Behavior profile map of vehicle driver

Abstract

A system for evaluating a vehicle includes a monitoring module configured to obtain information related to a combined force applied to the vehicle, and an analysis module configured to receive the obtained information and determine a plurality of force pairs based on the obtained information, each force pair of the plurality of force pairs includes a longitudinal force value and a lateral force value. The analysis module is configured to assign each force pair to one of the plurality of bins and construct a two-dimensional behavioral profile that spatially represents the combined force and presents a behavioral pattern during a time window, the behavioral profile comprising an array of two-dimensional data elements, each data element in the array of data elements corresponds to a respective bin, wherein the behavioral profile map is constructed by populating each data element based on one or more force pairs assigned to the respective bin.

Description

Technical Field

[0001] This subject matter discloses information in the field of vehicle monitoring, planning, and control. More specifically, this subject matter discloses systems and methods for summarizing and presenting behavioral information related to vehicle operation. Background Technology

[0002] Vehicles are increasingly equipped with sensors and perception devices that enhance vehicle control systems and driver awareness, and can provide autonomous control and / or driver support. Data from such systems can be used to monitor vehicle use and collect information that can be used to enhance the driver experience, and to provide insights into vehicle performance and repair and maintenance needs. There is a desire to provide systems and methods that can offer further insights. Summary of the Invention

[0003] In one exemplary embodiment, a system for evaluating a vehicle includes a monitoring module configured to acquire information relating to combined forces applied to the vehicle at each of a plurality of consecutive sampling times during a selected time window, the combined forces being based on driver control of the vehicle and including longitudinal and lateral forces. The system also includes an analysis module configured to receive the acquired information and determine a plurality of force pairs based on the acquired information, each force pair including a longitudinal force value and a lateral force value. The analysis module is configured to assign each force pair to one of a plurality of bins, each bin being associated with a corresponding longitudinal force range and a corresponding lateral force range, and to construct a two-dimensional behavioral profile that spatially represents the combined forces and presents a behavioral pattern during the selected time window. The two-dimensional behavioral profile includes a two-dimensional data element array, each data element corresponding to a corresponding bin, wherein the two-dimensional behavioral profile is constructed by populating each data element based on one or more force pairs assigned to the corresponding bin.

[0004] In addition to one or more features described herein, the system includes a control module configured to perform at least one of the following: controlling one aspect of vehicle operation based on a two-dimensional behavior profile, presenting suggestions to the driver of the vehicle based on the two-dimensional behavior profile, determining the driver's driving style based on acceleration from the two-dimensional behavior profile, and assessing the condition of the vehicle based on the two-dimensional behavior profile.

[0005] In addition to one or more features described herein, the monitoring module is configured to collect vehicle position, vehicle heading, vehicle longitudinal acceleration, and lateral acceleration for each sampling time window.

[0006] In addition to one or more features described herein, at least one of longitudinal acceleration and lateral acceleration is determined based on vehicle position, vehicle speed, and vehicle trajectory.

[0007] In addition to one or more features described herein, a two-dimensional data element array is a two-dimensional grid with a first axis representing longitudinal force values ​​and a second axis representing transverse force values, and the two-dimensional grid comprises multiple cells and is divided into a set of quadrants.

[0008] In addition to one or more features described herein, this set of quadrants includes the upper left quadrant representing forward acceleration and leftward acceleration, the upper right quadrant representing forward acceleration and rightward acceleration, the lower left quadrant representing longitudinal deceleration and leftward acceleration, and the lower right quadrant representing longitudinal deceleration and rightward acceleration.

[0009] In addition to one or more features described in this paper, each bin is a feature vector, and the analysis module is configured to determine a combined force vector based on the longitudinal and lateral force values ​​for each force pair, and to assign the combined force vector to the corresponding bin.

[0010] In addition to one or more features described herein, data elements are populated with a value based on a warehouse count, which represents the number of force pairs assigned to the associated warehouse.

[0011] In addition to one or more features described herein, data elements are populated with probability values ​​based on the warehouse count of the associated warehouse and the total warehouse count, which is the sum of the warehouse counts in the two-dimensional array of data elements.

[0012] In another exemplary embodiment, a method for evaluating a vehicle includes acquiring information relating to combined forces applied to the vehicle at each of a plurality of consecutive sampling times during a selected time window, the combined forces applied to the vehicle being based on driver control of the vehicle, and the combined forces including longitudinal and lateral forces. The method includes determining a plurality of force pairs based on the acquired information, each of the plurality of force pairs including a longitudinal force value and a lateral force value, and assigning each force pair to one of a plurality of compartments, each of the plurality of compartments being associated with a corresponding longitudinal force range and a lateral force range. The method also includes constructing a two-dimensional behavioral profile that spatially represents the combined forces and presents a pattern of driver behavior during the selected time window, the two-dimensional behavioral profile including a two-dimensional array of data elements, each data element corresponding to a corresponding compartment, wherein the two-dimensional behavioral profile is constructed by filling each data element based on one or more force pairs assigned to the corresponding compartment.

[0013] In addition to one or more features described in this paper, the information acquired includes vehicle position, vehicle heading, longitudinal acceleration, and lateral acceleration collected for each sampling time window.

[0014] In addition to one or more features described herein, at least one of longitudinal acceleration and lateral acceleration is determined based on vehicle position, vehicle speed, and vehicle trajectory.

[0015] In addition to one or more features described herein, a two-dimensional data element array is a two-dimensional grid with a first axis representing longitudinal force values ​​and a second axis representing transverse force values, and the two-dimensional grid comprises multiple cells and is divided into a set of quadrants.

[0016] In addition to one or more features described herein, each bin is a feature vector, and assigning force pairs includes determining a combined force vector based on longitudinal and lateral force values, and assigning the combined force vector to the corresponding bin.

[0017] In addition to one or more features described herein, data elements are populated with values ​​corresponding to the bin count of the associated bin, which represents the number of force pairs assigned to the associated bin, and constructing the two-dimensional behavior profile involves excluding cells in the central region of the mesh to generate the final behavior profile.

[0018] In yet another exemplary embodiment, the vehicle system includes a memory having computer-readable instructions and a processing device for executing the computer-readable instructions, which control the processing device to perform a method. The method includes acquiring information relating to combined forces applied to the vehicle at each of a plurality of consecutive sampling times during a selected time window, the combined forces applied to the vehicle being based on driver control of the vehicle, and the combined forces including longitudinal and lateral forces. The method includes determining a plurality of force pairs based on the acquired information, each of the plurality of force pairs including a longitudinal force value and a lateral force value, and assigning each force pair to one of a plurality of compartments, each of the plurality of compartments being associated with a corresponding longitudinal force range and a lateral force range. The method also includes constructing a two-dimensional behavioral profile that spatially represents the combined forces and presents a pattern of driver behavior during the selected time window, the two-dimensional behavioral profile including a two-dimensional array of data elements, each data element of the two-dimensional array corresponding to a corresponding compartment, wherein the two-dimensional behavioral profile is constructed by filling each data element based on one or more force pairs assigned to the corresponding compartment.

[0019] In addition to one or more features described in this paper, the information acquired includes vehicle position, vehicle heading, longitudinal acceleration, and lateral acceleration collected for each sampling time window.

[0020] In addition to one or more features described herein, at least one of longitudinal acceleration and lateral acceleration is determined based on vehicle position, vehicle speed, and vehicle trajectory.

[0021] In addition to one or more features described herein, each bin is a feature vector, and the force pair assignment involves determining a combined force vector based on longitudinal and lateral force values, and assigning the combined force vector to the bin.

[0022] In addition to one or more features described herein, data elements are populated with values ​​corresponding to the bin counts of the associated bins, which represent the number of force pairs assigned to the associated bins, and constructing the two-dimensional behavioral profile involves excluding a set of data elements in the central region of the two-dimensional array to generate the final behavioral profile.

[0023] The above-described features and advantages, as well as other features and advantages of this disclosure, will become apparent when taken in conjunction with the accompanying drawings and the following detailed description. Attached Figure Description

[0024] Other features, advantages, and details appear by way of example only in the following detailed description, which refers to the accompanying drawings, in which:

[0025] Figure 1 This is a top view of a motor vehicle including various aspects of a user interaction and prediction system according to an exemplary embodiment;

[0026] Figure 2 It is a flowchart depicting various aspects of a method for monitoring and evaluating driving behavior according to an exemplary embodiment;

[0027] Figure 3A and Figure 3B The diagram graphically illustrates various aspects of applying force values ​​to a bin or other data structure according to an exemplary embodiment.

[0028] Figure 4 Depicting according to Figure 2 An example of a two-dimensional grid for the method, which includes cells or other elements filled based on information collected during a vehicle journey;

[0029] Figure 5 Depicting according to Figure 2 The method Figure 4 A two-dimensional grid in which bins representing balanced forces and normal forces are excluded or discarded;

[0030] Figure 6 From Figure 5 An example of a heatmap exported from a mesh;

[0031] Figure 7A bar graph depicting the possibilities of harsh braking or acceleration generated by simulation of longitudinal acceleration according to an exemplary embodiment;

[0032] Figures 8A-8C Depicting based on Figure 4 The grid and according to Figure 2 Examples of methods for generating or constructing behavioral profile diagrams;

[0033] Figure 9 Examples of visualizations generated based on behavioral profiles associated with intersections are depicted.

[0034] Figure 10 An example depicting a behavioral profile;

[0035] Figure 11 An intersection is schematically shown;

[0036] Figure 12 Describing the target Figure 11 Examples of behavioral profiles generated at intersections; and

[0037] Figure 13 A computer system according to an exemplary embodiment is described. Detailed Implementation

[0038] The following description is exemplary in nature only and is not intended to limit this disclosure, its application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features.

[0039] According to one or more exemplary embodiments, methods and systems are provided for evaluating and characterizing vehicle and driver behavior during vehicle operation. Embodiments of the monitoring and evaluation system (referred to as the “monitoring system”) are configured to monitor the vehicle and generate a two-dimensional profile or data pattern representing vehicle behavior. The profile or data pattern is referred to herein as a “behavior profile” and may be associated with a specific vehicle or group of vehicles, a specific driver or group of drivers, and / or a given situation or condition.

[0040] Implementations of behavioral profile diagrams include two-dimensional (2D) data structures, such as 2D grids, which comprise arrays of data elements. Each element may be populated with a combined force value (or a value associated with a combination of force values ​​from multiple samples, such as a count or probability value), which includes a combination of longitudinal and lateral forces measured or estimated at a given measurement time or time window. For example, a behavioral profile diagram is a 2D graph defining longitudinal and lateral force axes. Compartmentation techniques can be used to construct the graph, where lateral and longitudinal force pairs are assigned to corresponding compartments. A behavioral profile diagram can be generated by assigning values ​​to each cell of the graph based on force data collected for the associated compartments. For example, each cell may be populated with a compartment count or probability value.

[0041] The embodiments described herein present numerous advantages. For example, the embodiments provide an intuitive spatial representation of driver behavior in a given context, which can be used to provide insights into driver behavior and its associated effects. Such insights can be used in a variety of ways, such as providing drivers with recommendations to improve their experience and performance, assessing vehicle wear, evaluating intersections and other routes, etc. By taking both longitudinal and lateral accelerations into account, the embodiments can reveal patterns that would not occur with other methods.

[0042] When driving, a vehicle experiences various stresses, which are not only longitudinal or lateral, but somewhere in between. The behavioral profiles described in this paper provide a combined distribution of lateral and longitudinal forces, overcoming the problems of existing methods.

[0043] For example, existing joint probabilistic methods (e.g., methods that separately compartmentalize applied acceleration and steering forces and use the intended joint probabilistic approach) may incorrectly represent the actual applied forces experienced by the vehicle. Collecting headway and lateral acceleration metrics separately hides the applied forces and inertia experienced by the vehicle, driver, and passenger compartment contents. The embodiments address this limitation.

[0044] Figure 1 An embodiment of a motor vehicle 10 is shown, which includes a vehicle body 12 that at least partially defines a passenger compartment 14. The vehicle body 12 also supports various vehicle subsystems, including a propulsion system 16, and other subsystems for supporting the functions of the propulsion system 16 and other vehicle components, such as a braking subsystem, a suspension system, a steering subsystem, and, if the vehicle is a hybrid electric vehicle, a fuel injection subsystem, an exhaust subsystem, etc.

[0045] Vehicle 10 may be an internal combustion engine vehicle, an electric vehicle (EV), or a hybrid vehicle. In one embodiment, vehicle 10 is a hybrid vehicle that includes an internal combustion engine system 18 and at least one electric motor assembly. In one embodiment, propulsion system 16 includes an electric motor 20 and may include one or more additional motors located at various positions. Vehicle 10 may be a fully electric vehicle with one or more electric motors.

[0046] The propulsion system 16 includes additional components for supporting propulsion, such as a cooling system and a transmission system 22 for controlling the transmission of torque from the engine 18 and / or motor 20 to the front drive shaft or front axle 24. The front axle 24 is connected to the front wheels 26.

[0047] The propulsion system 16 is not limited to the specific configuration shown. For example, the propulsion system 16 may include additional components, such as a drivetrain for transmitting torque to a rear drive shaft or rear axle 28 connected to the rear wheels 30. As previously mentioned, the propulsion system may include additional torque-generating devices, such as a rear electric motor 32. The vehicle may include various control devices for controlling various aspects of vehicle operation, such as a steering wheel 34, an accelerator pedal 36, and brakes 38.

[0048] Vehicle 10 includes various sensors and measurement systems that can be used in conjunction with vehicle monitoring system 40 to support vehicle operation. System 40 includes monitoring module 42 configured to collect force-related data (e.g., force measurements, position and speed information, etc.) on vehicle 10. Processing module 44 receives the measurement data and constructs or generates a two-dimensional behavioral profile, as discussed further herein. Processing module 44 includes or is connected to interface module 46 for presenting information to the driver or other users (e.g., displaying the behavioral profile and / or suggestions) or otherwise transmitting information to the user.

[0049] Various sensors can detect forces on vehicle 10, including forces applied to vehicle 10 via driver control (e.g., steering, acceleration, braking) and inertial forces. For example, an inertial measurement unit (IMU) 48 is included to measure vehicle parameters such as heading, speed, acceleration, turning rate, tilt, etc.

[0050] Other sensors may be included for monitoring and controlling the equipment, such as wheel speed sensors connected to one or more of wheels 26 and 30, a steering sensor connected to steering wheel 34, a brake sensor, etc. Other sensors may also include a Global Positioning System (GPS) unit for positioning and / or a Doppler GPS unit for velocity relative to global coordinates.

[0051] In one embodiment, the sensor includes a perception system for detecting and monitoring the environment around the vehicle. The perception system includes, for example, one or more optical cameras 50 configured to capture images, which may be still images and / or video images. Additional devices or sensors, such as one or more radar components 52, may be included in the vehicle 10. The perception system is not limited to this and may include other types of sensors, such as lidar and infrared sensors.

[0052] The monitoring system 40 can communicate with or operate in conjunction with a vehicle control system for autonomous or semi-autonomous control (e.g., driver assistance) of the vehicle 10. The vehicle control system can control various aspects of vehicle operation based on behavioral profiles.

[0053] Vehicle 10, monitoring system 40, and other vehicle systems include or are connected to onboard computer system 54, which includes one or more processing devices 56 and user interface 58. User interface 58 may include a touchscreen, a voice recognition system, and / or various buttons for allowing users to interact with features of the vehicle. User interface 58 may be configured to interact with the user via visual communication (e.g., text and / or graphical display), tactile communication or alarms (e.g., vibration) and / or auditory communication.

[0054] The monitoring system 40 is configured to collect data related to the applied forces and generate a behavioral profile that spatially represents the combined lateral and longitudinal forces on the vehicle. The behavioral profile may be specific to a given vehicle or driver (e.g., representing forces during a given journey or while traversing a route or trajectory), or it may be aggregated across multiple drivers in a given context. In one embodiment, the behavioral profile defines a set of cells or compartments arranged along the longitudinal and lateral force axes. Each compartment is filled with a count or other value representing the frequency with which the vehicle experiences the corresponding combined forces during the journey.

[0055] Behavioral profiles visually and spatially represent the various forces applied to vehicle 10 during a journey and provide indications of the driver's driving style and vehicle experience patterns. As vehicle 10 moves, actions including forward acceleration, braking, and cornering result in various applied forces and associated inertial effects. These inertial effects and forces affect the in-vehicle experience for the driver and passengers, and also influence vehicle conditions such as tire wear, suspension wear, and stabilizer performance.

[0056] Figure 2 A method 60 for evaluating vehicle operation and driver behavior is described. Method 60 is discussed in conjunction with boxes 61-67. Method 60 is not limited to the number or order of steps therein, as some steps represented by boxes 61-67 may be performed in a different order than that described below, or fewer than all steps may be performed.

[0057] Combination Figure 1 Method 60 is discussed in connection with a vehicle and a processing system, which may be, for example, a computer system 54, a monitoring system 40, or a combination thereof. For illustrative purposes, aspects of method 60 are discussed in conjunction with vehicle 10. Note that method 60 is not limited thereto and may be performed by any suitable processing equipment or system or combination of processing equipment.

[0058] At box 61, monitoring module 42 collects data and / or measurements that can be used to measure or estimate the forces initiated by the driver on vehicle 10. For example, the vehicle's position and heading are monitored (e.g., via GPS) as the vehicle traverses a route or trajectory. For example, module 42 collects dense force and / or trajectory data in multiple consecutive time windows (referred to as "sampling times") during a selected time period.

[0059] The time period is selected based on the environment in which vehicle 10 is operating. For example, the time period corresponds to the duration of the vehicle's "journey" during which the vehicle traverses a desired trajectory (e.g., intersection, road segment, track, etc.) or route.

[0060] Data collection can be performed periodically or continuously (e.g., at each sampling time of the sensor). For example, data can be collected repeatedly every 5 minutes (or other durations or time windows). In another example, data can be collected every 3 seconds.

[0061] At box 62, processing module 44 calculates a pair of force values ​​for each time window (or multiple pairs of force values ​​if multiple vehicles are detected), including the lateral force component G. f,x and longitudinal force component G f,y As described in this article, the "longitudinal" direction or axis is the direction or axis parallel to the heading of vehicle 10. Longitudinal forces can also be referred to as "headway" forces. The "lateral" direction or axis is the direction or axis perpendicular to the longitudinal direction or axis. The lateral direction can be to the right or to the left relative to the vehicle's heading. Lateral forces can also be referred to as "turning forces."

[0062] The force value can be determined in any suitable manner, such as by direct sensor measurement of force or acceleration (e.g., longitudinal and lateral acceleration can be directly measured by sensors such as IMU 48), by analyzing driver input, and / or by monitoring the position and movement of vehicle 10. The measured or estimated acceleration can be used as a force value, or the measured or estimated acceleration can be converted into a force (e.g., Newton or g-force).

[0063] Acceleration or force values ​​can be derived from driver input (e.g., driver engagement of the accelerator pedal 46 and / or brake 48). For example, lateral forces are estimated based on vehicle speed and steering wheel angle, and longitudinal forces are estimated based on the displacement of the accelerator pedal and brake. Alternatively, vehicle speed and movement can be monitored during a time window (e.g., via camera monitoring, such as traffic cameras or GPS), and lateral and longitudinal forces can be derived based on the vehicle's speed and trajectory.

[0064] Force values ​​can be expressed as acceleration or force. In one embodiment, each force value is expressed as g-force.

[0065] At box 63, the lateral force and longitudinal force pair (or the combined force value G calculated from the pair) are... f The force is assigned to a bin (e.g., a g-force bin). In one embodiment, each bin represents a feature vector of longitudinal (workshop time) and lateral acceleration forces. For example, the pair (or combined force value) is assigned to the bin by adding the feature vector to the bin.

[0066] exist Figure 3A and 3B The image shows examples of force pairs and aspects of assigning combined force pairs to a bin. Figure 3A and Figure 3B A grid 70 is shown, which has a central origin 72 and is composed of a longitudinal force G. f,y The vertical axis (longitudinal axis) and the force G used for the transverse force f,x The horizontal axis is defined. In this example, grid 70 defines a two-dimensional array of cells or bins 73, where each bin 73 has a corresponding longitudinal force range and a lateral force range.

[0067] In one embodiment, chamber 73 is defined by g-force. For example, chamber 73 represents a range of g-force values ​​multiplied by 10. Thus, chambers in the column labeled "1" have a range of lateral forces between zero and 0.1g, and chambers in the column labeled "-1" have a range of lateral forces between zero and -0.1g. In this way, all relevant forces are classified and represented by a consistent and simple convention, which allows for easy analysis and representation.

[0068] Grid 70 defines quadrants, including the upper left and upper right quadrants. The upper left quadrant includes positive longitudinal force (acceleration in the forward direction) and negative lateral force (force to the left), while the upper right quadrant includes positive longitudinal force and positive lateral force (force to the right). The lower left quadrant includes negative longitudinal force (deceleration or braking force) and negative lateral force, while the lower right quadrant includes negative longitudinal force and positive lateral force.

[0069] Grid 70 also defines the compartments associated with forces outside the expected or normal range and outside the balanced forces. For example, boundaries 75a and 75b depict which compartments are associated with longitudinal forces outside the normal range (associated with “hard” acceleration or hard braking). Boundaries 77a and 77b depict which compartments are associated with lateral forces outside the normal range (associated with hard cornering).

[0070] Examples of a pair of collected forces include a lateral force 74 and a longitudinal force 76, which define a combined force vector 78. If the combined force vector 78 is within the magnitudes of the lateral and longitudinal forces associated with the bin, the pair of collected forces is allocated to the bin. If the force vector 78 exceeds the bin structure, the pair is recorded in the nearest available bin.

[0071] As shown, the combined force vector 78 terminates at the chamber associated with hard acceleration and hard cornering. Force vector 78 can terminate at any point within the chamber. As force pairs are collected and distributed to the chamber, an outline 79 can be generated, representing the outer boundary of all observed forces. This outline 79 can be used as all or part of a behavioral profile (i.e., in place of the patterns and heatmaps discussed herein, or in addition to those discussed herein).

[0072] A given pair of forces (or the average of the pairs of forces) may terminate at the midpoint of the bin or at another point within bin 73. Therefore, profile line 79 does not need to connect the midpoints. For example, profile line 79 follows the pattern of force pairs in each bin 73.

[0073] Figure 3B The same grid 70 is shown, but the applied forces are converted into inertial forces felt by the driver and / or passengers. The inertial forces have the same magnitude as the applied forces, but their signs are reversed. The applied forces or inertial forces can be used to generate the behavioral profiles discussed in this paper.

[0074] At box 64, upon completion of the stroke, the total force measurement or estimate is applied to a two-dimensional data structure, such as a grid similar to or the same as grid 70 in Figure 3, where a value representing the occurrence of a combined force (i.e., a force having both lateral and longitudinal components) is inserted into each cell of the data structure. This value may be related to the frequency at which a given combined force occurs, or otherwise indicate the occurrence of force pairs having magnitudes within the cell boundaries. In one embodiment, the data structure is a two-dimensional graph with longitudinal and lateral force axes and includes a two-dimensional array of cells.

[0075] In one embodiment, the value assigned to a cell relates to the frequency of occurrence of a combination of forces within the range of lateral and longitudinal forces of the cell. For example, each cell is given a bin number indicating the number of instances of the combination force within the boundary of the bin associated with the cell. Other values, such as statistical values ​​or probabilities, may be used. For example, the probability of a given bin can be calculated by analyzing the lateral and longitudinal values.

[0076] Figure 4 An example of a grid 80 used to construct a behavioral profile is shown. Grid 80 includes a central origin 82, a vertical axis (Y) for longitudinal force values ​​(or related values, such as probabilities), and a horizontal axis (X) for lateral force values ​​(or related values). Grid 80 defines a plurality of cells 84, where each cell 84 corresponds to a bin having a range of values ​​related to longitudinal forces and a range of values ​​related to lateral forces.

[0077] Grid 80 defines four quadrants. The upper right (UR) quadrant includes elements 84 for positive or forward acceleration and force, and rightward lateral acceleration and force. The upper left (UL) quadrant includes elements 84 for positive or forward acceleration and force, and leftward lateral acceleration and force. The lower right (LR) quadrant includes elements 84 for negative acceleration (deceleration) and force, and rightward lateral acceleration and force. The lower left (LL) quadrant includes elements 84 for negative acceleration and force, and leftward lateral acceleration and force.

[0078] Each cell 84 is filled with a numerical value representing the total lateral and longitudinal forces allocated to the corresponding compartment. The value can be a count, a statistical value, a probability, or other relevant numerical value.

[0079] For example, a total count of all compartment forces is obtained and used to populate cell 84. Each cell 84 can be assigned a count number, which represents the number of sampled instances of lateral and longitudinal force pairs having sizes within the boundaries of the associated compartment, or a different value based on the count number (e.g., a probability value).

[0080] Figure 4 Bar graphs illustrating the distribution of compartment forces are also shown, including bar graph 86x showing the distribution along the X-axis and bar graph 86y showing the distribution along the Y-axis. These bar graphs visually demonstrate how normal and expected forces in the central unit typically govern the driver's experience.

[0081] As shown, the grid can be color-coded or shaded based on the fill value. Figure 4 In the example, grid 80 is filled with probabilities, where lighter colors or shadows indicate higher probabilities and darker colors or shadows indicate lower probabilities (non-shaded cells are filled with zero). Cell 84a is filled with probability values ​​from a first range, cell 84b is filled with probability values ​​from a second range that are smaller than the first range, and cell 84c is filled with probability values ​​from a third range that are smaller than the second range. The remaining cells 84 are filled with zero values. This article combines... Figures 8A-8C The calculation of probability values ​​will be discussed further.

[0082] Refer again Figure 2 At box 65, normal or balanced forces are excluded by discarding bins associated with balanced and normal forces. A "balanced force" is a combined force near the center of the grid where the longitudinal and lateral forces are zero or close to zero. A "normal force" is a force associated with the normal or expected level of acceleration, braking, or cornering. For example, a normal force is a force less than or equal to a force threshold of 0.2g, where "g" is gravity. Any suitable force threshold can be selected, for example, based on road type, vehicle type, and / or speed limits.

[0083] For example, refer to Figure 5A mask is applied to discard bins representing balanced and normal forces to generate a behavioral profile. As shown, a subset of bin 84 around the origin (denoted as bin 84d) is set to zero. Removing normal and expected forces alters the distribution, as shown in bars 86x and 86y.

[0084] Refer again Figure 2 At box 66, the obtained behavioral profile can be further analyzed or processed to enhance and reveal force patterns. For example, as... Figure 6 As shown, the behavioral profile 90 is converted into a heatmap or other visualization that highlights the changes in combined forces, displays the dominant force pairs as lobe 92, and clearly reveals the patterns associated with vehicle and driver behavior during the journey.

[0085] At box 67, a behavior profile can be used to perform one or more actions. Behavior profiles can be used to classify or represent driver styles, and can be used for driver risk assessment, maintenance scheduling, vehicle wear prediction, vehicle problem diagnosis, etc. Machine learning (e.g., unsupervised learning) can be used to identify and classify driving styles.

[0086] In the example, vehicle 10 includes autonomous or semi-autonomous control capabilities and can control various aspects of vehicle operation based on behavioral profiles. For example, driver profiles of traversing road segments and recent driver experiences can be used by the autonomous vehicle to avoid driving choices and minimize adversarial engagement with other vehicles.

[0087] In another example, suggestions can be presented to the driver based on a behavioral profile. These suggestions could include changes in driver style (e.g., reducing hard braking), which could improve the driver experience or increase the lifespan of vehicle components and systems.

[0088] Other actions may include assessing the vehicle's condition based on behavioral profiles, sending information to dealers or technicians, etc.

[0089] Behavioral profiles can be generated at the vehicle level to characterize the behavior of a given vehicle across various trip types, road networks, and traffic environments. Behavioral profiles can also be generated at the fleet level to characterize a group of vehicles. For example, vehicle trajectories from multiple vehicles traversing a segment or road can be collected and aggregated to generate a behavioral profile that reveals patterns across multiple vehicles when traversing a common segment or road.

[0090] Lateral and / or longitudinal forces can be directly measured, inferred, or estimated based on other data. In one embodiment, lateral and / or longitudinal forces are estimated based on monitored location information such as vehicle position, speed, heading, and / or trajectory.

[0091] Lateral forces address driving behaviors such as cornering and road curvature, exerting forces to the left and right on the vehicle. The calculation of lateral forces can be based on changes in the vehicle's heading and the observed velocity within a given time window (e.g., a 3-second interval). This calculation provides an estimate of the lateral g-force for a given change in heading and velocity.

[0092] In one embodiment, longitudinal and / or lateral forces are inferred based on monitoring the vehicle's speed and position. For example, for each instance of force pair collection, the vehicle's speed is sampled within a selected time window, and the speed changes within that time window can be used to calculate acceleration / deceleration and associated acceleration or braking forces (or lateral changes in speed and associated lateral or turning forces).

[0093] In some situations, the average speed change within a time window is sufficient to capture possible vehicle behavior (e.g., in sparse traffic conditions). However, in other situations, dynamic factors influence how the vehicle is controlled; therefore, the rate of speed change is not constant. For example, if maneuvering occurs in dense traffic, the presence of other vehicles may affect adjustments to speed and spacing.

[0094] Therefore, in one embodiment, longitudinal velocity changes are simulated by weighting different segments of the time window. This can be achieved by dividing the time window into continuous segments and applying weight values ​​to each segment to capture changes in velocity.

[0095] In the following example, the vehicle's velocity is captured within a 3-second time window. Although this example is discussed in conjunction with longitudinal acceleration and longitudinal force, lateral acceleration and lateral force can be estimated similarly.

[0096] The average change in velocity can be simply the difference in capture velocity between the current time window and the immediately preceding time window. Alternatively, segments of the time window can be weighted to reflect changes in velocity.

[0097] Various weighting modes can be selected to capture driver behavior patterns in various contexts and determine the probability of hard braking and acceleration.

[0098] The table below (“Table 1”) illustrates how a weighting scheme, including different weights on each of multiple 3-second measurement windows, is used to summarize the possible g-forces within the observed average. The column “|dv|dt” is the observed longitudinal velocity change for a given measurement window, which is then presented as the velocity change per second in the column “|dv / dt|”. The longitudinal velocity change is then converted into the average g-force in the column “gF”. The last three columns adjust the weights for how much braking or acceleration activity occurred in each time window. In this example, weight values ​​are assigned to 1-second intervals of the time window. “w0” is the weight assigned to the first interval, “w1” is the weight assigned to the next interval, and “w2” is the weight assigned to the last interval. In this example, the weights for w0, w1, and w2 are 0.15, 0.15, and 2.70, respectively, reflecting the application of a lighter pedal touch before a more aggressive change to produce the observed average. Given a weight profile defined by weights w1, w2, and w3, Table 1 shows the possible g-forces experienced during the measurement window.

[0099] Table 1

[0100]

[0101] Table 1 shows that an average velocity change of 4 kph or greater over a 3-second interval results in a g-force greater than 0.3g, and can therefore be considered to correspond to hard acceleration or braking.

[0102] In one embodiment, simulations of longitudinal and / or lateral forces, along with corresponding inertial forces, are performed under different weighting schemes and different average speed variations. Such simulations can be used to estimate the longitudinal and / or lateral forces of the vehicle based on its detected average speed. Furthermore, such simulations can be used to determine the probability of hard cornering, hard braking, and / or hard acceleration occurring within a given time window (e.g., within a given 3-second window or an interval within the time window).

[0103] Figure 7 A bar graph 130 is plotted to summarize the probability of braking or acceleration events exceeding 0.3G under several different weighting schemes. The horizontal axis represents the average velocity change (V) in kilometers per hour per second (kph / s) during a 3-second time window, and each bar has a vertical range indicating the probability (L) that the experienced g-force will be greater than 0.3g. As shown, the probability increases significantly when the average velocity exceeds approximately 4 kph.

[0104] Figures 8A-8C An example of generating a behavioral profile that indicates the total applied force is depicted. Figure 8AAn example of a grid 100 used to generate the profile is shown, comprising a 2D cell array 102 and an origin 104. Each cell 102 is associated with a corresponding bin and is filled with an integer count (or a value associated with the count).

[0105] The longitudinal force chamber is defined based on the velocity change in each window, where each row represents a velocity change of 1 kph / s. Therefore, row "1" represents a longitudinal velocity change ranging from zero to 1 kph / s, and row "-1" represents a longitudinal velocity change (deceleration) ranging from zero to -1 kph / s. Row "2" represents a longitudinal velocity change from 1 kph / s to 2 kph / s, and row "-2" represents a longitudinal velocity change from -1 kph / s to -2 kph / s.

[0106] The lateral force chamber is defined as g-force multiplied by 10. Therefore, column "1" represents a lateral (rightward) g-force ranging from zero to 0.1g, and column "-1" represents a lateral (leftward) g-force ranging from zero to 0.1g. Column "2" represents a lateral g-force ranging from 0.1g to 0.2g, and column "-2" represents a lateral g-force ranging from -0.1g to -2 kph / s.

[0107] The system monitors the intersection for a day and collects data (called "vehicle trajectories") for every vehicle that crosses the intersection, including turning and pedal force (accelerator and brake). It also records conditions associated with the intersection, including time, date, weather conditions, road surface conditions, etc.

[0108] As each vehicle crosses the intersection, lateral and longitudinal forces are measured (or determined based on GPS data), and a set (i.e., one or more) of force pairs are identified. Each force pair includes lateral force values ​​and longitudinal force values.

[0109] In this example, the longitudinal force is estimated based on the vehicle's position and velocity changes (kph / s) over a continuous 3-second window. The lateral force is calculated from the telemetry data, yielding the measured g-force. The measured g-force is then multiplied by 10 to conform to the cell range and align with the velocity change bin in kph / s.

[0110] In this example, an average speed change of 4 kph within a 3-second window was chosen as an indicator of hard braking or acceleration. An average of at least 4 kph per second within 3 seconds reflects a vehicle speed change of 12 kph, which is sufficient to influence the decisions of other drivers in the traffic flow.

[0111] In this example, hard braking corresponds to a speed reduction recorded on all measured vehicles, which is at least 4 kilometers per second. While hard braking maneuvers themselves are not dangerous, a larger set of hard braking maneuvers means a higher risk of collision due to the driver's approach to and reaction time to other vehicles.

[0112] Hard acceleration corresponds to a speed increase recorded on all measured vehicles of at least 4 kilometers per second. While hard braking is typically a reactive maneuver, hard acceleration is often an aggressive driver choice that can increase tension and churn in traffic flow.

[0113] Hard braking or acceleration can be defined as a change in velocity, or in terms of g-force. In this example, hard braking and acceleration are defined as a change in velocity per second that produces a force of 0.3g, which is dv / dt ≥ ~11 kph.

[0114] In the same example, a sharp turn is defined as a turn that results in a g-force greater than 0.39g. Therefore, lateral g-forces between 0 and 0.39g are considered normal and can be eliminated by masking.

[0115] The force boundaries are shown, illustrating the compartments associated with hard acceleration and hard cornering. In this example, lateral forces above 0.4g (in compartment 4 or higher) or below -0.4g (in compartment -4 or lower) are associated with hard cornering. Longitudinal forces above 0.3g (in compartment 4 or higher) or below -0.3g (in compartment -4 or lower) are associated with a higher probability of hard acceleration and braking.

[0116] like Figure 8A As shown, each cell 102 is filled with a count representing the number of force pairs assigned to it. A count summary is generated, including the count for each cell 102, and used to fill the grid 100.

[0117] like Figure 8B As shown, a transition mask is applied to set the selected cells 102 of mesh 100 to zero to remove normal forces. The transition mask sets a set of cells 108 around the origin to zero, thereby excluding cells considered to represent balanced and normal forces. At this point, the pattern of the counted quantities (and / or the associated contour line 106) can be used as a behavioral profile.

[0118] refer to Figure 8C A probability value for each bin is calculated based on the total lateral and longitudinal force values ​​in each bin (and inserted into the associated cell 102) to generate a force summary. The total bin count is calculated by summing all counts in grid 100. Each cell 102 is assigned a probability value equal to the count in cell 102 divided by the total count (551 in this example) and multiplied by 100 to derive a percentage.

[0119] Figure 8BBehavioral profiles and / or 8C profiles can be converted into any other visual display or format that can be used to visualize the patterns revealed by the behavioral profiles. For example, behavioral profiles are used to generate visualizations that convey aspects of a driver's driving patterns.

[0120] Figure 9 An example of a visualization 110 in graphical form is shown. Visualization 110 includes grid lines 112 corresponding to the cells of the behavioral profile. Additionally, the patterns revealed by the behavioral profile are indicated by a set of arrows 114 pointing to the spatial locations of the cells with the highest probabilities. Furthermore, circles 116 are displayed for the cells with the highest probabilities, with the size of each circle 116 corresponding to its probability.

[0121] Figure 10 Examples of behavioral profiles 90, represented as behavioral profiles 90a-90i, are depicted. Each profile represents a pattern of applied forces, corresponding to the number or probability of applied forces with a given magnitude and direction. Each profile represents the sum of forces applied to a single vehicle or multiple vehicles (e.g., a convoy) over a given time period and in a given environment.

[0122] For example, cross-sectional view 90c shows a pattern having regions 92c representing high acceleration (i.e., greater than the balancing force and normal force) in the forward and right lateral directions and regions 94c representing high acceleration (deceleration or braking force) in the backward and left directions. As shown, this pattern is dominated by high rightward acceleration.

[0123] For example, behavioral profiles can be analyzed to identify common driving styles. In one embodiment, machine learning algorithms (e.g., unsupervised learning) are used to identify shared driving profiles.

[0124] Behavioral profiles can be used for a variety of purposes, such as fleet management, vehicle control adjustments, recommendations for driving style changes, and maintenance and repair recommendations. For example, profile 90 can represent the driving style of an individual driver, which can be used to recommend changes in driver style for purposes such as improving mileage or range and providing customized maintenance plans.

[0125] Behavioral profile analysis can be performed, for example through supervised learning, to predict and forecast vehicle wear based on driving behavior and / or vehicle environment. Machine learning systems can be used to correlate behavioral profiles with specific maintenance needs. For example, if a vehicle's behavioral profile indicates a trend of aggressive braking, a maintenance schedule recommending brake checks after a shorter period than typical for vehicle type and age can be determined.

[0126] In another example, supervised learning or other suitable algorithms or processes can be used to analyze behavioral profiles to identify collision or accident risks. Behavioral profiles can be associated with the risk of certain types of accidents, such as rear-end or front-end collisions.

[0127] Figure 11 The intersection 121 is depicted schematically, and Figure 12 A behavioral profile diagram associated with intersection 121 is depicted. In this example, the behavior is initially characterized by line n. F NB This is a cross-sectional view showing the behavior of a northbound vehicle traveling in the forward direction. A right turn is achieved via curve n. R NB This indicates that a left turn is achieved via curve n. L NB express.

[0128] The behavior profile diagram 120 generated for intersection 121 is in Figure 12 The behavior profile is shown in grid 122. Location and heading information is collected for vehicles traveling at intersection 121 over a period of time, and behavior profile 120 represents the total behavior of the vehicles. Grid 122 is defined by four quadrants as discussed herein. Behavior profile 120 is a heatmap showing instances of normal and hard right turns (bubble 124), normal and hard left turns (bubble 126), and normal and hard forward acceleration and braking (bubble 128).

[0129] Figure 13 Various aspects of an embodiment of a computer system 140 capable of performing various aspects of the embodiments described herein are illustrated. The computer system 140 includes at least one processing device 142, which typically includes one or more processors for performing various aspects of the image acquisition and analysis methods described herein.

[0130] The components of computer system 140 include processing device 142 (such as one or more processors or processing units), memory 144, and bus 146, which connects various system components, including system memory 144, to processing device 142. System memory 144 may be a non-transitory computer-readable medium and may include various computer system-readable media. Such media may be any available media accessible by processing device 142, and includes volatile and non-volatile media as well as removable and non-removable media.

[0131] For example, system memory 144 includes non-volatile memory 148 such as a hard disk drive, and may also include volatile memory 150 such as random access memory (RAM) and / or cache memory. Computer system 140 may also include other removable / non-removable, volatile / non-volatile computer system storage media.

[0132] System memory 144 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments described herein. For example, system memory 144 stores various program modules that generally perform the functions and / or methods of the embodiments described herein. One or more modules 152 may be included to perform the functions discussed herein. System 140 is not limited thereto, as other modules may be included. As used herein, the term "module" refers to processing circuitry, which may include application-specific integrated circuits (ASICs), electronic circuitry, processors (shared, dedicated, or grouped) and memories executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components that provide the described functions.

[0133] The processing device 142 can also communicate with one or more external devices 156, which may be a keyboard, indicating device, and / or any device that enables the processing device 142 to communicate with one or more other computing devices (e.g., a network interface card, a modem, etc.). Communication with various devices may occur via input / output (I / O) interfaces 164 and 165.

[0134] Processing device 142 can also communicate via network adapter 168 with one or more networks 166, such as a local area network (LAN), a general wide area network (WAN), a bus network, and / or a public network (e.g., the Internet). It should be understood that, although not shown, other hardware and / or software components may be used in conjunction with computer system 140. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, and data archiving storage systems.

[0135] The terms “a” and “an” do not indicate a limitation of quantity, but rather that at least one of the referenced items is present. Unless the context clearly indicates otherwise, the term “or” means “and / or”. Throughout the specification, reference to “aspect” means that a particular element described in connection with that aspect (e.g., a feature, structure, step, or characteristic) is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in the aspects.

[0136] When an element, such as a layer, film, region, or substrate, is referred to as being “on” another element, it can be directly on the other element, or there may be intermediate elements present. Conversely, when an element is referred to as being “directly” on another element, there are no intermediate elements present.

[0137] Unless otherwise stated herein, all test standards are the most recent standards in effect as of the date of filing of this application, or, if priority is claimed, the date of filing of the earliest priority application in which a test standard appears.

[0138] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0139] While the foregoing disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from its scope. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this disclosure without departing from the basic scope of this disclosure. Therefore, it is intended that this disclosure be limited to the specific embodiments disclosed, but will include all embodiments falling within its scope.

Claims

1. A system for evaluating a vehicle, comprising: A monitoring module is configured to acquire information relating to the combined forces applied to the vehicle at each of a plurality of consecutive sampling times during a selected time window, the combined forces applied to the vehicle being based on driver control of the vehicle and including longitudinal and lateral forces. as well as An analysis module is configured to receive acquired information and determine multiple force pairs based on the acquired information, each of the multiple force pairs including a longitudinal force value and a lateral force value. The analysis module is configured to: Each force pair is assigned to one of a plurality of compartments, and each compartment is associated with a corresponding longitudinal force range and a corresponding lateral force range; as well as A two-dimensional behavioral profile is constructed that spatially represents combined forces and presents behavioral patterns during a selected time window. The two-dimensional behavioral profile includes a two-dimensional data element array, where each data element corresponds to a corresponding bin. The two-dimensional behavioral profile is constructed by filling each data element based on one or more force pairs assigned to the corresponding bin.

2. The system of claim 1, further comprising a control module configured to perform at least one of the following: Aspects of vehicle operation control based on two-dimensional behavioral profile diagrams; Suggestions are presented to the driver of the vehicle based on a two-dimensional behavioral profile. Determining driver style based on acceleration from two-dimensional behavioral profiles; and The condition of a vehicle is assessed based on a two-dimensional behavioral profile.

3. The system of claim 1, wherein the monitoring module is configured to collect vehicle position, vehicle heading, longitudinal acceleration and lateral acceleration for each sampling time window, and at least one of the longitudinal acceleration and lateral acceleration is determined based on the vehicle position, vehicle speed and trajectory.

4. The system of claim 1, wherein the two-dimensional data element array is a two-dimensional grid having a first axis representing longitudinal force values ​​and a second axis representing transverse force values, and the two-dimensional grid comprises a plurality of cells and is divided into a set of quadrants.

5. The system of claim 4, wherein a set of quadrants includes an upper left quadrant representing forward acceleration and leftward acceleration, an upper right quadrant representing forward acceleration and rightward acceleration, a lower left quadrant representing longitudinal deceleration and leftward acceleration, and a lower right quadrant representing longitudinal deceleration and rightward acceleration.

6. The system of claim 1, wherein the data elements are populated with values ​​based on a warehouse count of associated warehouses, the warehouse count representing the number of force pairs allocated to the associated warehouses.

7. The system of claim 6, wherein the data element is filled with a probability value based on the warehouse count of the associated warehouse and the total warehouse count, the total warehouse count being the sum of the warehouse counts in the two-dimensional array of the data element.

8. A method for evaluating a vehicle, comprising: Information is acquired relating to the combined forces applied to the vehicle at each of multiple consecutive sampling times during a selected time window. The combined forces applied to the vehicle are based on the driver's control of the vehicle and include longitudinal and lateral forces. Based on the information obtained, multiple force pairs are determined, each of which includes a longitudinal force value and a transverse force value; Each force pair is assigned to one of a plurality of compartments, and each compartment is associated with a corresponding longitudinal force range and a lateral force range; as well as A two-dimensional behavioral profile is constructed, which spatially represents the combined forces and presents the pattern of driver behavior during a selected time window. The two-dimensional behavioral profile consists of a two-dimensional data element array, where each data element corresponds to a corresponding compartment. The two-dimensional behavioral profile is constructed by filling each data element based on one or more force pairs assigned to the corresponding compartment.

9. The method of claim 8, wherein each bin is a feature vector, and assigning force pairs includes determining a combined force vector based on longitudinal and lateral force values, and assigning the combined force vector to the respective bin.

10. The method of claim 8, wherein data elements are populated with values ​​corresponding to warehouse counts of associated warehouses, the warehouse counts representing the number of force pairs assigned to the associated warehouses, and constructing the two-dimensional behavioral profile includes excluding cells in the central region of the grid to generate the final behavioral profile.

Images