Road network mapping using vehicle telematics data

Abstract

In example embodiments, methods and systems are provided, comprising: obtaining, via telematics systems of a plurality of vehicles, vehicle telematics data as the plurality of vehicles travel through one or more geographic regions; converting, from a computer processor, the vehicle telematics data into a geohash encoding format related to the one or more geographic regions; identifying, via the processor, a plurality of road intersections using the vehicle telematics data converted into the geohash encoding; identifying, via the processor, a plurality of road segments using the vehicle telematics data converted into the geohash encoding of the one or more geographic regions; and generating, via the processor, a road network map of the one or more geographic regions including the plurality of road intersections and the plurality of road segments using the vehicle telematics data converted into the geohash encoding.

Description

TECHNICAL FIELD

[0001] The technical field generally relates to vehicles, and more particularly to methods and systems for identifying road networks using telematics data from vehicles. BACKGROUND

[0002] Some vehicles today have telematics units that utilize vehicle telematics data. However, such vehicles can not always provide optimal use of vehicle telematics data.

[0003] Accordingly, it can be desirable to provide improved methods and systems for utilizing vehicle telematics data. Furthermore, other desirable features and characteristics of the present invention will become apparent from the subsequent detailed description and the appended claims, taken in conjunction with the accompanying drawings and this background. SUMMARY

[0004] According to an exemplary embodiment, a method is provided that includes obtaining, via telematics systems of a plurality of vehicles, vehicle telematics data as the plurality of vehicles travel through one or more geographic regions; converting, from a computer processor, the vehicle telematics data into a geohash encoding format related to the one or more geographic regions; identifying, via the processor, a plurality of road intersections using the vehicle telematics data converted into the geohash encoding; identifying, via the processor, a plurality of road segments using the vehicle telematics data converted into the geohash encoding for the one or more geographic regions; and generating, via the processor, a road network map of the one or more geographic regions including the plurality of road intersections and the plurality of road segments using the vehicle telematics data converted into the geohash encoding.

[0005] Also in an exemplary embodiment, obtaining the vehicle telematics data includes obtaining vehicle telematics data including vehicle location, vehicle heading, and vehicle speed for each of the plurality of vehicles; and the steps of identifying the plurality of road segments and identifying the plurality of road intersections via the processor includes using the vehicle telematics data converted into the geohash encoding to identify the plurality of road segments and identify the plurality of road intersections, respectively.

[0006] Also in an exemplary embodiment, the method further includes identifying, via the processor, pairs of consecutive telematics data points of the vehicle telematics data in which a change in heading is greater than a predetermined threshold, indicating a vehicle turn; and determining, via the processor, turn points for each pair of consecutive telematics points; wherein the steps of identifying the plurality of road segments and identifying the plurality of road intersections via the processor includes using the turn points to identify the plurality of road segments and identify the plurality of road intersections, respectively, via the processor.

[0007] Also in example embodiments, the step of determining turn points includes determining, via the processor, a turn point for each pair of consecutive telemetry points based on a linear interpolation between consecutive telemetry points in the pair of consecutive telemetry points; and wherein the steps of identifying the plurality of road segments and identifying the plurality of road intersections include identifying, via the processor, the plurality of road segments and the plurality of road intersections based on clustering of the turn points of the plurality of vehicles over the plurality of time periods, respectively, as the plurality of vehicles travel through the one or more geographic regions.

[0008] Also in example embodiments, the method further includes classifying, via the processor, the plurality of road intersections into the following classifications of road intersections based on the clustering of the turn points: intersections, residential driveways, U-turns, parking lots, commercial driveways, and curves.

[0009] Also in example embodiments, the step of identifying the plurality of road segments includes: removing, via the processor, geographic hashes of the plurality of road intersections; clustering, via the processor, remaining geographic hashes into segmented segments; merging, via the processor, segmented segments together based on geographic proximity; splitting, via the processor, disconnected segmented segments apart; and adding, via the processor, directions to each respective geographic hash.

[0010] Also in example embodiments, the method further includes stitching, via the processor, respective road network maps of the plurality of geographic regions in the one or more geographic regions based on identified boundaries and adjacencies of the respective road maps, thereby generating road network maps of the plurality of geographic regions in the one or more geographic regions.

[0011] Also in example embodiments, the method further includes obtaining, from computer memory, a prior network topology of the one or more geographic regions; wherein the step of generating the road network maps includes generating, via the processor, road network maps of the one or more geographic regions including the plurality of road intersections and the plurality of road segments using the vehicle telemetry data converted into geographic hash encodings and the prior network topology.

[0012] Also in example embodiments, the method further includes updating, via the processor, the prior network topology via one or more road segments, road intersections, or both identified in the road network maps in a manner different from the prior network topology.

[0013] Also in example embodiments, the method further includes defining, via the processor, a geographic hash resolution with respect to the one or more geographic regions of interest, wherein defining the geographic hash resolution includes defining, via the processor, both a coarse resolution and a fine resolution, wherein the coarse resolution provides for decomposition of the road network maps into parallelizable processes, and wherein the fine resolution provides for discrete units for describing road segments and intersections in the road network maps.

[0014] In another example embodiment, a system is provided that includes telematics systems from a plurality of vehicles and a processor. The processor is configured to facilitate at least: obtaining vehicle telematics data from the telematics systems of the plurality of vehicles as the plurality of vehicles travel through one or more geographic regions; converting the vehicle telematics into geohash encodings; identifying a plurality of road intersections using the vehicle telematics data that has been converted into geohash encodings for the one or more geographic regions; identifying a plurality of road segments using the vehicle telematics data that has been converted into geohash encodings for the one or more geographic regions; and generating a road network map for the one or more geographic regions including the plurality of road intersections and the plurality of road segments utilizing the vehicle telematics data that has been converted into geohash encodings.

[0015] Also in example embodiments, the processor is configured to facilitate at least: obtaining vehicle telematics data including a vehicle location, a vehicle heading, and a vehicle speed for each of the plurality of vehicles; and identifying the plurality of road segments and the plurality of road intersections using the vehicle telematics data that has been converted into geohash encodings for the one or more geographic regions, respectively.

[0016] Also in example embodiments, the processor is configured to facilitate at least: identifying pairs of consecutive telematics data points of the vehicle telematics data in which a change in heading is greater than a predetermined threshold, indicating a vehicle turn; determining a turn point for each pair of consecutive telematics points; and identifying the plurality of road segments and identifying the plurality of road intersections using the turn points, respectively.

[0017] Also in example embodiments, the processor is configured to facilitate at least: determining a turn point for each pair of consecutive telematics points based on a linear interpolation between consecutive telematics points in the pair of consecutive telematics points; and identifying the plurality of road segments and identifying the plurality of road intersections, respectively, based on clustering of the turn points of the plurality of vehicles over a plurality of time periods as the plurality of vehicles travel through the one or more geographic regions.

[0018] Also in example embodiments, the processor is configured to facilitate at least classifying the plurality of road intersections into the following classifications of road intersections based on clustering of turn movements: intersections, residential driveways, U-turns, parking lots, commercial driveways, and curves.

[0019] Also in example embodiments, the processor is configured to facilitate at least: removing geohashes for the plurality of road intersections; clustering remaining geohashes into segmented segments; merging segmented segments together based on geographic proximity; splitting disconnected segmented segments apart; and adding directions to each respective geohash.

[0020] Similarly, in an exemplary embodiment, the processor is configured to at least facilitate the stitching of corresponding road network maps of multiple geographic areas in one or more geographic areas based on the boundaries and adjacencies of the corresponding road network maps, thereby generating road network maps of multiple geographic areas in one or more geographic areas.

[0021] Also in an exemplary embodiment, the processor is configured to at least facilitate: obtaining a previous network topology of one or more geographic areas from a non-transitory computer-readable storage medium; generating a road network map of one or more geographic areas, including multiple road intersections and multiple road segments, using vehicle telemetry data that has been converted to a geo-hash code and the previous network topology; and updating the previous network topology in a manner different from the previous network topology via one or more road segments, road intersections, or both identified in the road network map.

[0022] Also in an exemplary embodiment, the processor is further configured to at least facilitate defining a geographic hash resolution for one or more geographic regions of interest as a coarse resolution and a fine resolution, wherein the coarse resolution provides for decomposing the road network map into a parallelizable process, and wherein the fine resolution provides discrete units for describing road segments and intersections in the road network map.

[0023] In another exemplary embodiment, a system is provided comprising a plurality of vehicles and a remote server. Each of the plurality of vehicles has a corresponding telematics system. The remote server is communicatively coupled to the plurality of vehicles. The remote server includes a processor coupled to the telematics systems of the plurality of vehicles and configured to at least facilitate: obtaining vehicle telemetry data from the telematics systems of the plurality of vehicles as the plurality of vehicles travel through one or more geographic areas; converting the vehicle telemetry data from the computer processor into a geo-hash encoding format relating to the one or more geographic areas; identifying a plurality of road intersections using the vehicle telemetry data converted to the geo-hash encoding of the one or more geographic areas; identifying a plurality of road segments using the vehicle telemetry data converted to the geo-hash encoding of the one or more geographic areas; and generating a road network map of the one or more geographic areas including the plurality of road intersections and the plurality of road segments using the vehicle telemetry data converted to the geo-hash encoding. Attached Figure Description

[0024] The present disclosure will be described below in conjunction with the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

[0025] Figure 1This is a functional block diagram of a communication system according to an exemplary embodiment, the communication system including a vehicle having a telematics unit and a control system configured to discover and map a road network using vehicle telemetry data converted to a geographic hash code; and

[0026] Figure 2 This is an exemplary embodiment for use with converted geographic hash encoding and can be used with Figure 1 A flowchart illustrating the process of discovering and mapping road networks using vehicle telemetry data in conjunction with a communication system, wherein the communication system includes vehicles, telematics units and their control units and components;

[0027] Figure 3 This is according to an exemplary embodiment. Figure 2 A flowchart of the steps in the process (i.e., identifying intersections in the road network);

[0028] Figure 4 This is according to an exemplary embodiment. Figure 2 A flowchart of the steps in the process (i.e., classifying intersections of the road network);

[0029] Figure 5 This is according to an exemplary embodiment. Figure 2 A flowchart of the steps in the process (i.e., identifying road segments of the road network);

[0030] Figure 6 This is according to an exemplary embodiment. Figure 2 A flowchart of the steps in the process (i.e., determining the adjacency of components in the road network);

[0031] Figure 7 This is according to an exemplary embodiment. Figure 2 A flowchart of the process steps (i.e., stitching together coarse geographic hashes across adjacencies); and

[0032] Figures 8-10 This is according to an exemplary embodiment. Figure 2 The process and Figures 2-7 A graphical representation of an exemplary implementation of the steps. Detailed Implementation

[0033] The following detailed description is exemplary in nature only and is not intended to limit this disclosure or its application and use. Furthermore, it is not intended to be bound by the foregoing background art or any theory presented in the following detailed description.

[0034] Figure 1 This is a functional block diagram of a communication system 10 according to an exemplary embodiment. As described in further detail below, the communication system 10 includes one or more vehicles 12. Although Figure 1A single vehicle 12 is depicted, but it should be understood that the communication system 10 can include a plurality of different vehicles 12 in various embodiments. In various embodiments, the communication system 10 (and the process 200 described below in connection with Figures 2-10 The process 200 described further below includes a number of different vehicles 12 obtaining vehicle telematics data at various different points in time (e.g., including the past, present, and future). Also in various embodiments, when a “vehicle 12” is discussed herein, it should be understood that similar discussion would apply to each of the vehicles 12 in the communication system 10 (e.g., each of the vehicles 12 obtaining vehicle telematics data, including the past, present, and future).

[0035] In various embodiments, the communication system 10 discovers and maps a road network using vehicle telematics data from the vehicles 12 that is converted to geohash encoding in accordance with steps of the process 200 described below in connection with Figures 2-10 In various embodiments, the communication system 10 discovers and maps a road network using vehicle telematics data from the vehicles 12 that is converted to geohash encoding in accordance with steps of the process 200 described below in connection with

[0036] As Figure 1 shown, in various embodiments, each vehicle 12 includes a telematics unit 24 and a control system 11 configured to discover and map a road network using vehicle telematics data from the telematics unit 24 that is converted to geohash encoding in accordance with example embodiments. As described further below in connection with Figure 1 The control system 11 includes a processor 38, a computer memory 40, a satellite-based location determination system component (e.g., a GPS system) 42, an antenna 70, and vehicle sensors 72 including one or more ignition sensors 73 and antenna sensors 74, as described further below.

[0037] As Figure 1 depicted in the communication system 10, the communication system 10 also includes an electronic device 15 (e.g., a smartphone, computer, and / or other electronic device) of a user 13 (e.g., a driver or other occupant) of the vehicle 12 and / or used in conjunction therewith.

[0038] Also as Figure 1 depicted, the communication system 10 generally includes a plurality of vehicles 12 (e.g., similar to the vehicle 12 shown Figure 1 in various embodiments. It should be understood that the overall architecture, setup, and operation of the illustrated system, as well as the individual components, are merely exemplary and that the example methods disclosed herein can also be implemented utilizing a communication system of different configuration. Accordingly, the following paragraphs providing a brief overview of the illustrated communication system 10 are not intended to be limiting.

[0039] In various embodiments, vehicle 12 can be any type of mobile vehicle, such as a motor vehicle, automobile, motorcycle, truck, recreational vehicle (RV), boat or other vessel, airplane or other aircraft, spacecraft, farm equipment, etc., and / or any number of other vehicles and / or other types of mobile platforms, and is equipped with suitable hardware and software that enable it to communicate via communication system 10. Figure 1 As shown, in various embodiments, vehicle hardware 20 is disposed within the main body of vehicle 12 and includes a telematics unit 24, a microphone 26, a speaker 28, and buttons and / or controls 30 connected to the telematics unit 24. A network connection or vehicle bus 32 is operatively coupled to the telematics unit 24. Examples of suitable network connections include Controller Area Network (CAN), System Transmission for Media (MOST), Local Interconnect Network (LIN), Ethernet, and other suitable connections such as those conforming to known ISO (International Organization for Standardization), SAE (Institute of Automotive Engineers), and / or IEEE (Institute of Electrical and Electronics Engineers) standards and specifications, to name just a few.

[0040] The telematics unit 24 is an in-vehicle device that provides various services through its communication with the remote server 18, and typically includes an electronic processing device (processor) 38, one or more types of electronic memory 40, a cellular chipset / component 34, a wireless modem 36, a dual-mode antenna 70, and a navigation unit including a GPS system 42. In one example, the wireless modem 36 includes a set of computer programs and / or software routines suitable for execution within the electronic processing device 38.

[0041] In various embodiments, processor 38 controls the operation of telematics unit 24 and vehicle 12. In some embodiments, processor 38 at least facilitates the discovery and mapping of road networks using vehicle telemetry data from telematics unit 24 that has been converted to geographic hash codes (e.g., in some embodiments, processor 38 can assist in...). Figure 1 One or more servers / processors of remote server 18 or one or more processors of processor 54 have such functionality. In some embodiments, processor 38 is based on... Figures 2-10 These functions are performed by the steps of process 200, which are described in the text and further described below.

[0042] In various embodiments, the telematics unit 24 can be embedded / installed within the vehicle 12 at the time of manufacture, or can be an after-market unit that is installed after the vehicle 12 is manufactured. In various embodiments, the telematics unit 24 is capable of voice and / or data communication over one or more wireless networks, such as the wireless carrier system 14, and / or via wireless networking, allowing communication with the remote servers 18 and / or other vehicles and / or systems.

[0043] In various embodiments, the telematics unit 24 can use radio transmissions to establish a voice and / or data channel with the wireless carrier system 14, such that voice and data transmissions can be sent and received over the voice and / or data channel. Vehicle communication is achieved via the cellular chipset / component 34 for voice communications and the wireless modem 36 for data transmissions. Any suitable encoding or modulation technique can be used with the present example, including digital transmission techniques such as TDMA (time division multiple access), CDMA (code division multiple access), WCDMA (wideband CDMA), FDMA (frequency division multiple access), OFDMA (orthogonal frequency division multiple access), etc. In one embodiment, the dual-mode antenna 70 serves both the GPS system 42 and the cellular chipset / component 34. In various embodiments, the telematics unit 24 utilizes cellular communication in accordance with industry standards such as LTE, 5G, etc. Additionally, in various embodiments, the telematics unit 24 performs wireless networking between the vehicle 12 and one or more other network devices, e.g., using one or more wireless protocols such as one or more IEEE 802.11 protocols, WiMAX, or Bluetooth.

[0044] The telematics unit 24 can provide a number of different services. In various embodiments, the telematics unit 24 provides vehicle telematics data for use in discovering and mapping road networks on which the vehicle 12 can travel, which is converted to geo-hash encoding.

[0045] In various embodiments, telematics unit 24 can also provide services, such as for example, for communicating with one or more electronic devices 15 and remote servers 18. For example, in certain embodiments, one or more short-range wireless connection (SRWC) protocols (e.g., Bluetooth / Bluetooth Low Energy or Wi-Fi) can be utilized. In various embodiments, once a SRWC is established, electronic device 15 can be bound and / or identified as a network participant of telematics unit 24, such as for current and future use. For example, in certain embodiments, when electronic device 15 is subsequently within wireless range of telematics unit 24 after initial pairing, telematics unit 24 (and / or remote servers 18) can confirm that electronic device 15 is identified as having been paired or established as a network participant for communicating with and receiving services from telematics unit 24.

[0046] Additionally, in various embodiments, telematics unit 24 can also provide other services, such as, by way of example: turn-by-turn directions and other navigation-related services provided in conjunction with GPS system 42, in addition to various other types of possible services; emergency assistance services, information requests from users of vehicle 12, and / or infotainment-related services (e.g., content) downloaded by infotainment center 46, which can be part of telematics unit 24 and / or operatively connected to telematics unit 24 via vehicle bus 32 and audio bus 22.

[0047] With respect to other electronic components used in conjunction with telematics unit 24, microphone 26 provides a means for a driver or other vehicle occupant to input verbal or other audible commands, and can be equipped with an embedded speech processing unit utilizing human-machine interface (HMI) technology known in the art. Conversely, speaker 28 provides audible output to vehicle occupants, and can be a standalone speaker specifically dedicated for use with telematics unit 24, or can be part of vehicle audio assembly 64. In either case, microphone 26 and speaker 28 enable vehicle hardware 20 and remote servers 18 to communicate with occupants via audible speech. Vehicle hardware also includes one or more buttons and / or controls 30 for enabling a vehicle occupant to activate or engage one or more of vehicle hardware assembly 20. For example, one of buttons and / or controls 30 can be an electronic button for initiating voice communication with remote servers 18, whether it is a person such as advisor 58 or an automated call response system. In another example, one of buttons and / or controls 30 can be for initiating emergency services.

[0048] The audio component 64 is operably connected to the vehicle bus 32 and the audio bus 22. The audio component 64 receives analog information via the audio bus 22, which it presents as sound. Digital information is received via the vehicle bus 32. The audio component 64 provides amplitude modulation (AM) and frequency modulation (FM) radio, compact disc (CD), digital video disc (DVD), and multimedia functionality independent of the infotainment center 46. The audio component 64 can incorporate a speaker system, or can utilize the speakers 28 via arbitration on the vehicle bus 32 and / or the audio bus 22. In various embodiments, the audio component 64 includes a radio system 65 (which in certain embodiments also includes an antenna 70, as well as amplifiers, speakers, etc.).

[0049] Also in various embodiments, the display component 67 provides a visual display for the user 13 of the vehicle 12. In various embodiments, the display component 67 provides a visual display for the user 13 of relevant information related to cellular communication, as well as in various embodiments, navigation information, camera images and video, etc.

[0050] The vehicle sensors 72, which are connected to the various sensor interface modules 44, are operably connected to the vehicle bus 32.

[0051] In various embodiments, the vehicle sensors 72 include both an ignition sensor 73 and a telemetry sensor 74. In various embodiments, the one or more ignition sensors 73 detect when an ignition cycle or vehicle drive is starting or about to start. For example, in various embodiments, the ignition sensor 73 detects when the vehicle 12 (e.g., its engine) is started, and / or when the user 13 enters the vehicle 12, unlocks the vehicle 12, provides an instruction to start the vehicle 12 (e.g., an input device and / or a key fob), etc. Also in various embodiments, the telemetry sensor 74 communicates with the location detection system via the GPS system 42, e.g., via its signals (e.g., with satellites of a GPS system), e.g., via the antenna 70.

[0052] Additionally, in various embodiments, the vehicle sensors 72 can also include any number of additional sensors, including, by way of example, gyroscopes, accelerometers, magnetometers, emissions detection and / or control sensors, etc. Further, in various embodiments, the exemplary sensor interface modules 44 include powertrain control, climate control, and body control, to name a few.

[0053] In various embodiments, wireless carrier system 14 can be any number of cellular telephone systems, satellite-based wireless systems, and / or any other suitable wireless systems, e.g., that transmit signals between vehicle hardware 20 and land network 16 (and / or in certain embodiments, that communicate directly with vehicle 12 and / or remote servers 18). According to certain examples, wireless carrier system 14 can include and / or be coupled to one or more cell towers 48, satellites 49, base stations, and / or mobile switching centers (MSCs) 50, as well as any other networking components needed to connect wireless carrier system 14 with land network 16. As those skilled in the art appreciate, various cell tower / base station / MSC arrangements are possible and can be used with wireless carrier system 14.

[0054] Land network 16 can be a conventional, land-based telecommunications network that connects to one or more land-line phones and that connects wireless carrier system 14 to remote servers 18. For example, land network 16 can include a public switched telephone network (PSTN) and / or an Internet Protocol (IP) network, as appreciated by those skilled in the art. Of course, one or more segments of land network 16 can be implemented in the form of standard wire-based networks, fiber or other optical networks, cable networks, other wireless networks such as wireless local area networks or networks that provide broadband wireless access (BWA), or any combination thereof.

[0055] Remote servers 18 are designed to provide a number of different system backend functions to vehicle hardware 20, and according to the example shown here, generally include one or more switches 52, servers 54, databases 56, advisors 58, and various other telecommunication / computer equipment 60. These various call center components are suitably coupled to one another via a network connection or bus 62, such as the network connection or bus previously described in connection with vehicle hardware 20. Switches 52, which can be private branch exchange (PBX) switches, route incoming signals so that voice transmissions are typically sent to advisors 58 or automated response systems, and data transmissions are passed to modems or other telecommunication / computer equipment 60 for demodulation and further signal processing.

[0056] In various embodiments, one or more servers 54 include one or more processors configured to discover and map a road network using vehicle telematics data from remote information processing unit 24 of vehicle 12 that is converted to a geo-hash encoding. In various embodiments, one or more servers 54 (including one or more computer processors thereof) perform these functions according to the steps of process 200, which are further described below. Figures 2-10 In various embodiments, one or more servers 54 include one or more processors configured to discover and map a road network using vehicle telematics data from remote information processing unit 24 of vehicle 12 that is converted to a geo-hash encoding. In various embodiments, one or more servers 54 (including one or more computer processors thereof) perform these functions according to the steps of process 200, which are further described below.

[0057] The modem or other telecommunication / computer device 60 can include an encoder as previously described and can be connected to various devices such as the server 54 and database 56. For example, as previously described, the database 56 can store regulatory radiation power requirements for various jurisdictions. In addition, in certain embodiments, the database 56 can also be designed to store other types of data such as, by way of example, subscriber profile records, subscriber behavior patterns, or any other relevant subscriber information. Although the illustrated example has been described as being used in conjunction with a manned remote server 18, it should be understood that the remote server 18 can be any central or remote facility, manned or unmanned, mobile or fixed.

[0058] In various embodiments, a large number of vehicles 12 (e.g., including every vehicle 12 that obtains vehicle telematics data in the past, present, and future) can be used with the remote server 18 and the communication network depicted herein to discover and map a road network using vehicle telematics data that is converted to a geographic hash code of a geographic location on Earth where the vehicle 12 is traveling in accordance with the process 200 described below in connection with Figures 2-10

[0059] Figure 2 is a flowchart of a process 200 for discovering a road network using vehicle telematics data that is converted to a geographic hash code in accordance with an example embodiment. In various embodiments, the process 200 can be used in conjunction with the communication system 10 of Figure 1 including the vehicles 12 and control system 11, telematics unit 24, GPS system 42, and remote server 18 and its processor 54 and database 56, and components thereof, in accordance with an example embodiment. The process 200 will be further described below in connection with Figure 2 and in connection with Figures 3-7 which describes different steps of the process 200 in accordance with an example embodiment, and Figures 8-10 which provides a graphical representation of an example implementation of the process 200 and its steps in accordance with an example embodiment, further describe the process 200.

[0060] In various embodiments, the process 200 begins at step 202. In one implementation, the process 200 begins when a vehicle drive or ignition cycle begins, such as when a driver approaches or enters the vehicle 12, or when the driver turns on the vehicle and / or ignites it (e.g., by turning a key, engaging a key fob, or actuating a start button, etc.), and / or otherwise operates the vehicle 12. In one embodiment, the steps of the process 200 are performed with aggregated data of a number of vehicles 12 at various different points in time.

[0061] ​In various embodiments, a geographic hash resolution is defined (step 204). In various embodiments, coarse and fine geographic hash resolutions are defined with respect to one or more geographic regions of interest relative to a proximity of the vehicle 12 at some past time. In various embodiments, the coarse and fine geographic hash units are retrieved from Figure 1 one or more computer memory devices 40 and / or databases 56. In various embodiments, the geographic hash resolution refers to a plurality of geographic hash resolutions at which the surface of the earth is discretized, including (i) a coarse resolution; and (ii) a fine resolution. In various embodiments, the coarse resolution provides for breaking up the road network into a parallelizable process, while the fine resolution provides for discrete units for describing road segments and intersections, as described in further detail below.

[0062] In various embodiments, the coarse geographic hashes are split for parallel processing (step 208). Specifically, in various embodiments, one or more processors 54 of the remote server 18 (such as the processor(s) 54 of the remote server 18) and / or one or more other processors physically remote from the vehicle select telematics data related to a particular geographic region corresponding to the coarse geographic hash. Figure 1

[0063] In various embodiments, for each coarse geographic hash, telematics data is collected (step 210). In various embodiments, during step 210, telematics data 206 related to the split represented by each coarse geographic hash is collected from the vehicle 12. In various embodiments, the telematics data 206 includes various signals (or “pings”) from the vehicle’s telematics sensors 74 and GPS system 42. Also in various embodiments, the telematics data 206 represents a geographic location of the vehicle 12 and information about the speed and directional heading of the vehicle 12. In various embodiments, telematics data (e.g., telematics data) is collected for each vehicle 12 (e.g., in a fleet of vehicles 12) for each coarse geographic hash (e.g., for each geographic split). Figure 1

[0064] Referring to Figure 8 , a graphical representation 800 of the telematics data is provided, having an x-axis 801 representing longitude and a y-axis 802 representing latitude. In various embodiments, each signal (or “ping”) of the HSVT telematics data is represented by a different dot 804 in the graphical representation 800. Figure 8

[0065] ​​​In various embodiments, each telemetry point is mapped to its corresponding geographic hash at a resolution of the fine-grained geographic hash defined in 204. In various embodiments, the observable output of the entire process 200 includes a set of fine-grained geographic hashes identified as belonging to road segments throughout the entire process 200 (e.g., using each vehicle at various different time points during different vehicle ignition cycles, etc.).

[0066] Return to reference Figure 2 In various embodiments, the intersection is identified (step 212). In various embodiments, the intersections of the road network (e.g., road junctions) are handled by one or more processors (such as...). Figure 1 One or more processors 54, 38) are identified based on the telemetry data from step 210 and encoded with corresponding geographic hash data.

[0067] refer to Figure 3 Provided Figure 2 A flowchart illustrating the steps for identifying the intersection in step 212. Figure 3 As shown, in various embodiments, telemetry data 206 is used to calculate the heading angle change between consecutive telemetry points (step 302). Specifically, in various embodiments, one or more processors (such as...) Figure 1 One or more processors 54, 38) calculate the vehicle 12 in continuous telemetry signals (or "pings") (such as... Figure 8 The graphic representation shows the change in heading angle between points 804.

[0068] Similarly, in various embodiments, telemetry points are paired (step 304). In various embodiments, one or more processors (such as...) Figure 1 One or more processors 54, 38) find telemetry point pairs with a heading angle variation within a predetermined range. In some embodiments, such telemetry point pairs are identified based on whether the heading angle variation is greater than a predetermined threshold (e.g., ninety degrees in one embodiment, but this may vary in other embodiments) in order to indicate that the vehicle is turning.

[0069] Additionally, in various embodiments, a "turning point" is calculated between consecutive telemetry points (step 306). In various embodiments, one or more processors (such as...) Figure 1 One or more processors 54, 38) determine the “turning point” as the midpoint between consecutive telemetry points. In some embodiments, the “turning point” is determined via linear interpolation between consecutive telemetry points.

[0070] In various embodiments, turning points are clustered together (step 308). In various embodiments, turning points near a specific geographic location are handled by one or more processors (such as...). Figure 1One or more processors (54, 38) are clustered together.

[0071] In various embodiments, each cluster is selected for analysis one at a time (step 310). Also in various embodiments, for each cluster, the intersections are classified with respect to that particular cluster (step 312). In various embodiments, this is done via one or more processors (such as...). Figure 1 One or more processors 54, 38) classify the intersections. In some embodiments, the prior network topology 350 is also used for intersection classification.

[0072] refer to Figure 4 Provided Figure 3 A flowchart illustrating the steps of classifying intersections in step 312. Figure 4 As shown, in various embodiments, telemetry data 206 is used to detect turning movement (step 402). Specifically, in various embodiments, one or more processors (such as...) Figure 1 One or more processors 54, 38) based on the sequential points of telemetry data (such as...) Figure 8 The turning movement of vehicle 12 is detected by changes in direction and / or heading in the point (804) represented by the graphic representation.

[0073] Similarly, in various embodiments, clustering is performed (step 404). In various embodiments, one or more processors (such as...) Figure 1 One or more processors 54, 38) cluster the points representing the turning movements of vehicle 12 and optimize the parameters used in the clustering. In various embodiments, the clustering of turning movements 404 is enhanced by optimizing the parameters used for clustering. Also in various embodiments, the purpose of this hyperparameter optimization is to optimize the identifier of the true turning movement cluster relative to the identifier of minimizing outliers.

[0074] In various embodiments, the clustering and optimization output of step 404 is provided for the intersection classification process 406. Specifically, in various embodiments, telemetry data is used via one or more processors (such as...) to examine common behaviors of different vehicles over time in the same geographic location (e.g., similar turns and / or other movements, etc.). Figure 1 One or more processors 54, 38) are used to implement the intersection classification process 406. In some embodiments, a network topology 350 (e.g., a previously known road network map) is also used in the classification process 406.

[0075] like Figure 4As shown, in various embodiments, the processor utilizes an intersection classification process to classify intersections into one or more of a plurality of different potential intersection categories by examining the turning movement patterns of different vehicles over time (and in some embodiments, other vehicle actions, such as ignition cycles, including ignition on and off determined by vehicle ignition sensors, and / or vehicle speed and / or other vehicle parameters) and their clustering (and in some embodiments, network topology 350). Specifically, in various embodiments, intersection categories include the following: intersection 408, residential lane 410, U-turn 412, parking lot 414, commercial lane 416, curve 418, and large intersection 420. In some embodiments, large intersection 420 may be further subclassified into (a) identified intersection 422 (e.g., an intersection previously known from network topology 350); and (b) new intersection 424 (e.g., an intersection previously unknown from network topology 350).

[0076] For example, refer to Figures 8-10 In various embodiments, telemetry points 804 can be clustered together to represent, for example, Figure 8 The road segment 806 and intersection (e.g., road junction) 808 are shown. Additionally, in some embodiments, a prior network topology 350 may be utilized, for example, as... Figure 9 The graphic representation is shown as 900. For example... Figure 9 As depicted, the x-axis 901 represents latitude, the y-axis 902 represents longitude, and previously known data points 904, segments 906, and intersections (e.g., road intersections) 908 are known from the network topology. Furthermore, as... Figure 10 As shown, the graphic represents 1000 including Figure 8 and Figure 9 The data is a combination of data, where similar x-axis 1001 represents latitude 1001, y-axis represents longitude 1002, and similar representations are given for data points 1004, road segments 1006, and intersections (e.g., crossroads) 1008.

[0077] Return to reference Figure 3 After classifying the intersections in step 312, the clustering is refined in various embodiments (step 314). Specifically, in various embodiments, one or more processors (such as...) Figure 1One or more processors (54, 38) refine cluster membership, for example, by decomposing turning movement clusters into appropriate classes, such as identifying intersections, residential driveways, parking lots, etc., in steps 410-418. In various embodiments, this also includes, as in step 420, decomposing clusters of large intersections that are identified as potentially agglomerates into individual intersections. Additionally, in various embodiments, a manifold is mapped around the clusters, and fine-grained geographic hashes within that manifold are assigned to the clusters to remove holes (step 316). In some embodiments, the manifold is mapped as a rectangle, the dimensions of which are based on the intersections and predetermined areas of influence of the intersections.

[0078] Similarly, in various embodiments, fine-grained geohashes are assigned to specific clusters (step 318). Specifically, in some embodiments, cross- and closed geohashes from known geohash-encoded data are processed by one or more processors (such as...). Figure 1 One or more processors (54, 38) are assigned to each specific intersection or intersection type. Also in various embodiments, intersections are labeled (step 320). Specifically, in various embodiments, intersections are labeled by the processor with the finest possible geohash resolution encoding about the geometric center of the geographic area in question. In various embodiments, a new cluster is selected (step 322), and the process returns to step 310, where steps 310-322 are repeated for each cluster until each cluster is complete.

[0079] Return to reference Figure 2 In various embodiments, segmentation is identified (step 214). In various embodiments, road segments of the road network are handled by one or more processors (such as...). Figure 1 One or more processors (54, 38) are identified based on the telemetry data from step 210 and encoded with corresponding geographic hash data.

[0080] refer to Figure 5 Provided for in Figure 2 An illustrative flowchart illustrating the steps that identify the segments in step 214. (See attached flowchart.) Figure 5 As shown, in various embodiments, intersection geohashing is removed from the road network analysis (step 502). For example, in some embodiments, it is removed from the corresponding graphical representations 800 and 1000, respectively, for the purpose of identifying road segments 806 and 1006 by the processor. Figure 8 and Figure 10 The intersection of 808 and 1008.

[0081] Furthermore, in various embodiments, the remaining geohashes (after removing the intersections) are clustered into segments by the processor (step 504). In various embodiments, the processor also merges the resulting segmented fragments together based on geographical proximity (step 506), and in some embodiments, it also uses a previously known network topology 350 to merge the segmented fragments. Additionally, in some embodiments, the processor further breaks down any disconnected segments (step 508), for example, to separate segments that are not adjacent to each other and / or physically / geographically connected. Furthermore, in various embodiments, for example, the processor adds direction to each geohash by utilizing patterns of movement direction of different vehicles over time in the same geographical area (step 510).

[0082] Return to reference Figure 2 In various embodiments, adjacency is determined (step 216). In various embodiments, the adjacency of road segments of the road network is determined by one or more processors (such as...). Figure 1 One or more processors 54, 38) determine the road segments based on the telemetry data from step 210 and the road segments identified in step 214, and encode them with the corresponding geographic hash data.

[0083] refer to Figure 6 Provided Figure 2 An illustrative flowchart of the steps for determining adjacency in step 216. (See attached flowchart.) Figure 6 As shown, in various embodiments, boundary geohashes are obtained (step 602). For example, in some embodiments, the processor identifies the boundary geohashes for each segment and intersection identified in steps 212 and 214 above. Also in various embodiments, for each boundary, the processor obtains a list of adjacent geohashes (step 604). In various embodiments, the processor also utilizes a self-join function on the band table, where the adjacent geohashes are equal to the boundary geohashes (step 606), to illuminate the boundary regions. Furthermore, in various embodiments, the processor filters the results (step 608) such that intersections are adjacent to segments or intersections, but segments are not adjacent to each other.

[0084] Return to reference Figure 2 In various embodiments, the next coarse geohash is selected (step 218). In various embodiments, the processor identifies the next or subsequent coarse geohash to be examined, and the process returns to steps 208-218, repeating for each coarse geohash until the analysis of all coarse geohashes is completed.

[0085] In various embodiments, once competition steps 208-218 are for each geohash, concatenation (step 220) is performed. In various embodiments, the processor performs concatenation across each of the adjacent geohashes in the road network.

[0086] refer to Figure 7 Provided for Figure 2 An illustrative flowchart of the steps in step 220, namely, splicing adjacent geographic hashes. Figure 7 As shown, in various embodiments, the road network is independently identified over a geohash region at a first resolution (step 702). In one embodiment, the processor identifies the road network over the geohash region at a coarse geohash resolution. Also in various embodiments, the processor identifies the boundary of each coarse geohash region within the coarse geohash region (step 706). Additionally, in some embodiments, the processor identifies boundary geohashes in adjacent coarse geohash regions at a fine geohash resolution (step 708). Furthermore, in some embodiments, the processor updates adjacencies (step 710). Specifically, in some embodiments, the processor updates adjacencies as follows: (i) by creating implicit connections for segment-to-segment adjacencies; (ii) by updating intersection types and intersection-to-intersection adjacencies; and (iii) by updating the adjacencies of segment-to-intersection adjacencies. In various embodiments, the processor also updates the previous network topology 350 with respect to those road segments, road intersections, or both that are identified in the road network map according to process 200 and (i) do not exist in the previous network topology 350 and / or (ii) are different from those presented in the previous network topology 350.

[0087] Return to reference Figure 2 In various embodiments, the process then terminates (step 222).

[0088] Therefore, methods and systems for generating road networks are provided. In various embodiments, the road network is generated using vehicle telemetry data (e.g., telemetry data) from multiple vehicles (e.g., in a convoy), which is converted into geo-hash codes for specific geographic areas of interest on which the vehicles are traveling. In some embodiments, telemetry data and geo-hash code data can also be combined to leverage a previous network topology, and in some embodiments, the network topology can be further updated based on the road network generated from the vehicle telemetry data and geo-hash code data.

[0089] It should be understood that the systems and methods may differ from those depicted in the figures and described herein. For example, in various embodiments, Figure 1 The communication system (including its vehicles, telematics units and their control systems, as well as remote servers, servers, processors and their components) can communicate with Figure 1 The differences between the descriptions herein and / or those herein are not identical. Similarly, the processes (and / or subprocesses) disclosed herein may differ from those described herein and / or... Figures 2-10the processes (and / or sub-processes) depicted therein, and / or steps thereof, can be performed in the sequence Figures 2-10 the processes (and / or sub-processes) depicted therein, and / or steps thereof, can be performed in the sequence Figures 2-10 the processes (and / or sub-processes) depicted therein, and / or steps thereof, can be performed in the sequence

[0090] While at least one example has been presented in the foregoing detailed description, it should be appreciated that a vast number of variations exist. It should also be appreciated that the exemplary is merely an example, and not intended to limit the scope, applicability or configuration in any way. Rather, the foregoing detailed description will provide those skilled in the art with a convenient road map for implementing an example. It should be understood that various changes can be made in the function and arrangement of elements without departing from the scope of the appended claims and their legal equivalents.

Claims

1. A method for road network mapping using vehicle telemetry data, comprising: When multiple vehicles travel through one or more geographical areas, vehicle telemetry data is obtained via the telematics system of the multiple vehicles. The acquisition of the vehicle telemetry data includes the vehicle telemetry data including the vehicle position, vehicle heading and vehicle speed of each of the multiple vehicles. The computer processor converts the vehicle telemetry data into a geographic hash encoding format related to the one or more geographic regions; The processor identifies consecutive telemetry data point pairs of the vehicle telemetry data in which the change in heading exceeds a predetermined threshold, and instructs the vehicle to turn. The intersection classification process is implemented using telemetry data via one or more processors by examining the common behaviors of different vehicles in the same geographical location over time. The processor determines the turning point of each pair of consecutive telemetry points based on linear interpolation between consecutive telemetry points in the consecutive telemetry point pair; The steps of identifying the multiple road segments and identifying the multiple road intersections include, as the multiple vehicles travel through the one or more geographical areas, identifying the multiple road segments and identifying the multiple road intersections respectively via the processor based on the clustering of the turning points of the multiple vehicles in multiple time periods; The steps for identifying the multiple road segments include: The processor removes the geographic hashes of the plurality of road intersections; The processor then clusters the remaining geographic hashes into segmented fragments. The processor merges the segmented pieces together based on geographical proximity; The processor separates the disconnected segments; and The processor adds directions to each corresponding geographic hash. Multiple road intersections are identified using the vehicle telemetry data, which has been converted into a geographic hash code, via a processor; Multiple road segments are identified via the processor using geo-hash codes converted to the one or more geographic regions; and The processor uses the vehicle telemetry data, which has been converted into a geographic hash code, to generate a road network map of one or more geographic areas, including the plurality of road intersections and the plurality of road segments.

2. The method according to claim 1, wherein: The steps of identifying the plurality of road segments and identifying the plurality of road intersections via the processor include identifying the plurality of road segments and identifying the plurality of road intersections respectively using the vehicle telemetry data converted into a geographic hash code.

3. The method according to claim 2, further comprising: The steps of identifying the plurality of road segments and identifying the plurality of road intersections include identifying the plurality of road segments and identifying the plurality of road intersections respectively via the processor using the turning points.

4. The method according to claim 3, further comprising: Based on the clustering of the turning points, the processor classifies the plurality of road intersections into the following categories: Intersections, residential driveways, U-turns, parking lots, commercial driveways, and curves.

5. The method according to claim 1, further comprising: The processor stitches together corresponding road network maps of multiple geographical regions based on the boundaries and adjacencies of the corresponding road map identifiers, thereby generating the road network maps of the multiple geographical regions.

6. The method according to claim 1, further comprising: Obtain the previous network topology of the one or more geographic regions from computer memory; The step of generating the road network map includes, via the processor, using the vehicle telemetry data converted to geospatial hash codes and the previous network topology, generating the road network map including the plurality of road intersections and the plurality of road segments, one or more geographical areas; and The method further includes updating the previous network topology in a manner different from the previous network topology via the processor, through one or more road segments, road intersections, or both identified in the road network map.

7. The method according to claim 1, further comprising: The processor defines a geohash resolution for one or more geographic regions of interest, wherein the definition of the geohash resolution includes defining both a coarse resolution and a fine resolution via the processor, wherein the coarse resolution provides a parallelization process for decomposing the road network map, and wherein the fine resolution provides discrete units for describing road segments and intersections in the road network map.

8. A system for road network mapping using vehicle telemetry data, comprising: Telematics processing system from multiple vehicles; as well as A processor, the processor being configured to at least facilitate: When the multiple vehicles travel through one or more geographical areas, vehicle telemetry data is obtained from the telematics system of the multiple vehicles. The acquisition of the vehicle telemetry data includes the acquisition of vehicle telemetry data including the vehicle position, vehicle heading and vehicle speed of each of the multiple vehicles. Convert the vehicle telemetry data into a geographic hash code; The processor identifies consecutive telemetry data point pairs of the vehicle telemetry data in which the change in heading exceeds a predetermined threshold, and instructs the vehicle to turn. The intersection classification process is implemented using telemetry data via one or more processors by examining the common behaviors of different vehicles in the same geographical location over time. The processor determines the turning point of each pair of consecutive telemetry points based on linear interpolation between consecutive telemetry points in the consecutive telemetry point pair; The steps of identifying the multiple road segments and identifying the multiple road intersections include, as the multiple vehicles travel through the one or more geographical areas, identifying the multiple road segments and identifying the multiple road intersections respectively via the processor based on the clustering of the turning points of the multiple vehicles in multiple time periods; The steps for identifying the multiple road segments include: The processor removes the geographic hashes of the plurality of road intersections; The processor then clusters the remaining geographic hashes into segmented fragments. The processor merges the segmented pieces together based on geographical proximity; The processor separates the disconnected segments; and The processor adds directions to each corresponding geographic hash. Multiple road intersections are identified using the vehicle telemetry data, which has been converted into a geo-hash code for the one or more geographic regions. Multiple road segments are identified using the vehicle telemetry data, which has been converted to a geo-hash code representing one or more geographic regions; and Using the vehicle telemetry data that has been converted into a geographic hash code, a road network map of one or more geographic areas, including the plurality of road intersections and the plurality of road segments, is generated.

Images