Method for measuring serviceability based on relative operator performance

Abstract

A system for measuring insurability (MIROP) based on relative vehicle operator performance includes a sensor that captures host vehicle and remote vehicle information and information about an environment of the host vehicle and the remote vehicle. The controller executes a MIROP application that identifies event information within the data obtained from the sensors, transmits the event information to a cloud computing server, and evaluates the physical location and proximity of the host vehicle relative to remote vehicles participating in the system. The MIROP application evaluates a road surface condition of a road segment on which the host vehicle travels, estimates traffic density over the road segment, integrates host vehicle behavior data, and identifies an event ID within the behavior data. The MIROP application calculates a vehicle operator safeguard score and automatically notifies the score to an insurance company, and automatically presents the score and suggestions to the host vehicle operator to improve the score.

Description

Technical Field

[0001] The present disclosure relates to a system and method for measuring the insurability of a vehicle operator and, more particularly, to a system and method for evaluating vehicle operator performance in a context - oriented manner. Background Art

[0002] Current systems and methods for measuring the insurability of a vehicle operator rely on absolute measurements, such as emergency braking or acceleration, without considering the context in which the absolute measurement event occurs. As a result, a current vehicle operator may be penalized for performing a safety maneuver, even when the driving context or environment design requires the maneuver.

[0003] Accordingly, while current systems and methods for determining the insurability of a vehicle operator achieve their intended purpose, there is a need for a new and improved system and method for measuring insurability based on relative vehicle operator performance, which provides a high - fidelity estimate of vehicle operator performance based on how a vehicle operator behaves compared to other vehicle operators at substantially the same time and substantially the same geographic location, and scores behaviors based on relative deviation from behavioral norms to accurately assess the risk of a vehicle operator based on context, while minimizing false positives due to road design, and accurately assessing the skills of a vehicle operator while operating on existing hardware and leveraging existing systems, and maintaining or reducing complexity. Summary of the Invention

[0004] According to several aspects of the present disclosure, a system for measuring insurability based on relative vehicle operator performance is provided, including a host vehicle and one or more remote vehicles. One or more sensors capture information of the host vehicle and the remote vehicles, and capture environmental information about the environment of the host vehicle and the one or more remote vehicles. The system further includes a cloud computing server communicatively coupled to the host vehicle and the one or more remote vehicles. Each of the host vehicle, the one or more remote vehicles, and the cloud computing server has a controller. Each controller has a processor, a memory, and one or more input / output (I / O) ports. The I / O ports communicate with the one or more sensors. The memory stores program control logic. The processor executes the program control logic. The program control logic includes an application for measuring insurability based on relative vehicle operator performance (MIROP application). The MIROP application includes at least first, second, third, fourth, fifth, sixth, seventh, eighth, and ninth control logics. The first control logic identifies event information within data obtained from the one or more sensors. The second control logic transmits the event information to the cloud computing server via the I / O ports of one or more of the controllers in the host vehicle and the I / O ports of the one or more remote vehicles. The third control logic evaluates the physical location and proximity of the host vehicle relative to the remote vehicles participating in the system. The fourth control logic evaluates the road surface condition of the section of road on which the host vehicle travels. The fifth control logic estimates the traffic density on the section of road. The sixth control logic integrates the host vehicle behavior data and identifies an event ID within the host vehicle behavior data. The seventh control logic calculates a vehicle operator insurability score. The eighth control logic automatically notifies an insurance company of the vehicle operator insurability score. The ninth control logic automatically presents score information and vehicle operation suggestions to the host vehicle operator via a human-machine interface (HMI) to increase the vehicle operator insurability score.

[0005] In another aspect of the present disclosure, the first control logic further includes control logic for detecting event information, the event information including: instances of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, forward collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or the remote vehicles.

[0006] In yet another aspect of the present disclosure, the first control logic further includes: control logic for comparing instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or the remote vehicles with acceleration thresholds, braking thresholds, and turning thresholds; and control logic for executing the second control logic to periodically transmit event information to the cloud computing server, the event information being related to instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or the remote vehicles that reach or exceed the acceleration thresholds, braking thresholds, and turning thresholds.

[0007] In yet another aspect of the present disclosure, the third control logic further includes control logic for confirming the position of the host vehicle relative to the map information stored in the map database; control logic for determining the positions of one or more remote vehicles relative to the map information stored in the map database; and control logic for determining that one or more of the remote vehicles are at or below a physical distance threshold from the host vehicle, or for determining that one or more of the remote vehicles have traversed a road segment within or in a threshold amount of time relative to the host vehicle.

[0008] In yet another aspect of the present disclosure, the fourth control logic further includes: control logic for estimating road surface type, road surface condition, the presence of obstacles on a road segment, and the positions of lane markings on a road segment using data from one or more sensors, and control logic for obtaining information from one or more application programming interfaces (APIs) including a weather API. The weather API provides weather information about the environment around the host vehicle on a road segment.

[0009] In yet another aspect of the present disclosure, the fifth control logic further includes: control logic for obtaining information from one or more application programming interfaces (APIs) including one or more traffic APIs. The traffic APIs report current and historical traffic information related to a road segment to the host vehicle. The fifth control logic further includes control logic for estimating traffic density and determining when the host vehicle approaches or passes a traffic signal using data from the traffic APIs and from one or more sensors, the traffic density including traffic signal states with an accuracy of approximately one second.

[0010] In yet another aspect of the present disclosure, the sixth control logic further includes control logic for identifying event IDs corresponding to instances of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, forward collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or remote vehicles. The sixth control logic further includes control logic for determining when one or more remote vehicle perspectives are available. When determining that one or more remote vehicle perspectives are available, the sixth control logic uses the remote vehicle perspectives to provide context for the behavior of the host vehicle. The sixth control logic further includes control logic for accessing a road profile database that includes physical characteristics and context information of a road segment, including traffic data, time-of-day information, and road surface information related to the road segment.

[0011] In yet another aspect of the present disclosure, the seventh control logic further includes: control logic for calculating first-order vehicle operator driving characteristics; control logic for calculating a derived time series of vehicle operator driving parameters of interest; and control logic for applying a weighting factor to each to determine the relative performance of the vehicle operator compared to remote vehicle operators in similar situations in similar contexts on a road segment or similar road segment.

[0012] In yet another aspect of the present disclosure, the seventh control logic further includes control logic for calculating aggressiveness x(t) via sudden acceleration a(t) and close following distance b(t), and control logic for calculating average aggressiveness according to the following formula:

[0013] II.

[0014] Control logic for calculating the standard deviation of aggressiveness according to the following formula:

[0015] III. And

[0016] Control logic for calculating the vehicle operator aggressiveness trend over time according to the following formula:

[0017] IV.

[0018] Where is a normalized feature, and indicates whether the operator of vehicles 12, 12’ becomes more aggressive, less aggressive, or equally aggressive within a predetermined amount of time. The seventh control logic further includes control logic for calculating a cumulative distribution function (CDF) that ranks the operator performance of all participating host vehicles and remote vehicles according to the following formula:

[0019] I.

[0020] Where each a n defines the characteristics of a specific event Q of each vehicle n n and w i defines the weighting factor.

[0021] In yet another aspect of the present disclosure, the eighth control logic further includes control logic for notifying an insurance company of a vehicle operator's insurability score based on one or more of the following: a predetermined schedule, the amount of distance traveled by the host vehicle operator, identified behavior changes, host vehicle location changes, and host vehicle commute pattern changes.

[0022] In yet another aspect of the present disclosure, the ninth control logic further includes control logic for presenting operator score information and vehicle operation suggestions on one or more of the following: the infotainment display of the host vehicle, the instrument cluster of the host vehicle, the interior rearview screen of the host vehicle, a cellular device, a laptop computer, or a tablet computer. The vehicle operation suggestions include: score improvement suggestions, driving behavior improvement suggestions, driving route modification suggestions, and host vehicle mode selection suggestions.

[0023] In several additional aspects of the present disclosure, a method for measuring insurability based on relative vehicle operator performance is provided, including capturing information about a host vehicle and one or more remote vehicles via one or more sensors, and capturing environmental information about the surroundings of the host vehicle and one or more remote vehicles. The method further includes utilizing a cloud computing server in communication with the host vehicle and one or more remote vehicles, and utilizing one or more controllers disposed in each of the host vehicle, one or more remote vehicles, and the cloud computing server; each controller includes a processor, a memory, and one or more input / output (I / O) ports; the I / O ports communicate with one or more sensors; the memory stores program control logic; and the processor executes the program control logic. The method further includes utilizing the controller to execute the program control logic, which includes an application for measuring insurability based on relative vehicle operator performance (MIROP application). The MIROP application includes: identifying event information within the data obtained from one or more sensors; transmitting the event information to the cloud computing server via the I / O ports of one or more of the controllers in the host vehicle and the I / O ports of one or more remote vehicles; evaluating the physical location and proximity of the host vehicle relative to the remote vehicles participating in the method. The MIROP application further includes: evaluating the road surface condition of the section of the road on which the host vehicle is traveling; estimating the traffic density on the section; integrating the host vehicle behavior data and identifying event IDs within the host vehicle behavior data. The MIROP application further includes: calculating a vehicle operator insurability score; automatically notifying an insurance company of the vehicle operator insurability score; and automatically presenting score information and vehicle operation suggestions to the host vehicle operator via a human-machine interface (HMI) to improve the vehicle operator insurability score.

[0024] In yet another aspect of the present disclosure, the method further includes: detecting event information, where the event information includes examples of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, front collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or a remote vehicle. The method further includes: comparing examples of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or a remote vehicle with an acceleration threshold, a braking threshold, and a turning threshold; and periodically transmitting the event information to a cloud computing server, where the event information is related to examples of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or a remote vehicle that reach or exceed the acceleration threshold, the braking threshold, and the turning threshold.

[0025] In yet another aspect of the present disclosure, the method further includes: confirming the position of the host vehicle relative to map information stored in a map database, and determining the position of one or more remote vehicles relative to map information stored in the map database. The method further includes determining that one or more of the remote vehicles are at or below a physical distance threshold from the host vehicle, or determining that one or more of the remote vehicles have traversed a road segment within or in a threshold amount of time relative to the host vehicle.

[0026] In yet another aspect of the present disclosure, the method further includes: using data from one or more sensors to estimate the road surface type, road surface condition, the presence of obstacles on the road segment, and the position of lane markings on the road segment; and obtaining information from one or more application programming interfaces (APIs) including a weather API. The weather API provides weather information about the environment around the host vehicle on the road segment.

[0027] In yet another aspect of the present disclosure, the method further includes: obtaining information from one or more application programming interfaces (APIs) including one or more traffic APIs. The traffic APIs report current and historical traffic information related to the road segment to the host vehicle. And using data from the traffic APIs and from one or more sensors to estimate traffic density and determine when the host vehicle approaches or passes a traffic signal, where the traffic density includes the traffic signal status with an accuracy of approximately one second.

[0028] In yet another aspect of the present disclosure, the method further includes: identifying event IDs corresponding to instances of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, front collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or remote vehicles. The method also includes determining when one or more remote vehicle perspectives are available. When determining that one or more remote vehicle perspectives are available, the method utilizes the remote vehicle perspectives to provide context for the behavior of the host vehicle and accesses a road profile database that includes physical characteristics and background information of a road segment, including traffic data, time-of-day information, and road surface information associated with the road segment.

[0029] In yet another aspect of the present disclosure, the method further includes: calculating first-order vehicle operator driving characteristics, including: calculating aggressiveness x(t) via sudden acceleration a(t) and close following distance b(t); calculating average aggressiveness according to the following formula:

[0030] II.

[0031] Calculating a derived time series of vehicle operator driving parameters of interest, including calculating the standard deviation of aggressiveness according to the following formula:

[0032] III.

[0033] Calculating the vehicle operator aggressiveness trend over time according to the following formula:

[0034] IV.

[0035] Wherein, is a normalized feature, and indicates whether the vehicle operator has become more aggressive, less aggressive, or equally aggressive within a predetermined amount of time. The method also includes calculating a cumulative distribution function (CDF) that ranks the operator performance of all participating host and remote vehicles according to the following formula:

[0036] I.

[0037] where each a n defines the characteristics of a specific event Q n for each vehicle n, and w i defines a weighting factor; and determining the relative performance of the vehicle operator compared to remote vehicle operators in a similar situation in a similar context on a road segment or similar road segment.

[0038] In yet another aspect of the present disclosure, the method further includes: selectively notifying an insurance company of an insurability score for a vehicle operator based on one or more of: a predetermined schedule, an amount of distance traveled by a primary vehicle operator, an identified behavior change, a change in a primary vehicle location, and a change in a primary vehicle commuting pattern; and presenting operator score information and vehicle operation suggestions on one or more of: an infotainment display of the primary vehicle, an instrument cluster of the primary vehicle, an interior rearview screen of the primary vehicle, a cellular device, a laptop computer, or a tablet computer. The vehicle operation suggestions include: score improvement suggestions, driving behavior improvement suggestions, driving route modification suggestions, and primary vehicle mode selection suggestions.

[0039] In several additional aspects of the present disclosure, a method for measuring insurability based on relative vehicle operator performance is provided, including: capturing information about a host vehicle and one or more remote vehicles via one or more sensors, and capturing environmental information about the environment around the host vehicle and one or more remote vehicles. The method further includes utilizing a cloud computing server in communication with the host vehicle and one or more remote vehicles, and utilizing one or more controllers disposed in each of the host vehicle, one or more remote vehicles, and the cloud computing server. Each controller includes a processor, a memory, and one or more input / output (I / O) ports. The I / O ports communicate with one or more sensors. The memory stores program control logic. The processor executes the program control logic. The program control logic includes an application for measuring insurability based on relative vehicle operator performance (MIROP application). The MIROP application includes: identifying event information within data obtained from one or more sensors, including: detecting event information, where the event information includes: instances of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, forward collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or remote vehicles. The MIROP application further includes comparing instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or remote vehicles with acceleration thresholds, braking thresholds, and turning thresholds. The MIROP application further includes periodically transmitting the event information to the cloud computing server via the I / O ports of one or more of the controllers in the host vehicle and the I / O ports of one or more remote vehicles, where the event information is related to instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or remote vehicles that meet or exceed the acceleration thresholds, braking thresholds, and turning thresholds. The MIROP application further includes evaluating the physical location and proximity of the host vehicle relative to the remote vehicles participating in the method, including: confirming the location of the host vehicle relative to map information stored in a map database, and determining the location of one or more remote vehicles relative to map information stored in the map database; and determining that one or more of the remote vehicles are at or below a physical distance threshold from the host vehicle, or determining that one or more of the remote vehicles have crossed a road segment relative to the host vehicle within a threshold amount of time or within the threshold amount of time. The MIROP application further includes evaluating the road surface condition of the road segment traveled by the host vehicle, including: using data from one or more sensors to estimate the road surface type, road surface condition, the presence of obstacles on the road segment, the location of lane markings on the road segment; and obtaining information from one or more application programming interfaces including a weather application programming interface (API). The weather API provides weather information about the environment around the host vehicle on the road segment.The MIROP application also includes estimating traffic density on a road segment, including: obtaining information from one or more application programming interfaces including one or more traffic application programming interfaces (APIs). The traffic API reports current and historical traffic information related to the road segment to the host vehicle. The MIROP application also includes using data from the traffic API and from one or more sensors to estimate traffic density and determine when the host vehicle approaches or passes a traffic signal, where the traffic density includes the traffic signal state with an accuracy of approximately one second. The MIROP application also includes integrating host vehicle behavior data and identifying event IDs within the host vehicle behavior data, including: identifying event IDs corresponding to instances of emergency braking, emergency acceleration, emergency turning, average speed, seat belt status, stability control status, forward collision avoidance (FCA) activation, lane departure warning (LDW) activation, driving distance, clock time, and fuel economy of the host vehicle and / or remote vehicles. The MIROP application also includes determining when one or more remote vehicle perspectives are available. When determining that one or more remote vehicle perspectives are available, the method uses the remote vehicle perspectives to provide context for the behavior of the host vehicle. The MIROP application also includes accessing a road profile database that includes physical characteristics and context information of the road segment, including traffic data, time-of-day information, and road surface information related to the road segment. The MIROP application also includes calculating a vehicle operator insurability score, including: calculating first-order vehicle operator driving characteristics; calculating a derived time series of vehicle operator driving parameters of interest; and applying a weighting factor to each to determine the relative performance of the vehicle operator compared to remote vehicle operators in similar situations in similar contexts on the road segment or similar road segments. The MIROP application also includes calculating aggressiveness x(t) via sudden acceleration a(t) and close following distance b(t); calculating the average aggressiveness according to the following formula:.

[0040] II.

[0041] Calculate the standard deviation of aggressiveness according to the following formula:

[0042] III. And

[0043] Calculate the vehicle operator aggressiveness trend over time according to the following formula:

[0044] IV.

[0045] Where is a normalized feature, and Indicates whether the operator of vehicles 12, 12’ has become more aggressive, less aggressive, or equally aggressive within a predetermined amount of time. The MIROP application also includes calculating a cumulative distribution function (CDF), which ranks the operator performance of all participating host and remote vehicles according to the following formula:

[0046] I.

[0047] where each a n defines a characteristic of a specific event Q for each vehicle n n and w i defines a weighting factor. The MIROP application also includes automatically notifying an insurance company of the insurability score of the vehicle operator, including: selectively notifying the insurance company of the insurability score of the vehicle operator based on one or more of the following: a predetermined schedule, the amount of distance traveled by the host vehicle operator, identified behavior changes, host vehicle location changes, and host vehicle commute pattern changes. The MIROP application also includes automatically presenting score information and vehicle operation suggestions to the host vehicle operator via a human-machine interface (HMI) to improve the insurability score of the vehicle operator, including: presenting the operator score information and vehicle operation suggestions on one or more of the following: the infotainment display of the host vehicle, the instrument cluster of the host vehicle, the interior rearview screen of the host vehicle, a cellular device, a laptop computer, or a tablet computer. The vehicle operation suggestions include: score improvement suggestions, driving behavior improvement suggestions, driving route modification suggestions, and host vehicle mode selection suggestions.

[0048] Further application areas will become apparent from the description provided herein. It should be understood that these descriptions and specific examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way.

[0050] Figure 1 is a schematic diagram of a system for measuring insurability based on relative vehicle operator performance according to an exemplary embodiment;

[0051] Figure 2A is according to an exemplary embodiment Figure 1 of a map image of a road segment to which a system for measuring insurability based on relative vehicle operator performance is applied;

[0052] Figure 2B is a chart depicting event information and score rankings of multiple vehicles, the multiple vehicles passing through Figure 2A the road segment and utilizing Figure 1A system for measuring insurability based on relative vehicle operator performance;

[0053] Figure 2C is a graphical representation of the cumulative distribution function (CDF) depicting the relative performance of multiple vehicles according to an exemplary embodiment, and utilizes Figure 2B a system for measuring insurability based on relative vehicle operator performance; and Figure 1 is a flowchart depicting a method for measuring insurability based on relative operator performance according to an exemplary embodiment.

[0054] Figure 3 DETAILED DESCRIPTION DETAILED DESCRIPTION

[0055] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0056] Referring to Figure 1 , Figure 2A , Figure 2B and Figure 2C , a system 10 for measuring insurability based on relative operator performance is shown. The system 10 generally includes one or more vehicles 12, such as a host vehicle 12 and a remote back-end or cloud computing server 14, and may also include infrastructure such as one or more cell towers 16, Global Positioning System (GPS) satellites 18, traffic signal devices (not specifically shown), etc. Although the host vehicle 12 shown is a sports car, it should be understood that the host vehicle 12 can be any of a variety of vehicles 12 without departing from the scope or intent of the present disclosure, including but not limited to sedans, trucks, sport utility vehicles (SUVs), buses, semi-trailer tractors, tractors for agriculture or construction, etc., boats, and aircraft such as airplanes or helicopters. Additional remote vehicles 12' may also be included in the system 10 without departing from the scope or intent of the present disclosure.

[0057] The host vehicle 12, the remote vehicle 12', and the cloud computing server 14 each include one or more controllers 20. The controller 20 is a non-generic electronic control device that has a pre-programmed digital computer or processor 22, a non-transitory computer-readable medium or memory 24 for storing data such as control logic, software applications, instructions, computer code, data, look-up tables, etc., and a transceiver or input / output (I / O) port 26. The computer-readable medium includes any type of medium that can be accessed by a computer, such as read-only memory (ROM), random access memory (RAM), hard disk drive, compact disc (CD), digital video disc (DVD), or any other type of memory. The "non-transitory" computer-readable memory 24 does not include wired, wireless, optical, or other communication links that transmit transitory electrical signals or other signals. The non-transitory computer-readable memory 24 includes media in which data can be permanently stored and media in which data can be stored and then rewritten, such as rewritable optical discs or erasable storage devices. The computer code includes any type of program code, including source code, object code, and executable code. The processor 22 is configured to execute the code or instructions. In the vehicle 12, the controller 20 can be a dedicated Wi-Fi controller or an engine control module, a transmission control module, a body control module, an infotainment control module, etc. The I / O port 26 is configured to perform wireless communication using Wi-Fi protocols under IEEE 802.11x, cellular protocols (such as Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Wireless Local Loop (WLL), General Packet Radio Service (GPRS), 1G, 2G, 3G, 4G Long Term Evolution (LTE), 5G, etc.).

[0058] The memory 24 can store one or more application programs 28. The application program 28 is a software program configured to perform a specific function or set of functions. The application program 28 can include one or more computer programs, software components, instruction sets, procedures, functions, objects, classes, instances, related data, or portions thereof suitable for implementation in appropriate computer-readable program code. The application program 28 can be stored in the memory 24 of the on-vehicle controller 20 in the vehicle 16, or stored in an additional or separate memory, such as in the memory 24 of a cloud computing device such as the cloud computing server 14. Examples of the application program 28 include audio or video streaming services, games, browsers, social media, and an application for measuring insurability based on relative operator performance (MIROP) 30.

[0059] The host vehicle 12 obtains and / or generates operation information from various sources, including but not limited to: one or more sensors 32, which are disposed on the host vehicle 12 and obtain information of the host vehicle 12, including the remote processing information and communication information of the host vehicle 12, such as the speed of the host vehicle 12, the position information of the host vehicle 12, the altitude of the host vehicle 12, etc. In several aspects, the sensors 32 disposed on the host vehicle 12 can include any one of a variety of sensor types, including but not limited to sensors 32 for detecting optical or electromagnetic information about the host vehicle 12, the remote vehicle 12', and the environment around the host vehicle and the remote vehicle 12, 12'. The sensors 32 can include but are not limited to: cameras, light detection and ranging (LiDAR) sensors, radio detection and ranging (RADAR) sensors, sound navigation and ranging (SONAR) sensors, ultrasonic sensors, or combinations thereof. The sensors 32 can also be motion sensors, such as an inertial measurement unit (IMU). The IMU uses a combination of some or all of the following components to measure and report the attitude or position, linear velocity, acceleration, and angular velocity relative to a global reference frame: accelerometers, gyroscopes, and magnetometers. In some examples, the IMU can also utilize global positioning system (GPS) data to indirectly measure the attitude or position, speed, acceleration, and angular velocity of the host vehicle 12 and / or one or more remote vehicles 12'.

[0060] In a further example, the host vehicle 12, the remote vehicle 12', and / or the remote cloud computing server 14 can obtain environmental data about the area around the host vehicle 12, such as traffic condition information, road condition and pavement information, weather information, etc. from a remote sensor 32 source (such as sensors 32 of infrastructure including GPS satellites 18, cellular towers 16, or roadside sensing devices, etc.).

[0061] The system 10 integrates the driving data of the host vehicle 12 on the road segment 34 and for each trip of the host vehicle 12 to characterize the operator performance of the host vehicle 12. The operator performance of the host vehicle 12 can be presented to the operator of the host vehicle 12 via a human-machine interface (HMI) 35. In several aspects, the HMI 35 includes one or more devices capable of presenting information to the operator of the host vehicle 12 and interacting with the operator of the host vehicle 12, such as a screen disposed within the host vehicle 12, such as an instrument cluster, an infotainment screen, a head-up display (HUD), an interior rearview screen, such as a rearview mirror enhanced by a screen. In additional examples, the HMI 35 can be a device that is partially or completely separated from the host vehicle 12, such as the operator's cellular device, laptop computer, or tablet computer, or other such third-party devices that communicate with the controller 20 of the host vehicle 12.

[0062] The driving data can include any one of a variety of data, including situations such as emergency braking, late-night driving, emergency acceleration, emergency turning, etc., as well as driving distance, clock time, fuel economy, average speed, speed equal to or greater than a threshold speed, seat belt status, stability control status, forward collision avoidance (FCA) events, lane departure warning (LDW) events, and the like. In several aspects, it should be understood that emergency or hard braking, emergency or hard acceleration, and / or emergency turning or rapid steering inputs can be characterized by detecting an acceleration that reaches or exceeds an acceleration threshold. For example, the threshold for emergency or hard acceleration and / or braking can be defined as greater than or equal to 0.3G, where G is the acceleration due to gravity. Similarly, the threshold for emergency turning or rapid steering inputs can be defined as greater than or equal to 0.6G. However, it should be understood that without departing from the scope or intent of the present disclosure, the thresholds for emergency or hard acceleration and / or braking and the threshold for emergency turning can vary significantly depending on the application, vehicle, and situation.

[0063] In additional aspects, the host vehicle 12 obtains vehicle data from sensors 32 operating on the controller area network (CAN) bus 33 of the host vehicle 12, including the following distance behind an additional remote vehicle 12', a congestion driving state based on the distance between vehicles, side object data, camera data, and the like. For a specific section 34, the speed of the host vehicle 12 relative to the speed limit and / or the ambient average traffic speed can also be recorded. The sensors 32 can also scan the area around the host vehicle 12 to determine the position of the host vehicle 12 or the offset deviation 36 of the host vehicle 12 within the lane 38 along the section 34. In several aspects, the offset deviation 36 of the host vehicle 12 is the relative position of the host vehicle 12 within the lane 38 and relative to the lane markings 40 or the edge of the lane 38 (not specifically shown), especially compared to the positions of other remote vehicles 12' located in the same lane 38 at a similar time point. The sensors 32 record lane 38 changes, lane 38 change attempts, and lane 38 change aborts, such as lane 38 change attempts using advanced driver assistance system (ADAS) alerts and / or corrections.

[0064] Sensors 32 installed on infrastructure or GPS satellites 18 can add to record the behavior information of the host vehicle 12, including but not limited to: each trip or consecutive red-light running violations, reverse driving, urban and / or highway driving, etc. Similarly, the sensors 32 of the host vehicle 12 and the sensors 32 of other vehicles 12' and / or infrastructure can perform microscopic collaborative behavior analysis based on locally sensed host vehicle 12 data. For example, the sensors 32 of the host vehicle 12, other vehicles 12', and / or infrastructure can determine the behavior characteristics of the host vehicle 12, such as not yielding to the vehicle 12' at an intersection, merging behavior, rapid steering movement (such as lane-changing behavior), remote horn activation, delayed braking event, braking behavior deviating from the behavior of other vehicles 12' in the surrounding traffic, and the use of the host vehicle 12 control or application. In several aspects, the above data is collected for each road segment 34 and enables comparison between other vehicles 12' on the same road segment 34, and / or enables comparison between other vehicles 12' for each trip. Standardized measurement of the behavior of the host vehicles 12, 12' is performed by quantifying the number of events for each road segment 34, each trip, each day, etc. In several aspects, the events described herein are classified into a list of event identifiers (event IDs) that characterize the behavior of the vehicles 12, 12' when operating.

[0065] In several aspects, the sensors 32 data can be obtained and analyzed periodically, enabling continuous measurement over time. That is, the sensors 32 data can be integrated by road segment 34, and the operator behavior of the host vehicle 12 is scored based on the relative deviation from the norm, such as the speed increment between the host vehicle 12 and the surrounding traffic, or lane 38 tracking relative to other remote vehicles 12'.

[0066] In additional aspects, the sensors 32 data can be obtained and analyzed for each event, enabling the characterization of intentional or reactive events and / or providing the ability to assess fault in a particular event instance. Events such as emergency braking, lane 38 change, etc. are recorded. An abnormal local event initiates a comparison of the scenario at the current time point and evaluates the vehicles 12, 12' involved to determine which vehicles 12, 12' reacted "correctly" and which vehicles 12, 12' may be "at fault". For example, the host vehicle 12 that fails to yield to another host vehicle 12' arriving at a particular intersection 48 on the road may be characterized as "at fault". Similarly, depending on the circumstances, a prior host vehicle 12 (not specifically shown) that brakes with a higher intensity than required and causes a following remote vehicle 12' to initiate an emergency braking event can be similarly characterized as "at fault", even if the following remote vehicle 12' collides with the prior host vehicle 12.

[0067] In several aspects, the context or situation in which emergency or hard acceleration, braking, or tight turns occur promotes the acceleration threshold. For example, acceleration of the host vehicle 12 on a short highway entrance ramp from a surface street to an interstate highway may cause the host vehicle 12 operator to apply full throttle or nearly full throttle, thereby causing the host vehicle 12 to exceed the 0.3G threshold that applies to the same host vehicle 12 when the host vehicle 12 is traveling along a surface street in low traffic conditions. That is, without departing from the scope or intent of the present disclosure, the acceleration threshold for a highway entrance ramp may exceed the acceleration threshold applicable to surface street driving. Similarly, the system 10 can utilize data from various sensor 32 sources to determine the road profile over a period of time. The road profile can include physical features of the road segment 34, such as: the number of lanes 38 within the road segment 34; the type of road surface (i.e., dirt, gravel, cement, asphalt, etc.); the presence of obstacles along the road segment 34, such as potholes, curbs, etc.; the location of lane markings 40 on the road segment 34; typical traffic patterns along the road segment 34 at a particular time of day, etc. For example, a road segment 34 in a downtown portion of a major metropolitan area such as Manhattan, Tokyo, etc., will experience higher vehicle traffic during the morning and afternoon rush hours than other physically similar road segments 34 in suburban areas. The road segment 34 is subdivided into sub-segments of predetermined lengths. In one example, the predetermined length of the sub-segment is approximately five hundred (500) meters, however, the predetermined length may be significantly different from 500 meters without departing from the scope or intent of the present disclosure. In a further example, the road segment 34 may be subdivided based on the location of an intersection or junction 48 or according to a complete trip defined by a key cycle (i.e., key-on to key-off), etc. Such data is then normalized over a trip or a series of trips.

[0068] An event is defined as a response by one of the subject vehicles 12 by analyzing local sensor 32 data and / or comparing the data from each subject vehicle 12, 12' within the cloud computing server 14. License plate information for each subject vehicle 12, 12' may be obtained by the sensor 32 and used to provide a negative impact on the insurability score based on a lookup table stored in the memory 24 of the cloud computing server 14. In several aspects, the insurability score is defined by a relative ranking process based on a cumulative distribution function (CDF) and / or utility function calculation that can be used to extract individual scores.

[0069] Now more specifically turn to Figure 2A , Figure 2B and Figure 2C And continue to refer to Figure 1 , Figure 2A An exemplary road segment 34 is shown in FIG. Figure 2B As shown in the diagram 50, Figure 2CA graphical representation 52 of the CDF data extracted from the graph 50 is shown. Specifically, the road segment 34 extends from the first intersection 48 to the second intersection 48'. Data obtained from sensors 32 associated with a plurality of host vehicles 12 and remote vehicles 12' along the exemplary road segment 34 are acquired, accumulated, and used in CDF and / or utility function calculations to extract individual scores for each vehicle 12, 12'. Figure 2B The leftmost column of Figure 2B includes the identifiers of each vehicle 12, 12' that is traveling along or has traveled along the exemplary road segment 34 for a known period of time. Column Q 1 through Q n include data obtained from the sensors 32 related to specific event metrics. For example, column Q 1 includes lane 38 change (LC) information for each vehicle 12, 12'. Column Q 2 includes emergency braking events and the like for each vehicle 12, 12'. For each vehicle 12, 12' (i.e., Figure 2B the vehicles 1, 2,..., m shown in the leftmost column of the graph 50 of Figure 2B ), all Q 1 through Q n the total ranking of the event data is shown in the rightmost column as follows:

[0070] I.

[0071] Then, the relative ranking of each of the vehicles 12, 12' in the graph 50 can be graphically represented as a CDF distribution line 54 as Figure 2C shown. Each data point 56 along the CDF distribution line 54 defines a different vehicle 12, 12' ranking. In several aspects, the ranking of each vehicle 12, 12' is defined by at least first-order and second-order driving characteristics. The first-order driving characteristics may include aggressiveness X(t) via sudden acceleration a(t) and close following distance b(t), etc. The second-order driving characteristics include the derived time series of the first-order driving characteristics, and a weighting factor is applied to them according to the mean value, standard deviation, and trend. The mean value can be expressed as:

[0072] II.

[0073] which defines the average aggressiveness X(t) of a specific vehicle 12, 12' operator. Similarly, the standard deviation can be expressed as:

[0074] III.

[0075] which defines the boundary of the aggressiveness of a specific vehicle 12, 12' operator. The trend can be expressed as:

[0076] IV.

[0077] Wherein, is a normalized feature, and indicates whether the operator of vehicles 12, 12' becomes more aggressive, less aggressive, or equally aggressive within a predetermined amount of time. In several respects, the trend can be considered as a change in the relative aggressiveness X(t) compared to the operators of other vehicles 12, 12' under similar conditions within a predetermined amount of time. The predetermined amount of time can vary depending on the application. However, in some examples, the predetermined amount of time can be about four to six weeks.

[0078] Now refer to Figure 3 and continue to refer to Figure 1 , Figure 2A , Figure 2B and Figure 2C, the control logic executed within the MIROP application 30 is shown as a plurality of method 200 steps in flowchart form. The method 200 begins at block 202 when the host vehicle 12 is started by an operator of the host vehicle 12. At block 204, when the host vehicle 12 is started, the CAN bus 33 performs event detection based on data obtained from sensors 32 on the vehicle. Event detection can include location, time, event ID, etc. as well as maps. At block 206, the system 10 performs target classification based on the sensors 32 communicating on the CAN bus 33. Target classification can include other information about the remote vehicle 12', information about the road segment 34, etc. At block 208, the system 10 periodically transmits the location information, event ID, etc. of the host vehicle 12 to the cloud computing server 14 via the I / O port of the controller 20 of the host vehicle 12. At block 210, within the cloud computing server 14, the system 10 receives the periodic transmission from the host vehicle 12 using a message processor. At block 212, the system 10 compares the location information of the host vehicle 12 with the map information stored in the map database 214 to confirm the location reported by the host vehicle 12. At block 216, the message processor of the cloud computing server 14 sends the periodic transmission from the host vehicle 12 to the crowdsourcing database. In several aspects, the crowdsourcing database includes not only the periodic transmission from the host vehicle 12 but also the periodic transmissions from other remote vehicles 12' that utilize the MIROP application 30. At block 218, the system 10 employs control logic that performs a lookup function to determine which participating remote vehicles 12' may be reporting or may have reported relevant data for the MIROP application 30. In several aspects, the relevant participating remote vehicles 12' can be at or below a predetermined or variable physical distance threshold from the host vehicle 12, or can cross the relevant road segment 34 within a predetermined or variable threshold amount of time, where the data reported by the remote vehicle 12' within the threshold amount of time can accurately apply to the state of the host vehicle 12. At block 220, the system 10 employs control logic to obtain weather information from one or more application programming interfaces (APIs), such as a weather API provided by the National Weather Service, etc. Other sources of weather information, such as a local weather service API, crowdsourced weather information obtained from remote vehicles 12' and / or infrastructure, etc. The weather data from block 220 is forwarded to the crowdsourcing database at block 216. The method 200 proceeds from block 218 to block 222, where the MIROP application 30 estimates the road surface conditions on the relevant road segment 34 based on the information from block 218 and the weather data obtained at block 220.

[0079] The MIROP application 30 proceeds from block 222 to block 224. At block 224, the MIROP application 30 calls a traffic API to obtain current and historical traffic information on section 34. In several aspects, the traffic API can be located in one or more cloud computing servers 14 and can obtain the status of traffic lights, etc. and associate it with the MIROP application 30 and the system 10. Additionally, the traffic API can send and receive information regarding traffic violations, such as the number of red traffic lights or stop signs that one or more vehicles 12, 12' have improperly passed through, or the number or relative rate of one or more vehicles 12, 12' that are passing through a yellow traffic light, and / or the acceleration rate of one or more vehicles 12, 12' when passing through a yellow or red traffic light, etc. The traffic violation information can be stored in one or more traffic violation databases within the cloud computing server 14, etc., and the data contained therein can be compared with the behavior of the host vehicle 12 and one or more remote vehicles 12'.

[0080] At block 226, the MIROP application 30 uses the data from blocks 222 and 224 to generate a traffic density estimate. The traffic density estimate takes into account the traffic light status with an accuracy of approximately + / - one second and uses the data of the host vehicle 12 to determine whether the host vehicle 12 is approaching or passing a traffic light on section 34, including determining whether the host vehicle 12 is passing through a yellow or red traffic light, or otherwise committing a traffic violation listed in the traffic violation database. At block 228, the control logic within the MIROP application 30 is executed to integrate periodic data from the host vehicle 12, from the remote vehicles 12', and from sensors 32 of the infrastructure, etc. Additionally, at block 228, the control logic of the MIROP application 30 integrates information from current and historical vehicles 12, 12' that have passed through the relevant section 34 over a predetermined amount of time, where the predetermined amount of time is selected to be relevant to the current context of the host vehicle 12. At block 230, the method 200 executes the control logic for determining event IDs within the data of the MIROP application 30.

[0081] At block 232, method 200 executes the control logic of the MIROP application 30, which determines whether a perspective of the remote vehicle 12’ is available. That is, when the remote vehicle 12’ is within a predetermined distance of the host vehicle 12 along the same road segment 34 for a predetermined amount of time, the MIROP application 30 can determine that the remote vehicle 12’ can provide a relevant remote vehicle perspective that provides the context of the host vehicle 12’s actions. When the perspective of the remote vehicle 12’ is available, method 200 proceeds to block 234, where the MIROP application 30 performs event analysis and generates consensus information. In several aspects, the consensus information includes a relative assessment of the driving behavior of the operator of the host vehicle 12 relative to a behavior norm to accurately assess the risk of the operator of vehicle 12 based on the context.

[0082] At block 236, the method causes the control logic of the MIROP application 30 to access a road profile database located in the cloud computing server 14. When the perspective of the remote vehicle 12’ is not available or when the event analysis and consensus are complete, method 200 proceeds to block 238, where the road profile from block 236 is used to generate an operator score for the host vehicle 12. In several aspects, the operator score of the host vehicle 12 defines the relative risk level of the operator of the host vehicle 12 compared to the operators of other similarly situated remote vehicles 12’ that are in a similar context on the same or a similar road segment 34, or that have traveled or made the same or a similar trip under similar circumstances.

[0083] Method 200 proceeds from block 238 to block 240, where the operator score of the host vehicle 12 is added to a performance database. The performance database is stored in the memory 24 of one or more cloud computing servers 14 and includes a record of the operator scores of the host vehicle 12 integrated over time. Method 200 proceeds from the performance database at block 240 to block 242, where the operator score information of the host vehicle 12 is periodically packaged for transmission at block 244 to an insurance company, and / or to a data processor 246 within the host vehicle 12. In several aspects, the packaged information can be transmitted based on a predetermined schedule, the amount of distance traveled by the operator of the host vehicle 12, and / or based on changes in behavior, location, commute pattern, etc. Changes in behavior can include, but are not limited to, changes in driving habits, such as acceleration and deceleration rates, frequency of turn signal use during lane changes, etc. In a further example, changes in behavior can include changes in commute pattern, such as use of an alternate route, use or non-use of surface streets instead of highway driving, etc.

[0084] At block 244, the insurance company can use the operator performance information of the host vehicle 12 from the performance database to determine whether the operator of a particular host vehicle 12 continues to operate the host vehicle 12 in a consistent manner, and / or whether the operator of the host vehicle 12 has changed behavior to operate the host vehicle 12 in a manner that indicates an increased or decreased assessed risk. The insurance company can then change the insurance rate based on the increased assessed risk, decreased assessed risk, etc.

[0085] From block 246, the MIROP application 30 forwards the operator score information of the host vehicle 12 to the HMI 35 at block 248. Without departing from the scope or spirit of the present disclosure, the operator score information of the host vehicle 12 can be presented on the HMI 35 in a variety of different ways. In some examples, the operator score information of the host vehicle 12 can be presented together with score improvement suggestions, driving behavior improvement suggestions, driving route modification suggestions, host vehicle 12 mode selection suggestions, etc. From block 248, method 200 either returns to the CAN event detection at block 204 while the host vehicle 12 is operating in the key-on state, or proceeds to block 250 when the host vehicle 12 is in the key-off state. At block 250, method 200 ends. When the ignition of the host vehicle 12 is engaged again in the key-on state, method 200 can be started again, in which case method 200 returns from block 250 to block 202.

[0086] The system 10 and method 200 of the present disclosure for measuring insurability based on the operator performance of the associated vehicle 12 provide several advantages. These advantages include the ability to derive a high-fidelity estimate of the operator performance of the vehicle 12 based on how the vehicle 12 operator behaves compared to other vehicle 12 operators at substantially the same time and in substantially the same geographical location. The system 10 and method 200 effectively and efficiently integrate the driving data for each segment 34, each trip, etc., and score the behavior based on the relative deviation from the behavior norm to accurately assess the operator risk of the vehicle 12 based on the context while minimizing false positives due to road design, effectively and accurately determine the relative braking, lateral acceleration, speed consistency of the vehicle 12 operator relative to its peers, and accurately assess the skills of the vehicle 12 operator while operating on existing hardware and leveraging existing systems. Thus, the system 10 and method 200 of the present disclosure significantly increase the functionality and accuracy of vehicle 12 operator risk assessment while maintaining or reducing complexity, and at the same time improve the accuracy of risk assessment and risk scoring.

[0087] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. These variations should not be regarded as departing from the scheme and scope of the present disclosure.

Claims

1. A system for measuring insurability based on relative vehicle operator performance, the system comprising: a host vehicle, and one or more remote vehicles; one or more sensors that capture information of a host vehicle and remote vehicles and capture environmental information about the environment of the host vehicle and the one or more remote vehicles; as well as a cloud computing server in communication with the host vehicle and the one or more remote vehicles; wherein each of the host vehicle, the one or more remote vehicles, and the cloud computing server has a controller, the controller including a processor, a memory, and one or more input / output (I / O) ports, the I / O ports communicating with the one or more sensors; the memory storing program control logic; the processor executing the program control logic; the program control logic including an application for measuring insurability based on relative vehicle operator performance (MIROP application), the MIROP application including: first control logic for identifying event information within data obtained from the one or more sensors; a second control logic for transmitting the event information to the cloud computing server via an I / O port of a controller of one or more of the host vehicles and an I / O port of the one or more remote vehicles; third control logic for evaluating the physical location and proximity of the host vehicle relative to remote vehicles participating in the system; a fourth control logic, the fourth control logic being used to evaluate a road surface condition of a road section on which the host vehicle is traveling; a fifth control logic, the fifth control logic being used to estimate the traffic density on the road segment; a sixth control logic for integrating the host vehicle behavior data and identifying an event ID within the host vehicle behavior data; seventh control logic for calculating a vehicle operator insurability score; eighth control logic for automatically notifying an insurance company of the vehicle operator insurability score; and A ninth control logic is provided for automatically presenting score information and vehicle operation suggestions to a host vehicle operator via a human machine interface (HMI) to improve the vehicle operator insurability score.

2. The system according to claim 1, wherein: The first control logic further includes: Control logic for detecting event information including instances of emergency braking, emergency acceleration, emergency turning, average speed, seatbelt status, stability control status, frontal collision avoidance (FCA) activation, lane departure warning (LDW) activation, distance traveled, clock time, and fuel economy for the host vehicle and / or remote vehicles.

3. The system according to claim 2, wherein: The first control logic further includes: control logic for comparing instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or remote vehicle to acceleration thresholds, braking thresholds, and turning thresholds; and The second control logic is executed to periodically transmit event information to the control logic of the cloud computing server, wherein the event information is related to instances of emergency braking, emergency acceleration, and emergency turning of the host vehicle and / or the remote vehicle that reach or exceed the acceleration threshold, braking threshold, and turning threshold.

4. The system according to claim 1, wherein: The third control logic further includes: control logic for determining a position of the host vehicle relative to map information stored in a map database; control logic for determining the position of the one or more remote vehicles relative to map information stored in the map database; and Control logic for determining that one or more of the remote vehicles is at or below a physical distance threshold from the host vehicle, or determining that one or more of the remote vehicles has traversed the road segment in or within a threshold amount of time relative to the host vehicle.

5. The system according to claim 1, wherein: The fourth control logic further includes: control logic for using data from the one or more sensors to estimate the type of road surface, the condition of the road surface, the presence of obstacles on the road segment, and the location of lane markings on the road segment; and Control logic for obtaining information from one or more application programming interfaces (APIs) including a weather application programming interface (API), wherein the weather API provides weather information surrounding the host vehicle on the road segment.

6. The system according to claim 1, wherein: The fifth control logic further includes: control logic for obtaining information from one or more application programming interfaces (APIs), including one or more traffic APIs, wherein the traffic APIs report current and historical traffic information related to the road segment to the host vehicle; and Data from the traffic API and from the one or more sensors is utilized to estimate traffic density, including a traffic light state to approximately one second accuracy, and control logic to determine when the host vehicle approaches or passes through a traffic light.

7. The system according to claim 1, wherein: The sixth control logic further includes: control logic for identifying event IDs corresponding to instances of emergency braking, emergency acceleration, emergency turning, average speed, seatbelt status, stability control status, frontal collision avoidance (FCA) activation, lane departure warning (LDW) activation, distance traveled, clock time, and fuel economy for the host vehicle and / or remote vehicle; control logic for determining when one or more remote vehicle perspectives are available, wherein upon determining that one or more remote vehicle perspectives are available, the remote vehicle perspectives are utilized to provide context for the host vehicle's behavior; and Control logic for accessing a road profile database that includes physical characteristics of road segments and contextual information, including traffic data, time of day information, and road surface information associated with the road segment.

8. The system according to claim 1, wherein: The seventh control logic further includes: control logic for calculating first-order vehicle operator driving characteristics; control logic for calculating a derived time series of a vehicle operator driving parameter of interest; and Control logic for applying a weighting factor to each to determine the relative performance of the vehicle operator compared to a similarly situated remote vehicle operator in a similar context on the road segment or similar road segments.

9. The system according to claim 8, further comprising: Control logic for calculating the aggressiveness x(t) via the sudden acceleration a(t) and the close following distance b(t); Control logic for calculating average aggressiveness according to the following formula: Ⅱ. Control logic for calculating the standard deviation of aggressiveness according to the following formula: Ⅲ. Control logic for calculating the vehicle operator aggressiveness trend over time according to the following formula: Ⅳ. in, is a standardized feature, and Indicates whether the operator of the vehicle 12 , 12 ′ has become more aggressive, less aggressive, or just as aggressive over a predetermined amount of time; and Control logic for calculating a cumulative distribution function (CDF) that ranks the operator performance of all participating host and remote vehicles according to the following formula: I. Each of these n Defines a specific event Q for each vehicle n n The characteristics of w i The weighting factors are defined.

10. The system according to claim 9, wherein: The eighth control logic further includes: Control logic for selectively notifying an insurance company of the vehicle operator insurability score based on one or more of a predetermined schedule, an amount of distance traveled by the host vehicle operator, an identified behavior change, a host vehicle location change, and a host vehicle commute pattern change.

Images