Systems and methods for monitoring vehicles - Patents.com

Abstract

The disclosure provides, in one aspect, a computer-implemented method for monitoring current usage of a vehicle in real time based on historical vehicle usage, the method including obtaining historical vehicle data for a vehicle indicative of previous vehicle usage, generating a historical baseline using the historical vehicle data to characterize historical usage of the vehicle, assessing current usage of the vehicle based on the historical baseline, and generating an alert based on the assessment.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Application No. 17 / 461,637, filed August 30, 2021. The disclosure of the prior application is considered part of (and is incorporated by reference into) the disclosure of this application.

[0002] (Field) The present disclosure relates generally to monitoring vehicles, more specifically to monitoring vehicles based on historical vehicle data, and even more specifically to monitoring and classifying vehicle locations based on historical vehicle routes. [Background technology]

[0003] (background) There are various multi-sensor systems that capture and represent the various behaviors exhibited by a vehicle. For example, a speedometer and an accelerometer represent the speed and acceleration of a vehicle, respectively. Vehicle navigation systems such as the Global Positioning System (GPS) and the Inertial Navigation System (INS) can characterize the geographic position or relative vehicle location of a vehicle, respectively. Other sensors and systems such as cameras, LiDAR, and RADAR can provide enhanced capabilities to a vehicle to detect cars, people, or other objects in the vicinity of the vehicle.

[0004] However, it remains desirable to develop further improvements and advances in connection with classifying, categorizing, monitoring, or assessing vehicles to overcome shortcomings of known techniques and to provide additional advantages.

[0005] This section is intended to introduce various aspects of the art that may be related to the present disclosure. The discussion is believed to help provide a framework to facilitate a better understanding of certain aspects of the present disclosure. As such, it should be understood that this section should be read in this light, and not necessarily as admissions of prior art. Summary of the Invention [Means for solving the problem]

[0006] The following are examples of systems and methods for classifying vehicle locations according to the present disclosure.

[0007] According to one aspect, the present disclosure provides a computer-implemented method for monitoring current usage of a vehicle in real time based on historical vehicle usage, the method including obtaining historical vehicle data for a vehicle indicative of previous vehicle usage, generating a historical baseline using the historical vehicle data to characterize historical usage of the vehicle, assessing current usage of the vehicle based on the historical baseline, and generating an alert based on the assessment.

[0008] According to an exemplary embodiment, the historical baseline comprises a number of geographic locations previously traveled by the vehicle.

[0009] According to an example embodiment, assessing the current usage of the vehicle against the historical baseline includes assessing the current vehicle location against the historical baseline.

[0010] According to an example embodiment, assessing the current vehicle location against the historical baseline further includes assessing the current vehicle location against a threshold criteria.

[0011] According to an exemplary embodiment, the threshold criterion is a maximum distance threshold, and assessing the current vehicle location further includes assessing the current vehicle location as unknown when the distance between the current vehicle location and the historical baseline exceeds the maximum distance threshold.

[0012] According to an example embodiment, the historical baseline comprises corresponding vehicle metadata associated with locations previously traveled by the vehicle.

[0013] According to an exemplary embodiment, the historical baseline comprises a number of data elements, each element associated with a geographic region and encoded with a corresponding geographic location previously traveled by the vehicle.

[0014] According to an example embodiment, each of the plurality of data elements comprises an indication of traffic density based on a percentage of a corresponding geographic location encoded with the data element.

[0015] According to an exemplary embodiment, the geographic regions correspond to hexagons.

[0016] In accordance with an exemplary embodiment, the historical baseline further comprises a bounding region for bounding the historical known vehicle locations from the historical unknown vehicle locations.

[0017] According to one aspect, the disclosure provides a non-transitory computer-readable medium having instructions stored thereon that, when executed by a computing device, cause the computing device to perform a method including obtaining a current vehicle location for a vehicle from a navigation system communicatively coupled to the computing device, comparing the current vehicle location to a historical baseline comprising previous locations traversed by the vehicle, determining a current vehicle location status based on the comparison, and issuing an alert if the current vehicle location status is unknown.

[0018] According to an exemplary embodiment, the current vehicle location status is unknown if the distance between the current vehicle location and a previous location traveled by the vehicle exceeds a threshold criterion.

[0019] According to an exemplary embodiment, the threshold criterion is the maximum distance between the current vehicle location and the nearest previous location traveled by the vehicle.

[0020] In accordance with an exemplary embodiment, the historical baseline further comprises a bounding region for bounding the historical known vehicle locations from the historical unknown vehicle locations.

[0021] According to one aspect, the present disclosure provides a system for monitoring current usage of a vehicle based on historical vehicle usage, the system comprising: a processor communicatively coupled to a navigation system for obtaining a current vehicle location for the vehicle; a memory communicatively coupled to the processor and having a historical baseline stored thereon, the historical baseline comprising previous locations traversed by the vehicle; and a display communicatively coupled to the processor and configured to output a current vehicle location status based on comparing the current vehicle location to the historical baseline.

[0022] According to an exemplary embodiment, the processor is configured to update the historical baseline based on the current vehicle location.

[0023] According to an exemplary embodiment, the display is configured to display the historical baseline as a plurality of hexagons, each hexagon corresponding to a geographic area that is encoded along with corresponding previous locations traveled by the vehicle.

[0024] According to an exemplary embodiment, the previous locations traveled by the vehicle correspond to previous locations traveled by multiple vehicles.

[0025] Embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying figures. [Brief description of the drawings]

[0026] [Figure 1] FIG. 1 is a schematic diagram of a road map illustrating three different driving routes followed by a vehicle equipped with a global positioning system to obtain geolocation data for the vehicle.

[0027] [Diagram 2] FIG. 2 is the road map of FIG. 1 overlaid with GPS geolocation data obtained for three different vehicle routes.

[0028] [Diagram 3] FIG. 3 is the diagram of FIG. 2 further including a rectangular bounding region for bounding the known location from the unknown location.

[0029] [Figure 4] FIG. 4 is the diagram of FIG. 2 further including a plurality of hexagons for defining a reference line and a bounding region that bounds the known location from the unknown location.

[0030] [Diagram 5] FIG. 5 is the schematic diagram of FIG. 2 further including a number of hexagons for defining reference lines with only known locations.

[0031] [Figure 6] FIG. 6 is a simplified diagram of FIG. 5 in which the geographic locations have been removed from the diagram to depict only the reference lines overlaid on the road map.

[0032] [Figure 7] FIG. 7 is a diagram of FIG. 6 in which the hexagons have modified line thickness based on the number of geographic locations that correspond to their respective locations.

[0033] [Figure 8A] FIG. 8A is a diagram illustrating a location assessment for a vehicle located at a first location outside the bounded area depicted in FIG.

[0034] [Figure 8B] FIG. 8B is a diagram illustrating one embodiment for displaying a route of known locations based on distance threshold criteria for a vehicle traveling to the first location illustrated in FIG. 8A.

[0035] [Figure 8C]FIG. 8C is a diagram illustrating one embodiment for displaying a route of known and unknown locations based on bounded area criteria for a vehicle traveling to the first location shown in FIG. 8A.

[0036] [Figure 9A] FIG. 9A is a diagram illustrating a location assessment for a vehicle located at a second location outside the bounded area depicted in FIG.

[0037] [Figure 9B] FIG. 9B is a diagram illustrating one embodiment for displaying a route of a known location based on a distance threshold criterion for a vehicle traveling to the second location illustrated in FIG. 9A.

[0038] [Figure 10A] FIG. 10A is a diagram illustrating a location assessment for a vehicle located at a third location outside the bounded area depicted in FIG.

[0039] [Figure 10B] FIG. 10B is a diagram illustrating one embodiment for displaying routes of known and unknown locations based on distance threshold criteria for a vehicle traveling to the third location illustrated in FIG. 10A.

[0040] [Figure 11] FIG. 11 is a graphical representation of one embodiment of a reference line and rectangular bounding region generated in accordance with the present disclosure and overlaid on a map of Ann Arbor, Michigan.

[0041] [Figure 12] FIG. 12 is a graphical representation of one embodiment of a reference line with hexagons and an irregular circular shaped bounding region generated in accordance with the present disclosure and overlaid on a map of Ann Arbor, Michigan.

[0042] [Figure 13] FIG. 13 is a block diagram of an example computing device or system for implementing a vehicle location classification system and method according to this disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0043] Throughout the drawings, at times, only one or less than all instances of an element visible in the figure are designated by a leader line and reference letter for simplicity only and to avoid clutter, however, in such cases, it should be understood that every other instance is likewise designated and encompassed by the corresponding description, in accordance with the corresponding description.

[0044] (Detailed Description) The vehicle monitoring systems and methods disclosed herein generally utilize historical driving data and / or driving patterns associated with one or more vehicles and one or more of their individual drivers to monitor and assess current vehicle behavior. In certain example aspects, the systems and methods disclosed herein generate a baseline based on data indicative of the historical driving data. For example, the systems and methods disclosed herein may generate a baseline of "known" locations based on the historical driving routes of the vehicle for use in classifying, categorizing, monitoring, and / or assessing, or otherwise characterizing the current behavior, status, or location of the vehicle. For example, the current vehicle location may be assessed against the baseline of "known" locations to determine whether the current vehicle location is known, unknown, or another type of status. The determined vehicle location classification may then be utilized for additional purposes, such as updating the baseline of known locations and / or providing an alert when the vehicle is in an unknown location. Such an alert may be provided directly to the driver, to the vehicle owner on a remote device, to a third party, etc. Such alerts may be leveraged to take further action, including, but not limited to, monitoring the vehicle's current location, providing routing instructions to the nearest known location, providing the driver with a warning about going too far from the known location, providing assistance to the driver, or other corrective action as may be necessary. Additionally, other vehicle data, including, but not limited to, vehicle speed, vehicle acceleration, cabin temperature, fuel economy, etc., may also be assessed against historical metadata for the corresponding vehicle location to evaluate current metrics differently against historical metrics for a given location, or to evaluate current metrics under different contexts, including, but not limited to, for historical values ​​for seasons, times of day, or days of the week.

[0045] Generating a baseline of known locations for a vehicle or fleet is based on applying machine learning algorithms, pattern recognition algorithms, or other statistical modeling techniques to data indicative of historical vehicle or driving routes for the vehicle. Such historical driving route data can be generated or obtained in several ways. For example, a vehicle may be equipped with a vehicle navigation or positioning system, such as a Global Positioning System (GPS), or other system known in the art, to obtain vehicle location data as a function of time. One example of vehicle location is the geographic location (e.g., latitude and longitude, or latitude, longitude, and elevation) of the vehicle for a given time point. Thus, while a vehicle navigation or positioning system is in use, it can generate multiple data indicative of the vehicle's geographic location, which may collectively describe the vehicle or driving route. This process can be repeated across several different vehicle journeys to generate multiple vehicle routes, which collectively provide a historical record of the vehicle or driving route for a given vehicle. For example, geographic location data for a vehicle may be generated over the course of a year to provide historical vehicle route data for that year of driving the vehicle. This process can also be repeated for the fleet to generate data indicative of historical vehicle routes for multiple vehicles. An embodiment of the present disclosure includes dynamically updating data indicative of historical driving routes based on real-time collection of the vehicle's current geographic location or position data while in use. For example, the current vehicle location may be classified as unknown because the vehicle has never traveled to the current vehicle location historically, or has traveled to the current vehicle location very infrequently. However, as the vehicle travels into new or previously unknown areas, the baseline may be updated accordingly.In one embodiment, the baseline may be updated using pattern recognition algorithms or statistical modeling techniques to provide an indication that previously unknown locations are now known and considered part of the baseline based on obtaining new geolocation data that indicates vehicles traveling to new areas and locations and / or vehicles traveling more frequently into areas and locations that were previously "unknown."

[0046] 1 and 2 are illustrative examples of obtaining vehicle data for a global positioning system (GPS) equipped vehicle 140. FIG. 1 is a schematic diagram of a road map 100, including a road 150. The vehicle 140 has taken three separate journeys over the road 150, as indicated by a first route 110, a second route 120, and a third route 130. The vehicle 140 has traveled the first route 110 and the second route 120, which start at point A and end at point C. The vehicle has traveled the third route 130, which start at point B and end at point C. FIG. 2 illustrates the corresponding geographic location obtained by the GPS equipped on the vehicle 140. Specifically, a plurality of first route geographic locations 112, marked as triangles, illustrate geographic locations obtained by the GPS system while the vehicle 140 traveled the first route 110, a plurality of second route geographic locations 122, marked by circles, illustrate geographic locations obtained by the GPS system while the vehicle 140 traveled the second route 120, and a plurality of third route geographic locations 132, marked by stars, illustrate geographic locations obtained by the GPS system while the vehicle 140 traveled the third route 130.

[0047] Vehicle 140 may be equipped with additional sensors and instruments, including, without limitation, speedometers, accelerometers, cabin sensors such as temperature and air flow sensors, wireless capabilities such as WiFi, charging stations such as through a USB connection, entertainment and / or infotainment systems, and fuel level indicators (gas, electric, hybrid, or otherwise), which may generate and provide additional metadata characterizing the behavior or status of the vehicle and may be further associated with the vehicle's corresponding geographic location or position. Historical driving route data for the vehicle may also be subdivided, categorized, or tagged with metadata based on other categories that identify a particular purpose or use of the vehicle, such as the type of driver (e.g., parent, friend, child), a particular use of the vehicle (e.g., work route, leisure driving, running errands), time of year (e.g., a particular month or season), or driving on a particular day of the week. Data indicative of historical vehicle or driving routes for a vehicle or fleet may be input into a model, such as a machine learning algorithm, pattern recognition algorithm, or statistical model, to generate a baseline associated with the locations, characteristics, traits, or classifications of the vehicles associated with the historical vehicle or driving route data. In other words, the model is used to characterize or aggregate historical behavior for vehicles, fleets, or their corresponding drivers based on their corresponding historical vehicle data. For example, statistical modeling may be applied to data indicative of historical vehicle or driving routes for a given vehicle or fleet to provide insight into the past behavior of the vehicles and / or their individual drivers. In one embodiment, a statistical model for traffic density is applied to the historical vehicle data to generate a baseline of known locations traveled by the vehicles. In this regard, statistical modeling is applied to the historical vehicle data to generate a baseline that classifies geographic locations associated with historical vehicle or driving routes for a given geographic area into known, unknown, or another status. In one embodiment, statistical modeling of traffic density is based on how frequently vehicles travel through a particular geographic location or area.For example, traffic density for a given location can be assigned a value based on the total number of trips taken by a vehicle versus the number of times the vehicle traverses a particular geographic location or area. The size of a given geographic area can be based on the desired granularity of the analysis. For example, traffic density may be assessed in terms of an area the size of a city block, or in terms of a larger or smaller area, depending on the desired granularity of the analysis. Additionally, historical data may be updated in real-time as vehicle geolocation data is obtained during vehicle use. In such real-time scenarios, statistical models for traffic density may be applied to the actual data to generate baselines that are more responsive to the vehicle's current and / or immediate location.

[0048] The traffic density values ​​for each geographic location and / or area can be further analyzed to determine whether a given location is "known" due to a relatively higher frequency of vehicle runs versus "unknown" when there are relatively fewer vehicle runs or no vehicle runs for the corresponding geographic location or area. In one embodiment, the statistical model generates traffic density values ​​for a given geographic location or area that are normalized to a value between 0 and 1 (0 represents the absence of traffic density and 1 represents the highest traffic density for the geographic location or area observed by the historical vehicle data). In one embodiment, a "known" location corresponds to a traffic density value that exceeds a minimum threshold. Baselines may be generated for single vehicles or fleets, and may be generated based on different aspects or subsets of historical data, characteristics or metadata associated with historical vehicle or driving route data, such as baselines of known vehicle locations generated for a particular driver or type of driver, for a particular use of a vehicle, or for other behaviors.

[0049] FIG. 3 illustrates one embodiment of a reference line of known locations generated in accordance with the present disclosure, where the reference line is defined by a bounding area 160. As illustrated in FIG. 3, the bounding area 160 is a rectangular area that bounds all geographic locations 112, 122, and 132 illustrated in FIG. 2. Accordingly, the interior of the bounding area 160 provides a reference line of known locations traversed by the vehicle 140 that is further bounded from areas external to the bounding area 160 that are unknown or otherwise unclassified. However, in accordance with the present disclosure, the bounding area is not limited to a particular shape. For example, the bounding area may be a polygon, such as, but not limited to, a hexagon, different types of rectangles, or other shapes, may include multiple sub-areas, and / or may have a more organically defined shape that mirrors roads, highways, and other driving infrastructure while also excluding non-driving areas, such as mountains, rivers, or other geographic features that may be difficult or impossible to traverse with a vehicle. In one embodiment, the bounding region is based on maximum and minimum longitude and latitude determined from underlying historical vehicle data.

[0050] FIG. 4 illustrates an embodiment of a reference line of known locations generated in accordance with the present disclosure, where the reference line is defined by a bounding area that includes a plurality of hexagons 170. As illustrated in FIG. 4, the plurality of hexagons 170 collectively encompass all of the geographic locations 112, 122, and 132 illustrated in FIG. 2. Similar to the rectangular bounding area 160 illustrated in FIG. 3, the plurality of hexagons collectively form a rectangular shape based on the maximum latitude, minimum latitude, maximum longitude, and minimum longitude of the plurality of geographic locations 112, 122, and 132. Accordingly, the plurality of hexagons 170 each encompasses none of the geographic locations 112, 122, and / or 132, or one or more of them. Collectively, however, the plurality of hexagons 170 provide a reference line of all known locations traversed by the vehicle 140 that are bounded from areas external to the plurality of hexagons 170 that are unknown or otherwise unclassified.

[0051] 5 illustrates one embodiment of a reference line of a known location generated in accordance with the present disclosure, in which the reference line is defined by a bounding area that includes a plurality of hexagons 170, each hexagon including at least one geographic location 112, 122, and / or 132. Accordingly, the more irregularly shaped reference line of the hexagons 170 depicted in FIG. 5 closely mirrors the road 150, more accurately bounding the area traveled by the vehicle 140 from the area not traveled by the vehicle 140. FIG. 6 further illustrates the reference line of the hexagons 170 depicted in FIG. 5, but removing the corresponding geographic locations.

[0052] In some embodiments, characteristics of elements used to depict or illustrate the reference lines may be modified based on the underlying historical vehicle data or metadata associated with the corresponding geographic location. For example, elements such as lines, dots, hexagons, or other shapes used to illustrate the reference lines may be enhanced with darker colors or shading, and / or with thicker lines, etc., to provide an indication of the degree of the underlying historical data or metadata associated with the corresponding geographic location relative to other geographic locations. For example, a hexagon having a darker and / or thicker line may indicate that a geographic location associated with the particular hexagon may have a higher frequency of journeys or traffic density relative to other hexagons in the reference line, and / or the hexagon may include relatively more geographic locations associated within the area represented by the hexagon that have been traveled by one or more vehicles associated with the underlying historical vehicle data. For example, FIG. 7 illustrates one embodiment of a known location baseline generated in accordance with the present disclosure, where the baseline is defined by a bounding area that includes a plurality of hexagons 170, each hexagon including at least one geographic location 112, 122, and / or 132, such as those illustrated in FIG. 7 is further modified with thicker lines to provide an indication of traffic density, whereby the thicker lines provide an indication that a particular hexagon includes a greater number of geographic locations 112, 122, and / or 132. For example, the lines for hexagon 170a are thicker than the lines for hexagon 170b, thereby providing an indication of the greater number of geographic locations 112, 122, and / or 132 found in hexagon 170a relative to 170b.

[0053] In an embodiment, each element of the reference line may be encoded with one or more geographic locations of the known location, including being encoded with metadata associated with the corresponding one or more geographic locations. In an embodiment, the characteristics of the elements of the reference line may be extended to provide an indication of a higher vehicle travel speed and / or a higher vehicle acceleration associated with the corresponding geographic location. In an embodiment, the elements used to depict or illustrate the reference line are hexagons. In an embodiment, the size of the elements used to depict or illustrate the reference line is modified to achieve a desired granularity or accuracy of the data. For example, a smaller hexagon will necessarily occupy a smaller geographic area than a relatively larger hexagon. As a result, the reference line will include a greater number of smaller hexagons and therefore more granular data, advantageously providing a more precise insight into a given area versus a relatively larger hexagon, which will necessarily include geographic locations distributed over a larger area.

[0054] According to the present disclosure, the current vehicle location, status, or other characteristics and / or behavior of the vehicle / driver may be assessed against a baseline to provide insight into the current vehicle location, driving patterns, or other behavior exhibited by the vehicle and / or driver. For example, the current vehicle location may be assessed against a baseline of known locations generated from historical vehicle data to determine whether the current vehicle location is in a known or unknown location. Assessing whether the current vehicle location is known or unknown can provide invaluable insight into the current vehicle driving patterns. For example, when the vehicle is in an unknown location, this may provide an indication that the driver is lost, on a wrong road, in need of assistance, requesting directions to return to a known location, taking a less desirable route (e.g., slower, longer, more fuel consumption), straying into an area that should be avoided, straying into an area that is not permitted to be entered, the vehicle has been stolen, etc. Assessing whether the current vehicle location is known or unknown against a baseline can be accomplished in several ways.

[0055] 8-10 illustrate examples of determining and displaying a current vehicle location according to the present disclosure. FIG. 8A depicts a baseline of a hexagon 170, like that depicted in FIG. 7, and further includes a vehicle 140 traveling from location B through multiple geographic locations 182 to a location D outside the baseline of the known location. The assessment of the vehicle's current location at location D is based on comparing the distance of the vehicle 140 from neighboring hexagons. In particular, distances D1, D2, D3, D4, and D5, which represent the distances between the vehicle 140 and the centers of the respective hexagons 171, 172, 173, 174, 175, are compared to a threshold distance D. TH In this example, the distance between the vehicle 140 and each of the five hexagons 171, 172, 173, 174, 175 is assessed against a threshold distance D THand thus, this position D constitutes a known location. However, whether the current location constitutes a known location relative to the baseline can be based on a number of criteria, including, but not limited to, the total number of hexagons within a threshold distance of the vehicle, the distance from the vehicle to the nearest hexagon, and / or the average distance from the vehicle to all hexagons in the baseline. Additionally, hexagons can be weighted based on underlying characteristics. For example, hexagons with higher traffic density, such as hexagons 174 and 175, may be considered more deeply in determining whether the current location is known or not.

[0056] FIG. 8B depicts an embodiment of a route 180D according to the present disclosure. The route 180D includes line segments illustrating the path of the vehicle 140 along multiple geographic locations 182 from location B to location D. In particular, FIG. 8B illustrates that the route 180D includes only known locations, including solid line segments indicating the path traveled. In an embodiment, an example route such as route 180D may be presented, for example, on a display associated with the vehicle, remotely via electronic communication such as email or text message, via a software application such as a dashboard app, or provided to another device such as a tablet, computer, remote server / database, etc. Properties of the line segments or other visual elements used to illustrate a route such as route 180D may be modified to illustrate aspects of the underlying data. For example, the line thickness, color, or other properties of the line segments may be varied to provide an indication of speed, acceleration, fuel economy, traffic density, whether the associated geographic location is known or unknown, or other properties of the metadata and / or historical metadata according to the present disclosure.

[0057] FIG. 8C depicts another embodiment of illustrating a path 180D based on a threshold criterion according to the present disclosure. In this embodiment, the determination of whether a position D is known or unknown is based on whether the position D is within the reference line of the hexagon 170. As illustrated in FIG. 8A, the position D is located outside the reference line of the hexagon 170, which indicates a known location. As a result, in this embodiment, a geographic location outside the reference line of the hexagon 170, such as the position D, is considered unknown. Thus, FIG. 8C differs from FIG. 8B in that the path 180D includes a first segment 180D1 illustrated as a solid line segment indicating a vehicle path traversed a known geographic location within the reference line, and a second segment 180D2 illustrated as a dashed line segment indicating a vehicle path traversed an unknown geographic location outside the reference line.

[0058] FIG. 9A depicts a baseline of a hexagon 170, like the one depicted in FIGS. 7 and 8A, and further includes a vehicle 140 traveling from location B through multiple geographic locations 182 to a location E outside the baseline of known locations. An assessment of the vehicle's current location at location E is based on comparing the distances of the vehicle 140 from neighboring hexagons. In particular, distances D6, D7, D8, D9, and D10, which represent the distances between the vehicle 140 and the centers of the respective hexagons 175, 174, 171, 172, 173, are compared to a threshold distance D TH In this example, the distances between the vehicle 140 and each of the five hexagons 175, 174, 171, 172, 173 are all assessed against a distance value D TH Therefore, this location E may not constitute a known location, depending on the criteria. For example, the criteria may be such that the vehicle 140 is within a threshold distance D of at least one nearby known location. TH If the criteria require that the vehicle 140 is within a threshold distance D of at least five nearby known locations, then the location E constitutes a known location. TH If we require that it is within, then position E constitutes an unknown location.

[0059] 9B depicts one embodiment of a path 180E according to the present disclosure. The path 180E includes line segments illustrating a path of the vehicle 140 along a plurality of geographic locations 182 from location B to location E. In particular, FIG. 9B illustrates the path 180E, including solid line segments indicating the path traveled, as the current location E (including associated geographic locations leading up to location E) is within a threshold distance D of a known location. TH 1 illustrates the inclusion of only known locations according to associated threshold criteria, such as whether or not the known locations are within

[0060] FIG. 10A depicts a baseline of a hexagon 170, like those depicted in FIGS. 7, 8A, and 9A, and further includes a vehicle 140 traveling from location B through multiple geographic locations 182 to a location F outside the baseline of known locations. An assessment of the vehicle's current location at location F is based on comparing the distances of the vehicle 140 from neighboring hexagons. In particular, distances D11, D12, and D13, which represent the distances between the vehicle 140 and the centers of the three nearest individual hexagons 174, 171, 172, are compared to a threshold distance D TH In this example, the distances between the vehicle 140 and each of the three nearest hexagons 174, 171, 172 are all assessed against a threshold distance D TH , and therefore this position F constitutes an unknown location since it is too far from any known location encompassed by the reference lines of hexagon 170.

[0061] 10B depicts one embodiment of a route 180F according to the present disclosure. The route 180F includes line segments illustrating a path of the vehicle 140 along a plurality of geographic locations 182 from location B to location F. In particular, FIG. 10B illustrates that the route 180F is aligned with the baseline threshold distance D TH A first segment 180F1 is illustrated as a solid line segment showing a vehicle path traveled through a known geographic location within the TH and a second segment 180F2, shown as a dashed line segment indicating the vehicle path traveled beyond the unknown geographic location.

[0062] In some embodiments, the current vehicle location is unknown when it exceeds a minimum distance from the nearest known location. In some embodiments, the minimum distance is at least 500 meters. In some embodiments, the current vehicle location is unknown when it is located within a reference-line hexagon having a traffic density value below a minimum threshold. In some embodiments, the current vehicle location is unknown when it is farther than a minimum radial distance from the reference-line geographic location or hexagon having the highest traffic density. In some embodiments, the current vehicle location is unknown if it is not located within an edge of a bounding region. Other characteristics of the current vehicle location or vehicle behavior may also be assessed against metadata associated with corresponding geographic locations within the reference-line, such as assessed against metadata related to speed, acceleration, or fuel level associated with the reference-line geographic location.

[0063] According to the present disclosure, embodiments of systems and methods for monitoring vehicles may take subsequent steps in response to identifying a vehicle in an unknown location or in response to analyzing the vehicle's current state (e.g., speed, temperature, fuel economy, etc.) against historical metadata for current or nearby known locations. For example, the systems and methods disclosed herein include providing a real-time alert indicating the vehicle is currently located in an unknown location. Such an alert may be issued to the driver, a remote user, or a third party and may be represented visually, textually, or audibly, for example, on a display or speaker system associated with the vehicle, via electronic communication such as email, text message, or voicemail message, represented via a software application such as a dashboard app, or provided to another device such as a tablet, computer, remote server / database, etc. Advantageously, the alert may be adaptive or dynamic, since the historical vehicle data and baselines generated therefrom may also dynamically change based on the current location, thereby modifying the baselines of the known locations or other driving behaviors being modeled. Such dynamic alerts thus provide a real-time advantage over static alerts that may otherwise need to be predefined or set by a user in advance.Example use cases for the alerts include, without limitation, monitoring whether a particular driver, such as a teenager, student driver, or novice driver, drives a vehicle to an unknown or restricted location, as may be the case with respect to an early stage driver who may be restricted from driving on a highway; monitoring whether the vehicle exceeds a speed limit associated with the known location metadata; monitoring whether traffic is slow based on historical speed limits associated with the known location metadata; determining whether the current driver has any associated restrictions (such as number of passengers) and obtaining data from corresponding sensors in the vehicle and assessing accordingly; monitoring the temperature of the vehicle against historical temperatures associated with the known location metadata; monitoring the fuel economy of the vehicle against historical fuel economy associated with the known location metadata; and monitoring whether delivery vehicles in a fleet of delivery vehicles are following a particular route, such as a route designed to optimize delivery time and / or minimize gas usage.

[0064] 11 and 12 illustrate two different baselines and bounding regions in accordance with the present disclosure that are generated based on data collected from two vehicles over the course of a year driving in and around Ann Arbor, Michigan. The baselines, bounding regions, and any associated metadata may then be used in accordance with the disclosures herein to monitor or otherwise assess the vehicles while in use.

[0065] FIG. 11 illustrates one embodiment of a reference line generated in accordance with the present disclosure, where the reference line 210 is overlaid on a map 200 of Ann Arbor, Michigan, and further includes known vehicle locations bounded by a rectangular bounding region 260. Thus, in addition to the more precise known locations identified by the reference line 210, the bounding region 260 bounds an interior region 262 as "known" from an exterior region 264 as "unknown". In this embodiment, the reference line 210 was generated based on applying a statistical model of traffic density to one year's worth of vehicle location data for two vehicles operating in and around Ann Arbor. In accordance with the present disclosure, the reference line 210 and / or the bounding region 260 may be represented in any number of ways. For example, as illustrated in FIG. 12, the reference line 210 resembles a line indicating different roads traveled by the vehicle, while the bounding region 260 is a rectangle bounding maximum and minimum geolocation coordinates from the underlying historical vehicle data. The thickness, color, shade, or darkness of the reference line may be generated to represent characteristics of the underlying historical vehicle data. For example, a particularly thick or dark line in the reference line may indicate that the vehicle has traveled that area or portion of the route more frequently than other areas. FIG. 12 illustrates an embodiment of a known vehicle location reference line 310 generated based on the same underlying data showing the historical vehicle and driving route used for FIG. 11, but rather the reference line 310 includes multiple elements 370, i.e., hexagons, within an irregular circular shaped bounding area 360. Each hexagon 370 represents an area within the geographic region of Ann Arbor that may include no geographic locations or may include one or more geographic locations associated with the underlying historical data. The characteristics of the hexagons may also be modified to provide an indication of the degree of underlying behavior or characteristics of the vehicle associated with the corresponding geographic location that is encompassed by the hexagon. For example, the darker shading and density of hexagons 370, particularly as visible in the eastern portion of map 300, provides an indication of additional characteristics of known vehicle locations, in this particular case representing a relative increase in traffic density or vehicle frequency.In other words, the darker shaded portions of the reference line 310 provide an indication of known locations that are more frequently traveled by vehicles relative to other geographic locations represented by the underlying historical vehicle data. Conversely, the lighter shaded, less densely filled hexagons observed to the west of the reference line 310 provide an indication of known locations that are less frequently traveled by vehicles relative to other geographic locations captured by the underlying historical vehicle data. In one embodiment, the multiple geographic locations represented by the reference line 310 are normalized to a value between 0 and 1 that indicates traffic density or frequency of traffic for a given geographic location.

[0066] In the example illustrated in FIG. 12, the irregular, circular-shaped bounding region 360 closely resembles the exterior of the reference line 310. In this regard, the bounding region 360 provides an improvement over the rectangular bounding region 260 illustrated in FIG. 11 because the bounding region 360 bounds the “known” interior 362 from the “unknown” exterior 364 based on distance from a plurality of hexagons 370, rather than based on minimum and maximum geographic locations, as in the rectangular bounding region 260. In this regard, the bounding region 360 more closely resembles the shape of the reference line 310, and advantageously provides a more accurate boundary of the “known” and “unknown” locations relative to the boundary of the “known” and “unknown” locations provided by the rectangular bounding region 260 illustrated in FIG. 11. The bounding region may also be based on geographic features, such as mountains, buildings, or other landmarks, and / or may more organically represent areas that a vehicle may be expected to traverse (or not) based on road and highway infrastructure. In some embodiments, interior portions of the bounding region may be identified as "unknown" locations if their geographic location does not meet certain criteria, e.g., not within a minimum distance of a known geographic location or area, etc. In some embodiments, the bounding region dynamically updates based on the vehicle's current location.

[0067] FIG. 13 is a block diagram of an example computerized device or system 1300 that may be used in implementing one or more aspects or components of an embodiment of a vehicle location classification system and method according to the present disclosure.

[0068] The computerized system 1300 may include one or more of a processor 1302, a memory 1304, a mass storage device 1310, an input / output (I / O) interface 1306, and a communication subsystem 1308. Additionally, the system 1300 may comprise multiple ones, such as multiple processors 1302 and / or multiple memories 1304. The processor 1302 may comprise one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information. These processing units may be physically located within the same device, or the processor 1302 may represent the processing functionality of multiple devices acting in conjunction. The processor 1302 may be configured to execute modules or otherwise perform functionality according to the modules through software, hardware, firmware, some combination of software, hardware, and / or firmware, and / or other mechanisms for configuring processing power on the processor 1302, and may include one or more physical processors during the execution of processor-readable instructions, processor-readable instructions, circuitry, hardware, storage media, or any other components.

[0069] One or more of the components or subsystems of the computerized system 1300 may be interconnected using one or more buses 1312 or in any other suitable manner.

[0070] The bus 1312 may be one or more of any type of several bus architectures, including a memory bus, a storage bus, a memory controller bus, a peripheral bus, or the like. The CPU 1302 may comprise any type of electronic data processor. The memory 1304 may comprise any type of system memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), synchronous DRAM (SDRAM), read only memory (ROM), combinations thereof, or the like. In one embodiment, the memory may include ROM for use at boot-up and DRAM for program and data storage for use while executing programs.

[0071] The mass storage device 1310 may comprise any type of storage device configured to store data, programs, and other information and make the data, programs, and other information accessible via the bus 1312. The mass storage device 1310 may comprise one or more of a solid state drive, a hard disk drive, a magnetic disk drive, an optical disk drive, or the like. In some embodiments, the data, programs, and other information may be stored remotely, for example, in the cloud. The computerized system 1300 may transmit information to and receive information from the remote storage device in any suitable manner, including over a network via the communications subsystem 1308 or via other data communications media.

[0072] The I / O interface 1306 may provide an interface to enable wired and / or wireless communication between the computerized system 1300 and one or more other devices or systems. For example, the I / O interface 1306 may be used to communicatively couple to a sensor, such as a camera or video camera. Additionally, additional or fewer interfaces may be utilized. For example, one or more serial interfaces (not shown), such as a Universal Serial Bus (USB), may be provided.

[0073] The computerized system 1300 may be used to configure, operate, control, monitor, sense, and / or regulate devices, systems, and / or methods according to the present disclosure.

[0074] The communications subsystem 1308 may provide for either or both transmitting and receiving signals via any form or medium of digital data communication, including a communications network. Examples of communications networks include local area networks (LANs), wide area networks (WANs), internal networks such as the Internet, and peer-to-peer networks such as ad-hoc peer-to-peer networks. The communications subsystem 1308 may include any component or collection of components for enabling communication via one or more wired and wireless interfaces. These interfaces include, but are not limited to, USB, Ethernet (e.g., IEEE 802.3), High Definition Multimedia Interface (HDMI), Firewire (e.g., IEEE 1394), Thunderbolt, and the like. TM ,Wifi TM (e.g., IEEE 802.11), WiMAX (e.g., IEEE 802.16), Bluetooth, or Near Field Communication (NFC), as well as GPRS, UMTS, LTE, LTE-A, and Dedicated Short Range Communications (DSRC). The communications subsystem 1308 may include one or more ports or other components (not shown) for one or more wired connections. Additionally or alternatively, the communications subsystem 1308 may include one or more transmitters, receivers, and / or antenna elements (none of which are shown).

[0075] The computerized system 1300 of Figure 13 is an example only and is not intended to be limiting. Various embodiments may utilize some or all of the components shown or described. Some embodiments may use other components not shown or described, but known to those of skill in the art.

[0076] In the preceding description, for purposes of explanation, numerous details are set forth to provide a thorough understanding of the embodiments. However, it will be apparent to one skilled in the art that these specific details are not required. In other instances, well-known electrical structures and circuits are shown in block diagram form in order not to obscure the understanding. For example, specific details are not provided about whether the embodiments described herein are implemented as a software routine, a hardware circuit, firmware, or a combination thereof.

[0077] An embodiment of the present disclosure can be represented as a computer program product stored in a machine-readable medium (also referred to as a computer-readable medium, a processor-readable medium, or a computer usable medium having computer-readable program code embodied therein). The machine-readable medium can be any suitable tangible, non-transitory medium, including magnetic, optical, or electrical storage media, including diskettes, compact disk read-only memories (CD-ROMs), memory devices (volatile or non-volatile), or similar storage mechanisms. The machine-readable medium can contain various sets of instructions, code sequences, configuration information, or other data that, when executed, cause a processor to perform steps in a method according to an embodiment of the present disclosure. Those skilled in the art will appreciate that other instructions and operations necessary to implement the described implementations can also be stored on the machine-readable medium. The instructions stored on the machine-readable medium can be executed by a processor or other suitable processing device and can interface with circuitry to perform the described tasks.

[0078] The above-described embodiments are intended to be examples only. Alterations, modifications, and variations may be effected to the particular embodiments by those of skill in the art without departing from the scope, which is defined solely by the claims appended hereto.

Claims

1. 1. A computer-implemented method for monitoring current usage of a vehicle in real time based on historical vehicle usage, the method comprising: obtaining historical vehicle data for the vehicle, the historical vehicle data indicating previous vehicle use; generating a historical baseline using the historical vehicle data that characterizes a historical use of the vehicle; and assessing a current usage of the vehicle based on the historical baseline; and generating an alert based on said assessment; and A method comprising:

2. The computer-implemented method of claim 1 , wherein the historical baseline comprises a plurality of geographic locations previously traversed by the vehicle.

3. The computer-implemented method of claim 2 , wherein assessing the current usage of the vehicle against the historical baseline comprises assessing a current vehicle location against the historical baseline.

4. The computer-implemented method of claim 3 , wherein assessing the current vehicle location against the historical baseline further comprises assessing the current vehicle location against a threshold criterion.

5. 5. The computer-implemented method of claim 4, wherein the threshold criterion is a maximum distance threshold, and assessing the current vehicle location further comprises assessing the current vehicle location as unknown when a distance between the current vehicle location and the historical baseline exceeds the maximum distance threshold.

6. The computer-implemented method of claim 2 , wherein the historical baseline comprises corresponding vehicle metadata associated with the plurality of locations previously traveled by the vehicle.

7. The computer-implemented method of claim 2 , wherein the historical baseline comprises a plurality of data elements, each element being associated with a geographic region and encoded with a corresponding geographic location previously traveled by the vehicle.

8. 8. The computer-implemented method of claim 7, wherein each of the plurality of data elements comprises an indication of traffic density based on a percentage of the corresponding geographic location encoded with the data element.

9. The computer-implemented method of claim 8 , wherein the geographic region corresponds to a hexagon.

10. The computer-implemented method of claim 2 , wherein the historical baseline further comprises a bounding region for bounding historical known vehicle locations from historical unknown vehicle locations.

11. A non-transitory computer readable medium having instructions stored thereon that, when executed by a computing device, cause the computing device to: obtaining a current vehicle location for the vehicle from a navigation system communicatively coupled to the computing device; comparing the current vehicle location to a historical baseline comprising previous locations traveled by the vehicle; determining a current vehicle location status based on the comparison; and issuing an alert if the current vehicle location status is unknown; and A non-transitory computer readable medium for carrying out a method comprising:

12. 12. The non-transitory computer readable medium of claim 11, wherein the current vehicle location status is unknown if a distance between the current vehicle location and the previous location traveled by the vehicle exceeds a threshold criterion.

13. The non-transitory computer readable medium of claim 12 , wherein the threshold criterion is a maximum distance between the current vehicle location and a nearest previous location traveled by the vehicle.

14. The non-transitory computer readable medium of claim 11 , wherein the historical baseline further comprises a bounding region for bounding historical known vehicle locations from historical unknown vehicle locations.

15. 1. A system for monitoring current usage of a vehicle based on historical vehicle usage, the system comprising: a processor communicatively coupled to a navigation system for obtaining a current vehicle location for the vehicle; a memory communicatively coupled to the processor and having a historical baseline stored thereon, the historical baseline comprising previous locations traversed by the vehicle; and a display communicatively coupled to the processor and configured to output a current vehicle location status based on comparing the current vehicle location to the historical baseline; A system comprising:

16. The system of claim 15 , wherein the processor is configured to update the historical baseline based on the current vehicle location.

17. 16. The system of claim 15, wherein the display is configured to display the historical baseline as a plurality of hexagons, each hexagon corresponding to a geographic area encoded with a corresponding previous location traveled by the vehicle.

18. The system of claim 15 , wherein the previous locations traveled by the vehicle correspond to previous locations traveled by a plurality of vehicles.

Images