Information processing apparatus and driving evaluation system

Abstract

The present disclosure relates to an information processing device and a driving evaluation system. The information processing device is configured to acquire first data related to a driving operation performed in a first vehicle and second data related to a surrounding situation of the first vehicle, and perform driving evaluation on the first vehicle based on the first data and the second data.

Description

Technical Field

[0001] The present disclosure relates to an information processing device and a driving evaluation system. Background Art

[0002] There is already a system for evaluating a driver's driving. For example, Japanese Unexamined Patent Application Publication No. 2020-177583 (JP 2020-177583 A) 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. Summary of the Invention

[0003] The present disclosure provides an information processing device and a driving evaluation system that improve the effectiveness of driving evaluation.

[0004] An information processing device according to a first aspect of the present disclosure includes a controller configured to acquire first data related to a driving operation performed in a first vehicle, acquire second data related to a peripheral condition of the first vehicle, and perform a driving evaluation on the first vehicle based on the first data and the second data.

[0005] In the information processing device, the second data may be data related to behavior of surrounding traffic of the first vehicle.

[0006] In the information processing device, the controller may be configured to perform the driving evaluation based on at least the first data generated in a first period and the second data generated in a second period prior to the first period.

[0007] In the information processing apparatus, the controller may be configured to make a determination as to whether the driving operation indicated by the first data is caused by the peripheral condition of the first vehicle indicated by the second data.

[0008] The information processing device may further include a memory configured to store data related to the peripheral conditions that affect the driving operation of the first vehicle.

[0009] In the information processing apparatus, the controller may be configured to make the determination by using the stored data.

[0010] In the information processing apparatus, the controller may be configured to correct an evaluation of the driving operation performed in the first vehicle when a causal relationship between the peripheral condition and the driving operation is found.

[0011] In the information processing apparatus, the controller can be configured to perform the driving evaluation by using an evaluation model in which the first data and the second data are input data and the driving evaluation is output data, and update the evaluation model to increase a value of the driving evaluation to be output for the input data when a causal relationship between the surrounding situation and the driving operation performed in the first vehicle is found.

[0012] In the information processing apparatus, the first data can include motion data acquired by a sensor mounted on the first vehicle.

[0013] In the information processing apparatus, the second data can be image data acquired by a camera mounted on the first vehicle.

[0014] In the information processing apparatus, the controller can be configured to make a determination about the surrounding situation of the first vehicle based on a result of analyzing the image data.

[0015] A driving evaluation system according to a second aspect of the present disclosure includes a first vehicle and an information processing apparatus. The first vehicle includes a first controller configured to acquire 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 apparatus includes a second controller configured to perform a driving evaluation on the first vehicle based on the first data and the second data.

[0016] In the driving evaluation system, the second data can be data related to a behavior of surrounding traffic of the first vehicle.

[0017] In the driving evaluation system, the first controller can be configured to periodically transmit the first data and the second data to the information processing apparatus, and the second controller can be configured to perform the driving evaluation based on at least the first data generated within a first period and the second data generated within a second period prior to the first period.

[0018] In the driving evaluation system, the second controller can be configured to make a determination about whether the driving operation indicated by the first data is caused by the surrounding situation of the first vehicle indicated by the second data.

[0019] In the driving evaluation system, the information processing apparatus can further include a memory configured to store data related to the surrounding situation that affects the driving operation of the first vehicle.

[0020] In the driving evaluation system, the second controller can be configured to make the determination by using the stored data.

[0021] In the driving evaluation system, the second controller can be configured to correct the evaluation of the driving operation performed in the first vehicle when a causal relationship between the surrounding situation and the driving operation is found.

[0022] In the driving evaluation system, the first vehicle can further include a sensor configured to acquire motion data as the first data.

[0023] In the driving evaluation system, the first vehicle can further include a camera configured to acquire image data as the second data.

[0024] Other aspects of the present disclosure relate to a program or a non-transitory computer-readable storage medium storing the program, the program causing a computer to execute a method to be executed by an information processing apparatus.

[0025] According to the present disclosure, it is possible to improve the effectiveness of driving evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0026] Features, advantages, and technical and industrial significance of exemplary embodiments of the application will be described below with reference to the accompanying drawings, wherein the same reference numerals denote the same elements, and wherein:

[0027] Figure 1 is a diagram showing an outline of a driving evaluation system;

[0028] Figure 2 is a diagram showing a configuration of a center server and an in-vehicle terminal;

[0029] Figure 3 shows an example of vehicle data stored in a memory;

[0030] Figure 4 shows an example of behavior data stored in a memory;

[0031] Figure 5A shows an example of an evaluation model stored in a memory;

[0032] Figure 5B shows an example of an evaluation model stored in a memory;

[0033] Figure 6 is a diagram showing data to be transmitted and received between modules in the first embodiment;

[0034] Figure 7 is a diagram showing a generation timing of data to be processed;

[0035] Figure 8 is a diagram showing the processing to be performed by the determiner;

[0036] Figure 9 is a flowchart of the processing to be performed by the controller in the first embodiment;

[0037] Figure 10 is a flowchart of the processing to be performed by the controller in the first embodiment;

[0038] Figure 11 is a diagram showing the data to be transmitted and received between the modules in the second embodiment; and

[0039] Figure 12 is a flowchart of the processing to be performed by the controller in the second embodiment. DETAILED DESCRIPTION

[0040] There is a system that evaluates driving by a driver based on a driving operation performed by the driver. In such a system, for example, the evaluation is performed based on the smoothness of the driving operation.

[0041] There are cases of operation for avoiding the occurrence of danger regardless of the responsibility of the driver. Examples of these cases include a pedestrian or a bicycle suddenly entering a street, and sudden braking caused by a sudden interruption from an adjacent lane. However, in the past driving evaluation system, even in these cases, it is possible to make an evaluation that the driver has performed an inappropriate driving operation.

[0042] In an information processing apparatus according to one aspect of the present disclosure, a controller acquires first data related to a driving operation performed in a first vehicle, acquires second data related to a surrounding situation of the first vehicle, and performs a driving evaluation on the first vehicle based on the first data and the second data.

[0043] The first data is data related to a driving operation performed by a driver. The first data can be data directly indicating the driving operation, or can be data indirectly indicating the driving operation. For example, the driving operation can be obtained indirectly by sensing the behavior of the first vehicle. Examples of the first data include the steering wheel operation amount, the accelerator or brake operation amount, the acceleration or deceleration of the vehicle, and the yaw rate. The first data can be acquired from the first vehicle, a computer installed on the first vehicle, or the like.

[0044] The second data is data related to a surrounding situation 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 imaging the surroundings of the first vehicle. The surrounding situation can be a traffic situation around the first vehicle. Examples of the traffic situation include the position or movement of another vehicle, a bicycle, and a pedestrian. The surrounding situation can be a situation of an obstacle around the first vehicle and a driving environment.

[0045] By performing the driving evaluation while taking into account the second data in addition to the first data, it is possible to make a determination as to whether or not the operation performed by the driver, for example, was effective (e.g., whether or not the operation was unavoidable). Thus, it is possible to improve the accuracy of the driving evaluation.

[0046] The second data can be data related to the behavior of the surrounding traffic of the first vehicle.

[0047] According to this configuration, it is possible to make a determination that, for example, the route of the first vehicle was obstructed and a driving operation was performed to avoid the obstruction.

[0048] The controller can perform the driving evaluation based on at least the first data generated in the first period and the second data generated in a second period prior to the first period.

[0049] For example, it is possible to make a determination as to whether or not the driving operation indicated by the first data was effective by referring to the second data retroactively traced in a period immediately prior to the driving operation.

[0050] The controller can make a determination as to whether or not the driving operation indicated by the first data was caused by a surrounding situation of the first vehicle indicated by the second data.

[0051] For example, when a certain event indicated by the second data obstructs the route of the first vehicle, it is possible to make a determination that the driving operation immediately after the event was caused by the event.

[0052] The information processing apparatus can further include a memory configured to store data related to a surrounding situation that affects a driving operation of the first vehicle.

[0053] The controller can make the determination using the stored data.

[0054] For example, by defining a surrounding situation that affects a driving operation of the first vehicle, such as a pedestrian suddenly entering a street or a vehicle stopping, and determining the degree of coincidence between the resulting surrounding situation and the defined surrounding situation, it is possible to make a determination as to whether or not there is a causal relationship.

[0055] When a causal relationship between the surrounding situation and the driving operation is found, the controller can correct the evaluation of the driving operation performed in the first vehicle.

[0056] The determination that the driving operation was caused by an unavoidable event can be made when there is a causal relationship between the surrounding situation and the driving operation. Therefore, the evaluation of the driving operation can be corrected, for example, in the positive direction. This makes it possible to compensate for a reduction in points caused by sudden operation or the like.

[0057] The controller can perform driving evaluation by using an evaluation model in which the first data and the second data are input data and the driving evaluation is output data, and update the evaluation model to increase the value of the driving evaluation to be output for the input data when a causal relationship between the surrounding situation and the driving operation performed in the first vehicle is found.

[0058] The driving evaluation can be performed by using an evaluation model (e.g., a machine learning model). In this case, when there is a surrounding situation having a causal relationship with the driving operation, the evaluation model is preferably updated (retrained) so that the value of the driving evaluation does not decrease in such a situation.

[0059] The first data can include motion data acquired by a sensor mounted on the first vehicle.

[0060] Examples of the motion data include data related to the motion of the first vehicle. Examples of the motion of the vehicle include acceleration, turning rate, and deceleration.

[0061] The second data can be image data acquired by a camera mounted on the first vehicle.

[0062] The controller can make a determination about the surrounding situation of the first vehicle based on the result of analyzing the image data.

[0063] By using an image acquired by a vehicle-mounted camera, a determination about the surrounding situation of the first vehicle can be made.

[0064] Hereinafter, specific embodiments of the present disclosure will be described with reference to the accompanying drawings. The hardware configuration, module configuration, functional configuration, and the like described in the respective embodiments are not intended to limit the technical scope of the present disclosure to these configurations unless otherwise specified.

[0065] First Embodiment

[0066] The outline of a driving evaluation system according to the first embodiment will be described with reference to Figure 1 The outline of a driving evaluation system according to the first embodiment will be described with reference to

[0067] Although Figure 1 One vehicle 10 is shown in FIG. 1, however, a plurality of vehicles 10 can be managed by the center server 100.

[0068] The in-vehicle terminal 200 is a computer installed in each vehicle 10 under management. The in-vehicle terminal 200 acquires vehicle data and periodically transmits the vehicle data to the center server 100. The vehicle data includes two types of data, i.e., "data related to a driving operation performed by a driver (first data)" and "data related to a surrounding situation of the vehicle 10 (second data)".

[0069] The center server 100 acquires a plurality of pieces of vehicle data from the vehicles 10 (in-vehicle terminals 200) under management of the system, and evaluates a driving operation performed by a driver based on the plurality of pieces of vehicle data (for example, evaluates a degree of smoothness of the performed driving operation).

[0070] The center server 100 determines which type of situation has occurred around the vehicle 10 based on the second data indicating the surrounding situation of the vehicle 10, and then evaluates the first data. Thereby, even when a sudden operation is performed due to an unavoidable event, the sudden operation can be effectively evaluated.

[0071] In the present embodiment, the first data is sensor data indicating a driving operation performed in the vehicle 10. The first data can be acquired by a sensor in the vehicle 10.

[0072] In the present embodiment, the second data is image data for analyzing behavior of surrounding traffic of the vehicle 10. The surrounding traffic refers to a moving body located in the vicinity of the vehicle 10, such as another vehicle, a bicycle, or a pedestrian. The image data can be acquired by, for example, a camera installed in the front portion of the vehicle 10.

[0073] Figure 2 is a diagram that illustrates in detail components of the driving evaluation system according to the present embodiment.

[0074] The in-vehicle terminal 200 is a computer installed in a vehicle. The in-vehicle terminal 200 includes a controller 201, a memory 202, a communicator 203, an input / output unit 204, a motion sensor 205, and a camera 206.

[0075] The controller 201 is an arithmetic unit responsible for control performed by the in-vehicle terminal 200. The controller 201 can be implemented by an arithmetic processing unit such as a central processing unit (CPU).

[0076] The controller 201 includes two functional modules, i.e., a vehicle data acquirer 2011 and a vehicle data transmitter 2012. These functional modules can be implemented by the CPU executing a program stored in the memory 202, which will be described later.

[0077] The vehicle data acquirer 2011 acquires vehicle data. In the present embodiment, the vehicle data includes the following two types of data.

[0078] (1) data related to a driving operation performed by a driver (sensor data)

[0079] (2) image data acquired by a vehicle-mounted camera

[0080] The sensor data corresponds to first data, and the image data corresponds to second data.

[0081] The data related to the driving operation is data indicating behavior of the vehicle (motion data), and is typically data indicating acceleration acquired by a motion sensor 205 described later. In the present example, acceleration measured by a sensor is exemplified as the sensor data, however the sensor data can also include other information as long as the sensor data is related to the driving operation. For example, the sensor data can include speed and yaw rate. The sensor data is not limited to data obtained by sensing motion of the vehicle. For example, the sensor data can be data indicating the driving operation and acquired from a steering sensor or a throttle sensor.

[0082] The vehicle data acquirer 2011 acquires the sensor data at a predetermined sampling rate (e.g., 10 Hz). The sensor data can be acquired at a sampling rate higher than the target sampling rate, and then smoothed by a filter. For example, data can be sampled at 100 Hz, and then down-sampled to 10 Hz by using a Gaussian filter or the like.

[0083] The image data is acquired by a camera 206 described later. The "image data" described herein can be one frame of data or multiple frames of data. The vehicle data acquirer 2011 can acquire data other than the sensor data and the image data, and include the data in the vehicle data. Examples of such data include position information, speed, and a travel direction of the vehicle 10.

[0084] The vehicle data transmitter 2012 periodically (e.g., at intervals of one second) transmits the vehicle data acquired by the vehicle data acquirer 2011 to the center server 100.

[0085] When the transmission interval of the vehicle data is one second, the vehicle data can include, for example, one second of sensor data and one second of image data. The image data can be a collection of multiple images. For example, when the transmission interval of the vehicle data is one second and the vehicle data acquirer 2011 can acquire images at 30 frames per second, the vehicle data transmitted at one time can include image data including 30 images. When the vehicle data acquirer 2011 can acquire sensor data at 10 Hz, one piece of vehicle data can include sensor data for 10 time steps.

[0086] The memory 202 includes a main storage device and a secondary storage device. The main storage device is a memory on which programs to be executed by the controller 201 and data to be used by the control program are loaded. The secondary storage device stores programs to be executed by the controller 201 and data to be used by the control program. The secondary storage device can store an application package of the programs to be executed by the controller 201. The secondary storage device can store an operating system for running these applications. The programs stored in the secondary storage device are loaded into the main storage device and executed by the controller 201. Thus, the processes to be described later are executed.

[0087] The main storage device can include a random access memory (RAM) or a read only memory (ROM). The secondary storage device can include an erasable programmable ROM (EPROM) or a hard disk drive (HDD). The secondary storage device can include a removable medium, i.e., a portable recording medium.

[0088] The communicator 203 is a wireless communication interface for connecting the in-vehicle terminal 200 to a network. The communicator 203 is communicable with the center server 100 via, for example, a wireless local area network (LAN) or a mobile communication service such as third generation (3G), long term evolution (LTE), or fifth generation (5G).

[0089] The input / output unit 204 receives an input operation performed by a user and presents information to the user. In the present embodiment, the input / output unit 204 is a single-touch panel display. That is, the input / output unit 204 includes a liquid crystal display and a controller thereof, and a touch panel and a controller thereof.

[0090] The motion sensor 205 measures an acceleration applied to the vehicle 10. Examples of the motion sensor 205 include a three-axis acceleration sensor capable of measuring an acceleration applied in a front-rear direction, a lateral direction, and a vertical direction of the vehicle. In this case, the sensor data can be a three-dimensional vector.

[0091] The camera 206 captures a view around the vehicle 10. Preferably, the camera 206 is installed in a position in which the camera 206 is capable of capturing at least a view of the front of the vehicle 10.

[0092] Next, the center server 100 will be described.

[0093] The center server 100 performs a process of receiving vehicle data from the in-vehicle terminal 200 and a process of evaluating a driving operation performed by the driver of the vehicle 10 based on the received vehicle data.

[0094] The center server 100 can be a general-purpose computer. That is, the center server 100 can be a computer including a processor such as a CPU or a graphic processing unit (GPU), a main storage device such as a RAM or a ROM, and an auxiliary storage device such as an EPROM, a hard disk drive, or a removable medium. An operating system (OS), various programs, various tables, and the like are stored in the auxiliary storage device. The programs stored in the auxiliary storage device are executed by being loaded into a work area of the main storage device. By the execution of the programs, the respective components are controlled to achieve various functions for predetermined purposes, as described later. Part or all of the functions can be realized by a hardware circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0095] The controller 101 is an arithmetic unit responsible for control performed by the center server 100. The controller 101 can be realized by an arithmetic processing unit such as a CPU.

[0096] The controller 101 includes three functional modules, namely, a data acquirer 1011, an evaluator 1012, and a determiner 1013. The respective functional modules can be realized by the CPU executing a stored program.

[0097] The data acquirer 1011 performs processing for acquiring vehicle data from the on-board terminal 200 installed on a vehicle under system management and storing the acquired vehicle data in a memory 102, which will be described later.

[0098] The evaluator 1012 evaluates a driving operation performed by the driver of the vehicle 10 on the basis of the stored vehicle data and generates data (evaluation data) indicating the evaluation result.

[0099] For example, the evaluator 1012 evaluates the sensor data by a predetermined evaluation model and acquires a value indicating the smoothness of the driving operation. The evaluator 1012 requests the determiner 1013, which will be described later, to determine whether the driving operation indicated by the sensor data is caused by the behavior of the surrounding traffic. The evaluator 1012 generates final evaluation data in consideration of the result of the determination made by the determiner 1013.

[0100] For example, when a determination is made that a particular driving operation is caused by the behavior of the surrounding traffic, as in the case where a pedestrian is observed jumping into the street immediately before a sudden braking, the evaluator 1012 takes an action not to penalize the sudden braking operation. The specific method will be described later.

[0101] Based on a request from the evaluator 1012, the determiner 1013 determines whether there is a causal relationship between the driving operation and the behavior of the surrounding traffic. Specifically, the determiner 1013 refers to the image data acquired immediately before the driving operation to be evaluated, and determines whether the behavior of the surrounding traffic obtained by analyzing the image data is consistent with a predetermined behavior pattern.

[0102] The predetermined behavior pattern is a behavior pattern of the surrounding traffic (e.g., sudden stop of a preceding vehicle or sudden entry of a pedestrian into a street) that can be associated with a specific driving operation (e.g., sudden braking). When the behavior of the surrounding traffic is consistent with the predetermined behavior pattern, a determination can be made that there is a causal relationship between the driving operation and the behavior of the surrounding traffic.

[0103] The memory 102 includes a main storage device and an auxiliary storage device. The main storage device is a memory that loads programs to be executed by the controller 101 and data to be used by the control program. The auxiliary storage device stores programs to be executed by the controller 101 and data to be used by the control program.

[0104] The memory 102 stores a vehicle database 102A, a behavior database 102B, and an evaluation model 102C.

[0105] The vehicle database 102A is a database that stores vehicle data acquired from the in-vehicle terminal 200. The vehicle database 102A stores a plurality of pieces of vehicle data acquired from a plurality of in-vehicle terminals 200.

[0106] Figure 3 is a diagram showing an example of data stored in the vehicle database 102A. An identifier (ID) that uniquely identifies a vehicle is stored in a vehicle ID field. The date and time when the vehicle data is generated are stored in a date and time information field. Position information of the vehicle is stored in a position information field. For example, the position information can be represented by latitude and longitude. Information indicating the traveling direction of the vehicle is stored in a direction information field.

[0107] Sensor data acquired by the motion sensor 205 of the vehicle 10 is stored in a sensor data field. Image data acquired by the camera 206 of the vehicle 10 is stored in an image data field. The image data can be motion image data composed of a plurality of frames.

[0108] The vehicle database 102A is periodically updated based on vehicle data transmitted from the in-vehicle terminal 200.

[0109] The behavior database 102B is a database that stores behavior patterns of the surrounding traffic (e.g., sudden entry of a pedestrian into a street) that can be associated with a specific driving operation (e.g., sudden braking). The behavior patterns stored in the behavior database 102B are patterns corresponding to external situations assumed to be unpredictable by the driver.

[0110] Figure 4 is a diagram illustrating an example of data stored in the behavior database 102B. Data uniquely identifying a behavior pattern is stored in the pattern ID field. Data obtained by converting the behavior of the surrounding traffic into feature amounts is stored in the feature amount data field. When the feature amounts obtained by converting the image data obtained by the in-vehicle camera show a high degree of similarity to a plurality of pieces of data, it is highly likely that a specific driving operation was performed due to the behavior of the surrounding traffic. That is, it is presumed that there is a causal relationship between the driving operation performed by the driver and the behavior of the surrounding traffic.

[0111] The vehicle database 102A and the behavior database 102B are constructed so that a program of a database management system (DBMS) executed by a processor manages data stored in a storage device. The vehicle database 102A and the behavior database 102B are, for example, a relational database.

[0112] The evaluation model 102C is a machine learning model for evaluating a driving operation performed by a driver. Figure 5A is a diagram illustrating input data and output data of the evaluation model 102C. As Figure 5A indicated, the evaluation model 102C acquires sensor data as input data, and generates a driving evaluation as output data. The driving evaluation is represented by, for example, a score. The evaluation model 102C is, for example, trained to output a higher score the more stable the driving operation is.

[0113] In the present example, only sensor data is exemplified as input to the evaluation model 102C, however, other information can be given as input data. For example, by giving information related to a road on which the vehicle 10 is traveling (for example, the number of lanes, the speed limit, the curvature, and whether there is a pedestrian crosswalk and a traffic signal), it is possible to determine whether the driving operation performed by the driver is appropriate with higher accuracy.

[0114] Accordingly, the center server 100 can store map data or the like including detailed information about a road on which the vehicle 10 can travel.

[0115] The communicator 103 is a communication interface for connecting the center server 100 to a network. The communicator 103 includes, for example, a network interface board and a wireless communication module for wireless communication.

[0116] Figure 2 The configuration illustrated is an example, and Figure 2 all or a part of the functions illustrated can be executed by using a circuit designed specifically for these functions. In addition to Figure 2 the combination illustrated, a program can be stored in or executed by a combination of a main storage device and an auxiliary storage device.

[0117] Figure 6 is a diagram showing the operation of the modules in the controller 101.

[0118] The data acquirer 1011 periodically receives vehicle data from the managed vehicle 10 (on-vehicle terminal 200). The received vehicle data is stored in the vehicle database 102A at all times.

[0119] The evaluator 1012 acquires sensor data corresponding to an evaluation target period from the plurality of pieces of information stored in the vehicle database 102A, and performs driving evaluation. Since the recorded sensor data is a transient value, a determination cannot be made as to which type of driving operation has been performed based on a single piece of sensor data. Therefore, the evaluator 1012 performs driving evaluation based on a collection of sensor data within a predetermined period (for example, one second).

[0120] Figure 7 is a diagram showing the relationship between a predetermined period and the timing at which driving evaluation is performed. In the present example, the evaluator 1012 inputs time-series sensor data that is traced back from the evaluation timing at a predetermined step (for example, five steps) to the evaluation model 102C, and acquires a value output from the evaluation model 102C. In the example shown, time-series sensor data corresponding to the period indicated by the reference numeral 701 is input to the evaluation model 102C.

[0121] The evaluator 1012 gives a determination request to the determiner 1013 to check whether the evaluation result obtained by the evaluation model 102C is valid. For example, when a pedestrian jumps into the street at the timing of t = 3, applies a sudden brake at the timing of t = 5, and then driving evaluation is performed, it is possible to make a determination that the driving operation is caused by an unavoidable event by checking the image data by tracing back by timing. In this way, the evaluator 1012 requests the determiner 1013 to check the image data by tracing back by timing at the timing at which driving evaluation is performed. In Figure 7 In the example shown, the determiner 1013 makes a determination by referring to the image data corresponding to the period indicated by the reference numeral 702.

[0122] In response to the determination request, the determiner 1013 refers to the image data acquired in the past, and determines whether the behavior of the surrounding traffic obtained by the analysis is consistent with a predetermined behavior pattern stored in the behavior database 102B. This determination can be made based on similarity. When the behavior of the surrounding traffic is consistent with the predetermined behavior pattern stored in the behavior database 102B, the determiner 1013 returns a determination result indicating that the behavior of the surrounding traffic that is presumed to have a causal relationship with the recent driving operation is detected to the evaluator 1012.

[0123] Figure 81013. The determiner 1013 determines a time period corresponding to a request from the evaluator 1012, acquires image data in the time period, and then converts the image data into a feature quantity. The time period may be predetermined. Preferably, the starting point of the time period is the starting point of the sensor data to be evaluated (at Figure 7 In the example of t=4) before the moment (in Figure 7 (In the example of t = 1). Determiner 1013 obtains feature quantities corresponding to each behavior pattern from behavior database 102B and compares the feature quantities. Based on this result, a determination can be made as to whether the behavior of the surrounding traffic corresponds to any predetermined behavior pattern. If a determination is made that two feature quantities coincide with each other as a result of comparing the feature quantities, a determination can be made that a causal relationship exists between the driving operation performed by the driver and the recently observed behavior of the surrounding traffic.

[0124] The evaluator 1012 adds the details of the determination made by the determiner 1013 to the driving evaluation generated by the evaluation model 102C, thereby generating evaluation data. For example, if sudden braking occurs on a road without a traffic light or a crosswalk, in principle, evaluation data indicating a low evaluation score is generated. If the determiner 1013 determines that the sudden braking was caused by the behavior of surrounding traffic (for example, a pedestrian suddenly entering the street), giving a low evaluation score is inappropriate. In this case, the evaluator 1012 modifies the evaluation criteria or corrects the evaluation results to improve the evaluation of the driving operation.

[0125] The amount used to correct the driving assessment can be determined based on the type of behavior pattern. For example, the amount of braking applied may differ between being interrupted by another vehicle and a pedestrian suddenly entering the street. For example, when the behavior pattern is "pedestrian suddenly entering the street," the correction amount may be greater than when the behavior pattern is "interrupted by another vehicle." The correction amount may be stored in association with the behavior pattern in the behavior database 102B.

[0126] Even if there is a causal relationship between the driving operation performed by the driver and the behavior of the surrounding traffic, the driving evaluation can not be corrected according to the conditions. Examples of such cases include a case where a pedestrian is crossing a pedestrian crossing, a case where the vehicle 10 is facing a red light signal, and a case where the vehicle 10 meets another vehicle traveling on a priority road. When the driver of the vehicle 10 is negligent, the driving evaluation should not be corrected. Therefore, the evaluator 1012 can further acquire other data related to the surrounding situation of the vehicle 10 (in addition to the behavior of the surrounding traffic), and further determine whether the driver is negligent based on the data. Examples of the other data related to the surrounding situation of the vehicle 10 include the position at which a traffic signal is installed, the position at which a pedestrian crossing is provided, the position at which a stop sign is provided, and map data that describes the priority relationship between roads. When a determination is made that the vehicle 10 is negligent as a result of referring to such data, the evaluator 1012 does not need to correct the driving evaluation regardless of the behavior of the surrounding traffic.

[0127] Next, a flowchart of the process performed by the respective modules of the controller 101 will be described. The process in the flowchart shown below is periodically performed for each vehicle 10 while the system is in operation. Figure 9

[0128] In step Sll, the data acquirer 1011 receives the vehicle data transmitted from the on-board terminal 200. The received vehicle data is stored in the vehicle database 102A.

[0129] In step S12, the evaluator 1012 generates evaluation data based on the acquired sensor data. For example, as shown in Figure 7 the time-series sensor data for a predetermined period of time is given to the evaluation model 102C as input data from the evaluation time, and the driving evaluation output is acquired.

[0130] In step S13, a determination is made as to whether the generated driving evaluation satisfies a predetermined penalty criterion. For example, when a driving evaluation having a score lower than a predetermined threshold is generated in step S12, a positive determination is made in step S13.

[0131] When a positive determination is made in step S13, the process proceeds to step S14, and the determiner 1013 determines the behavior of the surrounding traffic. That is, a determination is made as to whether the driving operation that caused the penalty is attributable to the behavior of the surrounding traffic.

[0132] Figure 10 is a flowchart of the process performed by the determiner 1013 in step S14.

[0133] ​In step S141, a reference period of image data for the determination is first determined. Preferably, the reference period of image data starts from a time point before the start point of the time-series sensor data to be evaluated. For example, when the driving evaluation is performed at a time point of t = 10 as shown in FIG. 7, a predetermined period (reference numeral 702) is determined to be traced back from the time point. In this example, a period corresponding to t = 1 to t = 9 is determined. Figure 7

[0134] In step S142, it is determined whether or not image data corresponding to the determined period is stored in the vehicle database 102A. When a negative determination is made, the process is terminated. When an affirmative determination is made, the process proceeds to step S143. In step S143, the image data corresponding to the determined period is acquired and converted into feature amounts. In step S144, as shown in FIG. 8, the feature amounts obtained by the conversion are compared with feature amounts corresponding to each of a plurality of behavior patterns stored in the behavior database 102B to obtain similarities. Figure 8

[0135] In step S145, a determination is made as to whether or not there is any behavior pattern having a similarity exceeding a predetermined value. When an affirmative determination is made, the determiner 1013 generates a determination result indicating that a behavior of the surrounding traffic presumed to have a causal relationship with the driving operation is detected. When negative determinations are made in steps S142 and S145, the determiner 1013 generates a determination result indicating that no behavior of the surrounding traffic presumed to have a causal relationship with the driving operation is detected.

[0136] Returning to Figure 9 , the description will be continued. When a causal relationship between the driving operation and the behavior of the surrounding traffic is found as a result of the determination made in step S14 (step S15: YES), the process proceeds to step S16 and the driving evaluation generated in step S12 is corrected. For example, when the driving evaluation shows a low score, the range of the score reduction is reduced or the score reduction is withdrawn. When no causal relationship between the driving operation and the behavior of the surrounding traffic is found (step S15: NO), the process is terminated. As described above, the amount of correction of the driving evaluation can differ depending on the behavior pattern. The evaluator 1012 can determine the carelessness of the driver of the vehicle 10 by referring to other data related to the driving environment of the vehicle 10, and need not correct the driving evaluation when a determination is made that there is carelessness.

[0137] In step S17, the evaluator 1012 generates evaluation data based on the driving evaluation acquired in step S12 or corrected in step S16. The evaluation data can be stored in the storage 102 or transmitted to an external device (for example, a device managed by an operator of the vehicle 10).

[0138] ​​As described above, in the driving evaluation system according to the first embodiment, when a low evaluation score is given for a driving operation, image data obtained immediately before the driving operation by the in-vehicle camera is acquired, and a causal relationship between the behavior of the surrounding traffic and the driving operation is estimated. When the causal relationship is found, the driving evaluation is corrected. This makes it possible to perform effective driving evaluation even when a sudden operation occurs due to an unavoidable event.

[0139] Second Embodiment

[0140] In the first embodiment, the evaluator 1012 generates a driving evaluation based on only sensor data. In the second embodiment, the evaluator 1012 generates a driving evaluation based on both sensor data and image data.

[0141] Figure 11 is a diagram illustrating the operation of the modules in the controller 101 in the second embodiment. The same parts as in the first embodiment are indicated by dotted lines, and the description thereof will be omitted. In the second embodiment, the evaluator 1012 acquires both sensor data and image data, inputs a plurality of pieces of data into the evaluation model 102C, and acquires a driving evaluation. Figure 5B is a diagram illustrating the input and output of the evaluation model 102C in the second embodiment.

[0142] In the second embodiment, as in the first embodiment, the evaluator 1012 acquires time-series sensor data that is reversely traced from the evaluation time by a predetermined step, and inputs the time-series sensor data to the evaluation model 102C. The evaluator 1012 acquires time-series image data that is reversely traced for a longer period than the sensor data, and inputs the time-series image data to the evaluation model 102C. These periods can be the same as the periods described with reference to Figure 7 This makes it possible to generate a driving evaluation based on sensor data corresponding to a driving operation and image data showing the behavior of the surrounding traffic that affected the driving operation.

[0143] In the second embodiment, when the evaluator 1012 corrects a driving evaluation, the evaluation model 102C is retrained based on the details of the correction. That is, when a predetermined behavior pattern is detected from the surrounding traffic and the driving evaluation is corrected, the algorithm of the evaluation model 102C is rebuilt so that the evaluation score does not decrease when a similar scenario occurs in the future. This makes it possible to obtain an evaluation model that can perform more effective driving evaluation.

[0144] Figure 12is a flowchart of the process executed by each module of the controller 101 in the second embodiment. The same process as in the first embodiment is indicated by a broken line, and the description thereof will be omitted. In the second embodiment, after the driving evaluation is corrected in step S16, the evaluator 1012 executes the process of step S16B. In step S16B, the evaluator 1012 updates the evaluation model 102C. Specifically, the algorithm is retrained so as not to penalize the input data (combination of sensor data and image data) that is a premise of the driving evaluation.

[0145] According to the second embodiment, the evaluation model can learn the scene of the driving operation caused by the inevitable event. Thus, a more accurate evaluation model can be obtained.

[0146] Variants

[0147] The above-described embodiments are merely illustrative, and the present disclosure can be appropriately modified without departing from the gist thereof. For example, the process and the apparatus described in the present disclosure can be combined as needed, provided that no technical contradiction arises.

[0148] In the description of the embodiments, the image data is exemplified as the second data, however the second data is not limited to the image data. For example, the second data can be a distance map acquired by a distance sensor, or can be sensor data acquired by another sensor. In the description of the embodiments, the data indicating the behavior of the surrounding traffic is exemplified as the second data, however the second data is not limited to the data indicating the behavior of the surrounding traffic as long as the data indicates the surrounding situation of the vehicle 10. For example, the second data can be data capable of providing a determination that the driving environment has suddenly deteriorated, or can be data indicating the approach of an obstacle such as a falling object or a rockfall.

[0149] In the description of the embodiments, the image data used as the second data is acquired by the in-vehicle camera, however can be acquired by an apparatus other than the vehicle 10. For example, the image data can be obtained by another vehicle located in the vicinity of the vehicle 10 or by a roadside apparatus. In the description of the embodiments, the feature quantity is stored in the behavior database 102B, however a plurality of pieces of image data corresponding to a plurality of behavior patterns can be stored in the database, and the behavior pattern can be determined by determining the similarity between the plurality of pieces of image data each time.

[0150] The process described as being executed by a single apparatus can be executed by a plurality of apparatuses in cooperation. Or, the process described as being executed by different apparatuses can be executed by a single apparatus. In a computer system, the hardware configuration (server configuration) that realizes the function can be flexibly changed.

[0151] The present disclosure can be implemented such that a computer program that realizes the functions described in the above-described embodiments is provided to a computer, and read and executed by one or more processors of the computer. The computer program can be provided to the computer by being stored in a non-transitory computer-readable storage medium connectable to a system bus of the computer, or can be provided to the computer via a network. Examples of the non-transitory computer-readable storage medium include any type of disk or disc, such as a magnetic disk (e.g., floppy disks (registered trademark) and hard disk drives (HDDs)) and optical disks (e.g., compact discs (CDs) and Blu-ray discs), and any type of medium suitable for storing electronic instructions, such as a read-only memory (ROM), a random-access memory (RAM), an EPROM, an electrically erasable programmable ROM (EEPROM), a magnetic card, a flash memory, and an optical card.

Claims

1. An information processing device, characterized in that comprising a controller configured to: acquiring first data related to a driving operation performed in a first vehicle; acquiring second data related to a surrounding condition of the first vehicle; making a determination as to whether the driving operation indicated by the first data is caused by the peripheral condition of the first vehicle indicated by the second data; performing a driving evaluation by using an evaluation model in which the first data and the second data are input data, and the driving evaluation is output data and is represented by a score; and When a causal relationship between the peripheral condition and the driving operation performed in the first vehicle is found, the evaluation model is updated to increase a value of the driving evaluation to be output for the first data and the second data as the input data.

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

3. The information processing device according to claim 1, wherein The controller is configured to perform the driving evaluation based on at least the first data generated within a first period and the second data generated within a second period prior to the first period.

4. The information processing device according to claim 1, wherein A memory is further included, the memory being configured to store data related to the surrounding conditions affecting the driving operation of the first vehicle.

5. The information processing device according to claim 4, wherein The controller is configured to make the determination by using the stored data.

6. The information processing device according to claim 1, wherein The controller is configured to correct an evaluation of the driving operation performed in the first vehicle when a causal relationship between the peripheral condition and the driving operation is found.

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

8. The information processing device according to any one of claims 1 to 7, characterized in that The second data is image data acquired by a camera mounted on the first vehicle.

9. The information processing device according to claim 8, wherein The controller is configured to make a determination regarding the surrounding condition of the first vehicle based on a result of analyzing the image data.

10. A driving evaluation system, characterized in that: include: first vehicle; and An information processing device, wherein: The first vehicle includes a first controller configured to acquire first data related to a driving operation performed in the first vehicle and second data related to a peripheral condition of the first vehicle; and the information processing device including a second controller configured to make a determination as to whether the driving operation indicated by the first data is caused by the peripheral condition of the first vehicle indicated by the second data; performing driving evaluation by using an evaluation model in which the first data and the second data are input data, and the driving evaluation is output data and is represented by a score; and When a causal relationship between the peripheral condition and the driving operation performed in the first vehicle is found, the evaluation model is updated to increase a value of the driving evaluation to be output for the first data and the second data as the input data.

11. The driving evaluation system according to claim 10, characterized in that: The second data is data related to the behavior of surrounding traffic of the first vehicle.

12. The driving evaluation system according to claim 10, wherein: The first controller is configured to periodically send the first data and the second data to the information processing device; and The second controller is configured to perform the driving evaluation based on at least the first data generated within a first period and the second data generated within a second period prior to the first period.

13. The driving evaluation system according to claim 10, characterized in that: The information processing device further includes a memory configured to store data related to the surrounding conditions that affect the driving operation of the first vehicle.

14. The driving evaluation system according to claim 13, wherein: The second controller is configured to make the determination by using the stored data.

15. The driving evaluation system according to claim 10, characterized in that: The second controller is configured to correct an evaluation of the driving operation performed in the first vehicle when a causal relationship between the peripheral condition and the driving operation is found.

16. The driving evaluation system according to claim 10, characterized in that The first vehicle further includes a sensor configured to acquire motion data as the first data.

17. The driving evaluation system according to any one of claims 10 to 16, characterized in that: The first vehicle further includes a camera configured to acquire image data as the second data.

Images