Information processing system, information processing method, and program

Abstract

The present invention improves the accuracy of determining the automatic driving state of a traveling vehicle. This information processing system comprises: a vehicle type identification means for identifying the vehicle type of a traveling vehicle; a motion characteristic detection means for detecting the motion characteristics of the traveling vehicle identified by the vehicle type identification means; and a driving state determination means for determining whether the traveling vehicle is in an automatic driving state or a manual driving state by comparing predetermined motion characteristics exhibited during automatic driving by the vehicle type identified by the vehicle type identification means with the motion characteristics detected by the motion characteristic detection means.

Description

Information Processing System, Information Processing Method, and Program

[0001] The present disclosure relates to an information processing system, an information processing method, and a program for determining the driving state of a traveling vehicle.

[0002] In recent years, automated driving vehicles and manually driven vehicles are running mixedly, and appropriate traffic control that takes both into consideration is required. Also, it is required to perform traffic control efficiently as a whole, and in that case, it is necessary to always grasp whether the vehicle is in an automated driving state or a manual driving state.

[0003] On the other hand, an information processing system for determining whether a traveling vehicle is in an automated driving state using a driving characteristic model of a vehicle is known (see, for example, Patent Document 1).

[0004] International Publication No. 2023 / 032276

[0005] However, in the determination by the above information processing system, it cannot be said that the conditions of each vehicle and the like are sufficiently considered, and there is a possibility that the determination accuracy is not sufficient.

[0006] An object of the present disclosure is to provide an information processing system, an information processing method, and a program that solve any of the above-described problems.

[0007] One aspect of the present disclosure for achieving the above objective is an information processing system comprising: a vehicle type identification means for identifying the type of vehicle being driven; a motion characteristic detection means for detecting the motion characteristics of the vehicle being driven identified by the vehicle type identification means; and a driving state determination means for determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the vehicle type identified by the vehicle type identification means during automated driving with the motion characteristics detected by the motion characteristic detection means. Another aspect of the present disclosure for achieving the above objective is an information processing method comprising: a step of identifying the type of vehicle being driven; a step of detecting the motion characteristics of the identified vehicle being driven; and a step of determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the identified vehicle being driven during automated driving with the detected motion characteristics. One aspect of this disclosure for achieving the above objective is a program that causes a computer to perform the following: a process for identifying the type of vehicle being driven; a process for detecting the motion characteristics of the identified vehicle being driven; and a process for determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics that the identified vehicle being driven exhibits during automated driving with the detected motion characteristics.

[0008] This disclosure provides an information processing system, an information processing method, and a program that solve any of the above-mentioned problems.

[0009] This is a block diagram showing the approximate hardware configuration of the information processing system related to this disclosure. This is a block diagram showing the approximate system configuration of the information processing system related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a block diagram showing the approximate system configuration of the information processing system related to this disclosure. This is a block diagram showing the approximate system configuration of the information processing system related to this disclosure.

[0010] Embodiment 1 The information processing system according to this disclosure determines the driving state of a moving vehicle with high accuracy. Figure 1 is a block diagram showing the schematic hardware configuration of the information processing system according to this disclosure.

[0011] The information processing system 1 related to this disclosure has a hardware configuration similar to that of a normal computer, as shown in Figure 1, for example, and includes a processor 11 such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit), internal memory 12 such as RAM (Random Access Memory) or ROM (Read Only Memory), storage devices 13 such as an HDD (Hard Disk Drive) or SSD (Solid State Drive), an input / output I / F 14 for connecting peripheral devices such as a display, and a communication I / F 15 for communicating with devices outside the device.

[0012] Figure 2 is a block diagram showing the schematic system configuration of the information processing system according to this disclosure. The information processing system 1 according to this disclosure includes a vehicle type identification unit 2 that identifies the type of vehicle being driven, a motion characteristic detection unit 3 that detects the motion characteristics of the vehicle being driven, a model acquisition unit 4 that acquires a driving characteristic model for autonomous driving, and a driving state determination unit 5 that determines the driving state of the vehicle being driven.

[0013] As shown in Figure 2, the information processing system 1 is configured as a central processing unit integrating a vehicle type identification unit 2, a motion characteristic detection unit 3, a model acquisition unit 4, and a driving state determination unit 5, but it is not limited to this configuration. At least one of the vehicle type identification unit 2, motion characteristic detection unit 3, model acquisition unit 4, and driving state determination unit 5 may be installed, for example, in road infrastructure. The central processing unit and road infrastructure may transmit and receive information via vehicle-to-infrastructure communication.

[0014] Furthermore, the central processing unit may be a server located in a traffic control center or a cloud server managed by a traffic control center, and may have traffic control (signal control) functions. Road infrastructure may also have traffic control (signal control) functions, such as traffic lights, intersections, or MEC (Mobile Edge Server) servers located in designated areas.

[0015] The vehicle type identification unit 2 is a specific example of a vehicle type identification means. The vehicle type identification unit 2 identifies the vehicle type of a vehicle entering a predetermined range from an intersection. Near an intersection, vehicles often accelerate, decelerate, turn left, turn right, etc., making it easier to detect the vehicle's motion characteristics, as described later.

[0016] Vehicle types can be classified by size, for example, and may include large vehicles (trucks, buses, etc.), medium-sized vehicles (general vehicles, taxis, etc.), and small vehicles (kei cars, etc.). Vehicle types can also be classified by their intended use, for example, and may include private cars and commercial vehicles (buses, trucks, taxis, etc.).

[0017] Vehicle types are classified by their drive system and may include, for example, electric vehicles, hybrid vehicles, fuel cell vehicles, and internal combustion engine vehicles. Vehicle types are also classified by the type of occupants in the vehicle and may include, for example, kindergarten buses and tour buses. Vehicle types are also classified by the product name of the vehicle and may include, for example, Prius (registered trademark).

[0018] The above classification method for vehicle types is merely an example and is not limited to it. Vehicle types may also be classified based on any criteria that result in differences in the vehicle's dynamic characteristics during autonomous driving, as described later.

[0019] The vehicle type identification unit 2 identifies the vehicle type based on images of the vehicle taken by cameras installed on roads, information about the vehicle transmitted via vehicle-to-infrastructure communication or vehicle-to-vehicle communication, etc. The vehicle information includes vehicle sensor information, GPS (Global Positioning System) information, identification information, etc.

[0020] The vehicle identification unit 2 may, for example, identify the license plate number of a moving vehicle based on an image of the vehicle, and then identify the vehicle type of the vehicle based on that number.

[0021] The motion characteristic detection unit 3 is a specific example of a motion characteristic detection means. The motion characteristic detection unit 3 detects the motion characteristics of a vehicle identified by the vehicle type identification unit 2. The motion characteristic detection unit 3 detects predetermined motion characteristics that have been set in advance.

[0022] The motion characteristics detection unit 3 may detect the motion characteristics of the moving vehicle based on images of the moving vehicle taken by a camera, information about the moving vehicle transmitted via vehicle-to-infrastructure communication or vehicle-to-vehicle communication, etc.

[0023] Here, the above-mentioned motion characteristics refer to, for example, the trajectory of a vehicle when it turns left or right during autonomous driving. This trajectory tends to differ depending on the vehicle type. Smaller vehicles tend to have smaller trajectories, while larger vehicles tend to have larger trajectories. Thus, the vehicle trajectory represents the characteristic motion characteristics that each vehicle type exhibits during autonomous driving.

[0024] It should be noted that the motion characteristics during autonomous driving are described, for example, as the trajectory of the vehicle when it turns left or right during autonomous driving, but are not limited to this. The motion characteristics during autonomous driving may also be, for example, the acceleration and deceleration tendency of the vehicle when it accelerates or decelerates during autonomous driving (speed change over time). Furthermore, the motion characteristics during autonomous driving may also be the frequency of braking, the timing of braking, the change in position within the lane, the change in direction of travel, the change in relative position with surrounding vehicles, etc. Any characteristic motion characteristics that each vehicle type exhibits during autonomous driving are acceptable.

[0025] The model acquisition unit 4 is a specific example of a model acquisition means. The model acquisition unit 4 acquires an autonomous driving characteristic model that associates multiple vehicle types with the motion characteristics exhibited by each vehicle type during autonomous driving.

[0026] The autonomous driving characteristics model may be pre-stored in a memory unit, for example. The model acquisition unit 4 may acquire the autonomous driving characteristics model from the memory unit, for example. Furthermore, the model acquisition unit 4 may acquire the autonomous driving characteristics model by generating it itself. The model acquisition unit 4 may generate the autonomous driving characteristics model by, for example, performing machine learning using motion characteristic data for each vehicle type, or by averaging motion characteristic data for each vehicle type.

[0027] The driving state determination unit 5 is a specific example of a driving state determination means. The driving state determination unit 5 selects motion characteristics from among the motion characteristics of the driving characteristic model acquired by the model acquisition unit 4 that correspond to the type of vehicle of the vehicle being driven, as identified by the vehicle type identification unit 2.

[0028] The driving state determination unit 5 compares the selected motion characteristics with the motion characteristics detection unit 3 to determine whether the vehicle is in an automatic driving state or a manual driving state.

[0029] For example, the driving state determination unit 5 may compare the selected motion characteristics with the motion characteristics detected by the motion characteristics detection unit 3, and if it determines that the two match, it may determine that the vehicle is in an autonomous driving state. Note that "matching" includes not only cases where the two match perfectly, but also cases where the difference between the two is within a predetermined reference range.

[0030] On the other hand, the driving state determination unit 5 may compare the selected motion characteristics with the motion characteristics detected by the motion characteristics detection unit 3, and if it determines that the two do not match, it may determine that the vehicle is in a manual driving state.

[0031] Next, we will explain the information processing method related to this disclosure. Figure 3 is a flowchart showing the flow of the information processing method related to this disclosure.

[0032] The vehicle identification unit 2 identifies the vehicle type based on images of the vehicle taken by a roadside camera, information about the vehicle being transmitted, etc. (step S101).

[0033] The motion characteristics detection unit 3 detects the motion characteristics of the vehicle identified by the vehicle type identification unit 2 based on images of the vehicle from a roadside camera, transmitted information about the vehicle, etc. (step S102).

[0034] The model acquisition unit 4 acquires an autonomous driving characteristic model that associates multiple vehicle types with the motion characteristics exhibited by each vehicle type during autonomous driving (step S103).

[0035] The driving state determination unit 5 selects from the motion characteristics of the driving characteristic model acquired by the model acquisition unit 4 that correspond to the type of vehicle identified by the vehicle type identification unit 2 (step S104).

[0036] The driving state determination unit 5 compares the selected motion characteristics with the motion characteristics detection unit 3 to determine whether the vehicle is in an automatic driving state or a manual driving state (step S105).

[0037] In the information processing system 1 related to this disclosure, the autonomous driving state is determined using an autonomous driving characteristics model that associates each vehicle type with the motion characteristics exhibited by each vehicle type during autonomous driving. Therefore, even if the motion characteristics in the autonomous driving state differ depending on the vehicle type, the autonomous driving state can be determined with high accuracy.

[0038] Embodiment 2 Figure 4 is a block diagram showing a schematic system configuration of the information processing system according to the present disclosure. In addition to the above configuration, the information processing system 20 according to the present disclosure further includes a vehicle information acquisition unit 6 that acquires vehicle information of a moving vehicle.

[0039] The vehicle information acquisition unit 6 is a specific example of a vehicle information acquisition means. The vehicle information acquisition unit 6 acquires vehicle information of the vehicle being driven, which has been identified by the vehicle type identification unit 2.

[0040] Vehicle information includes, for example, vehicle weight information and maintenance information. Maintenance information is information related to vehicle maintenance, such as replacement parts, engine oil level, deteriorated parts, and faulty parts in a running vehicle. Replacement parts information is, for example, whether or not parts such as brake pads and brake discs have been replaced. Differences in this vehicle information, like differences in vehicle type, will result in differences in the vehicle's dynamic characteristics during autonomous driving.

[0041] The vehicle information acquisition unit 6 may acquire vehicle information of a moving vehicle via vehicle-to-infrastructure communication or vehicle-to-vehicle communication. For example, the vehicle information acquisition unit 6 can acquire information on the weight of a moving vehicle from road sensors via vehicle-to-infrastructure communication. The vehicle information acquisition unit 6 may also acquire vehicle information of a moving vehicle by estimating it based on sensor information of the vehicle transmitted via vehicle-to-infrastructure communication or vehicle-to-vehicle communication.

[0042] The model acquisition unit 4 acquires an autonomous driving characteristics model by associating vehicle information related to the vehicle type and vehicle information with the motion characteristics exhibited by the vehicle during autonomous driving. Alternatively, the model acquisition unit 4 itself may acquire the autonomous driving characteristics model by performing machine learning or the like using the motion characteristics data for each vehicle type and vehicle information.

[0043] The driving state determination unit 5 selects motion characteristics from the motion characteristics of the autonomous driving characteristics model acquired by the model acquisition unit 4 that correspond to the vehicle type of the vehicle being driven, identified by the vehicle type identification unit 2, and the vehicle information acquired by the vehicle information acquisition unit 6. The driving state determination unit 5 compares the selected motion characteristics with the motion characteristics detected by the motion characteristics detection unit 3 to determine whether the vehicle is in an autonomous driving state or a manual driving state.

[0044] In the information processing system 20 according to the present disclosure, the determination of the automatic driving state is performed using a driving characteristic model of automatic driving in which each vehicle type and vehicle information are associated with the motion characteristics exhibited by the vehicle of each vehicle type and vehicle information during automatic driving. Therefore, even if the motion characteristics in the automatic driving state change depending on the vehicle type and vehicle information, the determination of the automatic driving state can be performed with higher accuracy.

[0045] Embodiment 3 FIG. 5 is a block diagram showing a schematic system configuration of the information processing system according to the present disclosure. The information processing system 30 according to the present disclosure further includes a driver information acquisition unit 7 that acquires information on the driver of the traveling vehicle in addition to the above configuration.

[0046] The driver information acquisition unit 7 is a specific example of a driver information acquisition means. The driver information acquisition unit 7 acquires information on the driver of the traveling vehicle specified by the vehicle type specifying unit 2.

[0047] The driver's information includes the driver's attribute information, identification information for identifying the driver individual, and the like. The driver's attribute information includes information such as the driver's age, gender, physical disability, physical characteristics (height, weight, etc.). Differences in these driver's information result in differences in the motion characteristics of the vehicle during manual driving.

[0048] The driver information acquisition unit 7 may acquire information on the driver of the traveling vehicle via vehicle-to-road communication, vehicle-to-vehicle communication, or the like. The driver information acquisition unit 7 may acquire information on the driver of the traveling vehicle (age, gender, etc.) by estimating it based on an image of the traveling vehicle captured by a camera.

[0049] The model acquisition unit 4 acquires a driving characteristic model of manual driving in which each vehicle type and driver information are associated with the motion characteristics exhibited by the vehicle of each vehicle type and driver information during manual driving. Further, the model acquisition unit 4 itself may acquire the driving characteristic model of manual driving by performing machine learning or the like using the motion characteristic data of each vehicle type and each driver's information.

[0050] The driving state determination unit 5 selects motion characteristics from among the motion characteristics of the manual driving characteristic model acquired by the model acquisition unit 4 that correspond to the vehicle type of the vehicle being driven, identified by the vehicle type identification unit 2, and the driver information acquired by the driver information acquisition unit 7. The driving state determination unit 5 compares the selected motion characteristics with the motion characteristics detected by the motion characteristic detection unit 3 to determine whether the vehicle is in an automatic driving state or a manual driving state.

[0051] The driving state determination unit 5 may compare the selected motion characteristics with the motion characteristics detected by the motion characteristics detection unit 3, and if it determines that the two match, it may determine that the vehicle is in a manual driving state.

[0052] In the information processing system 30 related to this disclosure, the manual driving state is determined using a manual driving characteristics model that associates vehicle type and driver information with the motion characteristics exhibited by each vehicle type and driver's information when manually driven. Therefore, even if the motion characteristics in the manual driving state change depending on the vehicle type and driver, the manual driving state can be determined with higher accuracy.

[0053] Embodiment 4 In this embodiment, the driving state determination unit 5 uses an automated driving characteristic model and a manual driving characteristic model to determine with higher accuracy whether the vehicle is in an automated driving state or a manual driving state.

[0054] First, the model acquisition unit 4 acquires an autonomous driving characteristic model that associates multiple vehicle types with the motion characteristics exhibited by each vehicle type during autonomous driving. Alternatively, the model acquisition unit 4 may acquire an autonomous driving characteristic model that associates vehicle type and vehicle information with the motion characteristics exhibited by the vehicle type and vehicle information during autonomous driving.

[0055] Furthermore, the model acquisition unit 4 acquires a manual driving characteristics model that associates vehicle type and driver information with the driving characteristics exhibited by the vehicle type and driver information when it is manually driven.

[0056] The driving state determination unit 5 determines that the vehicle is in an automated driving state if the motion characteristics of the automated driving characteristic model match the motion characteristics detected by the motion characteristics detection unit 3, and the motion characteristics of the manual driving characteristic model do not match the motion characteristics detected by the motion characteristics detection unit 3.

[0057] The driving state determination unit 5 performs a re-determination if the motion characteristics of the driving characteristic model for automatic driving match the motion characteristics detected by the motion characteristic detection unit 3, and the motion characteristics of the driving characteristic model for manual driving match the motion characteristics detected by the motion characteristic detection unit 3. In this case, the driving state determination unit 5 may perform the re-determination by comparing the motion characteristics of another driving characteristic model for automatic or manual driving with the motion characteristics detected by the motion characteristic detection unit 3.

[0058] The driving state determination unit 5 determines that the vehicle is in a manual driving state if the motion characteristics of the automatic driving characteristic model do not match the motion characteristics detected by the motion characteristics detection unit 3, and the motion characteristics of the manual driving characteristic model do not match the motion characteristics detected by the motion characteristics detection unit 3.

[0059] The driving state determination unit 5 determines that the vehicle is in manual driving mode if the motion characteristics of the automatic driving characteristic model do not match the motion characteristics detected by the motion characteristics detection unit 3, and the motion characteristics of the manual driving characteristic model match the motion characteristics detected by the motion characteristics detection unit 3.

[0060] This disclosure can also be implemented, for example, by having a processor execute a computer program, as shown in Figure 3.

[0061] Programs can be stored and supplied to a computer using various types of non-transitory computer-readable medium. Non-transitory computer-readable medium includes various types of tangible storage medium. Examples of non-transitory computer-readable medium include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memory)).

[0062] Programs may be supplied to a computer by various types of transient computer-readable medium. Examples of transient computer-readable medium include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable medium can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0063] Each component of the information processing system according to the above-described embodiment can be implemented not only by program, but also, in whole or in part, by dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0064] Furthermore, in this embodiment, we will explain how to utilize the results of the analysis and determination of automatic and manual driving by the driving state determination unit 5 described above. The results of the automatic and manual driving determination by the driving state determination unit 5 described above can be used for signal control (traffic control).

[0065] For example, if the control unit performing traffic control determines that the above-mentioned judgment result includes manually driven vehicles, that is, if there is a mix of automated and manually driven vehicles, it may use traffic signals to control manually driven vehicles by switching the signals in the order of "green light" → "yellow light" → "red light," and repeating this switching. In this case, the control unit may use vehicle-to-infrastructure communication to control automated vehicles by switching the instructions in the order of "go" → "caution" → "stop" in accordance with the signal switching from "green light" → "yellow light" → "red light," and repeating this switching. Furthermore, the control unit may use traffic signals to control manually driven vehicles and vehicle-to-infrastructure communication to control automated vehicles by instructing them to "turn right," etc. Furthermore, the control unit may use vehicle-to-infrastructure communication to instruct automated vehicles with more advanced control content. Examples of advanced control functions include "shortening or increasing the distance between vehicles," "driving in a convoy or not," and "making way for approaching emergency vehicles," but these are just examples and are not limited to these.

[0066] On the other hand, if the determination result indicates that no manually driven vehicles are included, that is, if only autonomous vehicles are present, the control unit may use vehicle-to-infrastructure communication to instruct the autonomous vehicles to always "proceed" as the content of traffic control. In terms of traffic lights, this is equivalent to a state where the "green light" is always on. Alternatively, the traffic control unit 13 may use vehicle-to-infrastructure communication to switch the instruction to the autonomous vehicles in the order of "proceed" → "stop" as the content of traffic control, and repeat this switching. In terms of traffic lights, this is equivalent to repeatedly switching between a "green light" and a "red light". Furthermore, the traffic control unit 13 may use vehicle-to-infrastructure communication to instruct the autonomous vehicles to perform more advanced control.

[0067] Assuming an environment with dedicated autonomous driving lanes, the control unit may issue a signal to guide a vehicle determined to be in autonomous driving mode to the dedicated autonomous driving lane. This assumes an instruction signal or setting change signal that changes the autonomous vehicle's lane setting from "the lane it is currently driving in (or the lane it is about to drive in)" to "the dedicated autonomous driving lane."

[0068] The control unit monitors the number of automatically and manually driven vehicles in each area and dynamically changes the areas that should be patrolled intensively. For example, it may automatically guide patrol cars to focus on areas with a high number of manually driven vehicles, or it may update the maps used by the police.

[0069] The control unit can track the ratio of automatic to manual driving, which can then be used to conduct surveys on the prevalence of autonomous driving.

[0070] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0071] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps described in any of the drawings may be changed as appropriate.

[0072] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) An information processing system comprising: a vehicle type identification means for identifying the type of vehicle being driven; a motion characteristic detection means for detecting the motion characteristics of the vehicle being driven identified by the vehicle type identification means; and a driving state determination means for determining whether the vehicle being driven is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the vehicle type identified by the vehicle type identification means during automated driving with the motion characteristics detected by the motion characteristic detection means. (Note 2) An information processing system as described in Note 1, further comprising a model acquisition means for acquiring an autonomous driving characteristic model that associates a plurality of vehicle types with predetermined motion characteristics exhibited by each vehicle type during autonomous driving, wherein the driving state determination means selects motion characteristics corresponding to the vehicle type of the vehicle being driven, identified by the vehicle type identification means, from among the motion characteristics of the driving characteristic model acquired by the model acquisition means, and determines whether the vehicle being driven is in an autonomous driving state or a manual driving state by comparing the selected motion characteristics with the motion characteristics detected by the motion characteristic detection means. (Note 3) An information processing system as described in Note 2, wherein the model acquisition means acquires an autonomous driving characteristic model that associates the vehicle type and vehicle information with the motion characteristics exhibited by the vehicle type and vehicle information during autonomous driving, and further comprises a vehicle information acquisition means that acquires vehicle information of a driving vehicle identified by the vehicle type identification means, and the driving state determination means selects motion characteristics from among the motion characteristics of the driving characteristic model acquired by the model acquisition means that correspond to the vehicle type of the driving vehicle identified by the vehicle type identification means and the vehicle information acquired by the vehicle information acquisition means, and determines whether the driving vehicle is in an autonomous driving state or a manual driving state by comparing the selected motion characteristics with the motion characteristics detected by the motion characteristics detection means.(Note 4) An information processing system as described in Note 3, wherein the vehicle information includes at least one of the following: weight information of the vehicle in motion and maintenance information relating to the maintenance of the vehicle in motion. (Note 5) An information processing system as described in Note 2, wherein the model acquisition means further acquires a manual driving characteristics model that associates the vehicle type and driver information with the driving characteristics exhibited by the vehicle type and driver information when it is manually driven, and further comprises a driver information acquisition means that acquires information about the driver of the vehicle in motion identified by the vehicle type identification means, and the driving state determination means selects from the driving characteristics of the driving characteristics model acquired by the model acquisition means a driving characteristics corresponding to the vehicle type identified by the vehicle type identification means and the driver information acquired by the driver information acquisition means, and determines whether the vehicle in motion is in an automatic driving state or a manual driving state by comparing the selected driving characteristics with the driving characteristics detected by the driving characteristics detection means.(Note 6) The information processing system described in Note 5, wherein the driving state determination means determines that the vehicle is in an automated driving state if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match; if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, then the determination is made again using a different automated driving or manual driving characteristic model; if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match, then the vehicle is in a manual driving state. An information processing system that determines that the vehicle is in a manual driving state if the motion characteristics of the autonomous driving characteristic model do not match the motion characteristics detected by the motion characteristics detection means, and the motion characteristics of the manual driving characteristic model match the motion characteristics detected by the motion characteristics detection means. (Note 7) An information processing system according to Note 2, wherein the model acquisition means generates a driving characteristic model that associates a plurality of vehicle types with the motion characteristics that each vehicle type exhibits when it is in autonomous driving. (Note 8) An information processing system according to Note 1, wherein the vehicle types are classified by vehicle size, vehicle use, vehicle drive system, or type of occupants in the vehicle. (Note 9) An information processing method comprising: identifying the type of vehicle being driven; detecting the motion characteristics of the identified vehicle being driven; and determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics that the identified vehicle being driven exhibits during automated driving with the detected motion characteristics.(Note 10) A program that causes a computer to perform the following: a process to identify the type of vehicle being driven; a process to detect the motion characteristics of the identified vehicle being driven; and a process to determine whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics that the identified vehicle exhibits during automated driving with the detected motion characteristics.

[0073] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 8 that are dependent on Appendice 1 {e.g., device} may also be dependent on Appendices 9 {e.g., method} and 10 {e.g., program} in the same way as in Appendices 2 to 8. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means, systems, and methods for recording software.

[0074] 1 Information processing system 2 Vehicle type identification unit 3 Motion characteristic detection unit 4 Model acquisition unit 5 Driving state determination unit 6 Vehicle information acquisition unit 7 Driver information acquisition unit 11 Processor 12 Internal memory 13 Storage device 20 Information processing system 30 Information processing system

Claims

1. An information processing system comprising: a vehicle type identification means for identifying the type of vehicle being driven; a motion characteristic detection means for detecting the motion characteristics of the vehicle being driven identified by the vehicle type identification means; and a driving state determination means for determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the vehicle type identified by the vehicle type identification means during automated driving with the motion characteristics detected by the motion characteristic detection means.

2. An information processing system according to claim 1, further comprising a model acquisition means for acquiring an autonomous driving characteristic model that associates a plurality of vehicle types with predetermined motion characteristics exhibited by each vehicle type during autonomous driving, wherein the driving state determination means selects motion characteristics corresponding to the vehicle type of the vehicle being driven, identified by the vehicle type identification means, from among the motion characteristics of the driving characteristic model acquired by the model acquisition means, and determines whether the vehicle being driven is in an autonomous driving state or a manual driving state by comparing the selected motion characteristics with the motion characteristics detected by the motion characteristic detection means.

3. An information processing system according to claim 2, wherein the model acquisition means acquires an autonomous driving characteristic model that associates vehicle information relating to the vehicle type and the vehicle with the motion characteristics exhibited by the vehicle type and the vehicle information during autonomous driving, and further comprises a vehicle information acquisition means that acquires vehicle information of a driving vehicle identified by the vehicle type identification means, and the driving state determination means selects motion characteristics from among the motion characteristics of the driving characteristic model acquired by the model acquisition means that correspond to the vehicle type of the driving vehicle identified by the vehicle type identification means and the vehicle information acquired by the vehicle information acquisition means, and determines whether the driving vehicle is in an autonomous driving state or a manual driving state by comparing the selected motion characteristics with the motion characteristics detected by the motion characteristics detection means.

4. An information processing system according to claim 3, wherein the vehicle information includes at least one of the following: weight information of a running vehicle and maintenance information relating to the maintenance of a running vehicle.

5. An information processing system according to claim 2, wherein the model acquisition means further acquires a manual driving characteristics model that associates the vehicle type and driver information with the driving characteristics exhibited by the vehicle type and driver information when it is manually driven, and further comprises a driver information acquisition means that acquires information of the driver of the vehicle identified by the vehicle type identification means, and the driving state determination means selects from the driving characteristics of the driving characteristics model acquired by the model acquisition means a driving characteristics corresponding to the vehicle type identified by the vehicle type identification means and the driver information acquired by the driver information acquisition means, and determines whether the vehicle is in an automatic driving state or a manual driving state by comparing the selected driving characteristics with the driving characteristics detected by the driving characteristics detection means.

6. The information processing system according to claim 5, wherein the driving state determination means determines that the vehicle is in an automated driving state if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match; if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means match, then the determination is made again using a different automated driving or manual driving characteristic model; if the motion characteristics of the automated driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match, and the motion characteristics of the manual driving characteristic model and the motion characteristics detected by the motion characteristics detection means do not match, then the vehicle is in a manual driving state. An information processing system that determines that the vehicle is in a manual driving state if the motion characteristics of the automated driving characteristic model do not match the motion characteristics detected by the motion characteristic detection means, and the motion characteristics of the manual driving characteristic model match the motion characteristics detected by the motion characteristic detection means.

7. An information processing system according to claim 2, wherein the model acquisition means generates a driving characteristic model that associates a plurality of vehicle types with the motion characteristics exhibited by each vehicle type during autonomous driving.

8. An information processing system according to claim 1, wherein the vehicle type is classified by the size of the vehicle, the use of the vehicle, the drive system of the vehicle, or the type of occupants riding in the vehicle.

9. An information processing method comprising: identifying the type of vehicle being driven; detecting the motion characteristics of the identified vehicle being driven; and determining whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the identified vehicle being driven during automated driving with the detected motion characteristics.

10. A program that causes a computer to perform the following steps: identify the type of vehicle being driven; detect the motion characteristics of the identified vehicle being driven; and determine whether the vehicle is in an automated driving state or a manual driving state by comparing predetermined motion characteristics exhibited by the identified vehicle being driven during automated driving with the detected motion characteristics.

Images