EP3963285A1

EP3963285A1 - Risk profiles for fleet management of a fleet of vehicles and its vehicle operators

Info

Publication number: EP3963285A1
Application number: EP20798743.9A
Authority: EP
Inventors: Reza Ghanbari; Nicholas Shayne Brookins; David Forney; Jason Palmer; Mark Freitas
Original assignee: SmartDrive Systems Inc
Current assignee: SmartDrive Systems Inc
Priority date: 2019-05-01
Filing date: 2020-04-07
Publication date: 2022-03-09
Also published as: WO2020222983A1; EP3963285A4

Abstract

Systems and methods for creating and using risk profiles for management of a fleet of vehicles are disclosed. Fleet management may include determining the performance levels of particular vehicle operators. The risk profiles characterize values representing likelihoods of occurrences of vehicle events, based on previously detected vehicle events. Exemplary implementations may: obtain vehicle event information for vehicle events that have been detected by the fleet of vehicles; or more of a risk profile; obtain a point of origin for and a target destination of a particular vehicle; determine a set of routes from the point of origin to the target destination; determine individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes; select the first route from the set of routes; and provide the selected first route to the particular vehicle.

Description

RISK PROFILES FOR FLEET MANAGEMENT OF A FLEET OF VEHICLES

AND ITS VEHICLE OPERATORS

FIELD OF THE DISCLOSURE

(01) The present disclosure relates to systems and methods for creating and using risk profiles for fleet management of a fleet of vehicles and its vehicle operators. Risk profiles may be specific to one or more of individual locations or areas, vehicle types, types of vehicle events, and/or vehicle operators. Fleet management may include determining the

performance levels of vehicle operators.

BACKGROUND

(02) Systems configured to record, store, and transmit video, audio, and sensor data associated with a vehicle, e.g. to monitor the speed of a vehicle, are known. Such systems may detect vehicle events such as speeding and transmit relevant event information to a stakeholder. Systems for monitoring and managing a fleet of vehicles are known.

SUMMARY

(03) One aspect of the present disclosure relates to a system configured for creating and using risk profiles for fleet management of a fleet of vehicles. The risk profiles may characterize values representing likelihoods of occurrences of vehicle events. The values may be based on previously detected vehicle events. The system may include one or more hardware processors configured by machine-readable instructions. The processor(s) may be configured to obtain vehicle event information for vehicle events that have been detected by the fleet of vehicles. The vehicle event information for the vehicle events may include locations of the vehicle events, vehicle types involved in the vehicle events, types of the vehicle events, and/or other information. The processor(s) may be configured to aggregate the vehicle event information for multiple ones of the events to create one or more of a first risk profile, a second risk profile, a third risk profile, and/or another risk profile. The first risk profile may be specific to individual locations. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events at the individual locations. The second risk profile may be specific to individual vehicle types. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events pertaining to the individual vehicle types. The third risk profile may be specific to individual types of the vehicle events.

The third risk profile may characterize a third set of values representing likelihoods of occurrences of vehicle events of the individual types of the vehicle events. The processor(s) may be configured to obtain a point of origin for a particular vehicle and a target destination the particular vehicle is intended to reach. The particular vehicle may have a particular vehicle type. The processor(s) may be configured to determine a set of routes from the point of origin to the target destination. The set of routes may include at least two different routes. The processor(s) may be configured to determine individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes. Determining the individual values (representing the likelihoods) may be based on one or more risk profiles and/or combinations thereof. The set of routes may include a first route and a second route. The determinations of the individual values may include a first determination of a first individual value for the first route and a second determination of a second individual value for the second route. The processor(s) may be configured to select the first route from the set of routes. The first route may be selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route. In other words, the likelihood of occurrences along the first route may be lower than the likelihood along the second route. The processor(s) may be configured to provide the selected first route to the particular vehicle.

(04) Another aspect of the present disclosure relates to a method for creating and using risk profiles for fleet management of a fleet of vehicles. The risk profiles may characterize values representing likelihoods of occurrences of vehicle events. The values may be based on previously detected vehicle events. The method may include obtaining vehicle event information for vehicle events that have been detected by the fleet of vehicles. The vehicle event information for the vehicle events may include locations of the vehicle events, vehicle types involved in the vehicle events, types of the vehicle events, and/or other information. The method may include aggregating the vehicle event information for multiple ones of the events to create one or more of a first risk profile, a second risk profile, a third risk profile, and/or another risk profile. The first risk profile may be specific to individual locations. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events at the individual locations. The second risk profile may be specific to individual vehicle types. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events pertaining to the individual vehicle types. The third risk profile may be specific to individual types of the vehicle events. The third risk profile may characterize a third set of values representing likelihoods of occurrences of vehicle events of the individual types of the vehicle events. The method may include obtaining a point of origin for a particular vehicle and a target destination the particular vehicle is intended to reach. The particular vehicle may have a particular vehicle type. The method may include determining a set of routes from the point of origin to the target destination. The set of routes may include at least two different routes. The method may include determining individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes.

Determining the individual values (representing the likelihoods) may be based on one or more risk profiles, and/or combinations thereof. The set of routes may include a first route and a second route. The determinations of the individual values may include a first determination of a first individual value for the first route and a second determination of a second individual value for the second route. The method may include selecting the first route from the set of routes. The first route may be selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route. In other words, the likelihood of occurrences along the first route may be lower than the likelihood along the second route. The method may include providing the selected first route to the particular vehicle.

(05) Another aspect of the present disclosure relates to a system configured for using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on vehicle event information for previously detected vehicle events. The system may include one or more hardware processors configured by machine-readable instructions. The processor(s) may be configured to obtain a first risk profile, a second risk profile, vehicle event

characterization information, and/or other information. The first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. The second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. The vehicle event characterization information may characterize one or more types of vehicle events to be used in determining performance levels by particular vehicle operators. The processor(s) may be configured to receive, from a particular vehicle, particular vehicle event information for particular vehicle events that have been detected by the particular vehicle. The particular vehicle may have a particular vehicle type and is operated by a particular vehicle operator. The particular vehicle event information may include particular locations of the particular vehicle events. The particular vehicle event information may further include particular types of the particular vehicle events. The processor(s) may be configured to determine one or more metrics that quantify a performance level of the particular vehicle operator. The determination of the one or more metrics may be based on one or more of the received particular vehicle event information, the first risk profile, the vehicle event characterization information, and/or other information. The processor(s) may be configured to compare the one or more metrics for the particular vehicle operator with aggregated metrics that quantify performance levels of a set of vehicle operators. The processor(s) may be configured to store, transferring, and/or presenting results of the comparison.

(06) Another aspect of the present disclosure relates to a method for using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on vehicle event information for previously detected vehicle events. The method may include obtaining a first risk profile, a second risk profile, vehicle event characterization information, and/or other information. The first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. The second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. The vehicle event characterization information may characterize one or more types of vehicle events to be used in determining performance levels by particular vehicle operators. The method may include receiving, from a particular vehicle, particular vehicle event information for particular vehicle events that have been detected by the particular vehicle. The particular vehicle may have a particular vehicle type and is operated by a particular vehicle operator. The particular vehicle event information may include particular locations of the particular vehicle events. The particular vehicle event information may further include particular types of the particular vehicle events. The method may include determining one or more metrics that quantify a performance level of the particular vehicle operator. The determination of the one or more metrics may be based on one or more of the received particular vehicle event information_; the first risk profile, the vehicle event characterization information, and/or other information. The method may include comparing the one or more metrics for the particular vehicle operator with aggregated metrics that quantify performance levels of a set of vehicle operators. The method may include storing, transferring, and/or presenting results of the comparison.

(07) As used herein, any association (or relation, or reflection, or indication, or correspondency) involving servers, processors, client computing platforms, vehicles, vehicle events, risk profiles, likelihoods, locations, vehicle types, event types, routes, metrics, performance levels, and/or another entity or object that interacts with any part of the system and/or plays a part in the operation of the system, may be a one-to-one association, a one-to- many association, a many-to-one association, and/or a many-to-many association or N-to-M association (note that N and M may be different numbers greater than 1).

(08) As used herein, the term "obtain" (and derivatives thereof) may include active and/or passive retrieval, determination, derivation, transfer, upload, download, submission, and/or exchange of information, and/or any combination thereof. As used herein, the term "effectuate" (and derivatives thereof) may include active and/or passive causation of any effect. As used herein, the term "determine" (and derivatives thereof) may include measure, calculate, compute, estimate, approximate, generate, and/or otherwise derive, and/or any combination thereof.

(09) These and other features, and characteristics of the present technology, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. As used in the specification and in the claims, the singular form of "a", "an", and "the" include plural referents unless the context clearly dictates otherwise.

BRIEF DESCRIPTION OF THE DRAWINGS (10) FIG. 1 shows a system configured for creating and using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(11) FIG. 2 includes a flow chart of a method for creating and using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(12) FIG. 3 illustrates a map depicting a geographical area and various routes for a vehicle, as may be used by a system configured for creating and using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(13) FIG. 4 shows a system configured for using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(14) FIG. 5 includes a flow chart of a method for using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(15) FIG. 6 illustrates a risk profile as may be used by a system configured for using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations.

(16) FIG. 7 shows a system configured for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, in accordance with one or more implementations.

(17) FIG. 8 includes a flow chart of a method for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, in accordance with one or more implementations.

(18) FIG. 9 illustrates a map as may be used by a system configured for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, in accordance with one or more implementations.

DETAILED DESCRIPTION

(19) FIG. 1 illustrates a system 100 configured for creating and using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations. The fleet may include a vehicle 12 and/or other vehicles. In some implementations, system 100 may be configured to couple with vehicle 12 that is operated by a vehicle operator. As used here, the term fleet may refer to a set of at least 5 vehicles, at least 10 vehicles, at least 100 vehicles, at least 1000 vehicles, and/or another number of vehicles. For example, the fleet may include a first vehicle, a second vehicle, a third vehicle, a fourth vehicle, and so forth. Individual vehicles may include a set of resources for data processing and/or electronic storage, including but not limited to persistent storage. Individual vehicles may include a set of sensors configured to generate output signals conveying information, e.g., related to the operation of the individual vehicles.

(20) System 100 may include one or more of vehicle 12, server(s) 102, electronic storage 103, client computing platform(s) 104, external resource(s) 107, network(s) 13, and/or other components. In some implementations, system 100 may be a distributed data center, include a distributed data center, or act as a distributed data center. Alternatively, and/or

simultaneously, system 100 may be a remote computing server, include a remote computing server, or act as a remote computing server, where a remote computing server is separate, discrete, and/or distinct from the fleet of vehicles. Server(s) 102 may be configured to communicate with one or more client computing platforms 104 according to a client/server architecture and/or other architectures. Client computing platform(s) 104 may be configured to communicate with other client computing platforms via server(s) 102 and/or according to a peer-to-peer architecture and/or other architectures. Users may access system 100 via client computing platform(s) 104.

(21) One or more components of system 100 may include one or more processors 105 and/or other mechanisms/components for processing information. For example, a set of resources (not depicted) included in and/or carried by an individual vehicle may include one or more processors. In some implementations, other vehicle-specific components, such as, by way of non-limiting example, a vehicle event recorder (not depicted), may include one or more processors. In some implementations, some or all of the processors may be configured via machine-readable instructions to perform various functions. One or more components of system 100 may include electronic storage 103 and/or other mechanisms/components for storing information. For example, a set of resources included in and/or carried by an individual vehicle may include electronic storage. In some implementations, other vehicle-specific components, such as, by way of non-limiting example, a vehicle event recorder, may include electronic storage. In some implementations, an event recorder may be configured to generate, detect, identify, capture, and/or record information related to the operation of a vehicle. Information related to a vehicle may include, by way of non-limiting example, information related to and/or based on vehicle events. An event recorder may be configured to off-load and/or otherwise transmit information. (22) A set of resources included in and/or carried by an individual vehicle may include one or more processors, electronic storage, a transceiver (not depicted), and/or other components. The first vehicle may carry a first set of resources. The second vehicle may carry a second set of resources, and so forth. The first set of resources may include a first transceiver. The second set of resources may include a second transceiver, and so forth.

(23) Transceivers may be configured to transfer and/or receive information to and/or from other elements of system 100, including but not limited to other vehicles (or components carried by other vehicles), the remote computing server, and/or other components. In some implementations, transceivers may be configured to transfer and/or receive information wirelessly, and/or otherwise provide resources for the distribution of information. For example, a transceiver may be configured to receive executable code, queries, and/or other information. For example, a transceiver may be configured to transmit results from executable code, responses to queries, and/or other information, e.g., to a remote computing server. In some implementations, the remote computing server may be configured to facilitate presentation of a user interface to a user of the remote computing server, e.g., to query system 100 and/or the fleet of vehicles. In some implementations, transceivers may be configured to obtain, measure, and/or otherwise determine one or more conditions related to data transmissions. For example, one or more current local data transmission conditions may include a current bandwidth (e.g., in MB/s), a current transmission protocol (e.g., LTE, 3G, 4G, 5G, Wi-Fi, etc.), a current transmission cost (e.g., in $/MB), and/or other conditions.

(24) Individual vehicles may include a set of sensors configured to generate output signals conveying information related to the operation of the individual vehicles, the surroundings of individual vehicles, and/or other information. As used herein, transmission and/or distribution of information may be considered a data processing function. As used herein, the terms data and information may be used interchangeably. As used herein, the terms "remote computing server" and "centralized server" may be used interchangeably.

(25) The sensors of a particular vehicle may be referred to as a set of sensors. A set of sensors may be carried by an individual vehicle. A set of sensors may be configured to generate output signals conveying information. In some implementations, the generated information may be related to one or both of the operation of one or more vehicles and the surroundings of one or more vehicles. The generated information may include timing information, location information, (vehicle) operator information, and/or other information. In some implementations, generated information may be associated with timing information ( e.g ., from a timer), location information, operator information, and/or other information.

(26) In some implementations, timing information may associate and/or otherwise relate the generated output signals with one or more moments of generation by one or more particular sensors. For example, timing information may include time stamps that indicate moments of generation. For example, at a time labeled ti the speed of a vehicle may be 50 mph, at a time labeled 12 the speed may be 55 mph, and so forth. A set of time stamps or moments in time may form a timeline. In some implementations, location information may associate and/or otherwise relate the generated output signals with one or more locations of generation (or, locations at the moment of generation) by one or more particular sensors. In some implementations, the operator information may associate and/or otherwise relate the generated output signals with individual vehicle operators at the moments of generation. For example, a particular sensor may generate a particular output signal conveying a particular operating parameter of an individual vehicle, such as speed and/or another operating parameter. The particular output signal may include and/or be associated with a timestamp (e.g., time=fx) that indicates when the particular output signal was generated. For example, a series of output signals may be associated with a corresponding series of timestamps. In some implementations, the particular output signal may be associated with a particular vehicle operator. For example, the particular output signal may be associated with the particular vehicle operator that was operating the individual vehicle at the time the particular output signal was generated. In some implementations, a set of resources may be configured to store generated information, timing information, location information, operator information, and/or other information, e.g. in electronic storage.

(27) Server(s) 102 may be configured by machine-readable instructions 106. Machine- readable instructions 106 may include one or more instruction components. The instruction components may include computer program components. The instruction components may include one or more of a vehicle event component 108, a event aggregation component 110, a location component 112, a routing component 114, a likelihood component 116, a route selection component 118, a route provision component 120, a risk map creation component 122, a risk map provision component 124, and/or other instruction components.

(28) Vehicle event component 108 may be configured to obtain and/or otherwise receive information, including but not limited to vehicle event information. In some implementations, vehicle event information may include information for vehicle events that have been detected by the fleet of vehicles. In some implementations, vehicle event information may be structured and/or organized into records representing individual vehicle events. In some

implementations, vehicle event information may be structured and/or organized in such a way that multiple individual vehicle events contribute to a single data point within the vehicle event information. For example, such a data point may be an aggregation of information from the information regarding multiple individual vehicle events.

(29) Detection of vehicle events may be based on output signals generated by one or more sensors (not depicted) of an individual vehicle. In some implementations, a sensor may be configured to generate output signals conveying information related to the operation of a vehicle (which may include information related to one or more operating conditions of the vehicle). Information related to the operation of the vehicle may include (feedback) information from one or more of the mechanical systems (not depicted) of the vehicle, and/or other information. In some implementations, at least one of the sensors may be a vehicle system sensor included in an engine control module or electronic control module (ECM) system of the vehicle. An individual sensor may be vehicle-specific.

(30) Individual sensors may be configured to generate output signals conveying information, e.g., vehicle-specific information. The information may include visual information, motion-related information, position-related information, biometric information, and/or other information. In some implementations, one or more components of system 100 may determine one or more parameters that are measured, derived, estimated, approximated, and/or otherwise determined based on one or more output signals generated by one or more sensors.

(31) Sensors may include, by way of non-limiting example, one or more of an altimeter (e.g. a sonic altimeter, a radar altimeter, and/or other types of altimeters), a barometer, a magnetometer, a pressure sensor (e.g. a static pressure sensor, a dynamic pressure sensor, a pitot sensor, etc.), a thermometer, an accelerometer, a gyroscope, an inertial measurement sensor, a geolocation sensor, global positioning system sensors, a tilt sensor, a motion sensor, a vibration sensor, an image sensor, a camera, a depth sensor, a distancing sensor, an ultrasonic sensor, an infrared sensor, a light sensor, a microphone, an air speed sensor, a ground speed sensor, an altitude sensor, medical sensors (including but not limited to blood pressure sensor, pulse oximeter, heart rate sensor, etc.), degree-of-freedom sensors (e.g. 6-DOF and/or 9-DOF sensors), a compass, and/or other sensors. As used herein, the term "motion sensor" may include one or more sensors configured to generate output conveying information related to position, location, distance, motion, movement, acceleration, and/or other motion-based parameters. Output signals generated by individual sensors (and/or information based thereon) may be stored and/or transferred in electronic files. In some implementations, output signals generated by individual sensors (and/or information based thereon) may be streamed to one or more other components of the system.

(32) As mentioned, individual sensors may include image sensors, cameras, and/or other sensors. As used herein, the terms "camera" and/or "image sensor" may include any device that captures images, including but not limited to a single lens-based camera, a camera array, a solid-state camera, a mechanical camera, a digital camera, an image sensor, a depth sensor, a remote sensor, a lidar, an infrared sensor, a (monochrome) complementary metal-oxide- semiconductor (CMOS) sensor, an active pixel sensor, and/or other sensors. Individual sensors may be configured to capture information, including but not limited to visual information, video information, audio information, geolocation information, orientation and/or motion information, depth information, and/or other information. Information captured by one or more sensors may be marked, timestamped, annotated, and/or otherwise processed such that information captured by other sensors can be synchronized, aligned, annotated, and/or otherwise associated therewith. For example, video information captured by an image sensor may be synchronized with information captured by an accelerometer, GPS unit, or other sensor. Output signals generated by individual image sensors (and/or information based thereon) may be stored and/or transferred in electronic files.

(33) In some implementations, an image sensor may be integrated with electronic storage such that captured information may be stored, at least initially, in the integrated embedded storage of a particular vehicle. In some implementations, one or more components carried by an individual vehicle may include one or more cameras. For example, a camera may include one or more image sensors and electronic storage media. In some implementations, an image sensor may be configured to transfer captured information to one or more components of system 100, including but not limited to remote electronic storage media, e.g. through "the cloud."

(34) By way of non-limiting example, the vehicle event information for the vehicle events may include one or more of locations of vehicle events, vehicle types involved in vehicle events, types of vehicle events, identifiers of vehicle operators involved in vehicle events, and/or other information. For example, locations of vehicle events may include geographical locations, including but not limited to global positioning system (GPS) coordinates. For example, vehicle types may include sedans, vans, trucks, 18-wheelers, and/or other types of vehicles. In some implementations, vehicle types may be classified by weight class and/or by other distinguishing features. For example, types of vehicle events may include speeding events, collision events, near-collision events, and/or other vehicle events. In some implementations, the types of vehicles events may include different types for different segments of a day. For example, identifiers of vehicle operators may include names, identification numbers, employee numbers, and/or other identifiers.

(35) By way of non-limiting example, vehicle event information may be aggregated (e.g., by event aggregation component 110) to create risk profiles. As used herein, the term "vehicle event" may refer to one or more of forward motion, motion in reverse, making a turn, speeding, unsafe driving speed, collisions, near-collisions, driving in a parking lot or garage, being stalled at a traffic light, loading and/or unloading of a vehicle, transferring gasoline to or from the vehicle, and/or other vehicle events in addition to driving maneuvers such as swerving, a U-turn, freewheeling, over-revving, lane-departure, short following distance, imminent collision, unsafe turning that approaches rollover and/or vehicle stability limits, hard braking, rapid acceleration, idling, driving outside a geo-fence boundary, crossing double-yellow lines, passing on single-lane roads, a certain number of lane changes within a certain amount of time or distance, fast lane change, cutting off other vehicles during lane-change speeding, running a red light, running a stop sign, parking a vehicle, performing fuel-inefficient maneuvers, and/or other driving maneuvers or combinations thereof. Some types of vehicle events may be based on the actions or motion of the vehicle itself. Other types of vehicle events may be based on the actions taken or performed by a vehicle operator. Some types of vehicle events may be based on a combination of both the actions or motion of the vehicle itself and the actions taken or performed by a vehicle operator. For example, a particular vehicle event may include hard braking followed (within a predetermined window of time) by a sharp turn and/or swerve. This particular vehicle event may indicate a near-collision that was severe enough that the vehicle operator decided that merely braking hard would not be sufficient to avoid the collision. Another example of a vehicle event that includes a

combination of actions may be a lane change followed (within a predetermined window of time) by hard braking, which may indicate a poor decision to initiate the lane change. In some implementations, a particular type of vehicle event may involve a vehicle exceeding a speed threshold. In some implementations, a particular type of vehicle event may involve collisions and near-collisions of a vehicle.

(36) Event aggregation component 110 may be configured to aggregate the vehicle event information for multiple ones of the events. In some implementations, event aggregation component 110 may be configured to aggregate the vehicle event information to create one or more of a first risk profile, a second risk profile, a third risk profile, a fourth risk profile, and/or other risk profiles. The first risk profile may be specific to individual locations. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events at the individual locations. The second risk profile may be specific to individual vehicle types. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events pertaining to the individual vehicle types. The third risk profile may be specific to individual types of the vehicle events. The third risk profile may characterize a third set of values representing likelihoods of occurrences of vehicle events of the individual types of the vehicle events. The fourth risk profile (or personal risk profile) may be specific to individual vehicle operators. The fourth risk profile may characterize a fourth set of values representing likelihoods of occurrences of vehicles events involving the individual vehicle operators. In some implementations, a risk profile may characterize a set of values

representing likelihoods of occurrences of different types of vehicle events at different locations involving different vehicle types.

(37) Location component 112 may be configured to obtain and/or otherwise receive information related to current and/or intended locations of vehicles. In some implementations, location component 112 may be configured to obtain points of origin for individual vehicles. In some implementations, location component 112 may be configured to obtain target destinations for individual vehicles. Target destinations may be locations the individual vehicles intended to reach. The particular vehicle may be being operated by a particular vehicle operator. In some implementations, obtaining a point of origin for a particular vehicle and a target destination for the particular vehicle may include receiving information from the particular vehicle, its vehicle operator, and/or from an external resources involved in route planning for the particular vehicle. The received information may represent a point of origin for the particular vehicle and a target destination. The particular vehicle may have a particular vehicle type, including but not limited to a particular weight class for the vehicle.

(38) Routing component 114 may be configured to determine routes for vehicles. In some implementations, routing component 114 may be configured to determine a set of routes from a point of origin to a target destination ( e.g ., for a particular vehicle). In some

implementations, a particular set of routes may include at least two different routes. In some implementations, a particular set of routes may include at least three different routes, and/or more than three different routes. For example, a set of routes may include a first route, a second route, a third route, and so forth. By way of non-limiting example, FIG. 3 illustrates a map 300 depicting a geographical area around vehicle 12 and various routes. For example, map 300 may include a target destination 301 for vehicle 12. For example, map 300 may include a point of origin 302 for vehicle 12. For example, point of origin 302 may be the current location of vehicle 12. A routing component similar to or the same as routing component 114 may determine a first route 310, a second route 311, a third route 312, and/or other routes from point of origin 302 to target destination 301. Identifiers 303, 304, 305, 306, and 307 may represent previously detected vehicle events, also referred to as event 303, event 304, event 305, event 306, and event 307, respectively.

(39) Referring to FIG. 1, likelihood component 116 may be configured to determine individual values representing likelihoods. For example, the individual values may be numerical values, percentages, and/or other types of values. In some implementations, the determined individual values may represent likelihoods of occurrences of vehicle events along one or more routes and/or near one or more locations. For example, the one or more routes may be the individual routes in a set of routes determined by routing component 114. By way of non limiting example, determining the individual values may be based on one or more risk profiles. For example, a particular individual value may be based on one or more of the first, second, and/or third risk profile. In some implementations, determining one or more individual values may be based on one or more of the first, second, third, and/or fourth risk profile. For example, determining the individual values may include determining the individual values representing likelihoods of occurrences of collisions and near-collisions along the individual routes in the set of routes. In some implementations, the set of routes may include a first route, a second route, a third route, and so forth. The determinations by likelihood component 116 may include a first determination of a first individual value for the first route, a second determination of a second individual value for the second route, a third determination of a third individual value for the third route, and so forth.

(40) By way of non-limiting example, FIG. 3 illustrates map 300 depicting a geographical area around vehicle 12 and first route 310, second route 311, and third route 312. A likelihood component similar to or the same as likelihood component 116 may determine a first value representing a first likelihood of occurrences of vehicle events along first route 310, a second value representing a second likelihood of occurrences of vehicle events along second route 311, and a third value representing a third likelihood of occurrences of vehicle events along third route 312. For example, assuming events are treated equally and the quantity of events is used to determine likelihoods, the first value may be 6%, based on event 303, event 304, and event

305 along the route. For example, the second value may be 4%, based on event 303 and event

306 along the route. For example, the third value may be 2%, based on event 307 along the route. In this example, third route 312 may be selected and/or used to route vehicle 12 to target destination 301.

(41) In some implementations, the first, second, and third value may be based on a first risk profile {i.e., based on individual locations of previously detected vehicle events). In this example, third route 312 may be selected and/or used to route vehicle 12 to target destination 301. In some implementations, the first, second, and third value may be based on the first risk profile and the second risk profile. For example, assume that events 303, 304, and 305 happened to a sedan, while events 306 and 307 happened to a truck. If vehicle 12 is a truck, the first value might be lower than the second and third value. If vehicle 12 is a sedan, the first value might be higher than the second and third value.

(42) In some implementations, the first, second, and third value may be based on the first risk profile and the third risk profile. For example, assume that events 303, 304, and 305 involved hard braking, while events 306 and 307 involved collisions. If collision events are weighed more heavily than hard-breaking events, the first value might be higher than the second and third value. In some implementations, the first, second, and third value may be based on the first risk profile, the second risk profile, and the third risk profile.

(43) Referring to FIG. 1, in some implementations, determinations by likelihood component 116 of the individual values for a particular vehicle operator may be performed such that previously detected vehicle events that involved the particular vehicle operator weigh more heavily than previously detected vehicle events that did not involve the particular vehicle operator. By way of non-limiting example, FIG. 3 illustrates map 300 depicting a geographical area around vehicle 12 and first route 310, second route 311, and third route 312. For example, based on the quantity of events along the different routes, and as initially determined, the first value may be 6%, the second value may be 4%, and the third value may be 2%. However, if event 307 previously happened to vehicle 12 a likelihood component similar to or the same as likelihood component 116 may be configured to adjust values involving detected events of vehicle 12 along the different routes. Accordingly, the third value may be adjusted from 2% to 20%. Alternatively, and/or simultaneously, third route 312 may be deemed ineligible for selection based on event 307 having happened to vehicle 12. After such an adjustment, in this example, second route 311 may be selected and/or used to route vehicle 12 to target destination 301.

(44) Referring to FIG. 1, route selection component 118 may be configured to select the first route from the set of routes. The first route may be selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route. In some implementations, the first route may be selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than other individual values representing likelihoods of occurrences of vehicle events along other routes, e.g., the second route and/or the third route.

(45) Route provision component 120 may be configured to provide routes to vehicles.

For example, route provision component 120 may be configured to provide the selected first route (as selected by route selection component 118) to a particular vehicle. In some implementations, route provision component 120 may be configured to effectuate a transfer of information (such as a route) through a transceiver and/or other transmission components. In some implementations, provided routes may be presented to vehicle operators, e.g., through a user interface. In some implementations, provided routes may be used to control autonomous vehicle operators and/or autonomous operation of a vehicle.

(46) Risk map creation component 122 may be configured to create a risk map of a geographical area. The risk map may be based on one or more risk profiles. For example, a risk map may be based on a first risk profile. For example, a risk map may be based on the combination of the first risk profile and another risk profile. For example, a risk map may be based on the combination of the first risk profile, the third risk profile, and the personal risk profile. Other combinations of risk profiles are envisioned within the scope of this disclosure. The risk map may characterize values representing likelihoods of occurrences of vehicles events at specific locations within the geographical area.

(47) Risk map provision component 124 may be configured to provide risk maps to vehicles, vehicle operators, and/or other users. For example, risk map provision component 124 may be configured to provide a risk map as created by risk map creation component 122 to a particular vehicle, a particular vehicle operator, and/or other users. In some

implementations, risk map provision component 124 may be configured to effectuate a transfer of information (such as a risk map) through a transceiver and/or other transmission components. In some implementations, provided risk maps may be presented to vehicle operators, e.g., through a user interface. In some implementations, provided risk maps may be used to control autonomous vehicle operators and/or autonomous operation of a vehicle.

(48) In some implementations, one or more of server(s) 102, client computing platform(s) 104, and/or external resources 107 may be operatively linked via one or more electronic communication links. For example, such electronic communication links may be established, at least in part, via one or more networks 13 such as the Internet and/or other networks. It will be appreciated that this is not intended to be limiting, and that the scope of this disclosure includes implementations in which server(s) 102, client computing platform(s) 104, and/or external resources 107 may be operatively linked via some other communication media.

(49) A given client computing platform 104 may include one or more processors configured to execute computer program components. The computer program components may be configured to enable an expert or user associated with the given client computing platform 104 to interface with system 100 and/or external resources 107, and/or provide other functionality attributed herein to client computing platform(s) 104. By way of non-limiting example, the given client computing platform 104 may include one or more of a desktop computer, a laptop computer, a handheld computer, a tablet computing platform, a NetBook, a Smartphone, a gaming console, and/or other computing platforms.

(50) External resources 107 may include sources of information outside of system 100, external entities participating with system 100, and/or other resources. In some

implementations, some or all of the functionality attributed herein to external resources 107 may be provided by resources included in system 100. For example, contextual information related to weather conditions may be received from a particular external provider that provides weather information. For example, contextual information related to road surface conditions may be received from a particular external provider that provides road condition information. For example, contextual information related to traffic conditions may be received from a particular external provider that provides traffic information. In some implementations, external resources 107 include one or more external providers.

(51) Server(s) 102 may include electronic storage 103, one or more processors 105, and/or other components. Server(s) 102 may include communication lines, or ports to enable the exchange of information with a network and/or other computing platforms. Illustration of server(s) 102 in FIG. 1 is not intended to be limiting. Server(s) 102 may include a plurality of hardware, software, and/or firmware components operating together to provide the functionality attributed herein to server(s) 102. For example, server(s) 102 may be

implemented by a cloud of computing platforms operating together as server(s) 102.

(52) Electronic storage 103 may comprise non-transitory storage media that

electronically stores information. The electronic storage media of electronic storage 103 may include one or both of system storage that is provided integrally {i.e., substantially nonremovable) with server(s) 102 and/or removable storage that is removably connectable to server(s) 102 via, for example, a port (e.g., a USB port, a firewire port, etc.) or a drive (e.g., a disk drive, etc.). Electronic storage 103 may include one or more of optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, magnetic hard drive, floppy drive, etc.), electrical charge-based storage media (e.g., EEPROM, RAM, etc.), solid-state storage media (e.g., flash drive, etc.), and/or other electronically readable storage media. Electronic storage 103 may include one or more virtual storage resources (e.g., cloud storage, a virtual private network, and/or other virtual storage resources). Electronic storage 103 may store software algorithms, information determined by processor(s) 105, information received from server(s) 102, information received from client computing platform(s) 104, and/or other information that enables server(s) 102 to function as described herein.

(53) Processor(s) 105 may be configured to provide information processing capabilities in server(s) 102. As such, processor(s) 105 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information. Although processor(s) 105 is shown in FIG. 1 as a single entity, this is for illustrative purposes only. In some implementations, processor(s) 105 may include a plurality of processing units. These processing units may be physically located within the same device, or processor(s) 105 may represent processing functionality of a plurality of devices operating in coordination. Processor(s) 105 may be configured to execute components 108, 110, 112, 114,

116. 118. 120. 122, and/or 124, and/or other components. Processor(s) 105 may be configured to execute components 108, 110, 112, 114, 116, 118, 120, 122, and/or 124, and/or other components by software; hardware; firmware; some combination of software, hardware, and/or firmware; and/or other mechanisms for configuring processing capabilities on processor(s) 105. As used herein, the term "component" may refer to any component or set of components that perform the functionality attributed to the component. This may include one or more physical processors during execution of processor readable instructions, the processor readable instructions, circuitry, hardware, storage media, or any other components.

(54) It should be appreciated that although components 108, 110, 112, 114, 116, 118,

120. 122, and/or 124 are illustrated in FIG. 1 as being implemented within a single processing unit, in implementations in which processor(s) 105 includes multiple processing units, one or more of components 108, 110, 112, 114, 116, 118, 120, 122, and/or 124 may be implemented remotely from the other components. The description of the functionality provided by the different components 108, 110, 112, 114, 116, 118, 120, 122, and/or 124 described below is for illustrative purposes, and is not intended to be limiting, as any of components 108, 110, 112,

114. 116. 118. 120. 122, and/or 124 may provide more or less functionality than is described.

For example, one or more of components 108, 110, 112, 114, 116, 118, 120, 122, and/or 124 may be eliminated, and some or all of its functionality may be provided by other ones of components 108, 110, 112, 114, 116, 118, 120, 122, and/or 124. As another example, processor(s) 105 may be configured to execute one or more additional components that may perform some or all of the functionality attributed below to one of components 108, 110, 112,

114, 116, 118, 120, 122, and/or 124.

(55) FIG. 2 illustrates a method 200 for creating and using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations. The operations of method 200 presented below are intended to be illustrative. In some implementations, method 200 may be accomplished with one or more additional operations not described, and/or without one or more of the operations discussed. Additionally, the order in which the operations of method 200 are illustrated in FIG. 2 and described below is not intended to be limiting.

(56) In some implementations, method 200 may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information). The one or more processing devices may include one or more devices executing some or all of the operations of method 200 in response to instructions stored electronically on an electronic storage medium. The one or more processing devices may include one or more devices configured through hardware, firmware, and/or software to be specifically designed for execution of one or more of the operations of method 200.

(57) An operation 202 may include obtaining vehicle event information for vehicle events that have been detected by the fleet of vehicles. The vehicle event information for the vehicle events may include locations of the vehicle events, vehicle types involved in the vehicle events, and types of the vehicle events. Operation 202 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to vehicle event component 108, in accordance with one or more implementations.

(58) An operation 204 may include aggregating the vehicle event information for multiple ones of the events to create a risk profile. The risk profile may characterize a set of values representing likelihoods of occurrences of different types of vehicle events at different locations involving different vehicle types. Operation 204 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to event aggregation component 110, in accordance with one or more implementations.

(59) An operation 206 may include obtaining a point of origin for a particular vehicle and a target destination the particular vehicle is intended to reach. The particular vehicle may have a particular vehicle type. Operation 206 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to location component 112, in accordance with one or more

implementations. (60) An operation 208 may include determining a set of routes from the point of origin to the target destination. The set of routes may include at least two different routes. Operation 208 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to routing component 114, in accordance with one or more implementations.

(61) An operation 210 may include determining individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes. Determining the individual values may be based on the risk profile. The set of routes may include a first route and a second route. The determinations may include a first determination of a first individual value for the first route and a second determination of a second individual value for the second route. Operation 210 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to likelihood component 116, in accordance with one or more implementations.

(62) An operation 212 may include selecting the first route from the set of routes. The first route may be selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route. Operation 212 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to route selection component 118, in accordance with one or more implementations.

(63) An operation 214 may include providing the selected first route to the particular vehicle. Operation 214 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to route provision component 120, in accordance with one or more implementations.

(64) FIG. 4 illustrates a system 400 configured for using risk profiles for fleet

management of a fleet of vehicles, in accordance with one or more implementations. In some implementations, system 400 may be configured to couple with vehicle 12 that is operated by a vehicle operator. As used regarding system 400, the term fleet may refer to a set of at least 5 vehicles, at least 10 vehicles, at least 400 vehicles, at least 4000 vehicles, and/or another number of vehicles. For example, the fleet may include a first vehicle, a second vehicle, a third vehicle, a fourth vehicle, and so forth. (65) As used regarding system 400, the risk profiles may characterize values representing likelihoods of certain occurrences. For example, a first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. In some implementations, the first risk profile may be context-specific. For example, a second risk profile may be specific to operators. As used herein, an operator involved in a vehicle event may be a human vehicle operator, an autonomous driving algorithm, a type of vehicle, and/or a combination thereof. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. In some implementations, the second risk profile may be operator-specific. In some implementations, additional and/or different risk profiles are envisioned within the scope of this disclosure. In some implementations, values characterized by risk profiles may be based on vehicle event information for previously detected vehicle events.

(66) As used regarding system 400, individual vehicles may include a set of resources for data processing and/or electronic storage, including but not limited to persistent storage. Individual vehicles may include a set of sensors configured to generate output signals conveying information, e.g., related to the operation of the individual vehicles. Individual vehicles may be configured to detect vehicle events, e.g., based on output signals generated by sensors.

(67) System 400 may include one or more of vehicle 12, server(s) 102, electronic storage 103, client computing platform(s) 104, external resource(s) 107, network(s) 13, and/or other components. In some implementations, system 400 may be a distributed data center, include a distributed data center, or act as a distributed data center. Alternatively, and/or

simultaneously, system 400 may be a remote computing server, include a remote computing server, or act as a remote computing server, where a remote computing server is separate, discrete, and/or distinct from the fleet of vehicles. Users may access system 400 via client computing platform(s) 104.

(68) Server(s) 102 may be configured by machine-readable instructions 106. Machine- readable instructions 106 may include one or more instruction components. The instruction components may include computer program components. As used regarding system 400, the instruction components may include one or more of a risk profile component 408, a vehicle event information component 410, a performance determination component 412, a performance comparison component 414, a result component 416, a metric analysis component 418, an information presentment component 420, a team component 422, a recommendation presentment component 424, a driver switching component 426, and/or other instruction components.

(69) Risk profile component 408 may be configured to obtain and/or determine information, including but not limited to risk profiles. Risk profiles may include and/or represent likelihoods of occurrences of particular events, including but not limited to vehicle events. In some implementations, risk profiles may include and/or characterize values that represent likelihoods. In some implementations, the obtained and/or determined information may include a first risk profile, a second risk profile, vehicle event characterization information, and/or other information. In some implementations, the first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context.

In some implementations, the second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching and/or otherwise involving the operators. The vehicle event characterization information may characterize one or more types of vehicle events to be used in determining performance levels by vehicle operators. In some implementations, the first set of values, the second set of values, and/or other sets of values for risk profiles may be based on vehicle event information. In some implementations, the vehicle event information may be based on previously detected vehicle events. In some implementations, the vehicle event information may include information about previously detected vehicle events, including but not limited to certain context for the previously detected vehicle events and/or the operators for the previously detected vehicle events.

(70) As used regarding system 400, in some implementations, the certain context for detecting vehicle events may include one or more of (geographical) location, local weather, heading of one or more vehicles, traffic conditions, and/or other context information. For example, a location-based risk profile may include a set of locations in a particular geographical area where previously detected vehicles events occurred. In some implementations, a location- based risk profile may form the basis for a risk map of the particular geographical area. In some implementations, a risk profile may include traffic conditions ( e.g ., whether traffic was heavy or light, what kind of participants were part of the traffic, how close other vehicles were, etc.). In some implementations, a risk profile may combine different kinds of context information. For example, a location-based risk profile may also indicate likelihoods of occurrences of certain vehicle events during heavy traffic, light traffic, during rain or snow, heading east or west, and so forth.

(71) In some implementations, the certain context for detecting vehicle events may include one or more of objects on roadways during detection of vehicle events, other incidents within a particular timeframe of detection of vehicle events, time of day, lane information, presence of autonomously operated vehicles within a particular proximity, and/or other (dynamic) context information, as well as combinations thereof.

(72) The vehicle event characterization information may characterize one or more types of vehicle events to be used in determining performance levels by particular vehicle operators. For example, in some scenarios, a performance level of a particular vehicle operator may be determined based on occurrences of hard braking, because hard braking may be especially important to avoid for certain driving responsibilities. In other scenarios, hard braking may be relatively unimportant and/or common, for example for taxis in certain downtown areas. In such scenarios, the types of vehicle events that correspond to hard braking should not be paramount when determining a performance level. For example, in some scenarios, a performance level of a particular vehicle operator may be determined based on occurrences of U-turns, because U-turns may be especially important to avoid for certain driving

responsibilities, including but not limited to 18-wheelers. In other scenarios, U-turns may be relatively unimportant and/or common, for example for taxis in certain downtown areas. In such scenarios, the types of vehicle events that correspond to U-turns should not be paramount when determining a performance level. In some implementations, vehicle event

characterization information may characterize exceeding a speed threshold. In some implementations, vehicle event characterization information may characterize one or more of swerving, a U-turn, freewheeling, over-revving, lane-departure, short following distance, imminent collision, unsafe turning that approaches rollover and/or vehicle stability limits, hard braking, rapid acceleration, idling, driving outside a geo-fence boundary, crossing double-yellow lines, passing on single-lane roads, a certain number of lane changes within a certain amount of time or distance, fast lane change, cutting off other vehicles during lane-change speeding, running a red light, running a stop sign, parking a vehicle, and/or performing fuel-inefficient maneuvers. In some implementations, vehicle event characterization information may characterize collisions and near-collisions. (73) Vehicle event information component 410 may be configured to determine and/or receive, particular vehicle event information for particular vehicle events that have been detected by a particular vehicle. The particular vehicle event information may include information representing a route traversed by the particular vehicle. The particular vehicle may have a particular vehicle type. The particular vehicle may be operated by a particular vehicle operator. In some implementations, the particular vehicle operator may be an autonomous driving algorithm. In some implementations, the particular vehicle operator may be a team including a human vehicle operator and an autonomous driving algorithm. In some implementations, the particular vehicle event information may be context-specific, operator- specific, and/or otherwise specific. For example, the particular vehicle event information may include particular locations of particular vehicle events that have been detected along the route. In some implementations, the particular vehicle event information may include particular types of the detected particular vehicle events.

(74) Performance determination component 412 may be configured to determine performance levels of vehicle operators. In some implementations, a performance level may be related to a specific and actual performance of a human vehicle operator while driving a vehicle along an actual route. Alternatively, and/or simultaneously, in some implementations, a performance level may be related to actual performance of a vehicle operator over a longer period of time, e.g., spanning weeks, months, years, the current employment with a particular fleet, and/or other periods. For example, performance determination component 412 may be configured to determine one or more metrics that quantify a performance level of a particular vehicle operator. In some implementations, determination of one or more metrics may be based on one or more of the particular vehicle event information (e.g., as received by vehicle event information component 410), the first risk profile, the vehicle event characterization information, and/or other information. For example, a metric to quantify a performance level may be a numerical value that is decreased for vehicle events that have been detected along a route, and increased for every particular number of miles driven without such occurrences. In some implementations, detected vehicle events may be filtered by one or more of certain contexts, particular vehicle type, vehicle event characterization information, and/or other specifics for vehicle events. Other mechanisms for increasing and/or decreasing (numerical) values are envisioned within the scope of this disclosure. (75) In some implementations, determining one or more metrics may include estimating (and/or comparing) expected occurrences of vehicle events during traversal of some route by the particular vehicle. For example, on average, a vehicle having the same type as the particular vehicle and traversing the same route as the particular vehicle could be expected to have 3 different vehicle events, by way of non-limiting example. Such expectations may be based on previously detected vehicle events for some fleet of vehicles, and/or based on the values in one or more risk profiles, and/or based on other information. If the particular vehicle operator had fewer than 3 vehicle events (or less severe or less important vehicle events), the particular vehicle operator would have a performance level that is better than average, in this example. Conversely, if the particular vehicle operator had more than 3 vehicle events (or more severe or more important vehicle events), the particular vehicle operator would have a performance level that is worse than average, in this example. In some implementations, averages may be determined for multiple vehicle operators in a particular company, in a particular geographical area, in a particular age or experience range, and/or based on any distinguishing characteristic(s) of a vehicle operator. Determining the one or more metrics may include comparing the particular vehicle event information for the particular vehicle events that have been detected by a particular vehicle during traversal of a particular route with the estimated expected occurrences of vehicles events. In some implementations, determinations and/or estimations by performance determination component 412 may be based on one or more of the first risk profile, the second risk profile, the vehicle event characterization information, and/or other information.

(76) By way of non-limiting example, FIG. 6 illustrates a map 600 depicting a geographical area around vehicles 12a-12b-12c and various routes. For example, map 600 may include a target destination 601 for vehicles 12a-12b-12c. For example, map 600 may include a point of origin 602 for vehicles 12a-12b-12c. For example, point of origin 602 may be the current location of vehicles 12a-12b-12c. Vehicle 12a may intend to traverse a first route 610, vehicle 12b may intend to traverse a second route 611, and vehicle 12c may intend to traverse a third route 612 to target destination 301. Identifiers 603, 604, 605, 606, and 607 may represent previously detected vehicle events, also referred to as event 603, event 604, event 605, event 606, and event 607, respectively. In one example, first route 610 may be more prone to the occurrence of vehicle events (compared to second route 611 and third route 612) based on previously detected vehicle events. A performance determination component similar to performance determination component 412 in FIG. 4 may determine a first performance level for the vehicle operator of vehicle 12a upon completion of first route 610, a second

performance level for the vehicle operator of vehicle 12b upon completion of second route 611, and a third performance level for the vehicle operator of vehicle 12c upon completion if third route 612. In a case where none of vehicles 12a-12b-12c have any vehicle events, the first performance level may be higher than the second or third performance level. In some implementations, the system as disclosed may determine and/or estimate how many occurrences of a particular type of vehicle event are expected along each route (which may be a fraction). For example, 0.02 vehicle events may be expected along first route 610, 0.01 vehicle events may be expected along second route 611, and 0.05 vehicle events may be expected along third route 612. In such a case, if none of vehicles 12a-12b-12c have any vehicle events, the third performance level may be higher than the first or second performance level, based on expectations.

(77) Referring to FIG. 4, performance comparison component 414 may be configured to compare performance levels, metrics that quantify performance levels, and/or other information related to performances by vehicle operators. In some implementations, the one or more metrics for a particular vehicle operator may be compared with aggregated metrics that quantify performance levels of a set of vehicle operators. In some implementations, aggregated metrics may be determined for multiple vehicle operators in a particular company, in a particular geographical area, in a particular age or experience range, and/or based on any distinguishing characteristic(s) of a vehicle operator.

(78) Result component 416 may be configured to store, transfer, and/or present results of the determination, estimation, comparison, analysis, and/or otherwise processing of performance levels. For example, a fleet manager or other stakeholder may be presented with an overview of the performance levels of the vehicle operators within the fleet for this year, this month, this week, etc.

(79) Metric analysis component 418 may be configured to analyze performance levels, metrics that quantify performance levels, and/or other information related to performances by vehicle operators. In some implementations, metric analysis component 418 may be configured to analyze the one or more metrics that quantify a performance level for a particular vehicle operator. In some implementations, metric analysis component 418 may be configured to determine, based on analysis, which particular vehicle event, particular vehicle event type, and/or particular driving scenario contributes disproportionately to a particular performance level for a particular vehicle operator. For example, in some implementations, the particular vehicle event that contributes disproportionately may be the particular vehicle event that, had it not occurred, would have improved the particular performance level by the greatest amount. In some implementations, the particular vehicle event that contributes disproportionately may be the particular vehicle event that contributes most to a difference between the one or more metrics for the particular vehicle operator and the aggregated metrics that quantify performance levels of a set of vehicle operators.

(80) In some implementations, system 400 may be configured to select a route from a set of routes for a particular vehicle operator based on analysis by metric analysis component 418. For example, a first route may be less suitable than a second route based on the performance level of the particular vehicle operator in view of the type of vehicle event that contributed disproportionately to the particular performance level of the particular vehicle operator.

(81) Information presentment component 420 may be configured to present, via a user interface, information regarding the analysis by metric analysis component 418. For example, information presentment component 420 may present specifics regarding a driving scenario that contributed disproportionately to a worse-than-average level of performance. In some implementations, the presented information may reflect advice on improving a level of performance, and, in particular, for improving the one or more metrics that quantify a performance level of the particular vehicle operator.

(82) Team component 422 may be configured to determine a combined value representing a likelihood of occurrences of vehicles events involving a team of vehicle operators cooperatively operating the same vehicle. In some implementations, the team may include a first vehicle operator and a second vehicle operator. In some implementations, the first operator may be a human vehicle operator and the second operator may be an autonomous driving algorithm. In some implementations, the combined value may be based on estimated expected occurrences (e.g., by performance determination component 412).

(83) Recommendation presentment component 424 may be configured to present, via a user interface, a recommendation regarding suitability of the team for cooperative operation of the same vehicle. By way of non-limiting example, cooperative driving may include a first driver acting as the primary operator, and a second driver acting as the back-up operator that can take over driving responsibilities from the primary operator. The recommendation may be based on the combined value, e.g., as determined by team component 422. In some implementations, a recommendation may be route-specific, and/or otherwise based on the expected driving scenarios along a particular route. For example, if a human driver and an autonomous driving algorithm are both below-average for the specific types of vehicle events and/or driving scenarios that are expected along a particular route, the recommendation may be negative. Alternatively, a recommendation may be to change the particular route to a particular destination. In some implementations, a recommendation may be to combine different operators together as a team for a specific target route.

(84) Driver switching component 426 may be configured to determine when a second driver should take over driving responsibilities from a first driver. By way of non-limiting example, cooperative driving may include a first driver acting as the primary operator, and a second driver acting as the back-up operator that can take over driving responsibilities from the primary operator. In some implementations, determinations by driving switching component 426 may be based on different types of information, including but not limited to values representing expectations of particular types of vehicle event occurring, for example of a particular route. In some implementations, driver switching component 426 may be configured to determine when a second driver should take over driving responsibilities from a first driver, the determination being based on a first value representing a first expectation of a particular type of vehicle event occurring if the first driver continues driving a current route, in comparison to a second value representing a second expectation of the particular type of vehicle event occurring if the second driver drives the current route. In some implementations, the previously detected vehicle events may have been detected by the fleet of vehicles. In some implementations, the first driver may be a human and the second driver is an autonomous driving algorithm.

(85) As used regarding system 400, processor(s) 105 may be configured to execute components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426, and/or other

components. Processor(s) 105 may be configured to execute components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426, and/or other components by software; hardware;

firmware; some combination of software, hardware, and/or firmware; and/or other mechanisms for configuring processing capabilities on processor(s) 105. (86) It should be appreciated that although components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426 are illustrated in FIG. 4 as being implemented within a single processing unit, in implementations in which processor(s) 105 includes multiple processing units, one or more of components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426 may be implemented remotely from the other components. The description of the functionality provided by the different components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426 described below is for illustrative purposes, and is not intended to be limiting, as any of components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426 may provide more or less functionality than is described. For example, one or more of components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426 may be eliminated, and some or all of its functionality may be provided by other ones of components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426. As another example, processor(s) 105 may be configured to execute one or more additional components that may perform some or all of the functionality attributed below to one of components 408, 410, 412, 414, 416, 418, 420, 422, 424, and/or 426.

(87) FIG. 5 illustrates a method 500 for using risk profiles for fleet management of a fleet of vehicles, in accordance with one or more implementations. The risk profiles may characterize values representing likelihoods of occurrences of vehicle events. The values may be based on vehicle event information for previously detected vehicle events. The operations of method 500 presented below are intended to be illustrative. In some implementations, method 500 may be accomplished with one or more additional operations not described, and/or without one or more of the operations discussed. Additionally, the order in which the operations of method 500 are illustrated in FIG. 5 and described below is not intended to be limiting.

(88) In some implementations, method 500 may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information). The one or more processing devices may include one or more devices executing some or all of the operations of method 500 in response to instructions stored electronically on an electronic storage medium. The one or more processing devices may include one or more devices configured through hardware, firmware, and/or software to be specifically designed for execution of one or more of the operations of method 500. (89) An operation 502 may include obtaining a first risk profile, a second risk profile, and vehicle event characterization information. The first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. The second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. The vehicle event characterization information may characterize one or more types of vehicle events to be used in determining performance levels by vehicle operators. Operation 502 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to risk profile component 408, in accordance with one or more implementations.

(90) An operation 504 may include receiving, from a particular vehicle, particular vehicle event information for particular vehicle events that have been detected by the particular vehicle. The particular vehicle may have a particular vehicle type and may be operated by a particular vehicle operator. The particular vehicle event information may include particular locations of the particular vehicle events. The particular vehicle event information may further include particular types of the particular vehicle events. Operation 504 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to vehicle event information component 410, in accordance with one or more implementations.

(91) An operation 506 may include determining one or more metrics that quantify a performance level of the particular vehicle operator. The determination of the one or more metrics may be based on one or more of the received particular vehicle event information, the first risk profile, and the vehicle event characterization information. Operation 506 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to performance determination component 412, in accordance with one or more implementations.

(92) An operation 508 may include comparing the one or more metrics for the particular vehicle operator with aggregated metrics that quantify performance levels of a set of vehicle operators. Operation 508 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to performance comparison component 414, in accordance with one or more implementations. (93) An operation 510 may include storing, transferring, and/or presenting results of the comparison. Operation 510 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to result component 416, in accordance with one or more implementations.

(94) FIG. 7 illustrates a system 700 configured for using risk profiles for creating and deploying new vehicle event definitions to a fleet 12 of vehicles, in accordance with one or more implementations. In some implementations, system 700 may be configured to couple with vehicles that are operated by vehicle operators. As used here, the term fleet may refer to a set of at least 5 vehicles, at least 10 vehicles, at least 700 vehicles, at least 7000 vehicles, and/or another number of vehicles. For example, fleet 12 may include a first vehicle 12a, a second vehicle 12b, a third vehicle 12c, a fourth vehicle, and so forth.

(95) As used regarding system 700, the risk profiles may characterize values representing likelihoods of certain occurrences. For example, a first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. In some implementations, the first risk profile may be context-specific. For example, a second risk profile may be specific to operators. As used herein, an operator involved in a vehicle event may be a human vehicle operator, an autonomous driving algorithm, a type of vehicle, and/or a combination thereof. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. In some implementations, the second risk profile may be operator-specific. In some implementations, additional and/or different risk profiles are envisioned within the scope of this disclosure. In some implementations, values characterized by risk profiles may be based on vehicle event information for previously detected vehicle events.

(96) As used regarding system 700, individual vehicles may include a set of resources for data processing and/or electronic storage, including but not limited to persistent storage. Individual vehicles may include a set of sensors configured to generate output signals conveying information, e.g., related to the operation of the individual vehicles. Individual vehicles may be configured to detect vehicle events, e.g., based on output signals generated by sensors.

(97) System 700 may include one or more of fleet 12 of vehicles, server(s) 102, electronic storage 126, client computing platform(s) 104, external resource(s) 124, network(s) 13, and/or other components. In some implementations, system 700 may be a distributed data center, include a distributed data center, or act as a distributed data center. Alternatively, and/or simultaneously, system 700 may be a remote computing server, include a remote computing server, or act as a remote computing server, where a remote computing server is separate, discrete, and/or distinct from the fleet of vehicles. Server(s) 102 may be configured to communicate with one or more client computing platforms 104 according to a client/server architecture and/or other architectures. Client computing platform(s) 104 may be configured to communicate with other client computing platforms via server(s) 102 and/or according to a peer-to-peer architecture and/or other architectures. Users may access system 700 via client computing platform(s) 104.

(98) Server(s) 102 may be configured by machine-readable instructions 106. Machine- readable instructions 106 may include one or more instruction components. The instruction components may include computer program components. As used regarding system 700, the instruction components may include one or more of a risk profile obtaining component 708, an event selection component 710, a circumstance determination component 712, a vehicle event definition component 714, a vehicle event distribution component 716, a vehicle event information receiving component 718, a risk profile modification component 720, a

presentation component 722, and/or other instruction components.

(99) Risk profile obtaining component 708 may be configured to obtain and/or determine information, including but not limited to risk profiles. In some implementations, the first risk profile may be specific to a certain context for detecting vehicle events. As used regarding system 700, by way of non-limiting example, the certain context for detecting vehicle events may include one or more of location, local weather, heading of one or more vehicles, and/or traffic conditions. Alternatively, and/or simultaneously, by way of non-limiting example, the certain context for detecting vehicle events may include one or more of objects on roadways during detection of vehicle events, other incidents within a particular timeframe of detection of vehicle events, time of day, lane information, and/or presence of autonomously operated vehicles within a particular proximity. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. In some implementations, the first risk profile may characterize the first set of values representing likelihoods of occurrences of collisions and near-collisions at the individual locations. (100) As used regarding system 700, in some implementations, the second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching and/or otherwise involving the operators. The vehicle event information may include the certain context for the previously detected vehicle events and the operators for the previously detected vehicle events.

(101) The first set of values, the second set of values, and/or other sets of values for risk profiles may be based on the vehicle event information. In some implementations, the vehicle event information may include information about previously detected vehicle events, including but not limited to certain context for the previously detected vehicle events and/or the operators for the previously detected vehicle events.

(102) As used regarding system 700, in some implementations, the certain context for detecting vehicle events may include one or more of (geographical) location, local weather, heading of one or more vehicles, traffic conditions, and/or other context information. For example, a location-based risk profile may include a set of locations in a particular geographical area where previously detected vehicles events occurred. In some implementations, a location- based risk profile may form the basis for a risk map of the particular geographical area. In some implementations, a risk profile may include traffic conditions ( e.g ., whether traffic was heavy or light, what kind of participants were part of the traffic, how close other vehicles were, etc.). In some implementations, a risk profile may combine different kinds of context information. For example, a location-based risk profile may also indicate likelihoods of occurrences of certain vehicle events during heavy traffic, light traffic, during rain or snow, heading east or west, and so forth.

(103) Event selection component 710 may be configured to select vehicle events from a set of vehicle events. In some implementations, events may be selected from previously detected vehicle events. For example, selected events may have one or more characteristics in common. By way of non-limiting example, the one or more characteristics may include one or more of geographical location, time of day, demographic information of vehicle operators, a sequence of operations performed by vehicle operators, and/or other characteristics. In some implementations, characteristics may be based on vehicle event information of previously detected vehicle events. In some implementations, characteristics may be based on context.

By way of non-limiting example, the selection may be based on one or more of the first risk profile, the second risk profile, the vehicle event characterization information, and/or other information. In some implementations, event selection may be based on statistical analysis of a set of vehicle events. For example, a subset of vehicle events may form a statistical outlier when compared to the entire set of vehicle events. In some implementations, statistical analysis may expose a concentration of events that indicates commonality among those events.

(104) By way of non-limiting example, FIG. 9 illustrates a map 900 depicting a geographical area around vehicles 12a-12b-12c and various routes these vehicles have traversed. For example, map 900 may include a destination 901 for vehicles 12a-12b-12c. For example, map 900 may include a point of origin 902 for vehicles 12a-12b-12c. Vehicle 12a may have traversed a first route 910, vehicle 12b may have traversed a second route 911, and vehicle 12c may have traversed a third route 912 to destination 901. Identifiers 903, 904, 905, 906, and 907 may represent detected vehicle events, also referred to jointly as a set of events that include event 903, event 904, event 905, event 906, and event 907, respectively. For example, all these events may be sudden complete stops. An event selection component similar to event selection component 710 in FIG. 7 may select a subset of vehicle events from the set in map 900. For example, the subset may include event 905, event 906, and event 907. This subset could be based on the time of day these events happened. Alternatively, and/or

simultaneously, this subset could be based on physical surroundings of the locations of the events, such as a one-way street in a downtown area. Alternatively, and/or simultaneously, this subset could be based on the type of vehicle involved in the events, such as a particular type of truck.

(105) Referring to FIG. 7, circumstance determination component 712 may be configured to determine circumstances for vehicle events. In some implementations, circumstances may be determined for at least a predefined period prior to occurrences of the selected vehicle events. The predefined period may be 30 seconds, 1 minute, 2 minutes, 3 minutes, 4 minutes,

5 minutes, 10 minutes, and/or another period. As used herein, circumstances may include context, physical surroundings, characteristics, and/or other specifics for vehicle events and/or other operations of vehicles. In some implementations, a set of circumstances may be a precursor to a particular type of vehicle event. For example, an occurrences of a set of circumstances may be likely to be followed by an occurrence of a vehicle event of the particular type. In some implementations, a set of circumstances may be a combination of elements, wherein individual elements may be independent. For example, a particular set of

circumstances may include one or more of a particular time of day, a particular location, a particular weather and/or visibility condition, a particular action or actions performed by a vehicle operator, a particular action or actions performed by a vehicle, and/or other circumstances.

(106) By way of non-limiting example, FIG. 9 illustrates map 900 depicting a geographical area around vehicles 12a-12b-12c, and various detected vehicle events. By way of non-limiting example, a subset of vehicle events may have been selected, as described previously, that includes event 905, event 906, and event 907. A circumstance determination component similar to circumstance determination component 712 in FIG. 7 may determine a set of circumstances that is associated with the subset of vehicles events in FIG. 9. In some implementations, a set of circumstances may be based on analyzing a predefined period prior to occurrences of the pertinent vehicle events. For example, the circumstances associated with the subset of vehicle events may include one or more of locations near a school, time of occurrence right before school begins or ends (say, between 7 am and 8 am, or between 2 pm and 3 pm), a right turn followed by hard braking, a turn at a stop sign followed by hard braking, a turn in a downtown area when weather conditions indicate fog and/or low visibility, three or more lanes going in the same direction, multiple lane changes immediately prior to a turn, more than a predetermined number of vehicle detected within a predetermined proximity (e.g., more than 10 vehicles detected going in the same direction within 50 feet), reversion of a lane change within a short amount of time (e.g., change lane and change back within 10 seconds), and/or other circumstances. For example, some of these circumstances may represent an elevated likelihood of an occurrence of a vehicle event involving a pedestrian. For example, some of these circumstances may represent an elevated likelihood that a vehicle operator acted in a rush and/or was in a hurry. For example, some of these circumstances may represent an elevated likelihood that a vehicle operator made a turn (or took another action) at a higher speed than would usually be considered prudent. By combining independent circumstances, a driving scenario is created with an elevated likelihood of an occurrence of a vehicle event immediately following {i.e., within 30 seconds, 1 minute, 2 minutes, and so forth) the occurrence of the combination of circumstances. By creating vehicle event definitions (based on these circumstances) and subsequently detecting corresponding vehicle events that represent the occurrence of these circumstances (or combinations of circumstances), batter fleet management may be facilitated. For example, vehicle operators (human or autonomous) may receive additional training on the types of driving scenarios detected through new vehicle event definitions matching the occurrences of these circumstances.

(107) Referring to FIG. 7 , vehicle event definition component 714 may be configured to create vehicle event definitions, including but not limited to a new vehicle event definition that is based on one or more circumstances. For example, a new vehicle event definition may be based on a set of circumstances determined by circumstance determination component 712.

(108) Vehicle event distribution component 716 may be configured to distribute and/or otherwise provide vehicle event definitions to fleet 12. For example, a new vehicle event definition as created by vehicle event definition component 714 may be distributed to individual vehicles in fleet 12 of vehicles. Individual vehicles may use (new) vehicle event definitions to detect vehicle events. In particular, vehicles may use the new vehicle event definition to detect vehicle events of a type that corresponds to the new vehicle event definition. Vehicle event information regarding detected vehicle events may be received by system 700.

(109) Vehicle event information receiving component 718 may be configured to receive additional vehicle event information from the individual vehicles in the fleet of vehicles. The additional vehicle event information may include information regarding detection of additional vehicle events. The additional vehicle events may have been detected in accordance with the new vehicle event definition.

(110) Risk profile modification component 720 may be configured to modify risk profiles, e.g. based on received vehicle event information. For example, a risk profile may be modified based on additional vehicle event information as received by vehicle event information receiving component 718. In some implementations, risk profile modification component 720 may be configured to modify one or more of the first risk profile and/or the second risk profile based on the additional vehicle event information. For example, a risk profile may distinguish between acute vehicle events (such as a collision) and vehicle events that are a precursor to acute vehicle events (e.g., vehicle events that correspond to a new vehicle event definition created by vehicle event definition component 714).

(111) Presentation component 722 may be configured to present, via a user interface, information regarding the vehicle event information, including but not limited to additional vehicle event information (e.g., as received by vehicle event information receiving component 718). In some implementations, presentation component 722 may be configured to store, transfer, and/or present results of system 700 and/or its components to users. In some implementations, presentation component 722 may be configured to present information resulting from one or more of the determination, estimation, comparison, analysis, and/or otherwise processing of vehicle event information, including but not limited to additional vehicle event information. For example, a fleet manager or other stakeholder may be presented with an overview of the detection of vehicle events that match new vehicle event definitions within the fleet for this year, this month, this week, etc.

(112) In some implementations, the previously detected vehicle events may have been detected by fleet 12 of vehicles. In some implementations, the one or more types of vehicle event may involve a vehicle exceeding a speed threshold. In some implementations, by way of non-limiting example, a particular type of vehicle event may involve one or more of swerving, a U-turn, freewheeling, over-revving, lane-departure, short following distance, imminent collision, unsafe turning that approaches rollover and/or vehicle stability limits, hard braking, rapid acceleration, idling, driving outside a geo-fence boundary, crossing double-yellow lines, passing on single-lane roads, a certain number of lane changes within a certain amount of time or distance, fast lane change, cutting off other vehicles during lane-change speeding, running a red light, running a stop sign, parking a vehicle, and/or performing fuel-inefficient maneuvers. Alternatively, and/or simultaneously, these vehicle events may be categorize using multiple vehicle event types. For example, different vehicle event types may have different levels of accountability, severity, potential for damage, and/or other differences.

(113) As used regarding system 700, processor(s) 128 may be configured to execute components 708, 710, 712, 714, 716, 718, 720, and/or 722, and/or other components.

Processor(s) 128 may be configured to execute components 708, 710, 712, 714, 716, 718, 720, and/or 722, and/or other components by software; hardware; firmware; some combination of software, hardware, and/or firmware; and/or other mechanisms for configuring processing capabilities on processor(s) 128.

(114) It should be appreciated that although components 708, 710, 712, 714, 716, 718, 720, and/or 722 are illustrated in FIG. 7 as being implemented within a single processing unit, in implementations in which processor(s) 128 includes multiple processing units, one or more of components 708, 710, 712, 714, 716, 718, 720, and/or 722 may be implemented remotely from the other components. The description of the functionality provided by the different components 708, 710, 712, 714, 716, 718, 720, and/or 722 described below is for illustrative purposes, and is not intended to be limiting, as any of components 708, 710, 712, 714, 716,

718, 720, and/or 722 may provide more or less functionality than is described. For example, one or more of components 708, 710, 712, 714, 716, 718, 720, and/or 722 may be eliminated, and some or all of its functionality may be provided by other ones of components 708, 710,

712, 714, 716, 718, 720, and/or 722. As another example, processor(s) 128 may be configured to execute one or more additional components that may perform some or all of the functionality attributed below to one of components 708, 710, 712, 714, 716, 718, 720, and/or 722.

(115) FIG. 8 illustrates a method 800 for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, in accordance with one or more

implementations. The operations of method 800 presented below are intended to be illustrative. In some implementations, method 800 may be accomplished with one or more additional operations not described, and/or without one or more of the operations discussed. Additionally, the order in which the operations of method 800 are illustrated in FIG. 8 and described below is not intended to be limiting.

(116) In some implementations, method 800 may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information). The one or more processing devices may include one or more devices executing some or all of the operations of method 800 in response to instructions stored electronically on an electronic storage medium. The one or more processing devices may include one or more devices configured through hardware, firmware, and/or software to be specifically designed for execution of one or more of the operations of method 800.

(117) An operation 802 may include obtaining a first risk profile, a second risk profile, and vehicle event characterization information. The first risk profile may be specific to a certain context for detecting vehicle events. The first risk profile may characterize a first set of values representing likelihoods of occurrences of vehicle events matching the certain context. The second risk profile may be specific to operators. The second risk profile may characterize a second set of values representing likelihoods of occurrences of vehicle events matching the operators. The vehicle event characterization information may characterize one or more types of vehicle events to be used in creating and deploying the new vehicle event definitions. Operation 802 may be performed by one or more hardware processors configured by machine- readable instructions including a component that is the same as or similar to risk profile obtaining component 708, in accordance with one or more implementations.

(118) An operation 804 may include selecting individual ones of the previously detected vehicle events that have one or more characteristics in common. The selection may be based on one or more of the first risk profile, the second risk profile, and the vehicle event characterization information. Operation 804 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to event selection component 710, in accordance with one or more implementations.

(119) An operation 806 may include determining circumstances for at least a predefined period prior to occurrences of the selected vehicle events. Operation 806 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to circumstance determination component 712, in accordance with one or more implementations.

(120) An operation 808 may include creating a new vehicle event definition based on the determined set of circumstances and/or physical surroundings. Operation 808 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to vehicle event definition component 714, in accordance with one or more implementations.

(121) An operation 810 may include distributing the new vehicle event definition to individual vehicles in the fleet of vehicles. Operation 810 may be performed by one or more hardware processors configured by machine-readable instructions including a component that is the same as or similar to vehicle event distribution component 716, in accordance with one or more implementations.

(122) An operation 812 may include receiving additional vehicle event information from the individual vehicles in the fleet of vehicles. The additional vehicle event information may include information regarding detection of additional vehicle events. The additional vehicle events may have been detected in accordance with the new vehicle event definition.

Operation 812 may be performed by one or more hardware processors configured by machine- readable instructions including a component that is the same as or similar to vehicle event information receiving component 718, in accordance with one or more implementations. (123) Although the present technology has been described in detail for the purpose of illustration based on what is currently considered to be the most practical and preferred implementations, it is to be understood that such detail is solely for that purpose and that the technology is not limited to the disclosed implementations, but, on the contrary, is intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present technology contemplates that, to the extent possible, one or more features of any implementation can be combined with one or more features of any other implementation.

Claims

What is claimed is:

1. A system configured for creating and using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on previously detected vehicle events, the system comprising:

one or more hardware processors configured by machine-readable instructions to: obtain vehicle event information for vehicle events that have been detected by the fleet of vehicles, wherein the vehicle event information for the vehicle events includes locations of the vehicle events, vehicle types involved in the vehicle events, and types of the vehicle events;

aggregate the vehicle event information for multiple ones of the vehicle events to create a risk profile, wherein the risk profile characterizes a set of values representing likelihoods of occurrences of different types of vehicle events at different locations involving different vehicle types;

obtain a point of origin for a particular vehicle and a target destination the particular vehicle is intended to reach, wherein the particular vehicle has a particular vehicle type;

determine a set of routes from the point of origin to the target destination, wherein the set of routes includes at least two different routes;

determine individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes, wherein determining the individual values is based on the risk profile, wherein the set of routes includes a first route and a second route, wherein the determinations include a first determination of a first individual value for the first route and a second determination of a second individual value for the second route;

select the first route from the set of routes, wherein the first route is selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route; and

provide the selected first route to the particular vehicle.

2. The system of claim 1, wherein the vehicle event information further includes identifiers of vehicle operators involved in the vehicle events, wherein aggregating the vehicle event information further creates a personal risk profile that is specific to individual vehicle operators, wherein the personal risk profile characterizes a second set of values representing likelihoods of occurrences of vehicles events involving the individual vehicle operators, and wherein determining the individual values is further based on the personal risk profile.

3. The system of claim 1, wherein the types of vehicle events include a first type of vehicle event, and wherein the first type of vehicle event involves a vehicle exceeding a speed threshold.

4. The system of claim 1, wherein the types of vehicle events include a first type of vehicle event, and wherein the first type of vehicle event involves one or more of swerving, a U-turn, freewheeling, over-revving, lane-departure, short following distance, imminent collision, unsafe turning that approaches rollover and/or vehicle stability limits, hard braking, rapid acceleration, idling, driving outside a geo-fence boundary, crossing double-yellow lines, passing on single lane roads, a certain number of lane changes within a certain amount of time or distance, fast lane change, cutting off other vehicles during lane-change speeding, running a red light, running a stop sign, parking a vehicle, and/or performing fuel-inefficient maneuvers.

5. The system of claim 1, wherein determining the individual values includes determining the individual values representing likelihoods of occurrences of collisions and near-collisions along the individual routes in the set of routes.

6. The system of claim 1, wherein obtaining the point of origin for the particular vehicle and the target destination includes receiving information from the particular vehicle, wherein the received information represents the point of origin for the particular vehicle and the target destination.

7. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to:

create a risk map of a geographical area, wherein the risk map is based on the risk profile, and wherein the risk map characterizes values representing likelihoods of occurrences of vehicles events at specific locations within the geographical area; and provide the risk map to the particular vehicle.

8. The system of claim 1, wherein the types of vehicles events include different types for different segments of a day.

9. The system of claim 1, wherein the particular vehicle is being operated by a particular vehicle operator, and wherein determining the individual values is performed such that previously detected vehicle events that involved the particular vehicle operator weigh more heavily than previously detected vehicle events that did not involve the particular vehicle operator.

10. A method for creating and using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on previously detected vehicle events, the method comprising:

obtaining vehicle event information for vehicle events that have been detected by the fleet of vehicles, wherein the vehicle event information for the vehicle events includes locations of the vehicle events, vehicle types involved in the vehicle events, and types of the vehicle events;

aggregating the vehicle event information for multiple ones of the vehicle events to create a risk profile, wherein the risk profile characterizes a set of values representing likelihoods of occurrences of different types of vehicle events at different locations involving different vehicle types;

obtaining a point of origin for a particular vehicle and a target destination the particular vehicle is intended to reach, wherein the particular vehicle has a particular vehicle type;

determining a set of routes from the point of origin to the target destination, wherein the set of routes includes at least two different routes;

determining individual values representing likelihoods of occurrences of vehicle events along individual routes in the set of routes, wherein determining the individual values is based on the risk profile, wherein the set of routes includes a first route and a second route, wherein the determinations include a first determination of a first individual value for the first route and a second determination of a second individual value for the second route; selecting the first route from the set of routes, wherein the first route is selected such that the first individual value representing likelihood of occurrences of vehicle events along the first route is lower than the second individual value representing likelihood of occurrences of vehicle events along the second route; and

providing the selected first route to the particular vehicle.

11. The method of claim 10, wherein the vehicle event information further includes identifiers of vehicle operators involved in the vehicle events, wherein aggregating the vehicle event information further creates a personal risk profile that is specific to individual vehicle operators, wherein the personal risk profile characterizes a second set of values representing likelihoods of occurrences of vehicles events involving the individual vehicle operators, and wherein determining the individual values is further based on the personal risk profile.

12. The method of claim 10, wherein the types of vehicle events include a first type of vehicle event, and wherein the first type of vehicle event involves a vehicle exceeding a speed threshold.

13. The method of claim 10, wherein the types of vehicle events include a first type of vehicle event, and wherein the first type of vehicle event involves one or more of swerving, a U- turn, freewheeling, over-revving, lane-departure, short following distance, imminent collision, unsafe turning that approaches rollover and/or vehicle stability limits, hard braking, rapid acceleration, idling, driving outside a geo-fence boundary, crossing double-yellow lines, passing on single-lane roads, a certain number of lane changes within a certain amount of time or distance, fast lane change, cutting off other vehicles during lane-change speeding, running a red light, running a stop sign, parking a vehicle, and/or performing fuel-inefficient maneuvers.

14. The method of claim 10, wherein determining the individual values includes

determining the individual values representing likelihoods of occurrences of collisions and near collisions along the individual routes in the set of routes.

15. The method of claim 10, wherein obtaining the point of origin for the particular vehicle and the target destination includes receiving information from the particular vehicle, wherein the received information represents the point of origin for the particular vehicle and the target destination.

16. The method of claim 10, further comprising:

creating a risk map of a geographical area, wherein the risk map is based on the risk profile, and wherein the risk map characterizes values representing likelihoods of occurrences of vehicles events at specific locations within the geographical area; and

providing the risk map to the particular vehicle.

17. The method of claim 10, wherein the types of vehicles events include different types for different segments of a day.

18. The method of claim 10, wherein the particular vehicle is being operated by a particular vehicle operator, and wherein determining the individual values is performed such that previously detected vehicle events that involved the particular vehicle operator weigh more heavily than previously detected vehicle events that did not involve the particular vehicle operator.

19. A system configured for using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on vehicle event information for previously detected vehicle events, the system comprising:

one or more hardware processors configured by machine-readable instructions to: obtain a first risk profile, a second risk profile, and vehicle event characterization information, wherein the first risk profile is specific to a certain context for detecting vehicle events, wherein the first risk profile characterizes a first set of values representing likelihoods of occurrences of vehicle events matching the certain context, wherein the second risk profile is specific to operators, wherein the second risk profile characterizes a second set of values representing likelihoods of occurrences of vehicle events matching the operators, and wherein the vehicle event characterization information characterizes one or more types of vehicle events to be used in determining performance levels by particular vehicle operators;

receive, from a particular vehicle, particular vehicle event information for particular vehicle events that have been detected by the particular vehicle, wherein the particular vehicle has a particular vehicle type and is operated by a particular vehicle operator, wherein the particular vehicle event information includes particular locations of the particular vehicle events, and wherein the particular vehicle event information further includes particular types of the particular vehicle events;

determine one or more metrics that quantify a performance level of the particular vehicle operator, wherein the determination of the one or more metrics is based on one or more of the received particular vehicle event information, the first risk profile, and the vehicle event characterization information;

compare the one or more metrics for the particular vehicle operator with aggregated metrics that quantify performance levels of a set of vehicle operators; and

store, transfer, and/or present results of the comparison.

20. A method for using risk profiles for fleet management of a fleet of vehicles, wherein the risk profiles characterize values representing likelihoods of occurrences of vehicle events, wherein the values are based on vehicle event information for previously detected vehicle events, the method comprising:

obtaining a first risk profile, a second risk profile, and vehicle event characterization information, wherein the first risk profile is specific to a certain context for detecting vehicle events, wherein the first risk profile characterizes a first set of values representing likelihoods of occurrences of vehicle events matching the certain context, wherein the second risk profile is specific to operators, wherein the second risk profile characterizes a second set of values representing likelihoods of occurrences of vehicle events matching the operators, and wherein the vehicle event characterization information characterizes one or more types of vehicle events to be used in determining performance levels by particular vehicle operators;

receiving, from a particular vehicle, particular vehicle event information for particular vehicle events that have been detected by the particular vehicle, wherein the particular vehicle has a particular vehicle type and is operated by a particular vehicle operator, wherein the particular vehicle event information includes particular locations of the particular vehicle events, and wherein the particular vehicle event information further includes particular types of the particular vehicle events;

determining one or more metrics that quantify a performance level of the particular vehicle operator, wherein the determination of the one or more metrics is based on one or more of the received particular vehicle event information, the first risk profile, and the vehicle event characterization information;

comparing the one or more metrics for the particular vehicle operator with aggregated metrics that quantify performance levels of a set of vehicle operators; and

storing, transferring, and/or presenting results of the comparison.

21. A system configured for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, the system comprising:

one or more hardware processors configured by machine-readable instructions to: obtain a first risk profile, a second risk profile, and vehicle event characterization information, wherein the first risk profile is specific to a certain context for detecting vehicle events, wherein the first risk profile characterizes a first set of values representing likelihoods of occurrences of vehicle events matching the certain context, wherein the second risk profile is specific to operators, wherein the second risk profile characterizes a second set of values representing likelihoods of occurrences of vehicle events matching the operators, and wherein the vehicle event characterization information characterizes one or more types of vehicle events to be used in creating and deploying the new vehicle event definitions;

select individual ones of the previously detected vehicle events that have one or more characteristics in common, wherein the selection is based on one or more of the first risk profile, the second risk profile, and the vehicle event characterization information;

determine circumstances for at least a predefined period prior to occurrences of the selected vehicle events;

create a new vehicle event definition based on the determined set of circumstances;

distribute the new vehicle event definition to individual vehicles in the fleet of vehicles; and

receive additional vehicle event information from the individual vehicles in the fleet of vehicles, wherein the additional vehicle event information includes information regarding detection of additional vehicle events, and wherein the additional vehicle events have been detected in accordance with the new vehicle event definition.

22. A method for using risk profiles for creating and deploying new vehicle event definitions to a fleet of vehicles, the method comprising:

obtaining a first risk profile, a second risk profile, and vehicle event characterization information, wherein the first risk profile is specific to a certain context for detecting vehicle events, wherein the first risk profile characterizes a first set of values representing likelihoods of occurrences of vehicle events matching the certain context, wherein the second risk profile is specific to operators, wherein the second risk profile characterizes a second set of values representing likelihoods of occurrences of vehicle events matching the operators, and wherein the vehicle event characterization information characterizes one or more types of vehicle events to be used in creating and deploying the new vehicle event definitions;

selecting individual ones of the previously detected vehicle events that have one or more characteristics in common, wherein the selection is based on one or more of the first risk profile, the second risk profile, and the vehicle event characterization information;

determining circumstances for at least a predefined period prior to occurrences of the selected vehicle events;

creating a new vehicle event definition based on the determined set of circumstances; distributing the new vehicle event definition to individual vehicles in the fleet of vehicles;

receiving additional vehicle event information from the individual vehicles in the fleet of vehicles, wherein the additional vehicle event information includes information regarding detection of additional vehicle events, and wherein the additional vehicle events have been detected in accordance with the new vehicle event definition.