Information processing device and driving evaluation system

Abstract

To improve validity of driving evaluation.SOLUTION: An information processing device performs: acquiring first data related to a driving operation executed in a first vehicle and second data related to the surrounding situations of the first vehicle; and executing driving evaluation with respect to the first vehicle based on the first and second data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a technique for evaluating a driver's driving. [Background technology]

[0002] Systems for evaluating the driving behavior of drivers are known. For example, Patent Literature 1 discloses a system that collects data related to driving operations at predetermined intervals and diagnoses the degree of dangerous driving based on the collected data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-177583 A Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure aims to improve the validity of driving evaluation. [Means for solving the problem]

[0005] An information processing device according to a first aspect of the present disclosure has a control unit that acquires first data regarding driving operations performed in a first vehicle, acquires second data regarding the surrounding conditions of the first vehicle, and performs a driving evaluation of the first vehicle based on the first and second data.

[0006] In addition, a driving evaluation system according to a second aspect of the present disclosure is a driving evaluation system including a first vehicle and an information processing device, wherein the first vehicle has a first control unit that acquires first data regarding driving operations performed in the first vehicle and second data regarding the surrounding conditions of the first vehicle, and the information processing device has a second control unit that performs a driving evaluation of the first vehicle based on the first and second data.

[0007] Another aspect of the present disclosure is a program for causing a computer to execute the method executed by the information processing device described above, or a computer-readable storage medium non-transiently storing the program. Effect of the Invention

[0008] According to the present disclosure, the validity of driving evaluation can be improved. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an outline of a driving evaluation system. [Diagram 2] FIG. 2 is a diagram for explaining the configuration of a center server and an in-vehicle terminal. [Diagram 3] 4 shows an example of vehicle data stored in a storage unit. [Figure 4] 4 shows an example of behavior data stored in a storage unit. [Diagram 5] 4 shows an example of an evaluation model stored in a storage unit. [Figure 6] 5A to 5C are diagrams for explaining data transmitted and received between modules in the first embodiment. [Figure 7] FIG. 4 is a diagram for explaining the generation timing of data to be processed. [Figure 8] FIG. 4 is a diagram for explaining a process executed by a determination unit. [Figure 9] 5 is a flowchart of a process performed by a control unit in the first embodiment. [Figure 10] 5 is a flowchart of a process performed by a control unit in the first embodiment. [Figure 11]13A and 13B are diagrams for explaining data transmitted and received between modules in the second embodiment. [Figure 12] 10 is a flowchart of a process performed by a control unit in a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] There is a system that evaluates a driver's driving based on the driving operations performed by the driver. In such a system, the driver is evaluated according to, for example, the smoothness of the driving operations. On the other hand, there are cases where drivers perform operations to avoid danger that are not their fault. For example, sudden braking due to a pedestrian or bicycle suddenly jumping out, or a sudden cut-in from an adjacent lane. However, with conventional driving evaluation systems, even in such cases, the driver may be evaluated as having performed inappropriate driving operations.

[0011] In order to address this problem, an information processing device according to one embodiment of the present disclosure has a control unit that acquires first data regarding driving operations performed in a first vehicle, acquires second data regarding the surrounding conditions of the first vehicle, and performs a driving evaluation of the first vehicle based on the first and second data.

[0012] The first data is data related to a driving operation performed by a driver. The first data may be data directly representing the driving operation, or may be data indirectly representing the driving operation. For example, the driving operation can be indirectly obtained by sensing the behavior of the first vehicle. Examples of the first data include the amount of steering operation, the amount of accelerator or brake operation, the acceleration / deceleration of the vehicle, and the yaw rate. The first data can be acquired from the first vehicle or a computer mounted on the first vehicle.

[0013] The second data is data related to the surrounding conditions of the first vehicle. Examples of the second data include sensor data obtained by sensing the surroundings of the first vehicle and image data obtained by capturing an image of the surroundings of the first vehicle. The surrounding conditions may be traffic conditions around the first vehicle. The traffic conditions are, for example, the positions and movements of other vehicles, bicycles, pedestrians, etc. In addition, the surrounding conditions may be the conditions of obstacles around the first vehicle, the driving environment, etc.

[0014] By performing a driving evaluation taking into account the second data in addition to the first data, it is possible to determine, for example, whether an operation performed by the driver was appropriate (e.g., whether it was unavoidable), thereby improving the accuracy of the driving evaluation.

[0015] The second data may be data relating to the behavior of traffic around the first vehicle. With this configuration, it is possible to determine, for example, that the path of the first vehicle has been obstructed and that a driving operation has been performed to avoid this.

[0016] The control unit may also be characterized in that it performs the driving evaluation based at least on the first data generated in a first period and the second data generated in a second period that is a period prior to the first period. For example, by retroactively referring to second data generated in a period immediately prior to the driving operation indicated by the first data, it is possible to determine whether the driving operation was appropriate.

[0017] The control unit may also be characterized in that it determines whether or not the driving operation indicated by the first data occurred due to the surrounding conditions of the first vehicle indicated by the second data. For example, the second data indicates that a particular event is interfering with the path of the first vehicle. If so, it can be determined that the driving operation immediately following the event was caused by the event.

[0018] The vehicle may further include a storage unit that stores data relating to the surrounding conditions that affect the driving operation of the first vehicle. The control unit may make the determination using the stored data. For example, surrounding conditions that affect the driving operation of the first vehicle, such as a pedestrian suddenly running out or a vehicle cutting in front, are defined in advance, and the presence or absence of a causal relationship can be determined by determining the extent to which the surrounding conditions that have occurred match.

[0019] The control unit may also be characterized in that, when a causal relationship is recognized between the surrounding circumstances and a driving operation performed in the first vehicle, the control unit corrects an evaluation of the driving operation. If there is a causal relationship between the surrounding circumstances and the driving operation, it can be determined that the driving operation occurred due to an unavoidable force, and the evaluation of the driving operation may be corrected, for example, in a positive direction. This makes it possible to compensate for deductions caused by abrupt operations, etc.

[0020] The control unit may also perform the driving evaluation using an evaluation model that uses the first and second data as input data and the driving evaluation as output data, and when a causal relationship is recognized between the surrounding circumstances and a driving operation performed in the first vehicle, update the evaluation model so as to improve the driving evaluation output for the input data. The driving evaluation can be performed using an evaluation model (e.g., a machine learning model). In this case, when a surrounding situation occurs that has a causal relationship with the driving operation, it is preferable to update (re-learn) the evaluation model so that the driving evaluation is not lowered under such a situation.

[0021] The first data may include motion data acquired by a sensor mounted on the first vehicle. The motion data is, for example, data related to the motion of the first vehicle. Examples of the motion of the vehicle include acceleration, turning rate, acceleration, deceleration, and the like.

[0022] The second data may be image data acquired by a camera mounted on the first vehicle. The control unit may determine a surrounding situation of the first vehicle based on a result of analyzing the image data. By using images captured by the onboard camera, the surrounding situation of the first vehicle can be determined.

[0023] Specific embodiments of the present disclosure will be described below with reference to the drawings. Unless otherwise specified, the hardware configuration, module configuration, functional configuration, and the like described in each embodiment are not intended to limit the technical scope of the disclosure to only those.

[0024] First Embodiment An overview of a driving evaluation system according to a first embodiment will be described with reference to Fig. 1. The driving evaluation system according to this embodiment includes a center server 100 that performs driving evaluation of a driver, and an in-vehicle terminal 200 mounted on a vehicle 10. Although one vehicle 10 is shown in FIG. 1, the center server 100 may manage a plurality of vehicles 10.

[0025] The vehicle-mounted terminal 200 is a computer mounted in each of the multiple vehicles 10 under its management. The in-vehicle terminal 200 acquires vehicle data and periodically transmits it to the center server 100. The vehicle data includes two types of data: "data related to the driving operation performed by the driver (first data)" and "data related to the surrounding conditions of the vehicle 10 (second data)."

[0026] The center server 100 is a device that acquires vehicle data from multiple vehicles 10 (vehicle-mounted terminals 200) under the management of the system, and evaluates the driving operations performed by the driver based on the vehicle data (for example, evaluates how smoothly the driver performed the driving operations). The center server 100 judges the situation of the vehicle 10 based on the second data indicating the surrounding situation of the vehicle 10, and then evaluates the first data. This makes it possible to properly evaluate even a sudden operation due to an unavoidable event.

[0027] In this embodiment, the first data is sensor data that represents a driving operation performed in the vehicle 10. The first data can be acquired by a sensor that the vehicle 10 has. In this embodiment, the second data is image data for analyzing the behavior of surrounding traffic of the vehicle 10. The surrounding traffic is, for example, other vehicles, bicycles, pedestrians, and other moving objects located in the vicinity of the vehicle 10. The image data can be acquired, for example, by a camera mounted on the front of the vehicle 10.

[0028] FIG. 2 is a diagram showing the components of the driving evaluation system according to this embodiment in more detail.

[0029] The on-board terminal 200 is a computer mounted on a vehicle and includes a control unit 201, a storage unit 202, a communication unit 203, an input / output unit 204, a motion sensor 205, and a camera 206.

[0030] The control unit 201 is a calculation device that controls the on-board terminal 200. The control unit 201 can be realized by a calculation processing device such as a CPU (Central Processing Unit). . The control unit 201 is configured to have two functional modules: a vehicle data acquisition unit 2011 and a vehicle data transmission unit 2012. These functional modules may be realized by causing a CPU to execute a program stored in a storage unit 202, which will be described later.

[0031] The vehicle data acquisition unit 2011 acquires vehicle data. In this embodiment, the vehicle data includes the following two types of data. (1) Data related to the driving operations performed by the driver (sensor data) (2) Image data acquired by the onboard camera The sensor data corresponds to the first data and the image data corresponds to the second data.

[0032] The data related to driving operation is data (motion data) that represents the behavior of the vehicle, and is typically data indicating acceleration acquired by a motion sensor 205 described later. In this example, acceleration measured by a sensor is exemplified as the sensor data, but the sensor data may include other information related to driving operation. For example, the sensor data may include speed and yaw rate. Furthermore, the sensor data is not limited to data obtained by sensing the vehicle movement itself. For example, the sensor data may be data that represents the driving operation itself acquired from a steering sensor, a throttle sensor, or the like.

[0033] The vehicle data acquisition unit 2011 acquires sensor data at a predetermined sampling rate (for example, 10 Hz). Note that the sensor data may be acquired at a sampling rate higher than a target sampling rate and then smoothed by a filter. For example, the sensor data may be sampled at 100 Hz and then downsampled to 10 Hz by a Gaussian filter or the like. You may also use it.

[0034] The image data is acquired by a camera 206, which will be described later. Note that "image data" described in this specification may be data for one frame or data for multiple frames. The vehicle data acquisition unit 2011 may also acquire data other than the sensor data and image data and include it in the vehicle data. Such data includes, for example, the position information, speed, and traveling direction of the vehicle 10.

[0035] The vehicle data transmission unit 2012 transmits the vehicle data acquired by the vehicle data acquisition unit 2011 to the center server 100 periodically (for example, at one second intervals). When the transmission interval of the vehicle data is one second, the vehicle data may include, for example, one second of sensor data and one second of image data. The image data may be a collection of multiple images. For example, when the transmission interval of the vehicle data is one second and the vehicle data acquisition unit 2011 can acquire images at 30 frames per second, the vehicle data transmitted at one time may include image data consisting of 30 images. Furthermore, when the vehicle data acquisition unit 2011 can acquire sensor data at 10 Hz, one piece of vehicle data may include sensor data for 10 time steps.

[0036] The storage unit 202 includes a main storage device and an auxiliary storage device. The main storage device is a memory in which the programs executed by the control unit 201 and data used by the control programs are expanded. The auxiliary storage device is a device in which the programs executed by the control unit 201 and data used by the control programs are stored. The auxiliary storage device may store the programs executed by the control unit 201 packaged as applications. It may also store an operating system for executing these applications. The programs stored in the auxiliary storage device are loaded into the main storage device and executed by the control unit 201, thereby performing the processes described below.

[0037] The primary storage device may include a random access memory (RAM) or a read only memory (ROM). The secondary storage device may include an erasable programmable read only memory (EPROM) or a hard disk drive (HDD). It may also include a disk drive (HDD, Hard Disk Drive). may include removable media, i.e., portable recording media.

[0038] The communication unit 203 is a wireless communication interface for connecting the on-board terminal 200 to a network. The communication unit 203 is configured to be able to communicate with the center server 100 via, for example, a wireless LAN or a mobile communication service such as 3G, LTE, or 5G. The input / output unit 204 is a unit that accepts input operations performed by a user and presents information to the user. In this embodiment, it is made up of a single touch panel display. That is, it is made up of a liquid crystal display and its control means, and a touch panel and its control means.

[0039] The motion sensor 205 is a sensor that measures the acceleration applied to the vehicle 10. The motion sensor 205 may be, for example, a three-axis acceleration sensor that can measure the acceleration applied to the front-rear, left-right, and up-down directions of the vehicle. In this case, the sensor data may be a three-dimensional vector. The camera 206 is a camera that captures images of the surroundings of the vehicle 10. The camera 206 is preferably mounted at a position where it can capture at least the area in front of the vehicle 10.

[0040] Next, the center server 100 will be described. The center server 100 executes a process of receiving vehicle data from the vehicle-mounted terminal 200 and a process of evaluating the driving operation performed by the driver of the vehicle 10 based on the received vehicle data. .

[0041] The center server 100 can be configured by a general-purpose computer. That is, the center server 100 can be configured as a computer having a processor such as a CPU or GPU, a main storage device such as a RAM or ROM, and an auxiliary storage device such as an EPROM, a hard disk drive, or a removable medium. The auxiliary storage device stores an operating system (OS), various programs, various tables, etc., and the programs stored therein are loaded into the working area of ​​the main storage device and executed. Each component is controlled through the execution of the programs, thereby realizing each function that matches a predetermined purpose, as described below. However, some or all of the functions may be realized by a hardware circuit such as an ASIC or an FPGA.

[0042] The control unit 101 is a calculation device that manages the control performed by the center server 100. The control unit 101 can be realized by a calculation processing device such as a CPU. The control unit 101 is configured to have three functional modules: a data acquisition unit 1011, an evaluation unit 1012, and a determination unit 1013. Each functional module may be realized by executing a stored program by a CPU.

[0043] The data acquisition unit 1011 acquires vehicle data from the on-board terminal 200 mounted in a vehicle under the control of the system, and executes a process of storing the acquired vehicle data in the storage unit 102, which will be described later.

[0044] The evaluation unit 1012 evaluates the driving operation performed by the driver of the vehicle 10 based on the stored vehicle data, and generates data (evaluation data) that represents the evaluation result. The evaluation unit 1012, for example, evaluates the sensor data using a predetermined evaluation model and obtains a numerical value that evaluates the smoothness of the driving operation. The evaluation unit 1012 also requests the determination unit 1013, which will be described later, to determine whether or not the driving operation indicated by the sensor data is caused by the behavior of surrounding traffic. The evaluation unit 1012 also generates final evaluation data by taking into account the result of the determination made by the determination unit 1013. For example, if it is determined that a specific driving operation is caused by the behavior of surrounding traffic, such as when a pedestrian jumps out immediately before sudden braking, the system will not deduct points for the sudden braking operation. The specific method will be described later.

[0045] The determination unit 1013 determines whether there is a causal relationship between a driving operation and the behavior of surrounding traffic based on a request from the evaluation unit 1012. Specifically, the determination unit 1013 refers to image data acquired immediately before the driving operation to be evaluated occurs, and determines whether the behavior of surrounding traffic obtained by analyzing the image data matches a predetermined behavior pattern. The predetermined behavior pattern is a pattern of the behavior of surrounding traffic (e.g., a sudden stop of a preceding vehicle, a pedestrian running out, etc.) that is likely to be linked to a specific driving operation (e.g., sudden braking). If the behavior of the surrounding traffic matches the predetermined behavior pattern, it can be determined that there is a causal relationship between the driving operation and the behavior of the surrounding traffic.

[0046] The storage unit 102 includes a main storage device and an auxiliary storage device. The main storage device is a memory in which the programs executed by the control unit 101 and data used by the control programs are expanded. The auxiliary storage device is a device in which the programs executed by the control unit 101 and data used by the control programs are stored.

[0047] Furthermore, the storage unit 102 stores a vehicle database 102A, a behavior database 102B, and an evaluation model 102C.

[0048] The vehicle database 102A is a database that stores vehicle data acquired from the in-vehicle terminal 200. In the vehicle database 102A, a plurality of vehicle data acquired from a plurality of in-vehicle terminals 200 are stored.

[0049] FIG. 3 is a diagram showing an example of data stored in vehicle database 102A. The vehicle ID field stores an identifier that uniquely identifies the vehicle. The date and time information field stores the date and time when the vehicle data was generated. The position information field stores the position information of the vehicle. The position information may be expressed by, for example, latitude and longitude. The direction information field stores information indicating the traveling direction of the vehicle.

[0050] The sensor data field stores sensor data acquired by the motion sensor 205 of the vehicle 10. The image data field stores image data acquired by the camera 206 of the vehicle 10. The image data may be video image data consisting of multiple frames. The vehicle database 102A is periodically updated based on the vehicle data transmitted from the vehicle-mounted terminal 200.

[0051] The behavior database 102B is a database that stores behavior patterns of surrounding traffic (e.g., pedestrians rushing out) that are likely to be linked to a specific driving operation (e.g., sudden braking). The behavior patterns stored in the behavior database 102B correspond to external situations that are assumed to be unpredictable by the driver.

[0052] FIG. 4 is a diagram showing an example of data stored in the behavior database 102B. The pattern ID field stores data that uniquely identifies a behavior pattern. The feature data field stores data obtained by converting the behavior of surrounding traffic into features. If the feature data obtained by converting the image data captured by the vehicle-mounted camera show a high similarity to these data, it means that there is a high possibility that a specific driving operation was performed due to the behavior of the surrounding traffic. In other words, it is estimated that there is a causal relationship between the driving operation performed by the driver and the behavior of the surrounding traffic.

[0053] The vehicle database 102A and the behavior database 102B are constructed by a database management system (DBMS) program executed by a processor that manages data stored in a storage device. The vehicle database 102A and the behavior database 102B are, for example, relational databases.

[0054] The evaluation model 102C is a machine learning model for evaluating the driving operation performed by the driver. FIG. 5(A) is a diagram for explaining input data and output data to the evaluation model 102C. As shown in the figure, the evaluation model 102C acquires sensor data as input data and generates driving evaluation as output data. The driving evaluation is expressed by, for example, a score. The evaluation model 102C is a model that is trained to output a higher score as the driving operation is smoother, for example.

[0055] In this example, only the sensor data is illustrated as an input to the evaluation model 102C, but other information may be provided as input data. For example, by providing information about the road on which the vehicle 10 is traveling (such as the number of lanes, speed limit, curvature, and the presence or absence of crosswalks and traffic lights), it is possible to more accurately determine whether the driving operation performed by the driver is appropriate. For this reason, the center server 100 may store map data including detailed information about roads on which the vehicle 10 can travel.

[0056] The communication unit 103 is a communication interface for connecting the center server 100 to a network. The communication unit 103 includes, for example, a network interface board and a wireless communication module for wireless communication.

[0057] 2 is an example, and all or part of the functions shown in the figure may be executed using a dedicated circuit. Also, the programs may be stored or executed using a combination of a main memory device and an auxiliary memory device other than those shown in the figure.

[0058] FIG. 6 is a diagram for explaining the operation of each module included in the control unit 101. As shown in FIG. The data acquisition unit 1011 periodically receives vehicle data from the vehicle 10 (the in-vehicle terminal 200) under its management. The received vehicle data is stored in the vehicle database 102A as needed.

[0059] The evaluation unit 1012 acquires sensor data corresponding to the period to be evaluated from the data stored in the vehicle database 102A, and performs driving evaluation. Since the recorded sensor data is an instantaneous value, it is not possible to determine what driving operation was performed from a single piece of sensor data. Therefore, the evaluation unit 1012 performs driving evaluation based on a set of sensor data for a predetermined period (for example, one second).

[0060] 7 is a diagram showing the relationship between the timing of performing driving evaluation and a predetermined period. In this example, the evaluation unit 1012 inputs time-series sensor data obtained going back a predetermined number of steps (e.g., five steps) from the evaluation timing to the evaluation model 102C, and acquires values ​​output from the evaluation model 102C. In the illustrated example, time-series sensor data corresponding to the period indicated by reference numeral 701 is input to the evaluation model 102C.

[0061] On the other hand, the evaluation unit 1012 requests the judgment unit 1013 to judge whether the result of the evaluation obtained by the evaluation model 102C is valid. For example, if a pedestrian jumps out at t=3, the vehicle brakes suddenly at t=5, and then a driving evaluation is performed, by checking the image data going back in time, it can be determined that the driving operation was due to an act of God. In this way, the evaluation unit 1012 requests the determination unit 1013 to check image data going back in time at the timing of performing driving evaluation. In the example shown in Fig. 7, the determination unit 1013 refers to image data corresponding to the period indicated by the reference numeral 702 and performs a determination.

[0062] In response to the determination request, the determination unit 1013 refers to image data acquired in the past and determines whether the behavior of the surrounding traffic obtained by the analysis matches a predetermined behavior pattern stored in the behavior database 102B. The determination may be performed based on the similarity. If the behavior of the surrounding traffic matches a predetermined behavior pattern stored in the behavior database 102B, the determination unit 1013 returns a determination result to the evaluation unit 1012 indicating that "a behavior of the surrounding traffic that is presumed to have a causal relationship with the driving operation performed immediately before has been detected."

[0063] FIG. 8 is a diagram illustrating the determination process executed by the determination unit 1013. As shown in FIG. The determination unit 1013 identifies a period corresponding to the request from the evaluation unit 1012, acquires image data during the period, and converts the image data into a feature quantity. The period can be determined in advance, but it is preferable to set the start point to a time (t=1 in the example of FIG. 7) earlier than the start point of the sensor data to be evaluated (t=4 in the example of FIG. 7). In addition, the determination unit 1013 acquires the feature quantity corresponding to each behavior pattern from the behavior database 102B and compares the feature quantities with each other. Based on the result, it is possible to determine whether the behavior of the surrounding traffic corresponds to any of the predefined behavior patterns. If the features are compared and it is determined that they match, it can be determined that there is a causal relationship between the driving operations performed by the driver and the behavior of the surrounding traffic observed immediately before.

[0064] The evaluation unit 1012 generates evaluation data by taking into account the contents of the judgment made by the judgment unit 1013 to the driving evaluation generated by the evaluation model 102C. For example, if sudden braking occurs on a road without traffic lights or crosswalks, evaluation data indicating a low evaluation is generated according to the general rule. On the other hand, if the judgment unit 1013 judges that the sudden braking is caused by the behavior of surrounding traffic (for example, a pedestrian running out), a low evaluation should not be given. In such a case, the evaluation unit 1012 modifies the evaluation criteria or corrects the evaluation result to improve the evaluation of the driving operation.

[0065] The amount of correction of the driving evaluation may be determined based on the type of behavior pattern. For example, the amount of brake operation may differ between when another vehicle cuts in and when a pedestrian rushes out. Therefore, for example, when the behavior pattern is "pedestrian rushes out", the amount of correction may be larger than when the behavior pattern is "when another vehicle cuts in". The amount of correction may be stored in the behavior database 102B in association with the behavior pattern.

[0066] Even if there is a causal relationship between the driving operation performed by the driver and the behavior of the surrounding traffic, there are cases in which the driving evaluation should not be corrected depending on the conditions. For example, when a pedestrian crosses the road at a crosswalk, when the vehicle 10 faces a red light, or when the vehicle 10 encounters another vehicle traveling on a priority road. In this way, when the driver of the vehicle 10 is negligent, the driving evaluation should not be corrected. For this reason, the evaluation unit 1012 may further acquire other data (related to things other than the behavior of surrounding traffic) related to the surrounding conditions of the vehicle 10, and further determine whether or not the driver is at fault based on the data. Examples of other data related to the surrounding conditions of the vehicle 10 include map data describing the locations of traffic lights, crosswalks, designated places for stopping, priority relationships between roads, and the like. If, as a result of referring to such data, it is determined that the vehicle 10 is at fault, the evaluation unit 1012 may not correct the driving evaluation regardless of the behavior of the surrounding traffic.

[0067] Next, a description will be given of a flowchart of the processing executed by each module of the control unit 101. The flowchart shown in Fig. 9 is periodically executed for each of the multiple vehicles 10 while the system is in operation.

[0068] In step S11, the data acquisition unit 1011 receives the vehicle data transmitted from the in-vehicle terminal 200. The received vehicle data is stored in the vehicle database 102A.

[0069] Next, in step S12, the evaluation unit 1012 generates evaluation data based on the acquired sensor data. For example, as shown in Fig. 7, time-series sensor data acquired going back a predetermined period from the evaluation timing is provided as input data to the evaluation model 102C, and the output driving evaluation is acquired.

[0070] In step S13, it is determined whether the generated driving evaluation satisfies a predetermined deduction criterion. For example, if a driving evaluation having a score lower than a predetermined threshold is generated in step S12, a positive determination is made in this step. If the determination in step S13 is affirmative, the process proceeds to step S14, where the determination unit 1013 determines the behavior of the surrounding traffic. That is, it determines whether the driving operation that caused the points deduction is due to the behavior of the surrounding traffic.

[0071] FIG. 10 is a flowchart of the process performed by the determination unit 1013 in step S14. First, in step S141, a reference period of image data for making a judgment is determined. It is preferable that the data reference period start from a time earlier than the start point of the time-series sensor data to be evaluated. For example, as shown in Fig. 7, when a driving evaluation is performed at a timing of t=10, a period (reference numeral 702) going back a predetermined period from the timing is identified. In this example, a period corresponding to t=1 to 9 is identified.

[0072] Next, in step S142, it is determined whether image data corresponding to the determined period is stored in the vehicle database 102A. If the determination is negative, the process ends. If the determination is positive, the process proceeds to step S143. In step S143, image data corresponding to the determined period is acquired, and the image data is converted into feature quantities. In step S144, as shown in FIG. 8, the feature amount obtained by the conversion is compared with the feature amount corresponding to each of a plurality of behavior patterns stored in the behavior database 102B, and the similarity between each of them is calculated.

[0073] In step S145, it is determined whether or not there is a behavior pattern whose similarity exceeds a predetermined value. If the determination is positive, the determination unit 1013 generates a determination result indicating that "behavior of surrounding traffic that is presumed to have a causal relationship with driving operation has been detected." If the determinations are negative in steps S142 and S145, the determination unit 1013 generates a determination result indicating that "behavior of surrounding traffic that is presumed to have a causal relationship with driving operation has not been detected."

[0074] Returning to FIG. 9, the explanation will be continued. If a causal relationship is found between the driving operation and the behavior of the surrounding traffic as a result of the determination made in step S14 (step S15-Yes), the process proceeds to step S16, where the driving evaluation generated in step S12 is corrected. For example, if the driving evaluation indicates a low score, the amount of deduction is reduced or the deduction is withdrawn. If a causal relationship is not found between the driving operation and the behavior of the surrounding traffic (step S15-No), the process ends. As described above, the correction amount of the driving evaluation may differ for each behavior pattern. In addition, the evaluation unit 1012 may refer to other data related to the driving environment of the vehicle 10 to determine the negligence of the driver of the vehicle 10, and may not correct the driving evaluation if it is determined that there is negligence.

[0075] In step S17, the evaluation unit 1012 generates evaluation data based on the driving evaluation acquired in step S12 or corrected in step S16. The evaluation data may be stored in the storage unit 102, or may be transmitted to an external device (for example, a device managed by an operation manager of the vehicle 10).

[0076] As described above, in the driving evaluation system according to the first embodiment, when a driving operation is evaluated poorly, image data captured by an on-board camera immediately before the driving operation is performed is acquired, and a causal relationship between the behavior of surrounding traffic and the driving operation is estimated. Furthermore, when a causal relationship is recognized, the driving evaluation is revised. This makes it possible to perform a reasonable driving evaluation even when an abrupt operation occurs due to an unavoidable force.

[0077] Second Embodiment In the first embodiment, the evaluation unit 1012 generates the driving evaluation based only on the sensor data. In contrast, in the second embodiment, the evaluation unit 1012 generates the driving evaluation based on both the sensor data and the image data.

[0078] FIG. 11 illustrates the operation of each module included in the control unit 101 in the second embodiment. Portions similar to those in the first embodiment are indicated by dotted lines, and descriptions thereof will be omitted. In the second embodiment, the evaluation unit 1012 acquires both the sensor data and the image data, and inputs these data to the evaluation model 102C to acquire the driving evaluation. Fig. 5(B) is a diagram for explaining the input and output of the evaluation model 102C in the second embodiment.

[0079] In the second embodiment, the evaluation unit 1012, like the first embodiment, acquires time-series sensor data obtained going back a predetermined number of steps from the evaluation timing, and inputs it to the evaluation model 102C. Furthermore, the evaluation unit 1012 acquires time-series image data obtained going back a longer time than the sensor data, and inputs it to the evaluation model 102C. These periods may be the same as the periods described with reference to FIG. 7. This makes it possible to generate a driving evaluation based on both the sensor data corresponding to the driving operation and the image data capturing the behavior of surrounding traffic that affects the driving operation.

[0080] Furthermore, in the second embodiment, when the evaluation unit 1012 corrects the driving evaluation, the evaluation model 102C is re-learned based on the contents of the correction. That is, when a predetermined behavior pattern is detected from surrounding traffic and the driving evaluation is corrected, the algorithm of the evaluation model 102C is reconstructed so that the evaluation will not be lowered when a similar scene occurs in the future. This makes it possible to obtain an evaluation model that can give a more appropriate driving evaluation.

[0081] 12 is a flowchart of the processes executed by each module of the control unit 101 in the second embodiment. Processes similar to those in the first embodiment are indicated by dotted lines, and a description thereof will be omitted. In the second embodiment, after correcting the driving evaluation in step S16, the evaluation unit 1012 executes the process of step S16B. Step S16B is a step in which the evaluation unit 1012 updates the evaluation model 102C. Specifically, the evaluation unit 1012 re-learns the algorithm so as not to deduct points from the input data (combination of sensor data and image data) that was the premise of the driving evaluation.

[0082] According to the second embodiment, it is possible to learn the scene itself in which a driving operation occurs due to an unavoidable force, so that it is possible to obtain a more accurate evaluation model.

[0083] (Modification) The above-described embodiment is merely an example, and the present disclosure can be modified and implemented as appropriate without departing from the spirit and scope of the present disclosure. For example, the processes and means described in this disclosure can be freely combined and implemented as long as no technical contradiction occurs.

[0084] In addition, in the description of the embodiment, image data is exemplified as the second data, but the second data is not limited to image data. For example, the second data may be a distance map acquired by a distance sensor or sensor data acquired by another sensor. In addition, in the description of the embodiment, the data indicating the behavior of surrounding traffic is exemplified as the second data, but the second data is not limited to the data indicating the behavior of surrounding traffic as long as it indicates the surrounding conditions of the vehicle 10. For example, the second data may be data that can determine that the driving environment has suddenly deteriorated, or may be data that indicates the approach of an obstacle such as a falling object or falling rocks.

[0085] In addition, in the description of the embodiment, the image data, which is the second data, is acquired by an on-board camera, but the image data may be captured by a device other than the vehicle 10. For example, the image may be captured by another vehicle located near the vehicle 10, or may be captured by a roadside device. In the embodiment, the feature amount is stored in the behavior database 102B. A behavior pattern may be identified by storing a plurality of image data corresponding to a plurality of behavior patterns in the database and calculating the similarity between the image data each time.

[0086] Furthermore, a process described as being performed by one device may be shared and executed by multiple devices. Alternatively, a process described as being performed by different devices may be executed by one device. In a computer system, the hardware configuration (server configuration) by which each function is realized can be flexibly changed.

[0087] The present disclosure can also be realized by supplying a computer program implementing the functions described in the above embodiments to a computer, and having one or more processors of the computer read and execute the program. Such a computer program may be provided to the computer by a non-transitory computer-readable storage medium connectable to the system bus of the computer, or may be provided to the computer via a network. Non-transitory computer-readable storage media include, for example, any type of disk, such as a magnetic disk (floppy disk, hard disk drive (HDD), etc.), an optical disk (CD-ROM, DVD disk, Blu-ray disk, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic card, a flash memory, an optical card, and any type of medium suitable for storing electronic instructions. [Explanation of symbols]

[0088] 100: Center server 101,201...Control unit 102,202...Storage section 103,203···Communications Department 200 ···In-vehicle terminal 204...Input / output section 205···Motion Sensor 206...Camera

Claims

1. Obtaining first data relating to a driving maneuver performed in a first vehicle; Obtaining second data relating to a surrounding situation of the first vehicle; and Determining whether the driving operation indicated by the first data occurred due to a surrounding condition of the first vehicle indicated by the second data; performing a driving evaluation for the first vehicle using an evaluation model having the first and second data as input data and a driving evaluation score as output data; updating the evaluation model so as to improve a driving evaluation score output for the first and second data, which are the input data, when a causal relationship is recognized between the surrounding circumstances and a driving operation performed in the first vehicle; An information processing device having a control unit that executes the above.

2. The second data is data regarding the behavior of surrounding traffic of the first vehicle. The information processing device according to claim 1 .

3. The control unit performs the driving evaluation based at least on the first data generated in a first period and the second data generated in a second period that is a period prior to the first period.

3. The information processing device according to claim 1 or 2.

4. The vehicle driving method further includes the step of: The information processing device according to claim 1 .

5. The control unit performs the determination using the stored data. The information processing device according to claim 4.

6. The control unit corrects an evaluation of a driving operation performed in the first vehicle when a causal relationship is recognized between the surrounding situation and the driving operation performed in the first vehicle. The information processing device according to claim 1 .

7. The first data includes motion data acquired by a sensor mounted on the first vehicle. The information processing device according to claim 1 .

8. The second data is image data acquired by a camera mounted on the first vehicle. The information processing device according to claim 1 .

9. The control unit determines a surrounding situation of the first vehicle based on a result of analyzing the image data. The information processing device according to claim 8.

10. A driving evaluation system including a first vehicle and an information processing device, The first vehicle is a first control unit that acquires first data related to a driving operation performed in the first vehicle and second data related to a surrounding situation of the first vehicle; The information processing device includes: Determining whether the driving operation indicated by the first data occurred due to a surrounding condition of the first vehicle indicated by the second data; performing a driving evaluation for the first vehicle using an evaluation model having the first and second data as input data and a driving evaluation score as output data; updating the evaluation model so as to improve a driving evaluation score output for the first and second data, which are the input data, when a causal relationship is recognized between the surrounding circumstances and a driving operation performed in the first vehicle; A second control unit that executes Driving evaluation system.

11. The second data is data regarding the behavior of surrounding traffic of the first vehicle. The driving evaluation system according to claim 10.

12. the first control unit periodically transmits the first and second data to the information processing device; The second control unit performs the driving evaluation based at least on the first data generated in a first period and the second data generated in a second period that is a period prior to the first period. The driving evaluation system according to claim 10 or 11.

13. The information processing device further includes a storage unit configured to store data regarding the surrounding conditions that affect the driving operation of the first vehicle. The driving evaluation system according to claim 10.

14. The second control unit performs the determination using the stored data. The driving evaluation system according to claim 13.

15. The second control unit corrects an evaluation of a driving operation performed in the first vehicle when a causal relationship is recognized between the surrounding situation and the driving operation performed in the first vehicle. The driving evaluation system according to any one of claims 10 to 14.

16. The first vehicle further includes a sensor that acquires motion data as the first data. The driving evaluation system according to any one of claims 10 to 15.

17. The first vehicle further includes a camera that acquires image data as the second data. The driving evaluation system according to any one of claims 10 to 16.

Images