships to other lines and objects, fiber optic data, etc. The ability to go out in the field and locate various underground objects or assets associated with utilities and communication systems, store large amounts of data, and quickly and accurately analyze the data to determine asset characteristics such as the types of underground assets, electrical characteristics, what the assets are connected to, and who owns them is currently very limited. It would also be desirable to understand how, for example, a phone system is grounded to other lines since they are all connected. If above ground data was also available, also known as “ground truth data,” this data could also be included in the data suite and be used to determine origin and ownership of assets. For instance, are the underground assets pail of the equipment owned by AT&T®, Verizon®, T-Mobile®, the local cable or utility company, etc.? Processing, understanding, and classifying this enormous amount of data requires the ability to learn and notice patterns. This task is too complex for humans to perform but perfectly suited for Artificial Intelligence (Al).

[0005] Utility locators typically have some local, i.e. on-board computing capabilities (e.g. processing and memory functionality). The amount of processing available is of course limited towhatever physical computing resources are available, and also to what the processing is being used for. Because of this limitation, high level processing as is typically needed for Al and Neural Networks applications may be severely limited.

[0006] What is needed in the art is the ability to automate the process using Deep Learning by providing training data to a Neural Network, and using Artificial Intelligence (Al) to predict, with a very high probability level, specific characteristics of underground objects or assets. Furthermore, it would be highly beneficial to be able to access additional remote processing power such as is readily available in a typical smartphone (e.g. iPhone, Android, or other type of mobile phone). In fact, smartphones are well suited for the type of processing necessary for Artificial Intelligence / Neural Network applications.

[0007] Accordingly, the present invention is directed towards addressing the abovedescribed problems and other problems associated with collecting very large sets of multifrequency electromagnetic data associated with buried objects, processing that data, and predicting with a high degree of probability the type and source of the buried object associated with the data.SUMMARY

[0008] This disclosure relates generally to systems and methods for determining and distinguishing buried objects using Artificial Intelligence (Al). More specifically, but not exclusively, this disclosure relates to systems and methods for collecting utility and communication data by using utility locating equipment, or other electromagnetic receiving equipment, to gather and measure multifrequency electromagnetic signals from passive and activelines which are buried and / or underground. Once collected, multifrequency electromagnetic data may be combined with other data, for instance user predefined classifier data, or ground truth data, etc., and provided to a processor which outputs “Training Data.” Neural Networks using Al rely on Training Data to learn and improve analysis and prediction accuracy. Ground truth data may consist of visually observable data that a user would notice about specific assets such as type of asset, location, connections, ownership, utility box or junction data, obstacle data, etc. Obstacle data may be any type of observable obstacle which may or may not make it harder to collect data at a specific location: for instance a wall, pipe, building, signage, waterway, equipment, etc. The training data is then provided to at least one neural network for processing using Artificial Intelligence (Al). By analyzing the training data, and recognizing patterns using Deep Learning, the neural network can classify the collected data based on a predicted probability. Classified data may then be displayed and presented to a user.

[0009] Neural machine translation (NMT) uses an artificially produced neural network. This Deep Learning technique, when translating text and / or language, looks at full sentences, not only individual words. Neural networks require a fraction of the memory needed by statistical methods. They also work far faster.

[0010] Deep Learning or Artificial Intelligence applications for translation appeared first in speech recognition in the 1990s. The first scientific paper on using neural networks in machine translation appeared in 2014. The article was followed rapidly by many advances in the field. In 2015 an NMT system appeared for the first time in Open MT, a machine translation competition. From then on, competitions have been filled almost exclusively with NMT tools.

[0011] The latest NMT approaches use what is called a bidirectional recurrent neural network, or RNN. These networks combine an encoder which formulates a source sentence for asecond RNN, called a decoder. A decoder predicts the words that should appear in the target language. Google uses this approach in the NMT that drives Google Translate. Microsoft uses RNN in Microsoft Translator and Skype Translator. Both aim to realize the long-held dream of simultaneous translation. Harvard’s NLP group recently released an open-source neural machine translation system, OpenNMT. Facebook is involved in extensive experiments with open source NMT, learning from the language of its users (source: http: / / sciencewise.info / media / pdf / 1507.08818vl .pdf).

[0012] In one aspect, a user may walk, ride, or drive along a road, street, highway, or various other terrain, while using a locating device with the ability to measure and collect buried or underground multifrequency electromagnetic data at a desired location. The locating device may include a locator, sonde, transmitting antenna, receiving antenna, transceiver, a satellite system, or any other measuring or locating device well known in the art. The assets may include underground lines that are passive or active.

[0013] Other forms of data may also be collected using various methods and techniques well known in the art. For instance, data may include imaging data taken from a camera, received data measured by applying a current, voltage, or similar property to an underground line and then measuring the resultant current or voltage at various points along that line or other lines, either by a hardwired connection, or wirelessly, which may also include inductive measurements.

[0014] Collected data may include, for example, multifrequency electromagnetic data, imaging data, mapping data which may include depth and orientation data, current and voltage data, even and odd harmonics, active and passive signals, spatial relationships to other lines and objects, fiber optic data, etc. Collected data may be single phase ( 1 <[)) or multiphase: for example, three phase (3c|>). Collected data could also include Phase Difference Data. As an example, in theUSA where the electrical power utility frequency is 60 Hz, the phase differences between narrow band 60 Hz harmonic signals could be extracted and used as Training Data.

[0015] In one aspect, some or all of the collected underground data may be combined with additional data from other sources to form a “Data Suite.” Types of additional data are almost limitless and are well known in the ait. For example, additional data may include data already known about underground assets such as type of equipment, orientation, connections, manufacturer, ownership, etc. Additional data may also include observational data observed below ground, for instance seen in an open pipe or trench, or above ground data, such as specific equipment, layout of equipment, manufacturer information placed on equipment, etc. Observed or measured above ground data is also almost limitless and well known in the art: for instance, utility boxes, power poles and lines, radio and cellular antennas, transformers, observable connections, line and pipe paths, conduits, etc.

[0016] Once collected, the Suite of Data by itself, or in combination with user defined underground asset classification or category data, is provided as Training Data, also known as a “Training Data Suite,” for Deep Learning to one or more neural networks. The neural networks are programmed to use Artificial Intelligence (Al) for determining with a high probability of accuracy specific information about the underground or buried assets. In one aspect, specific information or characteristics may include types of underground assets, electrical characteristics, what the assets are connected to, and who owns them. Some of this information will be geographic location specific. For instance, in the USA and Canada, household and business power is typically delivered at 110 VAC, 60 Hz; however, in Europe it is delivered at 230 VAC, 50 Hz. There are of course many other examples. Also, the types of underground assets, types of connections, andcompanies who own them may vary greatly from city to city, among states, regions, and from country to country.

[0017] In another aspect, specific information could include right of way information, location and / or direction information, and even damaged asset information. As an example, if it is known or learned that specific electrical characteristics are present at the input of an electrical line or powerline, it may be expected that specific electrical characteristics should be present at the output. However, if the output is not as expected, it could be assumed that the line itself or other related equipment is damaged or malfunctioning.

[0018] In one aspect, the training data would be dynamically updated. Updates could be incremental, for instance at specific time intervals, or continuous. Also, training data sets could be different in different geographic locations. For instance, training data sets could be updated to take into account different electrical and other characteristics due to local, regional, or country differences, etc. As an example, Al predicted results could be compared to known results in order to test result accuracy. The term “predicted results” takes into account the fact that Al is making a probability or likelihood prediction that the data it has analyzed corresponds to a certain utility system, and to specific characteristics of the system.

[0019] In another aspect, Testing Data, and / or Quality Metrics could be provided to the Neural Network to get a confidence level of the accuracy of and results determined by Al.

[0020] In this disclosure the terms “Deep Learning” and “Artificial intelligence (Al)” are used synonymously. However, there is actually a subtle difference. Deep Learning is an Al function that mimics the workings of the human brain in processing data for use in detecting objects, recognizing speech, translating languages, and making decisions. Deep Learning Al is able to learn without human supervision, drawing from data that is both unstructured and unlabeled(source: Investopedia.com). Deep Learning is a subset of machine learning where artificial neural networks, algorithms inspired by the human brain, learn from large amounts of data. Deep Learning allows machines to solve complex problems even when using a data set that is very diverse, unstructured and interconnected (source: Forbes.com). The task of analyzing and making sense of enormous amounts of collected data related to multifrequency electromagnetic data, as well as the addition of additional related data joined to form a Data Suite is too complex for humans to perform but perfectly suited for Artificial Intelligence (Al). In one aspect, Al, which is perfectly suited for pattern recognition, provides a user with classification and type probabilities for underground as well as above ground assets. Results may be provided to a user in numerous ways, including visually rendered on a display, audibly, tactilely, etc.

[0021] In another aspect, received and analyzed training data may allow Al to classify or categorize certain types of equipment. As an example, a group of underground objects may exhibit 25 different frequencies with each object having a certain amount of energy or current, each object being at a different depth and orientation from the other objects and the ground at specific locations. Al should be able to use the data to make a probability guess about what kind of utility is underground and even who the owner is if ownership classification data was pail of the Data Suite used as training data.

[0022] In another aspect, a neural network using Al may learn that in a utility system every two houses have a street crossing and always include installed electricity, cable TV, and phone lines. It may also learn that gas lines are between houses, water meters are present and have leads with certain depths, utilities have certain depths and frequencies, utilities are located with respect to specific addresses on certain positions on the street, and that utilities are miming along or across the street. Additionally it may be determined which frequency of passive energy is being measuredon a specific utility if you get AM frequencies in the utility and the ration of harmonics on the utility. These are all patterns Al can recognize and use to estimate a probability that the utility is a waterline, or a gas line, or a fiber optic cable, or more specifically for example, an AT&T® fiber optic cable. Al can make this assumption because it has learned that AT&T® uses a certain type of equipment and that the equipment has a certain type of harmonics because it is made, for instance, by Samsung®, and it has learned that other lines are made by other companies.

[0023] As another example, observed data included in a Training Data Suite may include a pipe, manhole cover, valve, or utility box that is labeled SDGE (San Diego Gas & Electric). So it can be assumed that this type of equipment has a certain type of frequency. Al can look at all the training data at once and predict with a high probability, that it is, for example, an SDGE, three phase (3([>) powerline, that feeds nearby houses with single phase (lc[>) power, or that it is a powerline going to an industrial feed because it has all of the different and correct 3(|) harmonics.

[0024] The Al could also learn and form associations with the training data. For instance, in one aspect Al could determine there is a traffic light near a specific location, and that waterlines are grounded to a powerline, and that a specific waterline is associated with a specific powerline because the bleeding off of additional harmonic energy into the waterline is different than that bleeding off of additional harmonic energy into the power line. Al might then notice that the same gas line is three blocks down because it has learned how high frequencies bleed off faster than low frequencies, and the fourth house down is starting to bleed off some additional harmonic energy into the gas line ten houses away as well, based on the frequency content of the spectral signature of a given target utility that is close in spatial distance. Al does not need to know physics or do ground modeling as a human would or a computer program would, all Al has to do is recognize patterns, make sense of the patterns, and make sense of the relationship between different patterns.

[0025] Al can use its training to output the probability of specific attributes being related to specific underground assets and the utilities the assets are related to. More specifically Al can determine the probability that certain things are related to other things, the nature between the different things, how far away the connections between the different things are, how far the connection between two things might be from where a current or previous measurement was taken based on the difference between the two things, and if some ground truth data was provided as part of the Training Data, very specific information like who owns or operates specific equipment, e.g. AT&T®, Verizon®, T-Mobile®, etc. Al can also be used to distinguish a specific communication standard used by a specific company, for instance 4G vs 5G cellular protocols, etc.

[0026] Some prior art systems exist that allow for frequency monitoring and the use of computers to calculate certain system parameters using various methods, for instance using Eigenvalues. However, these systems are very slow and do not allow the processing of large blocks of data in real or near real-time. Even if they could be programmed to accomplish such a task, systems such as these would take days, weeks, or even months to calculate any worthwhile parameters with even a reasonable accuracy. And with very large data sets, a final reliable solution may never be realized.

[0027] Current technology, for instance a cellphone, can be used while going down a street to map the position of things that can be seen. This does not really have much value because it is so limited. Deep Learning which uses Al can be used to map the relationship of things that cannot be seen, for instance underground or buried assets.

[0028] Processing or preprocessing of Training Data could be performed real-time or at a later time (post-processing). For instance, Collected Data and Other Data could be stored in local or remote memory, including the Cloud, and post-processed (as opposed to real-time processing),and then provided to a Neural Network as Training Data. Additionally, the Neural Network itself could process and analyze the Training Data in real-time, or post-process the data at a later time.

[0029] In one aspect, a utility locator gathers raw electromagnetic data (EM data) related to a buried utility line or conductor. This information is then wirelessly streamed via WiFi or any other common communication protocol (preferably with a high bandwidth) to a remote device with Al processing capabilities such as a smartphone, laptop, etc. for utility type and location prediction via a Neural Network running on the remote device.

[0030] The EM data may include estimated position and orientation, and current magnitude in the foim of a current vector placed in the ground at a position where the EM data indicates a likely position of a buried wire. Also included may be data related to measurement frequency used, frequency band, current strength, and current phase. Basically, this represents a class of raw data related to the location and orientation of the locator which is provided to the Neural Network for processing / predictions, or the raw data may be pre-processed at the locator, and vectors representing the raw data calculated in the world frame can be sent to the remote device for further processing using the Neural Network. In other words data sent to the remote device needs to have dependencies of the locator built into the data, or the data needs to stand alone so its own position and orientation in the world frame are independent of the locator.

[0031] At the remote device, a trained Al model is used to analyze locator data, and recognize patterns using the EM data to compute an estimate regarding if a utility is present, what type of utility it is, and its predicted exact location. Many other predictions related to the underground utility could be included as well. For example depth of the utility, owner of the utility, conductor or pipe size, ownership of the utility, etc. Al can also provide a confidence level of the likelihood that the presence and location of a utility is accurate, the kind of utility, e.g.powerline, gas line, big pipe, small pipe, etc. Al is well suited to make these predictions because it is good at recognizing multi-dimensional patterns, and making sense of them. With so much dimensionality, i.e. so much data, standard networks (as opposed to Al / Ncural Networks), just can not process this data in a timely and efficient manner. Al, therefore, is much better suited for such tasks.F0032] In one aspect, a high bandwidth WiFi connection is provided between a smartphone (iPhone, Android, or another type), and a utility locator. Apple and Android both have tool kits available to facilitate writing applications for this type of purpose. Raw or preprocessed data from the locator is streamed in real-time or near real-time from the utility locator to the smartphone, the phone runs Al to extract utility positions, make estimates about which utilities they are, their location, confidence level of estimates / predictions, and other utility related data predictions. The phone sends the extracted / analyzed information in real-time or near real-time back to the locator, and the locator integrates that information to a user interface (UI) also in real-time or near realtime.

[0033] In another aspect, a smartphone can be used as a relay to the Cloud. Some or all of the information from the locator can be streamed to the Cloud via the smartphone for Al processing, the processed data can then be relayed back to the locator using the smartphone. One advantage of Cloud processing is that any preexisting data, e.g. utility data from the same area, can be used in addition to the new data. As an example, similar map trends from the location of a utility survey being walked using a locator, a previous frequency sweep, etc., that provided some previous information related to a specific utility.

[0034] In another aspect, if a utility pipe inspection camera cable drum-reel includes WiFi or another wireless protocol communication module, the module can be used as a relay tocommunicate between a locator and the Cloud. If the locator itself includes a WiFi or other wireless protocol communication module with enough bandwidth, data from the locator may be transmitted directly to the Cloud for Al processing on a Neural Network to obtain a prediction result, and then the prediction data may be sent directly back to the locator for display, and / or sent to another remote device such as a smartphone, laptop, etc., for display.

[0035] In some aspects, training data may be sent from a utility locator and / or a camera cable drum-reel along with a trained model that has been created on a Neural Network located on the utility locator and / or the camera cable drum-reel itself to a remote device for Al processing. In another aspect, only the training data may be sent to a remote device, a training model is created in a Neural Network on the remote device, and then the model can be used to process prediction data to obtain a prediction result. The remote device may also relay training data to the Cloud, a prediction model can be created in the Cloud, prediction data may then be relayed from the remote device to the Cloud to be used with the prediction model to obtain a prediction result. Prediction results from the Cloud can then be relayed back to the remote device. Any data from the Cloud or from the remote device may be displayed on the remote device and / or transmitted back to the locator and / or the camera cable drum-reel for display.

[0036] In another aspect, prediction data, and / or prediction results may then be used as training data to create a new model. This feedback process may be done a single time, or may be in iterative process.

[0037] Locator information may be related to either electrical utilities as detected by EM data, or gas and pipe utilities related to detecting current induced into pipe tracer lines, or detected from pipes using cathodic protection. As an example, Al can be used to determine that there is a similar gas line similar to one previously detected, so it could be the same gas line but 100 feetdown the road. It appears to be on the right side of the road as previously determined, as well as about the right depth. All of this data, as well as stored imagery data, mapping data, raw data, and any other available data can be used as training data, and incorporated into a prediction model. The model can then use new raw EM data, new mapping data, along with existing mapping data, utility data, etc. to look for patterns.

[0038] In one aspect, Al processing via a Neural Network may be done in the utility locator itself, or in a camera used for utility locating. This processing can be done in real-time or near real-time.

[0039] In another aspect, the Al processing may be done in both locally in a utility locator or in a camera, and remotely in a smartphone or other remotely located device with Al processing capabilities. As an example, EM data and other sensor data received by the locator, or image or other sensor data received by the camera can be used as training data. The training data can be used in a neural network located in the locator or the camera to create an Al model. The training data and the model can be streamed to a remote device. New data to be predicted (prediction data) that is received by the locator or the camera can be streamed to the remote device and be input into the Al model in a Neural Network to analyze, and extract a prediction.

[0040] In another aspect, the training data can be streamed to a smartphone or other remote device to create an Al model on a Neural Network that resides on the remote device. As previously mentioned, the smartphone or other remote device can also be used as a relay to stream data from the locator or camera to the Cloud. Any Al processing on a Neural Network can then be accomplished in the Cloud. It would be obvious to one skilled in the art that Al processing could also be split up into tasks, some done locally in the locator or camera, some done on a smartphone or other smart device, and some Al processing tasks done in the Cloud. It would also be obviousto one skilled in the art that some of the tasks may be computing tasks, including processing, storing, organizing, etc., that do not require the power of Al processing or a Neural Network to be accomplished.

[0041] Different level Al models may be created for different types of processing. As an example, a base model may use EM data to extract patterns, and decide which patterns show a high likelihood of the presence of one or more utilities. In another example, a partial utility model may be used when there is a lower probability that a utility has been located. Any additional data that is available, i.e. previous data located on a remote device or in the Cloud, or additional sensor input data from the locator, a camera, or the remote device itself, or any available data, including mapping data, taken over multiple sessions, can be used in either model to determine which identified patterns should be incorporated into a map.

[0042] In another aspect, remote processing may be done at a vehicle or a remote facility or building. For instance, at some work sites, i.e. excavation sites, where locator equipment and cameras / imaging system are used, distributed processing or a separate Al processor may available for data processing as well. Taking advantage of this would make available a higher level of computer power because of the likelihood of a larger source of power that would typically not be available locally at a utility locator or camera / imaging system. For instance, a work truck or other vehicle would have access to at least one on board battery vehicle battery, multiple batteries, or even an available generator to be used for computing / processing tasks on any available computing machines. In some aspects, data could be streamed to a large facility which may even include MWs of running power for data centers which may even have their own cooling towers. This would provide a huge processing advantage over the processing power and level you would beable to carry around in a locator, camera, smartphone, or other handheld or easily transportable device or system.

[0043] Wirelessly streaming data bidirectionally using WiFi or another streaming protocol between a vehicle or a facility, either directly or relayed through a smartphone or other remote device, would allow the harnessing of large amounts of processing power not available to a smaller device. Some or all data could also be processed in the Cloud, as previously mentioned. Any information to be displayed could ultimately be sent back to a handheld instrument, such as a smartphone or other remote device, a utility locator, or any other display available to system users.

[0044] Outsourcing, so to speak, Al processing to a smartphone which most people already carry, allows a user to leverage the processing capabilities already existing in most smartphones, along with the additional advantage of using the existing communication functionality in smartphones to wirelessly communicate with the Cloud, and / or back to a locator. Other types of conventional, i.e. non-AI or Neural Network processing, can also be done on a smartphone. For instance, algorithmic, i.e. if then, else type filter processing, filtering of signals, and other calculations that do not require the calculating power of Al. If enough bandwidth is available, you can send large amounts of the raw, unfiltered data to a smartphone, and the smartphone can do all of the filtering and display processing. The smartphone's own display can be used, or the processed information can be sent back to a locator for display. Other non-visual ways of providing information to a user are well known in the art, and can be used alone or in combination with a visual display, e.g. audio, tactile, etc. A visual display may render information to a user in the form of raw data, processed data, organized data, filtered data, textual data, mapped, data, etc., or a combination of any of those.

[0045] In another aspect, data from a utility locator or camera may be directly sent to a vehicle for display, or the data may be processed using a smartphone and / or the Cloud, and then displayed in the vehicle. The vehicle display may be an on-board display, or a remote device such as an iPad or laptop inside the vehicle. If one or more utility locators are attached to the vehicle, e.g. with a hitch or other attachment, any built in display on the locator will not be able to be seen when inside the vehicle. In this case processed data may not need to be sent back to the locator(s) at all.

[0046] In one aspect, logging may be provided to create a historical record of where the locator has been, e.g. position, location, time, date, etc. As an example, EM data from the locator may be sent to an Al model on a smartphone for processing on the phone, once processed the data may be sent back to the locator to display position in real-time or near real-time. Displayed utility data may include estimated position and orientation, magnitude of current, i.e.. a current vector placed in the ground at an indicated position, phase, etc. If only a narrow bandwidth is available for communication, vectors already calculated in a real frame can be sent to the smartphone or other remote device for further processing.

[0047] In one aspect, locator position in the world frame, and locator orientation in the world frame can be sent to a smartphone, along with offset positions of the utilities with respect to a single position. As an example, you might have 200 different frequencies, and some of those frequencies are being sent and sampled at different rates, e.g. 8 Hz, 64 Hz, PCA (principal component analysis), narrow band, etc. Also, might have DC magnetometry, moving magnetometery around calculating positions of dipoles, etc. Dipole and cylindrical processing can be done in DC. DC is another frequency, in essence its frequency is zero. Similar type processingfor both cylindrical and dipole fields can be done in DC, e.g. if we have a 12 channel array we can do the same calculations with DC as in AC.

[0048] Various additional aspects, features, and functions are describe below in conjunction with the Drawings.

[0049] Details of example devices, systems, and methods that may be combined with the embodiments disclosed herein, as well as additional components, methods, and configurations that may be used in conjunction with the embodiments described herein, are disclosed in co-assigned patents and patent applications including: United States Patent 7,009,399, issued March 7, 2006, entitled OMNIDIRECTIONAL SONDE AND LINE LOCATOR; United States Patent 7,136,765, issued November 14, 2006, entitled A BURIED OBJECT LOCATING AND TRACING METHOD AND SYSTEM EMPLOYING PRINCIPAL COMPONENTS ANALYSIS FOR BLIND SIGNAL DETECTION; United States Patent 7,221,136, issued May 22, 2007, entitled SONDES FOR LOCATING UNDERGROUND PIPES AND CONDUITS; United States Patent 7,276,910, issued October 2, 2007, entitled A COMPACT SELF-TUNED ELECTRICAL RESONATOR FOR BURIED OBJECT LOCATOR APPLICATIONS; United States Patent 7,288,929, issued October 30, 2007, entitled INDUCTIVE CLAMP FOR APPLYING SIGNAL TO BURIED UTILITIES; United States Patent 7,298,126, issued November 20, 2007, entitled SONDES FOR LOCATING UNDERGROUND PIPES AND CONDUITS; United States Patent 7,332,901, issued February 19, 2008, entitled LOCATOR WITH APPARENT DEPTH INDICATION; United States Patent 7,443,154, issued October 28, 2008, entitled MULTISENSOR MAPPING OMNIDIRECTIONAL SONDE AND LINE LOCATOR; United States Patent 7,498,797, issued March 3, 2009, entitled LOCATOR WITH CURRENT-MEASURING CAPABILITY; United States Patent 7,498,816, issued March 3, 2009, entitledOMNIDIRECTIONAL SONDE AND LINE LOCATOR; United States Patent 7,336,078, issued February 26, 2008, entitled MULTI-SENSOR MAPPING OMNIDIRECTIONAL SONDE AND LINE LOCATORS; United States Patent 7,518,374, issued April 14, 2009, entitled RECONFIGURABLE PORTABLE LOCATOR EMPLOYING MULTIPLE SENSOR ARRAYS HAVING FLEXIBLE NESTED ORTHOGONAL ANTENNAS; United States Patent 7,557,559, issued July 7, 2009, entitled COMPACT LINE ILLUMINATOR FOR BURIED PIPES AND CABLES; United States Patent 7,619,516, issued November 17, 2009, entitled SINGLE AND MULTLTRACE OMNIDIRECTIONAL SONDE AND LINE LOCATORS AND TRANSMITTER USED THEREWITH; United States Patent 7,619,516, issued November 17, 2009, entitled SINGLE AND MULTI-TRACE OMNIDIRECTIONAL SONDE AND LINE LOCATORS AND TRANSMITTER USED THEREWITH; United States Patent 7,733,077, issued June 8, 2010, entitled MULTI-SENSOR MAPPING OMNIDIRECTIONAL SONDE AND LINE LOCATORS AND TRANSMITTER USED THEREWITH; United States Patent 7,741,848, issued June 22, 2010, entitled ADAPTIVE MULTICHANNEL LOCATOR SYSTEM FOR MULTIPLE PROXIMITY DETECTION; United States Patent 7,755,360, issued July 13, 2010, entitled PORTABLE LOCATOR SYSTEM WITH JAMMING REDUCTION; United States Patent 7,825,647, issued November 2, 2010, entitled METHOD FOR LOCATING BURIED PIPES AND CABLES; United States Patent 7,830,149, issued November 9, 2010, entitled AN UNDERGROUND UTILITY LOCATOR WITH A TRANSMITTER, A PAIR OF UPWARDLY OPENING POCKET AND HELICAL COIL TYPE ELECTRICAL CORDS; United States Patent 7,864,980, issued January 4,2011, entitled SONDES FOR LOCATING UNDERGROUND PIPES AND CONDUITS; United States Patent 7,948,236, issued May 24, 2011, entitled ADAPTIVEMULTICHANNEL LOCATOR SYSTEM FOR MULTIPLE PROXIMITY DETECTION; UnitedStates Patent 7,969,151 , issued June 28, 2011 , entitled PRE-AMPLIFIER AND MIXER CIRCUITRY FOR A LOCATOR ANTENNA; United States Patent 7,990,151, issued August 2, 2011, entitled TRLPOD BURIED LOCATOR SYSTEM; United States Patent 8,013,610, issued September 6, 2011, entitled HIGH Q SELF-TUNING LOCATING TRANSMITTER; United States Patent 8,035,390, issued October 11, 2011, entitled OMNIDIRECTIONAL SONDE AND LINE LOCATOR; United States Patent 8,106,660, issued January 31, 2012, entitled SONDE ARRAY FOR USE WITH BURIED LINE LOCATOR; United States Patent 8,203,343, issued June 19, 2012, entitled RECONFIGURABLE PORTABLE LOCATOR EMPLOYING MULTIPLE SENSOR ARRAYS HAVING FLEXIBLE NESTED ORTHOGONAL ANTENNAS; United States Patent 8,264,226, issued September 11, 2012, entitled SYSTEM AND METHOD FOR LOCATING BURIED PIPES AND CABLES WITH A MAN PORTABLE LOCATOR AND A TRANSMITTER IN A MESH NETWORK; United States Patent 8,248,056, issued August 21, 2012, entitled A BURIED OBJECT LOCATOR SYSTEM EMPLOYING AUTOMATED VIRTUAL DEPTH EVENT DETECTION AND SIGNALING; United States Patent Application 13 / 769,202, filed February 15, 2013, entitled SMART PAINT STICK DEVICES AND METHODS; United States Patent Application 13 / 793,168, filed March 11, 2013, entitled BURIED OBJECT LOCATORS WITH CONDUCTIVE ANTENNA BOBBINS; United States Patent 8,400,154, issued March 19, 2013, entitled LOCATOR ANTENNA WITH CONDUCTIVE BOBBIN; United States Patent Application 14 / 027,027, filed September 13, 2013, entitled SONDE DEVICES INCLUDING A SECTIONAL FERRITE CORE STRUCTURE; United States Patent Application 14 / 033,349, filed September 20, 2013, entitled AN UNDERGROUND UTILITY LOCATOR WITH A TRANSMITTER, A PAIR OFUPWARDLY OPENING POCKET AND HELICAL COIL TYPE ELECTRICAL CORDS;United States Patent 8,547,428, issued October 1 , 2013, entitled PIPE MAPPING SYSTEM; United States Patent 8,564,295, issued October 22, 2013, entitled METHOD FOR SIMULTANEOUSLY DETERMINING A PLURALITY OF DIFFERENT LOCATIONS OF THE BURIED OBJECTS AND SIMULTANEOUDLY INDICATING THE DIFFERENT LOCATIONS TO A USER; United States Patent Application 14 / 148,649, filed January 6, 2014, entitled MAPPING LOCATING SYSTEMS & METHODS; United States Patent 8,635,043, issued January 21, 2014, entitled LOCATOR AND TRANSMITTER CALIBRATION SYSTEM; United States Patent 8,717,028, issued May 6, 2014, entitled SPRING CLIPS FOR USE WITH LOCATING TRANSMITTERS; United States Patent 8,773,133, issued July 8, 2014, entitled ADAPTIVE MULTICHANNEL LOCATOR SYSTEM FOR MULTIPLE PROXIMITY DETECTION; United States Patent 8,841,912, issued September 23, 2014, entitled PREAMPLIFIER AND MIXER CIRCUITRY FOR A LOCATOR ANTENNA; United States Patent 9,041,794, issued May 26, 2015, entitled PIPE MAPPING SYSTEMS AND METHODS; United States Patent 9,057,754, issued June 16, 2015, entitled ECONOMICAL MAGNETIC LOCATOR APPARATUS AND METHOD; United States Patent 9,081,109, issued July 14, 2015, entitled GROUND-TRACKING DEVICES FOR USE WITH A MAPPING LOCATOR; United States Patent 9,082,269, issued July 14, 2015, entitled HAPTIC DIRECTIONAL FEEDBACK HANDLES FOR LOCATION DEVICES; United States Patent 9,085,007, issued July 21, 2015, entitled MARKING PAINT APPLICATOR FOR PORTABLE LOCATOR; United States Patent 9,207,350, issued December 8, 2015, entitled BURIED OBJECT LOCATOR APPARATUS WITH SAFETY LIGHTING ARRAY; United States Patent 9,341,740, issued May 17, 2016, entitled OPTICAL GROUND TRACKING APPARATUS, SYSTEMS, AND METHODS;United States Patent 9,372,117, issued June 21, 2016, entitled OPTICAL GROUND TRACKINGAPPARATUS, SYSTEMS, AND METHODS; United States Patent Application 15 / 187,785, filed June 21, 2016, entitled BURIED UTILITY LOCATOR GROUND TRACKING APPATUS, SYSTEMS, AND METHODS; United States Patent 9,411,066, issued August 9, 2016, entitled SONDES & METHODS FOR USE WITH BURIED LINE LOCATOR SYSTEMS; United States Patent 9,411,067, issued August 9, 2016, entitled GROUND-TRACKING SYSTEMS AND APPARATUS; United States Patent 9,435,907, issued September 6, 2016, entitled PHASE SYNCHRONIZED BURIED OBJECT LOCATOR APPARATUS, SYSTEMS, AND METHODS; United States Patent 9,465,129, issued October 11, 2016, entitled IMAGE-BASED MAPPING LOCATING SYSTEM; United States Patent 9,488,747, issued November 8, 2016, entitled GRADIENT ANTENNA COILS AND ARRAYS FOR USE IN LOCATING SYSTEM; United States Patent 9,494,706, issued November 15, 2016, entitled OMNI-INDUCER TRANSMITTING DEVICES AND METHODS; United States Patent 9,523,788, issued December 20, 2016, entitled MAGNETIC SENSING BURIED OBJECT LOCATOR INCLUDING A CAMERA; United States Patent 9,571,326, issued February 14, 2017, entitled METHOD AND APPARATUS FOR HIGH-SPEED DATA TRANSFER EMPLOYING SELFSYNCHRONIZING QUADRATURE AMPLITUDE MODULATION (QAM); United States Patent 9,599,449, issued March 21, 2017, entitled SYSTEMS AND METHODS FOR LOCATING BURIED OR HIDDEN OBJECTS USING SHEET CURRENT FLOW MODELS; United States Patent 9,599,740, issued March 21, 2017, entitled USER INTERFACES FOR UTILITY LOCATORS; United States Patent 9,625,602, issued April 18, 2017, entitled SMART PERSONAL COMMUNICATION DEVICES AS USER INTERFACES; United States Patent 9,632,202, issued April 25, 2017, entitled ECONOMICAL MAGNETIC LOCATORAPPARATUS AND METHODS; United States Patent 9,634,878, issued April 25, 2017, entitledSYSTEMS AND METHODS FOR DATA TRANSFER USING SELF-SYNCHRONIZINGQUADRATURE AMPLITUDE MODULATION (QAM); United States Patent Application, filed April 25, 2017, entitled SYSTEMS AND METHODS FOR LOCATING AND / OR MAPPING BURIED UTILITIES USING VEHICLE-MOUNTED LOCATING DEVICES; United States Patent 9,638,824, issued May 2, 2017, entitled QUAD-GRADIENT COILS FOR USE IN LOCATING SYSTEMS; United States Patent Application, filed May 9, 2017, entitled BORING INSPECTION SYSTEMS AND METHODS; United States Patent 9,651,711, issued May 16, 2017, entitled HORIZONTAL BORING INSPECTION DEVICE AND METHODS; United States Patent 9,684,090, issued June 20, 2017, entitled NULLED-SIGNAL LOCATING DEVICES, SYSTEMS, AND METHODS; United States Patent 9,696,447, issued July 4, 2017, entitled BURIED OBJECT LOCATING METHODS AND APPARATUS USING MULTIPLE ELECTROMAGNETIC SIGNALS; United States Patent 9,696,448, issued July 4, 2017, entitled GROUND-TRACKING DEVICES AND METHODS FOR USE WITH A UTILITY LOCATOR; United States Patent 9,703,002, issued June 11, 2017, entitled UTILITY LOCATOR SYSTEMS & METHODS; United States Patent Application 15 / 670,845, filed August 7, 2016, entitled HIGH FREQUENCY AC-POWERED DRAIN CLEANING AND INSPECTION APPARATUS & METHODS; United States Patent Application 15 / 681,250, filed August 18, 2017, entitled ELECTRONIC MARKER DEVICES AND SYSTEMS; United States Patent Application 15 / 681,409, filed August 20, 2017, entitled WIRELESS BURIED PIPE & CABLE LOCATING SYSTEMS; United States Patent 9,746,572, issued August 29, 2017, entitled ELECTRONIC MARKER DEVICES AND SYSTEMS; United States Patent 9,746,573, issued August 29, 2017, entitled WIRELESS BURIED PIPE AND CABLE LOCATING SYSTEMS; United States Patent 9,784,837, issued October 10, 2017, entitled OPTICAL GROUND TRACKING APPARATUS,SYSTEMS & METHODS; United States Patent Application 15 / 811 ,361 , filed November 13, 2017, entitled OPTICAL GROUND-TRACKING APPARATUS, SYSTEMS, AND METHODS; United States Patent 9,841,503, issued December 12, 2017, entitled OPTICAL GROUNDTRACKING APPARATUS, SYSTEMS, AND METHODS; United States Patent Application 15 / 846,102, filed December 18, 2017, entitled SYSTEMS AND METHOD FOR ELECTRONICALLY MARKING, LOCATING AND VIRTUALLY DISPLAYING BURIED UTILITIES; United States Patent Application 15 / 866,360, filed January 9, 2018, entitled TRACKED DISTANCE MEASURING DEVICES, SYSTEMS, AND METHODS; United States Patent 9,891,337, issued February 13, 2018, entitled UTILITY LOCATOR TRANSMITTER DEVICES, SYSTEMS, and METHODS WITH DOCKABLE APPARATUS; United States Patent 9,914,157, issued March, 13, 2018, entitled METHODS AND APPARATUS FOR CLEARING OBSTRUCTIONS WITH A JETTER PUSH-CABLE APPARATUS; United States Patent Application 15 / 925,643, issued March 19, 2018, entitled PHASE-SYNCHRONIZED BURIED OBJECT TRANSMITTER AND LOCATOR METHODS AND APPARATUS; United States Patent Application 15 / 925,671, issued March 19, 2018, entitled MULTI-FREQUENCY LOCATING SYSTEMS AND METHODS; United States Patent Application 15 / 936,250, filed March 26, 208, entitled GROUND TRACKING APPARATUS, SYSTEMS, AND METHODS; United States Patent 9,927,545, issued March 27, 2018, entitled MULTI-FREQUENCY LOCATING SYSTEMS & METHODS; United States Patent 9,928,613, issued March 27, 2018, entitled GROUND TRACKING APPARATUS, SYSTEMS, AND METHODS; United States Patent Application 15 / 250,666, filed March 27, 2018, entitled PHASE-SYNCHRONIZED BURIED OBJECT TRANSMITTER AND LOCATOR METHODS AND APPARATUS; UnitedStates Patent 9,880,309, issued March 28, 2018, entitled UTILITY LOCATOR TRANSMITTERAPPARATUS & METHODS; United States Patent Application 15 / 954,486, filed April 16, 2018, entitled UTILITY LOCATOR APPARATUS, SYSTEMS, AND METHODS; United States Patent 9,945,976, issued April 17, 2018, entitled UTILITY LOCATOR APPARATUS, SYSTEMS, AND METHODS; United States Patent 9,989,662, issued June 5, 2018, entitled BURIED OBJECT LOCATING DEVICE WITH A PLURALITY OF SPHERICAL SENSOR BALLS THAT INCLUDE A PLURALITY OF ORHTOGONAL ANTENNAE; United States Patent Application 16 / 036,713, issued July 16, 2018, entitled UTILITY LOCATOR APPARATUS AND SYSTEMS; United States Patent 10,024,994, issued July 17, 2018, entitled WEARABLE MAGNETIC FIELD UTILITY LOCATOR SYSTEM WITH SOUND FIELD GENERATION; United States Patent 10,031,253, issued July 24, 2018, entitled GRADIENT ANTENNA COILS AND ARRAYS FOR USE IN LOCATING SYSTEMS; United States Patent 10,042,072, issued August 7, 2018, entitled OMNI-INDUCER TRANSMITTING DEVICES AND METHODS; United States Patent 10,059,504, issued August 28, 2018, entitled MARKING PAINT APPLICATOR FOR USE WITH PORTABLE UTILITY LOCATOR; United States Patent Application 16 / 049,699, filed July 30, 2018, entitled OMNI-INDUCER TRANSMITTING DEVICES AND METHODS; United States Patent 10,069,667, issued September 4, 2018, entitled SYSTEMS AND METHODS FOR DATA TRANSFER USING SELF-SYNCHRONIZING QUADRATURE AMPLITUDE MODULATION (QAM); United States Patent Application 16 / 121,379, filed September 4, 2018, entitled KEYED CURRENT SIGNAL UTILITY LOCATING SYSTEMS AND METHODS; United States Patent Application 16 / 125,768, filed September 10, 2018, entitled BURIED OBJECT LOCATOR APPARATUS AND METHODS; United States Patent 10,073,186, issued September 11, 2018, entitled KEYED CURRENTSIGNAL UTILITY LOCATING SYSTEMS AND METHODS; United States Patent Application16 / 133,642, issued September 17, 2018, entitled MAGNETIC UTILITY LOCATOR DEVICES AND METHODS; United States Patent 10,078,149, issued September 18, 2018, entitled BURIED OBJECT LOCATORS WITH DODECAHEDRAL ANTENNA NODES; United States Patent 10,082,591, issued September 25, 2018, entitled MAGNETIC UTILITY LOCATOR DEVICES & METHODS; United States Patent 10,082,599, issued September 25, 2018, entitled MAGNETIC SENSING BURIED OBJECT LOCATOR INCLUDING A CAMERA; United States Patent 10,090,498, issued October 2, 2018, entitled MODULAR BATTERY PACK APPARATUS, SYSTEMS, AND METHODS INCLUDING VIRAL DATA AND / OR CODE TRANSFER; United States Patent Application 16 / 160,874, filed October 15, 2018, entitled TRACKABLE DIPOLE DEVICES, METHODS, AND SYSTEMS FOR USE WITH MARKING PAINT STICKS; United States Patent Application 16 / 222,994, filed December 17, 2018, entitled UTILITY LOCATORS WITH RETRACTABLE SUPPORT STRUCTURES AND APPLICATIONS THEREOF; United States Patent 10,105,723, issued October 23, 2018, entitled TRACKABLE DIPOLE DEVICES, METHODS, AND SYSTEMS FOR USE WITH MARKING PAINT STICKS; United States Patent 10,162,074, issued December 25, 2018, entitled UTILITY LOCATORS WITH RETRACTABLE SUPPORT STRUCTURES AND APPLICATIONS THEREOF; United States Patent Application 16 / 241,864, filed January 7, 2019, entitled TRACKED DISTANCE MEASURING DEVICES, SYSTEMS, AND METHODS; United States Patent Application 16 / 255,524, filed January 23, 2019, entitled RECHARGEABLE BATTERY PACK ONBOARD CHARGE STATE INDICATION METHODS AND APPARATUS; United States Patent 10,247,845, issued April 2, 2019, entitled UTILITY LOCATOR TRANSMITTER APPARATUS AND METHODS; United States Patent Application 16 / 382,136, filed April 11, 2019, entitled GEOGRAPHIC MAP UPDATING METHODS AND SYSTEMS; United StatesPatent 10,274,632, issued April 20, 2019, entitled UTILITY LOCATING SYSTEMS WITH MOBILE BASE STATION; United States Patent Application 16 / 390,967, filed April 22, 2019, entitled UTILITY LOCATING SYSTEMS WITH MOBILE BASE STATION; United States Patent Application 29 / 692,937, filed May 29, 2019, entitled BURIED OBJECT LOCATOR; United States Patent Application 16 / 436,903, filed June 10, 2019, entitled OPTICAL GROUND TRACKING APPARATUS, SYSTEMS, AND METHODS FOR USE WITH BURIED UTILITY LOCATORS; United States Patent 10,317,559, issued June 11, 2019, entitled GROUNDTRACKING DEVICES AND METHODS FOR USE WITH A UTILITY LOCATOR; United States Patent Application 16 / 449,187, filed June 21, 2019, entitled ELECTROMAGNETIC MARKER DEVICES FOR BURIED OR HIDDEN USE; United States Patent Application 16 / 455,491, filed June 27, 2019, entitled SELF-STANDING MULTI-LEG ATTACHMENT DEVICES FOR USE WITH UTILITY LOCATORS; United States Patent 10,353,103, issued July 16, 2019, entitled SELF-STANDING MULTI-LEG ATTACHMENT DEVICES FOR USE WITH UTILITY LOCATORS; United States Patent Application 16 / 551,653, filed August 26, 2019, entitled BURIED UTILITY MARKER DEVICES, SYSTEMS, AND METHODS; United States Patent 10,401,526, issued September 3, 2019, entitled BURIED UTILITY MARKER DEVICES, SYSTEMS, AND METHODS; United States Patent 10,324,188, issued October 9, 2019, entitled OPTICAL GROUND TRACKING APPARATUS, SYSTEMS, AND METHODS FOR USE WITH BURIED UTILITY LOCATORS; United States Patent Application 16 / 446,456, filed June 19, 2019, entitled DOCKABLE TRIPODAL CAMERA CONTROL UNIT; United States Patent Application 16 / 520,248, filed July 23, 2019, entitled MODULAR BATTERY PACK APPARATUS, SYSTEMS, AND METHODS; United States Patent 10,371,305, issued August 6,2019, entitled DOCKABLE TRIPODAL CAMERA CONTROL UNIT; United States PatentT110,490,908, issued November 26, 2019, entitled DUAL ANTENNA SYSTEMS WITH VARIABLE POLARIZATION; United States Patent Application 16 / 701,085, filed December 2, 2019, entitled MAP GENERATION BASED ON UTILITY LINE POSITION AND ORIENTATION ESTIMATES; United States Patent 10,534,105, issued January 14, 2020, entitled UTILITY LOCATING TRANSMITTER APPARATUS AND METHODS; United States Patent Application 16 / 773,952, filed January 27, 2020, entitled MAGNETIC FIELD CANCELING AUDIO DEVICES; United States Patent Application 16 / 780,813, filed February 3, 2020, entitled RESILIENTLY DEFORMABLE MAGNETIC FIELD CORE APPARATUS AND APPLICATIONS; United States Patent 10,555,086, issued February 4, 2020, entitled MAGNETIC FIELD CANCELING AUDIO SPEAKERS FOR USE WITH BURIED UTILITY LOCATORS OR OTHER DEVICES; United States Patent Application 16 / 786,935, filed February 10, 2020, entitled SYSTEMS AND METHODS FOR UNIQUELY IDENTIFYING BURIED UTILITIES IN A MULTI-UTILITY ENVIRONMENT; United States Patent 10,557,824, issued February 11, 2020, entitled RESILIENTLY DEFORMABLE MAGNETIC FIELD TRANSMITTER CORES FOR USE WITH UTILITY LOCATING DEVICES AND SYSTEMS; United States Patent Application 16 / 791,979, issued February 14, 2020, entitled MARKING PAINT APPLICATOR APPARATUS; United States Patent Application 16 / 792,047, filed February 14, 2020, entitled SATELLITE AND MAGNETIC FIELD SONDE APPARATUS AND METHODS; United States Patent 10,564,309, issued February 18, 2020, entitled SYSTEMS AND METHODS FOR UNIQUELY IDENTIFYING BURIED UTILITIES IN A MULTI-UTILITY ENVIRONMENT; United States Patent 10,571,594, issued February 25, 2020, entitled UTILITY LOCATOR DEVICES, SYSTEMS, AND METHODS WITH SATELLITE AND MAGNETICFIELD SONDE ANTENNA SYSTEMS; United States Patent 10,569,952, issued February 25,2020, entitled MARKING PAINT APPLICATOR FOR USE WITH PORTABLE UTILITY LOCATOR; United States Patent Application 16 / 810,788, filed March 5, 2019, entitled MAGNETICALLY RETAINED DEVICE HANDLES; United States Patent Application 16 / 827,672, filed March 23, 2020, entitled DUAL ANTENNA SYSTEMS WITH VARIABLE POLARIZATION; United States Patent Application 16 / 833,426, filed March 27, 2020, entitled LOW COST, HIGH PERFORMANCE SIGNAL PROCESSING IN A MAGNETIC-FIELD SENSING BURIED UTILITY LOCATOR SYSTEM; United States Patent 10,608,348, issued March 31, 2020, entitled DUAL ANTENNA SYSTEMS WITH VARIABLE POLARIZATION; United States Patent Application 16 / 837,923, filed April 1, 2020, entitled MODULAR BATTERY PACK APPARATUS, SYSTEMS, AND METHODS INCLUDING VIRAL DATA AND / OR CODE TRANSFER; United States Patent Application 17 / 235,507, filed April 20, 2021, entitled UTILITY LOCATING DEVICES EMPLOYING MULTIPLE SPACED APART GNSS ANTENNAS; United States Provisional Patent Application 63 / 015,692, filed April 27, 2020, entitled SPATIALLY AND PROCESSING-BASED DIVERSE REDUNDANCY FOR RTK POSITIONING; United States Patent Application 16 / 872,362, fded May 11, 2020, entitled BURIED LOCATOR SYSTEMS AND METHODS; United States Patent Application 16 / 882,719, filed May 25, 2020, entitled UTILITY LOCATING SYSTEMS, DEVICES, AND METHODS USING RADIO BROADCAST SIGNALS; United States Patent 10,670,766, issued June 2, 2020, entitled UTILITY LOCATING SYSTEMS, DEVICES, AND METHODS USING RADIO BROADCAST SIGNALS; United States Patent 10,677,820, issued June 9, 2020, entitled BURIED LOCATOR SYSTEMS AND METHODS; United States Patent Application 16 / 902,245, filed June 15, 2020, entitled LOCATING DEVICES, SYSTEMS, AND METHODSUSING FREQUENCY SUITES FOR UTILITY DETECTION; United States Patent Application16 / 902,249, filed June 15, 2020, entitled USER INTERFACES FOR UTILITY LOCATORS; United States Patent 10,690,795, issued June 23, 2020, entitled LOCATING DEVICES, SYSTEMS, AND METHODS USING FREQUENCY SUITES FOR UTILITY DETECTION; United States Patent Application 16 / 908,625, filed June 22, 2020, entitled ELECTROMAGNETIC MARKER DEVICES WITH SEPARATE RECEIVE AND TRANSMIT ANTENNA ELEMENTS; United States Patent 10,690,796, issued June 23, 2020, entitled USER INTERFACES FOR UTILITY LOCATORS; United States Patent Application 16 / 921,775, filed July 6, 2020, entitled AUTO-TUNING CIRCUIT APPARATUS AND METHODS; United States Provisional Patent Application 63 / 055,278, filed July 22, 2020, entitled VEHICLE-BASED UTILITY LOCATING USING PRINCIPAL COMPONENTS; United States Patent Application 16 / 995,801, filed August 17, 2020, entitled UTILITY LOCATOR TRANSMITTER DEVICES, SYSTEMS, AND METHODS; United States Patent Application 17 / 001,200, filed August 24, 2020, entitled MAGNETIC SENSING BURIED UTLITITY LOCATOR INCLUDING A CAMERA; United States Patent 16 / 995,793, filed August 17, 2020, entitled UTILITY LOCATOR APPARATUS AND METHODS; United States Patent 10,753,722, issued August 25, 2020, entitled SYSTEMS AND METHODS FOR LOCATING BURIED OR HIDDEN OBJECTS USING SHEET CURRENT FLOW MODELS; United States Patent 10,754,053, issued August 25, 2020, entitled UTILITY LOCATOR TRANSMITTER DEVICES, SYSTEMS, AND METHODS WITH DOCKABLE APPARATUS; United States Patent 10,761,233, issued September 1 , 2020, entitled SONDES AND METHODS FOR USE WITH BURIED LINE LOCATOR SYSTEMS; United States Patent 10,761,239, issued September 1, 2020, entitled MAGNETIC SENSING BURIED UTILITY LOCATOR INCLUDING A CAMERA; UnitedStates Patent Application 17 / 013,831, filed September 7, 2020, entitled MULTIFUNCTIONBURIED UTILITY LOCATING CLIPS; United States Patent 10,777,919, issued September 15, 2020, entitled MULTIFUNCTION BURIED UTILITY LOCATING CLIPS; United States Patent Application 17 / 020,487, fded September 14, 2020, entitled ANTENNA SYSTEMS FOR CIRCULARLY POLARIZED RADIO SIGNALS; United States Patent Application 17 / 068,156, filed October 12, 2020, entitled DUAL SENSED LOCATING SYSTEMS AND METHODS; United States Provisional Patent Application 63 / 091,67, filed October 14, 2020, entitled ELECTRONIC MARKER-BASED NAVIGATION SYSTEMS AND METHODS FOR USE IN GNSS-DEPRIVED ENVIRONMENTS; United States Patent 10,809,408, issued October 20,2020, entitled DUAL SENSED LOCATING SYSTEMS AND METHODS; United States Patent 10,845,497, issued November 24, 2020, entitled PHASE-SYNCHRONIZED BURIED OBJECT TRANSMITTER AND LOCATOR METHODS AND APPARATUS; United States Patent 10,859,727, issued December 8, 2020, entitled ELECTRONIC MARKER DEVICES AND SYSTEMS; United States Patent 10,908,311, issued February 2, 2021, entitled SELF-STANDING MULTLLEG ATTACHMENT DEVICES FOR USE WITH UTILITY LOCATORS; United States Patent 10,928,538, issued February 23, 2021, entitled KEYED CURRENT SIGNAL LOCATING SYSTEMS AND METHODS; United States Patent 10,935,686, issued March 2,2021, entitled UTILITY LOCATING SYSTEM WITH MOBILE BASE STATION; and United States Patent 10,955,583, issued March 23, 2021, entitled BORING INSPECTION SYSTEMS AND METHODS; United States Patent 9,927,368, issued March 27, 2021, entitled SELFLEVELING INSPECTION SYSTEMS AND METHODS; United States Patent 10,976,462, issued April 13, 2021, entitled VIDOE INFECTION SYSTEMS WITH PERSONAL COMMUNICATION DEVICE USER INTERFACES; United States Patent Application17 / 501,670, filed October 14, 2021, entitled ELECTRONIC MARKER-BASED NAVIGATIONSYSTEMS AND METHODS FOR USE IN GNSS-DEPRIVED ENVIRONMENTS; United States Patent Application 17 / 528,956, filed November 17, 2021, entitled VIDEO INSPECTION SYSTEM, APPARATUS, AND METHODS WITH RELAY MODULES AND CONNECTION PORT; United States Patent Application 17 / 541,057, filed December 2, 2021, entitled COLORINDEPENDENT MARKER DEVICE APPARATUS, METHODS, AND SYSTEMS; United States Patent Application 17 / 541,057, filed December 2, 2021, entitled VIDEO INSPECTION SYSTEM, APPARATUS, AND METHODS WITH RELAY MODULES AND CONNECTION PORTCOLOR-INDEPENDENT MARKER DEVICE APPARATUS, METHODS, AND SYSTEMS; United States Patent 11,193,767, issued December 7, 2021, entitled SMART PAINT STICK DEVICES AND METHODS ; United States Patent 11 ,199,510, issued December 14, 2021 , entitled PIPE INSPECTION AND CLEANING APPARATUS AND SYSTEMS; United States Provisional Patent Application 63 / 293,828, fded December 26, 2021, entitled MODULAR BATTERY SYSTEMS INCLUDING INTERCHANGEABLE BATTERY INTERFACE APPARATUS; United States Patent 11,209,115, issued December 28, 2021, entitled PIPE INSPECTION AND / OR MAPPING CAMERA HEADS, SYSTEMS, AND METHODS; United States Patent Application 17 / 563,049, filed December 28, 2021, entitled SONDE DEVICES WITH A SECTIONAL FERRITE CORE; United States Provisional Patent Application 63 / 306,088, filed February 2, 2022, entitled UTILITY LOCATING SYSTEMS AND METHODS WITH FILTER TUNING FOR POWER GRID FLUCTUATIONS; United States Patent Application 17 / 687,538, filed March 4, 2022, entitled ANTENNAS, MULTI-ANTENNA APPARATUS, AND ANTENNA HOUSINGS; United States Patent 11,280,934, issued March 22, 2022, entitled ELECTROMAGNETIC MARKER DEVICES FOR BURIED OR HIDDENUSE; United States Patent 11,300,597, issued April 12, 2022, entitled SYSTEMS ANDMETHODS FOR LOCATING AND / OR MAPPING BURIED UTILITIES USING VEHICLE-MOUNTED LOCATING DEVICES; MODULAR BATTERY SYSTEMS INCLUDING INTERCHANGEABLE BATTERY INTERFACE APPARATUS; United States Patent Application 18 / 162,663, filed January 31, 2023, entitled UTILTY LOCATING SYSTEMS AND METHODS WITH FILTER TUNING FOR POWER GRID FLUCTUATIONS; United States Provisional Patent Application 63 / 485,905, filed February 18, 2023, entitled SYSTEMS AND METHODS FOR INSPECTION ANIMATION; United States Provisional Patent Application 63 / 492,473, filed March 27, 2023, entitled VIDEO INSPECTION AND CAMERA HEAD TRACKING SYSTEMS AND METHODS; United States Patent 11,614,613, issued March 28, 2023, entitled DOCKABLE CAMERA CABLE DRUM-REEL AND CCU SYSTEM; United States Patent 11,649,917, issued May 16, 2023, entitled INTEGRATED FLEX-SHAFT CAMERA SYSTEM WITH HAND CONTROL; United States Patent 11,665,321, issued May 30, 2023, entitled PIPE INSPECTION SYSTEM WITH REPLACEABLE CABLE STORAGE DRUM; United States Patent 11,674,906, issued June 13, 2023, entitled SELF-LEVELING INSPECTION SYSTEMS AND METHODS; United States Provisional Patent Application 63 / 510,014, filed June 23, 2023, entitled INNER DRUM MODULE WITH PUSH-CABLE INTERFACE FOR PIPE INSPECTION; United States Patent 11,686,878, issued June 27, 2023, entitled ELECTRONIC MARKER DEVICES FOR BURIED OR HIDDEN USE; United States Provisional Patent Application 63 / 524,698, filed July 2, 2023, entitled FILTERING METHODS AND ASSOCIATED UTILITY LOCATOR DEVICES FOR LOCATING AND MAPPING BURIED UTILITY LINES; United States Provisional Patent Application 63 / 514,090, filed July 17, 2023, entitled SMARTPHONE MAPPING APPARATUS FOR ASET TAGGING AS USED WITH UTILITY LOCATOR DEVICES; United States Patent 11,709,289, issued July 25, 2023, entitledSONDE DEVICES WITH A SECTIONAL FERRITE CORE; United States Patent Application 18 / 365,225, filed August 3, 2023, entitled SYSTEMS AND METHODS FOR INSPECTION ANIMATION; United States Patent 11,719,376, issued August 8, 2023, entitled DOCKABLE TRIPOD AL CAMERA CONTROL UNIT; United States Patent 11,719,646, issued August 8, 2023, entitled PIPE MAPPING SYSTEMS AND METHODS; United States Patent 11,719,846, issued August 8, 2023, entitled BURIED UTILITY LOCATING SYSTEMS WITH WIRELESS DATA COMMUNICATION INCLUDING DETERMINATION OF CROSS COUPLING TO ADJACENT UTILITIES; United States Patent Application 18 / 233,285, filed August 11, 2023, entitled BURIED OBJECT LOCATOR; United States Patent Application 18 / 236,786, filed August 22, 2023, entitled MAGNETIC UTILITY LOCATOR DEVICES AND METHODS; United States Patent 11,747,505, issued September 5, 2023, entitled MAGNETIC UTILITY LOCATOR DEVICES AND METHODS; United States Patent Application 18 / 368,510, filed September 14, 2023, entitled MULTIFUNCTION BURIED UTILITY LOCATING CLIPS; United States Patent Application 18 / 365,203, filed September 14, 2023, entitled SYSTEMS AND METHODS FOR ELECTRONICALLY MARKING, LOCATING AND VIRTUALLY DISPLAYING BURIED UTILITIES; United States Patent 11,768,308, issued September 26, 2023, entitled SYSTEMS AND METHODS FOR ELECTRONICALLY MARKING, LOCATING AND VIRTUALLY DISPLAYING BURIED UTILITIES; United States Patent 11,769,956, issued September 26, 2023, entitled MULTIFUNCTION BURIED UTILITY LOCATING CLIPS; United States Patent 11 ,782,179, issued October 10, 2023, entitled BURIED OBJECT LOCATOR WITH DODECAHEDRAL ANTENNA CONFIGURATION APPARATUS AND METHODS; United States Patent 11,789,093, issued October 17, 2023, entitled THREE- AXIS MEASUREMENT MODULES AND SENSING METHODS; UnitedStates Provisional Patent Application 18 / 490,763, filed October 20, 2023, entitled LINKEDCABLE-HANDLING AND CABLE-STORAGE DRUM DEVICES AND SYSTEMS FOR COORDINATED MOVEMENT OF PUSH-CABLE; United States Patent 11,796,707, issued October 24, 2023, entitled USER INTERFACES FOR UTILITY LOCATORS; United States Patent Application 18 / 544,042, filed December 18, 2023, entitled SYSTEMS, APPARATUS, AND METHODS FOR DOCUMENTING UTILITY POTHOLES AND ASSOCIATED UTILITY LINES; United States Patent 11,876,283, issued January 16, 2024, entitled COMBINED SATELLITE NAVIGATION AND RADIO TRANSCEIVER ANTENNA DEVICES; United States Patent 11,894,707, issued February 6, 2024, entitled RECHARGEABLE BATTERY PACK ONBOARD CHARGE STATE INDICATION METHODS AND APPARATUS; United States Patent 11,909,104, issued February 20, 2024, entitled ANTENNAS, MULTI- ANTENNA APPARATUS, AND ANTENNA HOUSINGS; United States Provisional Patent Application 63 / 558,098, filed February 26, 2024, entitled SYSTEMS, DEVICES, AND METHODS FOR DOCUMENTING GROUND ASSETS AND ASSOCIATED UTILITY LINES; United States Patent 11,921,225, issued March 5, 2024, entitled ANTENNA SYSTEMS FOR CIRCULARLY POLARIZED RADIO SIGNALS; United States Patent Application 18 / 611,449, filed March 20, 2024, entitled VIDEO INSPECTION AND CAMERA HEAD TRACKING SYSTEMS AND METHODS; United States Patent 11,953,643, issued April 9, 2024, entitled MAP GENERATION BASED ON UTILITY LINE POSITION AND ORIENTATION ESTIMATES; United States Patent 11 ,962,943, issued April 16, 2024, entitled INSPECTION CAMERA DEVICES AND METHODS; United States Provisional Patent 63 / 643,915, filed May 7, 2024, entitled SYSTEMS AND METHODS FOR LOCATING AND MAPPING BURIED UTILITY OBJECTS USINGARTIFICIAL INTELLIGENCE WITH LOCAL OR REMOTE PROCESSING; United States Patent 11,988,951, issued May 21, 2024, entitled MULTI-DIELECTRIC COAXIAL PUSH-CABLES AND ASSOCIATED APPARATUS; United States Provisional Patent 63 / 659,722, filed June 13, 2024, entitled VEHICLE-MOUNTING DEVICES AND METHODS FOR USE IN VEHICLE-BASED LOCATING SYSTEMS; United States Provisional Application 18 / 747,912, filed June 19, 2024, entitled INNER DRUM MODULE WITH PUSH-CABLE INTERFACE FOR PIPE INSPECTION; United States Provisional Application 18 / 758,937, filed June 28, 2024, entitled FILTERING METHODS AND ASSOCIATED UTILITY LOCATOR DEVICES FOR LOCATING AND MAPPING BURIED UTILITY LINES; United States Patent Application 18 / 774,758, filed July 16, 2024, entitled SMARTPHONE MOUNTING APPARATUS AND IMAGING METHODS FOR ASSET TAGGING AND UTILITY MAPPING AS USED WITH UTILITY LOCATING DEVICES; United States Provisional Patent 63 / 674,749, issued July 23, 2024, entitled PIPE MAPPING FOR FEATURE AND ASSET RECOGNITION USING ARTIFICIAL INTELLIGENCE; United States Provisional Patent 63 / 692,642, issued September 9, 2024, entitled ELECTRONIC MODULES AND ASSOCIATED SYSTEMS; United States Provisional Patent 63 / 694,102, issued September 12, 2024, entitled METHODS AND APPARATUS FOR BATTERY SWAPPING IN UTILITY LOCATOR DEVICES AND OTHER COMPLEX BOOTABLE ELECTRONIC DEVICES; United States Provisional Patent 63 / 719,026, issued November 11, 2024, entitled PUSH-CABLE WITH OFFSET JACKET EXTRUSION; United States Provisional Patent 63 / 726,858, issued December 2, 2024, entitled DIGITAL SELF-LEVELING PIPE INSPECTION CAMERA SYSTEMS AND METHODS WITH AUTOMIC MAGNIFICATION; United States Patent Application 19 / 018,842, issued January 13, 2025, entitled ACCESSLBLE DRUM-REEL FRAME FOR PIPE INSPECTION CAMERA SYSTEM; United States Provisional Patent Application 63 / 761,029, filed February 20, 2025, entitled UTILITY LOCATING SYSTEMS, DEVICES, AND METHODS EMPLOYING SPATIAL AUDIO; United States Patent Application 19 / 059,288, filed February 21, 2025, entitled SYSTEMS, DEVICES, AND METHODS FOR DOCUMENTING GROUND ASSETS AND ASSOCIATED UTILITY LINES; United States Provisional Patent Application 63 / 770,287, filed March 11, 2025, entitled WORLD FRAME / LOCAL FRAME MAPPING AND RE-MAPPING IN A UTILITY LOCATION SYSTEM; and United States Patent 12,253,382, issued March 18, 2025, entitled VEHICLEBASED UTILITY LOCATING USING PRINCIPAL COMPONENTS. The content of each of the above-described patents and applications is incorporated by reference herein in its entirety. The above applications may be collectively denoted herein as the “co-assigned applications” or “incorporated applications.”

[0050] Articles hereby incorporated by reference herein in their entirety include https: / / www.section.io / engineering-education / understanding-pattem-recognition-in-machine- leaming / #:~:text=Pattern%20recognition%20is%20the%20use%20of%20machine%201eaming% 20algorithms%20to,to%20train%20pattern%20recognition%20systems; https: / / en. wikipedia.org / wiki / Deep_leaming; https : / / www. nature.com / articles / d41586-020- 03348-4; https: / / deepmind.com / research / case-studies / alphago-the-stoiy-so-far; and https: / / readwrite.com / 2019 / l l / 02 / machine-learning-for-translation-whats-the-state-of-the- language-art / ; http: / / sciencewise.info / media / pdf / ! 507.08818vl .pdfBRIEF DESCRIPTION OF THE DRAWINGS

[0051] FIG. 1 is an illustration of different methods for collecting multifrequency electromagnetic data from buried objects associated with utilities or communication systems, as known in the prior ail.

[0052] FIG. 2 is an illustration of an embodiment of a method of using Deep Learning / artificial intelligence to recognize patterns and make predictions related to underground utilities, in accordance with certain aspects of the present invention.

[0053] FIG. 3 is an illustration of an embodiment of a system, including a service worker using a portable locator and a sonde to collect electromagnetic frequency data or other data from underground or buried assets, in accordance with certain aspects of the present invention.

[0054] FIG. 4 is an illustration of an embodiment of a system, including a vehicle equipped with a locator to collect electromagnetic frequency data or other data from underground or buried assets, in accordance with certain aspects of the present invention.

[0055] FIG. 5 is an illustration of an embodiment of a method of providing training data to a neural network to use Deep Learning / artificial intelligence to recognize patterns and make predictions related to underground utilities, in accordance with certain aspects of the present invention.

[0056] FIG. 6 is an illustration of an embodiment of a chart showing various types of collected and other data as Training Data for Deep Learning in a Neural Network that uses Artificial Intelligence (Al), in accordance with certain aspects of the present invention.

[0057] FIG. 7 is an illustration of an embodiment of a system of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device and / or in the Cloud.

[0058] FIG. 8 is an illustration of an embodiment of a system using a remote device with a pipe inspection camera and a cable drum-reel to access additional conventional or Al processing resources available on the remote device and / or in the Cloud, in accordance with certain aspects of the present invention.

[0059] FIG. 9 is an illustration of an embodiment is an illustration of an embodiment of a system of a remote device with a utility locator and a vehicle to access additional conventional or Al processing resources available on the remote device, in accordance with certain aspects of the present invention.

[0060] FIG. 10 is an illustration of an embodiment of a method of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device, in accordance with certain aspects of the present invention.

[0061] FIG. 11 is an illustration of an embodiment of a method of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device with a feedback loop for improving a prediction model, in accordance with certain aspects of the present invention.

[0062] FIG. 12 is an illustration of an embodiment is an illustration of an embodiment of a method of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device, in accordance with certain aspects of the present invention.

[0063] FIG. 13 is an illustration of an embodiment of a method of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device and / or in the Cloud, in accordance with certain aspects of the present invention.

[0064] FIG. 14 is an illustration of an embodiment of a method of using a remote device with a utility locator to access additional conventional or Al processing resources available in the Cloud, in accordance with certain aspects of the present invention.DETAILED DESCRIPTION

[0065] It is noted that as used herein, the term "exemplary" means "serving as an example, instance, or illustration." Any aspect, detail, function, implementation, and / or embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects and / or embodiments.Example Embodiments

[0066] FIG. 1 illustrates details of an exemplary embodiment of different methods 100 for collecting multifrequency electromagnetic data from buried objects associated with utilities 150. Methods 100 may include collecting data from various apparatus with the ability to receive, measure, or sense single or multifrequency electromagnetic data from under or above ground sources. The various apparatus may include one or more of the following: GPS or other satellite systems 110, utility or other locator systems 120, equipment with one or more transmitters, receivers, or transceivers 130, sonde equipment 140, and many other types of utility sensing equipment well known by those skilled in the art.

[0067] FIG. 2 illustrates details of an exemplary method 200 of using Deep Learning / artificial intelligence to recognize patterns and make predictions related to underground utilities. The method starts at block 210 collecting data and proceeds to block 220 where a TrainingData Base, also known as a Data Suite or Training Data Suite, is assembled. The method thenproceeds to block 230 where Deep Learning is used to train a neural network using ArtificialIntelligence. Finally, the method proceeds to block 240 where Al estimates the probability that underground or buried objects or assets are specific types of equipment or utilities and other specifics including but not limited to current and / or voltage data, even and odd harmonics data, active and / or passive signal data, and spatial relationship data. r0068] FIG. 3 illustrates details of an exemplary embodiment 300 of a system including a service worker 310 using a portable locator 320, and a sonde 330 located underground 340 to collect single or multifrequency electromagnetic data from an underground or buried utility asset 350.

[0069] FIG. 4 illustrates details of an exemplary embodiment 400 of a system including a vehicle 410 equipped with an GNSS antenna 420, a locator 430, a dodecahedron antenna 440, and a sonde 450 located underground 460, used to collect single or multifrequency electromagnetic data from an underground or buried utility asset 470.

[0070] FIG. 5 illustrates details of an exemplary embodiment 500 of a method of providing training data to a neural network to use Deep Learning / artificial intelligence to recognize patterns and make predictions related to underground utilities. Multifrequency Electromagnetic Data 510 may be collected from multiple sources, any Predefined Classifier(s) 520 may be inputted or entered by a user, and both may be combined in block 530. Other data such as image data, harmonics data, etc. may also be combined in block 530. The Combined data is also known as a Data Suite. Data combined at 530 becomes available to be used as Training Data, also known as a Training Data Suite, at block 540. The Training Data 540 is then provided to one or more Neural Networks 550 which use Deep Learning to predict one or more data classes 560 for the underground or buried assets related to utility and communication systems. Artificial Intelligence(Al) is used to provide a probability that specific assets have specific characteristics, have relationships between other assets, and fall into one or more classification or categories by using the training data to recognize patterns.

[0071] FIG. 6 illustrates details of an exemplary embodiment 600 of a chart showing various types of collected and other data as Training Data for Deep Learning in a Neural Network that uses Artificial Intelligence (Al). Collected Data 605 may include Multifrequency Electromagnetic Data 610, Imaging Data 615, Mapping Data 620 which may include Depth and / or Orientation Data, Current and / or Voltage Data 625, Harmonics Data 630 including Even and / or Odd Harmonics Data, Active and / or Passive Signal Data 635, Spatial Relationship Data 640, Fiber Optic Data 645, Phase Data 650 which may include Single Phase or Multiphase Data, Phase Difference Data 655, Ground Penetrating Radar Data (GPR) 656, Acoustic Data 657, Tomography Data 658, Magnetic Gradiometry Data 659, LIDAR data 642, Point Cloud data 644, and GIS Asset Data 646. It is contemplated that additional types of Collected Data 605 related to utilities and communication systems could also be used, and would be apparent to those skilled in the art. Training Suite Data 660, which may include Collected Data 605, may also include Other Data 665. Other Data 665 may include one or more of the following: Observed Data 670, User Classification Data 675, and Ground Truth Data 680. It is contemplated that additional types of Other Data 665 related to utilities and communication systems could also be used, and would be apparent to those skilled in the art. Some examples of such data are paint marks including previous paint on the ground, pipeline markers, overhead utilities / powerlines, construction techniques uses, e.g. trenchfill (conductivity and magnetic permeability), local ground conductivity, type of equipment in operation on the grid. For instance, equipment could include horizontal drilling equipment that generally runs generally straight between a drill "in" pit and a drill "out pit. There are of courseinnumerable types of equipment that could be operating on the grid at any given time, these are well known in the art. Collected can include data collected walking and / or by vehicle including air collected data such as data collected by a drone. Collected data can be used separately or combined from multiple sources.

[0072] FIG. 7 illustrates details of an exemplary embodiment 700 of a system including a service worker 710 using a portable utility locator 720 to collect single or multifrequency electromagnetic data for an underground or buried utility 740. A smartphone or other remote device 730 may be provided to wirelessly communicate data between the locator 720 and itself. Optionally, the smartphone / remote device may also communicate with the Cloud 750 (a Cloud Server).

[0073] FIG. 8 illustrates details of an exemplary embodiment 800 of a system including a service worker 810 using a pipe inspection camera 820 to inspect an underground or buried pipe 830. The camera 820 is attached to a cable 840 which is stored and / or fed from a cable drum-reel 850. A wireless communication module 860 is provided to facilitate communication between the cable drum-reel 860 and a smart phone or other remote device 870. Optionally, the smartphone / remote device may also communicate with the Cloud 880 (Cloud Server).

[0074] FIG. 9 illustrates details of an exemplary embodiment 900 of a system including a vehicle 910 equipped with one or more utility locators 915 each with one or more EM antennas 917. The locators 720 include one or more GNSS antennas 920. Optionally, one or more GNSS antennas 920 may be mounted on or with one or more locators 915, mounted to the hitch 970, or vehicle mounted 910. A user 930 may drive or park the vehicle to enable the the locators 915 to collect multifrequency electromagnetic data from an underground or buried utility 940. Collecteddata may be communicated wirelessly to a smart phone or other remote device 950. Optionally, the smartphone / remote device may also communicate with the Cloud 960 (a Cloud Server).

[0075] FIG. 10 illustrates details of an exemplary a method 1000 of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device. The method starts at block 1010 collecting Utility Location Data "Collected Data" from a plurality of sources, and optionally providing Predefined Classifiers 1020, both of which are used as input for Training Data 1030. Next at block 1040, the Training Data is provided to at least one Neural Network to create a Location Prediction Model 1050. The Prediction Model 1050 and collected Utility Location Prediction Data 1060 (i.e. data to be used to make an Al prediction related underground or buried utilities) are then combined at block 1070. Next at block 1080, Prediction Data 1060 and the Location Prediction Model 1070 are wirelessly transmitted to a Remote Device. It should be noted that combining the Location Prediction Model 1050 and Location Prediction Data 1060 may mean they are combined into a single stream of data and transmitting the stream wirelessly, or transmitting the Model 1050 and Prediction Data separately at the same time, or at different times to a Remote Device 1080. Next, a Location Prediction Result is determined on the Remote Device at block 1085. Next, at least a portion of the Location Prediction Result from block 1085 is wirelessly transmitted back to the Utility Locator 1090 where at least a portion of the of the previously transmitted Location Prediction Result received by the Locator is presented to a user 1095, e.g. rendered on a display, provided as audio or tactile output, and other well known ways of providing data to a user. Displayed data may be provided in many forms including mapped data, alpha-numeric data, etc. Any previously mentioned data may be stored permanently or temporarily at any stage on the Utility Locator, on the Remote Device, or on any suitable external storage medium.

[0076] FIG. 11 illustrates details of an exemplary method 1 100 of a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device (refer back to FIG. 10 description) with a feedback loop 1110 for improving the Prediction Model. At block 1070 Collected Utility Location Prediction Data from block 1060 is combined with the created Prediction Model from block 1050. The Utility Location Prediction data 1060 may also be used as feedback 1110, i.e. Training Data 1030 to be used as input to at least one Neural Network 1040 to create an updated Location Prediction Model at block 1050. This may be a one time process or an iterative process, thereby constantly improving the Location Prediction Model.

[0077] FIG. 12 illustrates details of an exemplary method 1200 of using a remote device with a utility locator to access additional conventional or Al processing resources available on the remote device. The method starts at block 1210 collecting Utility Location Data "Collected Data" from a plurality of sources, and optionally providing Predefined Classifiers 1220, both of which are used as input for Training Data 1230. Next at block 1240, the Training Data is wirelessly transmitted to a Remote Device, and then the Training Data is provided to at least one Neural Network 1250 to create a Prediction Model on the Remote Device 1270. Collected Utility Location Data 1260 is then input into the Prediction Model 1270 to determine a Location Prediction Result on the Remote Device 1280. Next, at least a portion of the Location Prediction Result from block 1280 is wirelessly transmitted back to the Utility Locator 1285, and where at least a portion of the of the previously transmitted Location Prediction Result received by the Locator is presented to a user 1095, e.g. rendered on a display, provided as audio or tactile output, and other well known ways of providing data to a user and where at least a portion of the of the previously transmitted Location Prediction Result received by the Locator is presented to a user1290, e.g. rendered on a display, provided as audio or tactile output, and other well known ways of providing data to a user.

[0078] FIG. 13 illustrates details of an exemplary a method 1300 of using a remote device with a utility locator to access additional conventional or Al processing resources available in the Cloud. The method starts at block 1310 collecting Utility Location Data "Collected Data" from a plurality of sources, and optionally providing Predefined Classifiers 1320, both of which are used as input for Training Data 1330. Next at block 1340, the Training Data is provided to at least one Neural Network located on or at a Utility Locator or a Utility Inspection Camera Cable Drum-reel to create a Location Prediction Model 1340. The Prediction Model 1350 and collected Utility Location Prediction Data 1360 are then combined at block 1365. It should be noted that combining the Location Prediction Model 1050 and Location Prediction Data 1060 may mean they are combined into a single stream of data and transmitting the stream wirelessly, or transmitting the Model 1050 and Prediction Data separately at the same time, or at different times to a Remote Device 1080. Next at block 1370, Prediction Data 1360 and the Location Prediction Model 1350 are wirelessly transmitted to a Remote Device. The Remote Device is then used to wirelessly relay Utility Location Prediction Data and the Location Prediction Model to the Cloud 1375 to determine a Location Prediction Result 1380. At block 1385 at least a portion of the Prediction Result is wirelessly transmitted back to the Utility Locator or a Utility Inspection Camera Cable Drum-reel 1390 where at least a portion of the previously transmitted Location Prediction Result received by the Locator is presented to a user 1395, e.g. rendered on a display, provided as audio or tactile output, and other well known ways of providing data to a user.

[0079] Although a Utility Locator is described, a Utility Inspection Camera Cable Drumreel with processing and / or wireless communication capabilities may be used, or both a UtilityLocator and a Cable Drum-reel may be used. Multiple Locators and / or Drum-reels may also be used. Location Prediction Result information may be displayed on a Remote Device, on a Utility Locator, or on a Utility Inspection Camera Cable Drum-reel. Location Prediction Result information may also be received from a Remote Device to a Cable Drum-reel, and then relayed to a Utility Locator for storage or display. roo8oi FIG. 14 illustrates details of an exemplary method 1400 of using a remote device with a utility locator to access additional conventional or Al processing resources available in the Cloud. The method starts at block 1410 collecting Utility Location Data "Collected Data" from a plurality of sources, and optionally providing Predefined Classifiers 1420, both of which are used as input for Training Data 1430. Next at block 1440, the Training Data 1430 and Utility Location Prediction Data 1435 are wirelessly transmitted to a Remote Device, and then the Remote Device is used to relay the Training Data 1440 and Prediction Data 1435 to the Cloud in block 1445. In block 1450, a Prediction Model is Created with the Training Data by using a Neural Network in the Cloud. Next, a Location Prediction Result is Determined in the Cloud with the Model and the Prediction Data 1460. Next, at least a portion of the Location Prediction Result from block 1460 is wirelessly transmitted back to the Utility Locator or a Camera Inspection Cable-Drum Reel 1470 where at least a portion of the of the previously transmitted Location Prediction Result received by the Utility Locator or a Camera Inspection Cable-Drum Reel is presented to a user 1475, e.g. rendered on a display, provided as audio or tactile output, and other well known ways of providing data to a user.

[0081] The scope of the invention is not intended to be limited to the aspects shown herein but are to be accorded the full scope consistent with the disclosures herein and their equivalents, wherein reference to an element in the singular is not intended to mean “one and only one” unlessspecifically so stated, but rather “one or more.” Unless specifically stated otherwise, the term “some” refers to one or more. A phrase referring to “at least one of’ a list of items refers to any combination of those items, including single members. As an example, “at least one of: a, b, or c” is intended to cover: a; b; c; a and b; a and c; b and c; and a, b and c.

[0082] The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use embodiments of the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the disclosures herein and in the appended drawings.

Claims

CLAIMSWe claim:

1. A system for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: a receiving element for collecting utility location data ("collected data") from a plurality of sources; an input element for entering one or more predefined classifiers; a processing element for using at least a portion of the collected data alone or in combination with one or more predefined classifiers, wherein the processor outputs training data; a bi-directional communication clement for transmitting the training data and new collected data to be predicted ("prediction data") to a remote device, wherein the remote device includes at least one neural network for processing the training data and the prediction data using Deep Learning performed by Artificial Intelligence (Al) to determine a location prediction result; a transceiver integrated with the remote device for wirelessly transmitting at least a portion of the prediction result to the receiving element; and a user interface integrated with the receiving element for outputting at least a portion of the location prediction.

2. The system of Claim 1, wherein the remote device comprises at least one of a smartphone, a laptop, a PC, or other wireless device.

3. The system of Claim 2, where in the remote device communicates via at least one of WiFi, Bluetooth, or another wireless communication protocol.

4. The system of Claim 1, further comprising at least one of a utility locator and a cable drum-reel.

5. The system of Claim 4, where in the at least one utility locator and cable drum-reel comprises one or more transceivers.

6. The system of Claim 1, wherein training data further includes one or more of imaging data collected from a camera or imaging element, sensor data, fiber optic data, and mapping data.

7. The system of Claim 6, wherein mapping data includes at least one of depth or orientation data.

8. The system of Claim 1, wherein training data further includes one or more of image data, current and / or voltage data, even and odd harmonics data, active and / or passive signal data, and spatial relationship data, phase data and phase difference data.

9. The system of Claim 1, wherein training data further includes other data comprising one or more of observed data, user classification data, and ground truth data.

10. The system of Claim 9, wherein ground truth data comprises one or more of ownership data, manufacturer data, connection data, utility box or junction data, and obstacle data.

11. The system of Claim 1, wherein training data may be processed and classified in realtime, or stored and post-processed in the Cloud.

12. The system of Claim 1, wherein classifying the collected data comprises determining at least one of a utility type, electrical characteristics, connection type, asset type, manufacturer type, ownership type, location type, direction type, right of way type, or damaged asset type.

13. The system of Claim 4, wherein the at least one utility locator and / or cable drum-reel is removably attachable to a vehicle.

14. The system of Claim 13, wherein the vehicle comprises a hitching mechanism to removably attach the at least one utility locator and / or cable drum-reel.

15. The system of Claim 1 , wherein the output element comprises one or more of a visual display, a speaker or other sound producing clement, and a vibration or other tactile producing element.

16. A method for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: collecting utility location data ("collected data") from a plurality of sources; using the collected data alone or in combination with user predefined classifiers as training data; providing the training data to at least one neural network to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al); collecting utility data to be used for a location prediction ("prediction data"); wirelessly transmitting the prediction data and the location prediction model to at least one of a smartphone, laptop, PC, or other wireless device ("remote device"); determining a location prediction result on the remote device using the prediction data and the location prediction model; wirelessly transmitting at least a portion of the prediction result to a utility locator; and presenting the at least a portion of the location prediction to a user at the locator.

17. The method of Claim 16, wherein the collected data is at least one of multifrequency electromagnetic signal data, image data, or communication signal data.

18. The method of Claim 17, wherein collecting the at least one of of multifrequency electromagnetic signal data and communication signal data comprises receiving the data from at least one of a locator, Sonde, transmitting antenna, receiving antenna, transceiver, inductive clamp, electrical clip, or a satellite system.

19. The method of Claim 17, wherein image data is collected from a camera or imaging element.

20. The method of Claim 16, wherein training data further includes sensor data.

21. The method of Claim 16, wherein training data further includes mapping data.

22. The method of Claim 21, wherein mapping data includes at least one of depth or orientation data.

23. The method of Claim 16, wherein training data further includes fiber optic location data.

24. The method of Claim 16, wherein training data further includes one or more of image data, current and / or voltage data, even and odd harmonics data, active and / or passive signal data, and spatial relationship data.

25. The method of Claim 16, wherein training data further includes one or more of phase data and phase difference data.

26. The method of Claim 16, wherein training data further includes other data.

27. The method of Claim 26, wherein other data comprises one or more of observed data, user classification data, and ground truth data.

28. The method of Claim 27, wherein ground truth data comprises one or more of ownership data, manufacturer data, connection data, utility box or junction data, and obstacle data.

29. The method of Claim 16, wherein training data may be processed and classified in realtime or near real-time, or stored and post-processed in a cloud network.

30. The method of Claim 16, further comprising classifying the collected data by determining at least one of a utility type, electrical characteristics type, connection type, asset type,manufacturer type, ownership type, location type, direction type, right of way type, or damaged asset type.

31. The method of Claim 16, wherein presenting prediction data to a user comprises an output element including one or more of a visual display, a speaker or other sound producing element, and a vibration or other tactile producing element.

32. The method of Claim 16, wherein predicted data may include visually displayed mapping data.

33. A method for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: collecting utility location data ("collected data") from a plurality of sources; using the collected data alone or in combination with user predefined classifiers as training data; providing the training data to at least one neural network to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al); collecting utility data to be used for a location prediction ("prediction data"); wirelessly transmitting the prediction data and the location prediction model to at least one of a smartphone, laptop, PC, or other wireless device ("remote device"); determining a location prediction result on the remote device using the prediction data and the location prediction model; wirelessly transmitting at least a portion of the prediction result to a utility locator and or / a cable drum-reel; and presenting the at least a portion of the location prediction to a user at the locator and / or the cable drum-reel.

34. The method of Claim 33, wherein the collected utility location prediction data is also used as training data.

35. A method for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: collecting utility location data ("collected data") from a plurality of sources; using the collected data alone or in combination with user predefined classifiers as training data; wirelessly transmitting the training data to at least one of a smartphone, laptop, PC, or other wireless device ("remote device"); providing the training data to at least one neural network to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al); providing the training data to at least one neural network on the remote device to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al); collecting utility data to be used for a location prediction ("prediction data"); determining a location prediction result on the remote device using the prediction data and the location prediction model; wirelessly transmitting at least a portion of the prediction result to a utility locator and or a cable drum-reel; and presenting the at least a portion of the location prediction to a user at the locator and / or the cable drum-reel.

36. A method for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: collecting utility location data ("collected data") from a plurality of sources; using the collected data alone or in combination with user predefined classifiers as training data; providing the training data to at least one neural network on a locator and / or a cable drumreel to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al);collecting utility data to be used for a location prediction ("prediction data";) wirelessly transmitting the prediction data and the location prediction model to at least one of a smartphone, laptop, PC, or other wireless device ("remote device"); wirelessly relaying the prediction data from the remote device to the a cloud server ("the Cloud"); determining a location prediction result in the Cloud using the prediction data and the location prediction model; wirelessly transmitting at least a portion of the prediction result to the remote device; wirelessly transmitting at least a portion of the prediction result from a remote device to a locator and / or a cable drum-reel; and presenting the at least a portion of the location prediction to a user at the locator and / or a cable drum-reel.

37. A method for locating and mapping buried utilities using Artificial Intelligence (Al), comprising: collecting utility location data ("collected data") from a plurality of sources; using the collected data alone or in combination with user predefined classifiers as training data; collecting utility data to be used for a location prediction ("prediction data"); wirelessly transmitting the training data and the prediction data to at least one of a smartphone, laptop, PC, or other wireless device ("remote device"); relaying the training data and the prediction data to a cloud server ("the Cloud"); providing the training data to at least one neural network in the Cloud to create a location prediction model by processing the training data using Deep Learning performed by Artificial Intelligence (Al); processing the prediction data with the prediction model to determine a prediction result; wirelessly transmitting at least a portion of the prediction result to a utility locator and / or a cable reel-drum; and presenting at least a portion of the location prediction result received by the utility locator and / or the cable reel -drum to a user.

38. The method of Claim 37, wherein the remote device comprises the cable drum-reel.

Images