Information processing method and information processing device

Abstract

To provide an information processing method which can improve performance of autonomous mobile.SOLUTION: An information processing method acquires a first processing result by executing first preprocessing as preprocessing of travel control processing in autonomous driving of an autonomous mobile object on the basis of sensing data acquired by the autonomous mobile object, outputs the sensing data to an external device, acquires a second processing result obtained by executing second preprocessing as preprocessing advanced more than the first preprocessing on the basis of the sensing data from the external device, restricts travel of the autonomous mobile object when there is communication delay between the autonomous mobile object and the external device or when there is processing delay in the second preprocessing, and performs travel control of the autonomous mobile object on the basis of the first processing result or a third processing result when there is no communication delay between the autonomous mobile object and the external device or when there is no processing delay in the second preprocessing, in which the third processing result is the second processing result or obtained by correcting the first processing result.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present disclosure relates to an information processing method and an information processing apparatus for autonomous movement of an autonomous mobile body.

Background Art

[0002] Regarding the automatic driving system of an autonomous vehicle, it is desired to multiplex hardware or software in order to improve safety. For example, in Patent Documents 1 and 2, techniques for improving safety by multiplexing systems such as power supplies, detection functions, and control functions in an autonomous vehicle have been proposed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, from the viewpoints of cost, power consumption, space, etc., there are limitations on the computers that can be mounted on an autonomous mobile body such as an autonomous vehicle, and the performance of the autonomous movement system mounted on the autonomous mobile body may be low. For this reason, in the methods disclosed in Patent Documents 1 and 2 above, although the safety of autonomous movement can be improved by multiplexing the hardware or software mounted on the autonomous mobile body, the performance of autonomous movement may be insufficient.

[0005] Therefore, the present disclosure provides an information processing method and the like that can improve the performance of autonomous movement.

Means for Solving the Problems

[0006] The information processing method according to the present disclosure is an information processing method to be executed by an information processing device mounted on an autonomous mobile body. The autonomous mobile body executes a first preprocessing which is a preprocessing of a driving control process in the autonomous driving of the autonomous mobile body based on sensing data acquired by the autonomous mobile body to obtain a first processing result, outputs the sensing data to an external device, and acquires a second processing result obtained by executing a second preprocessing which is a preprocessing more advanced than the first preprocessing based on the sensing data from the external device. Here, the second preprocessing is executed by the external device connected to the autonomous mobile body via a network and having a higher processing ability than the information processing device. When there is a communication delay between the autonomous mobile body and the external device, or when there is a processing delay in the second preprocessing, the running of the autonomous mobile body is restricted. When there is no communication delay between the autonomous mobile body and the external device, or when there is no processing delay in the second preprocessing, the driving control of the autonomous mobile body is performed based on the first processing result or the third processing result. The third processing result is the second processing result, or a processing result obtained by correcting the first processing result.

[0007] Note that these general or specific aspects may be implemented by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, or may be implemented by any combination of a system, a method, an integrated circuit, a computer program, and a recording medium.

Advantages of the Invention

[0008] According to the information processing method and the like according to one aspect of the present disclosure, the performance of autonomous movement can be improved.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0010] An information processing method according to an aspect of the present disclosure is an information processing method to be executed by a computer, and includes acquiring, from the autonomous mobile body, a first processing result that is a result of a first preprocessing that is a preprocessing of a running control process in the autonomous movement process of the autonomous mobile body and sensing data acquired by the autonomous mobile body, executing a second preprocessing that is a preprocessing more advanced than the first preprocessing based on the sensing data to obtain a second processing result, determining a difference between the first processing result and the second processing result, and outputting to the autonomous mobile body a change instruction to change the first processing result to a third processing result according to the determined difference, where the third processing result is obtained based on at least one of the first processing result or the second processing result.

[0011] Separate from the first preprocessing executed in an autonomous vehicle or the like with limited computer mounting from the viewpoints of cost, power consumption, space, etc., second preprocessing more advanced than the first preprocessing is executed on a server or the like with fewer restrictions on cost, power consumption, space, etc., and the difference between the first processing result that is the result of the first preprocessing and the second processing result that is the result of the second preprocessing is determined. Then, according to the difference, a change instruction is output to the autonomous vehicle to change the first processing result that is the result of the first preprocessing, which is the preprocessing of the driving control process of the autonomous vehicle, to a third processing result based on the second processing result that is the result of the above-mentioned advanced second preprocessing. Alternatively, according to the difference, a change instruction is output to the autonomous vehicle to change the first processing result to a third processing result obtained by correcting or restricting the first processing result. Thereby, since a third processing result more advanced than the first processing result is used for the driving control process of the autonomous vehicle, the performance of autonomous driving can be improved.

[0012] Also, the first preprocessing is executed using a first resource, the second preprocessing is executed using a second resource, and the first resource and the second resource may be different resources.

[0013] In this way, the second preprocessing more advanced than the first preprocessing may be executed using a second resource different from the first resource used for the execution of the first preprocessing. Therefore, the second preprocessing can process with higher precision, higher speed, or lower latency than the first preprocessing.

[0014] Also, the first preprocessing is executed using a first algorithm, the second preprocessing is executed using a second algorithm, and the first algorithm and the second algorithm may be different algorithms.

[0015] In this way, the second preprocessing more advanced than the first preprocessing may be executed using a second algorithm different from the first algorithm used for the execution of the first preprocessing. Therefore, the second preprocessing can perform processing with higher precision, higher speed, lower latency, or more functions than the first preprocessing.

[0016] Further, the first preprocessing and the second preprocessing may include a recognition process for recognizing the environment in which the autonomous mobile body is placed.

[0017] In this way, each preprocessing may include a recognition process, and the result of the recognition process may be used in the travel control process of the autonomous mobile body. Therefore, the safety or comfort of the autonomous mobile body can be improved.

[0018] Further, the first preprocessing and the second preprocessing may include a travel determination process of the autonomous mobile body.

[0019] In this way, each preprocessing may include a travel determination process of the autonomous mobile body, and the result of the travel determination process of the autonomous mobile body may be used in the travel control process of the autonomous mobile body. Therefore, the safety or comfort of the autonomous mobile body can be improved.

[0020] Further, the third processing result may be the second processing result.

[0021] According to this, since the second processing result, which is the result of the second preprocessing more advanced than the first preprocessing, is used in the travel control process of the autonomous mobile body, the performance of autonomous travel can be improved.

[0022] Further, the third processing result may be obtained by correcting the first processing result based on the difference.

[0023] According to this, since the third processing result obtained by correcting the first processing result based on the difference between the second processing result, which is the result of the second preprocessing more advanced than the first preprocessing, and the first processing result is used for the travel control of the autonomous mobile body, the performance of autonomous travel can be improved.

[0024] Further, when a request for execution of the second preprocessing is received from the autonomous mobile body, the second preprocessing may be executed to obtain a second processing result, and the change instruction may be output to the autonomous mobile body as a response to the request.

[0025] According to this, for example, at the timing when the autonomous mobile body requests the execution of advanced second preprocessing, the second preprocessing can be executed.

[0026] Further, the request may include information specifying a specific process among the second preprocessing, and the second processing result may be obtained by executing the specific process.

[0027] According to this, for example, a specific process desired by the autonomous mobile body, which is specified from among the second preprocessing, can be selectively executed.

[0028] Also, when the request is received, it may be determined whether to execute the second preprocessing, and if it is determined not to execute the second preprocessing, the request may be rejected or ignored. For example, the determination of whether to execute the second preprocessing may be made based on at least one of the resources of the autonomous mobile body, the moving state of the autonomous mobile body, the external environment of the autonomous mobile body, the time, and the response time to the request.

[0029] When the request is received, there may be cases where the performance of autonomous movement cannot be improved even if the second preprocessing is executed depending on the situation. For example, depending on the resources of the autonomous mobile body, the moving state of the autonomous mobile body, the external environment of the autonomous mobile body, the time, or the response time to the request, there may be cases where the performance of autonomous movement cannot be improved even if the second preprocessing is executed and the driving control process of the autonomous mobile body is performed using the third processing result. In such cases, the request can be rejected or ignored.

[0030] An information processing system according to an aspect of the present disclosure is an information processing system capable of communicating with an autonomous mobile body, obtaining a first processing result that is a result of a first preprocessing which is a preprocessing of a travel control process in autonomous travel of the autonomous mobile body, and sensing data acquired by the autonomous mobile body from the autonomous mobile body, executing a second preprocessing which is a preprocessing more advanced than the first preprocessing based on the sensing data to obtain a second processing result, determining a difference between the first processing result and the second processing result, and outputting to the autonomous mobile body a change instruction to change the first processing result to a third processing result according to the determined difference, wherein the third processing result is obtained based on at least one of the first processing result or the second processing result.

[0031] According to this, an information processing system capable of improving the performance of autonomous travel can be provided.

[0032] An information processing device according to an aspect of the present disclosure is an information processing device mounted on an autonomous mobile body, executing a first preprocessing which is a preprocessing of a travel control process in autonomous driving of the autonomous mobile body to obtain a first processing result, outputting sensing data acquired by the autonomous mobile body to an external device, obtaining a second processing result obtained by executing a second preprocessing which is a preprocessing more advanced than the first preprocessing based on the sensing data from the external device, determining a difference between the first processing result and the second processing result, changing the first processing result to a third processing result according to the determined difference, and the third processing result is obtained based on at least one of the first processing result or the second processing result.

[0033] For example, separately from the first preprocessing executed in an autonomous mobile body such as an autonomous vehicle that has restrictions on the computers that can be mounted from the viewpoints of cost, power consumption, space, etc., a second preprocessing that is more advanced than the first preprocessing is executed by an external device such as a server with fewer restrictions on cost, power consumption, space, etc., and a second processing result that is the result of the second preprocessing is transmitted to the autonomous vehicle. A difference between the first processing result that is the result of the first preprocessing and the second processing result that is the result of the second preprocessing is determined in the autonomous vehicle. Then, according to the difference, the first processing result that is the result of the first preprocessing, which is the preprocessing of the driving control process of the autonomous mobile body, is changed to a third processing result based on the second processing result that is the result of the above-mentioned advanced second preprocessing. Alternatively, according to the difference, the first processing result is changed to a third processing result obtained by correcting or restricting the first processing result. Thereby, since a third processing result that is more advanced than the first processing result is used for the driving control process of the autonomous mobile body, the performance of autonomous movement can be improved.

[0034] Further, a request for execution of the second preprocessing may be output to the external device, and the second processing result may be acquired as a response to the request.

[0035] According to this, for example, at the timing when the autonomous mobile body desires to execute the advanced second preprocessing, the external device can be made to execute the second preprocessing.

[0036] Further, the request may be output to the external device based on at least one of the resources of the autonomous mobile body, the moving state of the autonomous mobile body, the external environment of the autonomous mobile body, the time, and the response time to an inquiry to the external device.

[0037] Depending on the situation, there may be cases where the performance of autonomous movement cannot be improved even if the second preprocessing is executed. For example, depending on the resources of the autonomous mobile body, the movement state of the autonomous mobile body, the external environment of the autonomous mobile body, the time, or the response time to a request, even if the second preprocessing is executed and the driving control process of the autonomous mobile body is performed using the third processing result, the performance of autonomous movement may not be improved. In such a case, it is possible not to output a request. In other words, depending on the situation, the performance of autonomous movement may be improved by executing the second preprocessing. When such a situation where the performance of autonomous movement can be improved occurs, a request can be output.

[0038] Further, the request may include information specifying a specific process among the second preprocessings, and the second processing result may be a result obtained by executing the specific process.

[0039] According to this, for example, a specific process desired by the autonomous mobile body can be specified from among the second preprocessings, and the external device can be selectively made to execute the specific process.

[0040] Also, when the second processing result is acquired after a lapse of a predetermined time or more from the output of the sensing data or the output of the request, (A) the determination of the difference may not be executed, or (B) the difference between some of the first processing results and the processing results corresponding to the some of the second processing results may be determined, and the some of the first processing results may be changed to the third processing result according to the determined difference.

[0041] According to this, when the second processing result is acquired after a lapse of a predetermined time or more from the output of the sensing data or the output of the request, there may be a communication delay with an external device. In such a case, by not executing the determination of the difference or by executing the determination of the difference only for some of the processing results that are not affected by the delay, the processing load on the information processing apparatus can be reduced.

[0042] Hereinafter, embodiments will be specifically described with reference to the drawings.

[0043] Note that all of the embodiments described below show comprehensive or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection forms of the components, steps, order of steps, etc. shown in the following embodiments are merely examples and are not intended to limit the present disclosure.

[0044] (Embodiment 1) Embodiment 1 will be described with reference to FIGS. 1 to 3.

[0045] FIG. 1 is a block diagram showing an example of an autonomous vehicle (specifically, an information processing device 20 mounted on the autonomous vehicle) and a remote autonomous driving server 10 according to Embodiment 1.

[0046] An autonomous vehicle is, for example, a vehicle that can travel automatically without a human performing a driving operation. The autonomous vehicle is equipped with sensors such as a camera, a thermograph, a radar, LiDAR (Light Detection and Ranging), a sonar, a GPS (Global Positioning System), or an IMU (Inertial Measurement Unit), and can recognize the surrounding environment and so on with these and travel autonomously. Note that the autonomous vehicle is an example of an autonomous mobile body. The autonomous mobile body may be a mobile robot, a flying body such as a drone, or a ship.

[0047] The remote autonomous driving server 10 can perform wireless communication with the autonomous vehicle and remotely control the autonomous driving of the autonomous vehicle. Note that autonomous driving is an example of autonomous movement.

[0048] The autonomous vehicle is equipped with an information processing device 20. The information processing device 20 is a computer including a processor, a memory, a communication interface, etc. The memory is such as a ROM (Read Only Memory) and a RAM (Random Access Memory), and can store programs executed by the processor. The information processing device 20 includes a sensing data acquisition unit 21, a sensing data transmission unit 22, a vehicle automatic driving system 23, a first processing result transmission unit 24, a processing result change unit 25, a communication confirmation unit 26, and a driving restriction unit 27. The sensing data acquisition unit 21, the sensing data transmission unit 22, the vehicle automatic driving system 23, the first processing result transmission unit 24, the processing result change unit 25, the communication confirmation unit 26, and the driving restriction unit 27 are realized by a processor or the like that executes a program stored in the memory.

[0049] The sensing data acquisition unit 21 acquires sensing data from sensors such as cameras, thermographs, radars, LiDARs, sonars, GPSs, or IMUs provided in the autonomous vehicle. Note that the sensing data acquisition unit 21 may acquire sensing data from sensors installed in other vehicles or traffic signals.

[0050] The sensing data transmission unit 22 transmits the sensing data acquired by the sensing data acquisition unit 21 to the remote automatic driving server 10. The sensing data transmission unit 22 transmits the sensing data to the remote automatic driving server 10 via, for example, a communication interface provided in the information processing device 20. The sensing data transmission unit 22 can transmit the sensing data with low latency by using, for example, data compression technology and high-speed transmission technology such as 5G.

[0051] The vehicle automatic driving system 23 executes a first preprocessing, which is a preprocessing of the driving control process in the automatic driving process of the autonomous vehicle, based on the sensing data acquired by the sensing data acquisition unit 21, and obtains a first processing result. The first processing result is the result of the first preprocessing. For example, the preprocessing includes a recognition process or a driving determination process of the autonomous vehicle. The recognition process includes a process of recognizing the environment in which the autonomous vehicle is placed. The environment includes the self-position, surrounding objects, road surface conditions, weather, or road conditions, etc. Specifically, the preprocessing includes a process of estimating the self-position of the autonomous vehicle, a process of detecting the objects around the autonomous vehicle, a process of predicting the movement of the objects around the autonomous vehicle, a driving determination process of the autonomous vehicle, or a route planning process of the autonomous vehicle, etc. For example, the vehicle automatic driving system 23 may perform these processes using a learning model. For example, the processing result includes a recognition result or a driving determination result of the autonomous vehicle. Specifically, the processing result includes an estimation result of the self-position of the autonomous vehicle, a detection result of the objects around the autonomous vehicle, a movement prediction result of the objects around the autonomous vehicle, a driving determination result of the autonomous vehicle, or a route planning result of the autonomous vehicle, etc.

[0052] The first processing result transmission unit 24 transmits the first processing result, which is the result of the first preprocessing executed by the vehicle automatic driving system 23, to the remote automatic driving server 10. The first processing result transmission unit 24 transmits the first processing result to the remote automatic driving server 10 via, for example, a communication interface provided in the information processing device 20.

[0053] Note that the sensing data transmission unit 22 may transmit only the sensing data used when the vehicle automatic driving system 23 executes the first preprocessing, or may transmit not only the sensing data used when the vehicle automatic driving system 23 executes the first preprocessing but also the sensing data not used when executing the first preprocessing (for example, sensing data with high resolution that the vehicle automatic driving system 23 could not handle).

[0054] The processing result changing unit 25 changes the first processing result to the third processing result based on the change instruction received from the remote automatic driving server 10. That is, when the first processing result is changed to the third processing result by the processing result changing unit 25, the third processing result is used instead of the first processing result that should have been originally used for the driving control of the autonomous vehicle.

[0055] The communication confirmation unit 26 checks the communication state of the wireless communication between the autonomous vehicle and the remote automatic driving server 10. For example, the communication confirmation unit 26 sends an inquiry to the remote automatic driving server 10 via a communication interface or the like provided in the information processing device 20, and checks the communication state according to the response to the inquiry. Specifically, when there is no response to the inquiry, the communication confirmation unit 26 can determine that the communication is not connected, and when there is a delay in the response to the inquiry, the communication confirmation unit 26 can determine that a communication delay has occurred. When the communication confirmation unit 26 determines that the communication is not connected or that a communication delay has occurred, it notifies the driving restriction unit 27 of a driving restriction instruction to restrict the driving.

[0056] The driving restriction unit 27 restricts the driving of the autonomous vehicle based on the driving restriction instruction. Specifically, the driving restriction unit 27 decelerates the autonomous vehicle, stops it, or expands the avoidance margin. Thereby, safety can be ensured in the autonomous vehicle even when the communication between the autonomous vehicle and the remote automatic driving server 10 is interrupted.

[0057] The remote automatic driving server 10 is a computer including a processor, a memory, a communication interface, etc. The remote automatic driving server 10 is an example of an information processing system capable of wireless communication with an autonomous vehicle. The memory is such as a ROM and a RAM, and can store programs executed by the processor. The remote automatic driving server 10 includes a sensing data acquisition unit 11, a pseudo-automatic driving system 12, a first processing result acquisition unit 13, a difference determination unit 14, and a change instruction output unit 15. The sensing data acquisition unit 11, the pseudo-automatic driving system 12, the first processing result acquisition unit 13, the difference determination unit 14, and the change instruction output unit 15 are realized by a processor or the like that executes a program stored in the memory. Note that the components constituting the remote automatic driving server 10 may be distributed and arranged in a plurality of servers.

[0058] The sensing data acquisition unit 11 acquires sensing data acquired by the autonomous vehicle from the autonomous vehicle. For example, the sensing data acquisition unit 11 acquires sensing data transmitted from the autonomous vehicle and received via a communication interface or the like provided in the remote automatic driving server 10.

[0059] The pseudo-automatic driving system 12 executes a second preprocessing, which is a preprocessing of the driving control process in the automatic driving of the autonomous vehicle, based on the sensing data acquired by the sensing data acquisition unit 11, and acquires a second processing result. The second preprocessing is a more advanced preprocessing than the first preprocessing. For example, the pseudo-automatic driving system 12 may perform the second preprocessing using a learning model. The second processing result is the result of the second preprocessing.

[0060] For example, there are limitations on the computers that can be installed in an autonomous vehicle from the perspectives of cost, power consumption, space, etc. Therefore, the resources used in the vehicle autonomous driving system 23 are reduced or the algorithms are low-computationally quantified. Here, the resources are the processing capacity or speed of the processor, the memory capacity, or the power, etc. On the other hand, the remote autonomous driving server 10 has fewer limitations in terms of cost, power consumption, space, etc. Therefore, the resources used in the virtual autonomous driving system 12 can be increased or the algorithms can be high-computationally quantified. Thus, the second preprocessing executed by the remote autonomous driving server 10 can be made more advanced than the first preprocessing executed by the information processing device 20 installed in the autonomous vehicle. For example, the first preprocessing is executed using the first resources (for example, small resources in the autonomous vehicle), and the second preprocessing is executed using the second resources different from the first resources (for example, large resources in the remote autonomous driving server 10), so that the second preprocessing can be made more advanced than the first preprocessing. That is, the second resources are richer than the first resources. Also, for example, the first preprocessing is executed using the first algorithm (for example, an algorithm with a small amount of computation that can be handled in the autonomous vehicle), and the second preprocessing is executed using the second algorithm different from the first algorithm (for example, an algorithm with a large amount of computation that can be handled in the remote autonomous driving server 10), so that the second preprocessing can be made more advanced than the first preprocessing. That is, the second algorithm is more advanced than the first algorithm. Note that the first preprocessing may be executed using both the first resources and the first algorithm, and the second preprocessing may be executed using both the second resources and the second algorithm.

[0061] The first processing result acquisition unit 13 acquires the first processing result from the autonomous vehicle. For example, the first processing result acquisition unit 13 acquires the first processing result transmitted from the autonomous vehicle and received via a communication interface or the like provided in the remote autonomous driving server 10.

[0062] The difference determination unit 14 determines the difference between the first processing result acquired by the first processing result acquisition unit 13 and the second processing result acquired by the pseudo-automatic driving system 12. Details of the operation of the difference determination unit 14 will be described later.

[0063] The change instruction output unit 15 outputs a change instruction to the autonomous vehicle to change the first processing result to a third processing result according to the difference determined by the difference determination unit 14. That is, by instructing the autonomous vehicle through the change instruction output unit 15 to change the first processing result to the third processing result, the third processing result is used instead of the first processing result that should originally be used for the driving control of the autonomous vehicle. Specific examples of the third processing result will be described later.

[0064] Next, the operation of the remote automatic driving server 10 will be described with reference to FIG. 2.

[0065] FIG. 2 is a flowchart showing an example of the information processing method according to the first embodiment. For example, the information processing method according to the first embodiment is a method executed by a computer (specifically, a processor) provided in the remote automatic driving server 10. Therefore, FIG. 2 is also a flowchart showing the operation of the remote automatic driving server 10.

[0066] First, the remote automatic driving server 10 acquires from the autonomous vehicle a first processing result that is the result of a first preprocessing, which is a preprocessing of a driving control process in the automatic driving process of the autonomous vehicle, and sensing data acquired by the autonomous vehicle (step S11). For example, the remote automatic driving server 10 acquires the detection processing result obtained by the autonomous vehicle performing a detection process of obstacles around the autonomous vehicle (for example, detection of the number of obstacles or detection of the position of obstacles) from the sensing data. Also, for example, the remote automatic driving server 10 acquires the estimation processing result obtained by the autonomous vehicle performing an estimation process of the position of the autonomous vehicle from the sensing data. Also, for example, the remote automatic driving server 10 acquires the driving determination processing result obtained by the autonomous vehicle performing a driving determination process (for example, determination of whether to continue driving or stop) from the sensing data.

[0067] Next, the remote automatic driving server 10 executes a second preprocessing, which is a preprocessing more advanced than the first preprocessing, based on the sensing data to obtain a second processing result (step S12). For example, the remote automatic driving server 10 performs a detection process of obstacles around the automatic driving vehicle (for example, detection of the number of obstacles or detection of the position of obstacles, etc.) from the sensing data to obtain the detection process result. Also, for example, the remote automatic driving server 10 performs an estimation process of the position of the automatic driving vehicle from the sensing data to obtain the estimation process result. Also, for example, the remote automatic driving server 10 performs a running determination process of the automatic driving vehicle (for example, determination of whether to continue running or stop, etc.) from the sensing data to obtain the running determination process result.

[0068] Next, the remote automatic driving server 10 determines whether there is a processing delay in the second preprocessing (step S13). For example, in the remote automatic driving server 10, the occupancy rate of resources for the second preprocessing may be high and a processing delay may occur in the second preprocessing.

[0069] When there is a processing delay in the second preprocessing (Yes in step S13), the remote automatic driving server 10 outputs an instruction to limit the driving of the autonomous vehicle (step S14). For example, the driving control of the autonomous vehicle should be performed with as little delay as possible from the timing when the sensing data is acquired. If it takes a long time to perform the driving control using the result of the preprocessing after the sensing data is acquired, the autonomous vehicle will move significantly from the point where the sensing data was acquired, and the result of the preprocessing executed based on the sensing data may become invalid at the current position of the autonomous vehicle that has deviated from the point where the sensing data was acquired. Therefore, when there is a processing delay in the second preprocessing, the autonomous vehicle cannot effectively utilize the result of the advanced second preprocessing by the remote automatic driving server 10, and there is a risk that the autonomous vehicle will be in a dangerous state. Thus, the remote automatic driving server 10 outputs an instruction to limit the driving of the autonomous vehicle to the autonomous vehicle. The instruction to limit the driving of the autonomous vehicle is, for example, an instruction to decelerate the autonomous vehicle, stop it, or expand the avoidance margin. Note that the remote automatic driving server 10 may notify the autonomous vehicle of an alert when there is a processing delay in the second preprocessing.

[0070] When there is no processing delay in the second preprocessing (No in step S13), the remote automatic driving server 10 determines the difference between the first processing result and the second processing result (step S15). For example, the remote automatic driving server 10 determines the difference between the number of obstacles indicated by the first processing result and the number of obstacles indicated by the second processing result. Also, for example, the remote automatic driving server 10 determines the difference between the positions of the obstacles indicated by the first processing result and the positions of the obstacles indicated by the second processing result (for example, the RMS (Root Mean Square) error value of the positions of the obstacles indicated by the first processing result when the positions of the obstacles indicated by the second processing result are correct). Also, for example, the remote automatic driving server 10 determines the difference between the position of the automatic driving vehicle indicated by the first processing result and the position of the automatic driving vehicle indicated by the second processing result (for example, the RMS error value of the position of the automatic driving vehicle indicated by the first processing result when the position of the automatic driving vehicle indicated by the second processing result is correct). Also, for example, the remote automatic driving server 10 determines the difference between the driving judgment processing result of the automatic driving vehicle indicated by the first processing result and the driving judgment processing result of the automatic driving vehicle indicated by the second processing result (for example, the number of times the driving judgment processing results indicated by the first processing result and the second processing result are different within a certain period). Note that these are only examples of the determination of the difference and are not limited thereto.

[0071] Next, the remote automatic driving server 10 determines whether the determined difference satisfies a predetermined condition (step S16). The predetermined condition is, for example, a condition regarding the magnitude of the determined difference. For example, the remote automatic driving server 10 determines whether the number of obstacles indicated by the first processing result is different from the number of obstacles indicated by the second processing result. Also, for example, the remote automatic driving server 10 determines whether the RMS error value is equal to or greater than a predetermined threshold. Also, for example, the remote automatic driving server 10 determines whether the number of times the driving judgment processing results indicated by the first processing result and the second processing result are different within a certain period is equal to or greater than a predetermined threshold. Note that these are only examples of the predetermined condition and are not limited thereto.

[0072] When the determined difference satisfies a predetermined condition (Yes in step S16), the remote automatic driving server 10 outputs a change instruction to change the first processing result to the third processing result to the automatic driving vehicle (step S17). The case where the determined difference satisfies a predetermined condition means, for example, when the number of obstacles indicated by the first processing result is different from the number of obstacles indicated by the second processing result, when the RMS error value is equal to or greater than a predetermined threshold value, or when the number of times the running determination processing result indicated by the first processing result and the running determination processing result indicated by the second processing result are different within a certain period is equal to or greater than a predetermined threshold value, etc.

[0073] The third processing result is obtained based on at least one of the first processing result and the second processing result. Since the second processing result is the result of advanced second preprocessing, the third processing result, which is the result of processing based on the second processing result, is an advanced processing result. For example, the third processing result may be the second processing result. As a result, the first processing result is not used for the driving control of the automatic driving vehicle, and the second processing result, which is the result of advanced second preprocessing, is used for the driving control of the automatic driving vehicle, thereby improving the performance of the automatic driving. Also, for example, the third processing result may be obtained by correcting the first processing result based on the determined difference. For example, only the necessary range or the processable range of the first processing result is corrected based on the difference between the second processing result and the first processing result. As a result, the first processing result is not used for the driving control of the automatic driving vehicle, and the first processing result corrected based on the difference between the second processing result, which is the result of advanced second preprocessing, and the first processing result (that is, the corrected first processing result) is used for the driving control of the automatic driving vehicle, thereby improving the performance of the automatic driving.

[0074] Note that when the determined difference satisfies a predetermined condition (Yes in step S16), the remote automatic driving server 10 may output an instruction to limit the running of the automatic driving vehicle. Also, in this case, the remote automatic driving server 10 may notify an abnormality to a remote monitor or a passenger of the automatic driving vehicle, etc.

[0075] When the determined difference does not meet the predetermined conditions (No in step S16), the remote automatic driving server 10 does not output the above change instruction to the autonomous vehicle (step S18). When the determined difference does not meet the predetermined conditions, for example, when the number of obstacles indicated by the first processing result is the same as the number of obstacles indicated by the second processing result, when the RMS error value is less than a predetermined threshold value, or when the number of times the driving determination processing result indicated by the first processing result and the driving determination processing result indicated by the second processing result are different within a certain period is less than a predetermined threshold value, etc. In this case, for example, the first processing result is not inferior to the second processing result, and the autonomous vehicle can perform the driving control of the autonomous vehicle using the first processing result that is not inferior to the second processing result without receiving a change instruction. In other words, after it is confirmed that the first processing result is not inferior to the second processing result or the degree of deterioration of the first processing result with respect to the second processing result is within the allowable range, the first processing result can be used for the driving control of the autonomous vehicle.

[0076] In addition, when the autonomous vehicle receives a change instruction with a delay due to communication delay, it may ignore the received change instruction and restrict the driving of the autonomous vehicle. Similar to the case where there is a processing delay in the second preprocessing described above, the autonomous vehicle cannot effectively utilize the third processing result even if the first processing result is changed to the third processing result, because the autonomous vehicle may be in a dangerous state.

[0077] In addition, the sensing data obtained by the autonomous vehicle is easily affected by the weather, and there may be cases where correct first processing results cannot be obtained even if the vehicle automatic driving system 23 executes the first preprocessing using the sensing data affected by the weather. For example, when the weather is rainy or cloudy, etc., and the visibility around the autonomous vehicle is poor, there may be a risk that the obstacles existing around the autonomous vehicle cannot be correctly recognized. Therefore, it may be determined whether the weather is suitable for autonomous driving by the vehicle automatic driving system 23. This will be described with reference to FIG. 3.

[0078] FIG. 3 is a flowchart showing another example of the information processing method according to the first embodiment.

[0079] The flowchart shown in FIG. 3 is different from the flowchart shown in FIG. 2 in that step S19 is added. Since the other points (i.e., steps S11 to S18) are the same as those shown in FIG. 2, the description thereof is omitted.

[0080] When there is no processing delay in the second preprocessing (No in step S13), the remote automatic driving server 10 determines whether the weather is suitable for automatic driving by the vehicle automatic driving system 23 (step S19). For example, when the weather is sunny, it is determined that the weather is suitable for automatic driving by the vehicle automatic driving system 23, and when the weather is rainy or cloudy, it is determined that the weather is not suitable for automatic driving by the vehicle automatic driving system 23.

[0081] When the weather is not suitable for automatic driving by the vehicle automatic driving system 23 (No in step S19), the remote automatic driving server 10 outputs a change instruction without performing the determination process of the difference between the first processing result and the second processing result in step S15 (step S17). This is because when the weather is not suitable for automatic driving by the vehicle automatic driving system 23, it is assumed that the first processing result will be inferior to the second processing result even without specifically performing the difference determination.

[0082] When the weather is suitable for automatic driving by the vehicle automatic driving system 23 (Yes in step S19), the processing after step S15 is performed in the same manner as the description in FIG. 2. When the weather is suitable for automatic driving by the vehicle automatic driving system 23, there is a possibility that the first processing result will not be inferior to the second processing result, so it is better to determine whether to perform the difference determination and output a change instruction.

[0083] In this way, it may be determined whether the weather is suitable for automatic driving by the vehicle automatic driving system 23.

[0084] As described above, separately from the first preprocessing executed in an autonomous vehicle (specifically, the information processing device 20 mounted on the autonomous vehicle) that has limitations on the computers that can be mounted from the viewpoints of cost, power consumption, space, etc., a second preprocessing that is more advanced than the first preprocessing is executed on the remote autonomous driving server 10 with fewer limitations on cost, power consumption, space, etc. The difference between the first processing result that is the result of the first preprocessing and the second processing result that is the result of the second preprocessing is determined. Then, according to the difference, a change instruction is output to the autonomous vehicle to change the first processing result that is the result of the first preprocessing, which is the preprocessing of the driving control process of the autonomous vehicle, to a third processing result based on the second processing result that is the result of the above-mentioned advanced second preprocessing. Alternatively, according to the difference, a change instruction is output to the autonomous vehicle to change the first processing result to a third processing result obtained by correcting or restricting the first processing result. As a result, since a third processing result that is more advanced than the first processing result is used for the driving control process of the autonomous vehicle, the performance of autonomous driving can be improved. For example, by improving the performance of autonomous driving, the drivable area of the autonomous vehicle can be expanded.

[0085] (Modification Example of Embodiment 1) For example, the execution of the second preprocessing on the remote autonomous driving server etc. may be started when there is a request from the autonomous vehicle. This will be described as a modification example of Embodiment 1 with reference to FIGS. 4 and 5.

[0086] FIG. 4 is a block diagram showing an example of an autonomous vehicle (specifically, the information processing device 20a mounted on the autonomous vehicle), a remote autonomous driving server 10a, and a remote processing management server 30 according to a modification example of Embodiment 1.

[0087] The information processing apparatus 20a further includes a remote processing request unit 28, and is different from the information processing apparatus 20 in the first embodiment in that it includes a sensing data acquisition unit 21a, a sensing data transmission unit 22a, and a first processing result transmission unit 24a instead of the sensing data acquisition unit 21, the sensing data transmission unit 22, and the first processing result transmission unit 24. Other points are the same as those in the information processing apparatus 20, and thus the description thereof is omitted. Note that the remote processing request unit 28 is realized by a processor or the like that executes a program stored in a memory in the same manner as other components.

[0088] The remote processing request unit 28 outputs a request for executing the second preprocessing to the remote automatic driving server 10a via the remote processing management server 30. For example, when there are a plurality of remote automatic driving servers 10a having a function of executing the second preprocessing, the remote processing management unit 31 of the remote processing management server 30, when receiving the above request, inquires of the plurality of remote automatic driving servers 10a whether they can execute the second preprocessing, and selects a remote automatic driving server 10a capable of executing the second preprocessing from among the plurality of remote automatic driving servers 10a according to the result of the inquiry. The remote processing management unit 31 notifies the selected remote automatic driving server 10a to the autonomous vehicle. The remote processing request unit 28 instructs the sensing data acquisition unit 21a to acquire sensing data, instructs the sensing data transmission unit 22a to transmit the sensing data to the selected remote automatic driving server 10a, and instructs the first processing result transmission unit 24a to transmit the first processing result to the selected remote automatic driving server 10a.

[0089] The sensing data acquisition unit 21a acquires sensing data by sensors provided in the autonomous vehicle upon receiving an instruction from the remote processing request unit 28. Other points regarding the sensing data acquisition unit 21a are the same as those of the sensing data acquisition unit 21, and thus the description thereof is omitted.

[0090] The sensing data transmission unit 22a transmits the sensing data acquired by the sensing data acquisition unit 21a to the selected remote automatic driving server 10a. Other aspects regarding the sensing data transmission unit 22a are the same as those of the sensing data transmission unit 22, and thus the description thereof is omitted.

[0091] The first processing result transmission unit 24a transmits the first processing result, which is the result of the first preprocessing executed by the vehicle automatic driving system 23a, to the selected remote automatic driving server 10a. Other aspects regarding the first processing result transmission unit 24a are the same as those of the first processing result transmission unit 24, and thus the description thereof is omitted.

[0092] The remote automatic driving server 10a further includes a request acquisition unit 16 and a second preprocessing execution determination unit 17, and is different from the remote automatic driving server 10 in the first embodiment in that it includes a sensing data acquisition unit 11a and a pseudo-automatic driving system 12a instead of the sensing data acquisition unit 11 and the pseudo-automatic driving system 12. Other aspects are the same as those of the remote automatic driving server 10, and thus the description thereof is omitted. Note that the request acquisition unit 16 and the second preprocessing execution determination unit 17 are realized by a processor or the like that executes a program stored in a memory in the same manner as other components.

[0093] The request acquisition unit 16 acquires a request for execution of the second preprocessing from the autonomous vehicle. For example, the request acquisition unit 16 acquires a request for execution of the second preprocessing from the autonomous vehicle via the remote processing management server 30.

[0094] When the second preprocessing execution determination unit 17 receives a request, it determines whether to execute the second preprocessing. For example, the second preprocessing execution determination unit 17 may determine whether to execute the second preprocessing based on the task status or resource status of the remote automatic driving server 10a. For example, when many tasks are being executed in the remote automatic driving server 10a or the resources are scarce, it is determined not to execute the second preprocessing. Also, for example, the second preprocessing execution determination unit 17 may make a determination on whether to execute the second preprocessing based on at least one of the resources of the autonomous vehicle, the moving state of the autonomous vehicle, the external environment of the autonomous vehicle, the time, and the response time to the request. The moving state is the moving speed, acceleration, deceleration, moving direction (steering angle), etc. of the autonomous vehicle. For example, when the resources of the autonomous vehicle are insufficient, when the moving state of the autonomous vehicle is, for example, a state of high vehicle speed, a state of large acceleration, or a state of large steering angle, when the external environment of the autonomous vehicle is an environment where the position of obstacles is close, an environment with a large number, or an environment where the type is a moving object, when the position of the autonomous vehicle is in a place with heavy traffic (for example, an intersection, etc.), an environment with low surrounding brightness, an environment with rainy or cloudy weather, etc., when the time is night time, when the response time to the request is short, etc., it is determined to execute the second preprocessing. Also, for example, when the resources of the autonomous vehicle are sufficient, when the moving state of the autonomous vehicle is, for example, a state of low vehicle speed, a state of small acceleration, or a state of small steering angle, when the external environment of the autonomous vehicle is an environment where the position of obstacles is far, an environment with a small number, or an environment where the type is a non-moving object, when the position of the autonomous vehicle is in a place with light traffic, an environment with bright surrounding brightness, an environment with sunny weather, etc., when the time is daytime, when the response time to the request is long, etc., it is determined not to execute the second preprocessing.

[0095] Thus, when receiving a request, depending on the situation, there may be cases where the performance of the automatic driving cannot be improved even by executing the second preprocessing. For example, depending on the resources of the autonomous vehicle, the moving state of the autonomous vehicle, the external environment of the autonomous vehicle, the time, or the response time to the request, there may be cases where the performance of the automatic driving cannot be improved even by executing the second preprocessing and performing the driving control of the autonomous vehicle using the third processing result. In such cases, the remote automatic driving server 10a can reject or ignore the request.

[0096] When the sensing data acquisition unit 11a receives a request from the autonomous vehicle, it acquires sensing data when it is determined that the second preprocessing is to be executed. Since other points regarding the sensing data acquisition unit 11a are the same as those of the sensing data acquisition unit 11, the description is omitted.

[0097] When the pseudo-automatic driving system 12a receives a request from the autonomous vehicle, it executes the second preprocessing based on the sensing data acquired by the sensing data acquisition unit 11a when it is determined that the second preprocessing is to be executed, and obtains a second processing result. Since other points regarding the pseudo-automatic driving system 12a are the same as those of the pseudo-automatic driving system 12, the description is omitted.

[0098] Next, the operation of the remote automatic driving server 10a will be described with reference to FIG. 5.

[0099] FIG. 5 is a flowchart showing an example of an information processing method in a modification of the first embodiment. For example, the information processing method according to the modification of the first embodiment is a method executed by a computer (specifically, a processor) provided in the remote automatic driving server 10a. Therefore, FIG. 5 is also a flowchart showing the operation of the remote automatic driving server 10a.

[0100] The flowchart shown in FIG. 5 is different from the flowchart shown in FIG. 2 in that steps S21, S22, and S23 are added. Since the other points (i.e., steps S11 to S18) are the same as those shown in FIG. 2, the description thereof is omitted.

[0101] The remote automatic driving server 10a determines whether or not a request to execute the second preprocessing is received from the automatic driving vehicle (step S21).

[0102] When the remote automatic driving server 10a has not received a request to execute the second preprocessing from the automatic driving vehicle (No in step S21), the process of step S21 is repeated until a request is received.

[0103] When the remote automatic driving server 10a has received a request to execute the second preprocessing from the automatic driving vehicle (Yes in step S21), it determines whether or not to execute the second preprocessing (step S22).

[0104] When the remote automatic driving server 10a determines not to execute the second preprocessing (No in step S22), it rejects or ignores the request (step S23). As a result, for example, the remote processing management server 30 does not select the remote automatic driving server 10a that has rejected or ignored the request as the server that executes the second preprocessing, but selects another remote automatic driving server 10a as the server that executes the second preprocessing. In addition, when all the remote automatic driving servers 10a reject or ignore the request, the remote processing management server 30 may instruct the automatic driving vehicle to restrict driving.

[0105] When the remote automatic driving server 10a determines to execute the second preprocessing (Yes in step S22), the processes after step S11 are performed in the same manner as the description in FIG. 2.

[0106] Note that the request from the autonomous vehicle may include information specifying a specific process among the second preprocesses. In this case, the remote autonomous driving server 10a executes the specific process in step S12 to obtain a second processing result. This is because depending on the moving state of the autonomous vehicle or the external environment, etc., there may be cases where it is sufficient to perform a difference determination only for a specific process (for example, only an obstacle detection process, only a driving determination process, etc.). As a result, the remote autonomous driving server 10a can selectively execute, for example, a specific process desired by the autonomous vehicle specified from among the second preprocesses. Note that when only obstacle detection is performed, the area where obstacle detection is performed may be limited. For example, when the autonomous vehicle changes lanes, obstacle detection may be performed for the lane in the lane change destination.

[0107] Note that when the remote processing management server 30 receives requests from a plurality of autonomous vehicles, it may select an autonomous vehicle that preferentially accepts requests based on at least one of the resources possessed by each autonomous vehicle, the moving state of each autonomous vehicle, the external environment of each autonomous vehicle, the time, and the response time to the request.

[0108] As described above, the execution of the second preprocess in the remote autonomous driving server 10a and the like may be started when there is a request from the autonomous vehicle. Thereby, the remote autonomous driving server 10a can execute the second preprocess at the timing when the autonomous vehicle desires the execution of the advanced second preprocess.

[0109] (Embodiment 2) In Embodiment 1, an example in which the determination of the difference between the first processing result and the second processing result is performed by the remote autonomous driving server 10 has been described, but the determination may be performed by an information processing device mounted on the autonomous vehicle. This will be described as Embodiment 2 with reference to FIGS. 6 and 7.

[0110] FIG. 6 is a block diagram showing an example of an autonomous vehicle (specifically, an information processing device 200 mounted on the autonomous vehicle) and a remote autonomous driving server 100 according to Embodiment 2.

[0111] The remote automatic driving server 100 performs wireless communication with the autonomous vehicle.

[0112] The autonomous vehicle is equipped with an information processing device 200. The information processing device 200 is a computer including a processor, a memory, a communication interface, etc. The memory is a ROM, a RAM, etc., and can store programs executed by the processor. The information processing device 200 includes a sensing data acquisition unit 201, a sensing data transmission unit 202, a vehicle automatic driving system 203, a second processing result acquisition unit 204, a difference determination unit 205, a processing result change unit 206, a communication confirmation unit 207, and a driving restriction unit 208. The sensing data acquisition unit 201, the sensing data transmission unit 202, the vehicle automatic driving system 203, the second processing result acquisition unit 204, the difference determination unit 205, the processing result change unit 206, the communication confirmation unit 207, and the driving restriction unit 208 are realized by a processor or the like that executes a program stored in the memory.

[0113] The functions of the sensing data acquisition unit 201, the sensing data transmission unit 202, the vehicle automatic driving system 203, the communication confirmation unit 207, and the driving restriction unit 208 are basically the same as those of the sensing data acquisition unit 21, the sensing data transmission unit 22, the vehicle automatic driving system 23, the communication confirmation unit 26, and the driving restriction unit 27 in the first embodiment, so the description is omitted.

[0114] The second processing result acquisition unit 204 acquires a second processing result obtained by executing a second preprocessing, which is a more advanced preprocessing than the first preprocessing, based on the sensing data, from the remote automatic driving server 100. For example, the second processing result acquisition unit 204 acquires the second processing result transmitted from the remote automatic driving server 100 and received via a communication interface or the like provided in the autonomous vehicle.

[0115] The difference determination unit 205 determines the difference between the first processing result acquired by the vehicle automatic driving system 203 and the second processing result acquired by the second processing result acquisition unit 204. The difference determination unit 205 in the second embodiment and the difference determination unit 14 in the first embodiment are basically the same in function, except that whether they are provided in the information processing device 200 or in the remote automatic driving server 10 is different. Therefore, a detailed description of the difference determination unit 205 is omitted.

[0116] The processing result change unit 206 changes the first processing result to the third processing result according to the determined difference. In the first embodiment, an example in which the processing result change unit 25 changes the first processing result to the third processing result in response to a change instruction from the remote automatic driving server 10 was described. However, in the second embodiment, the processing result change unit 206 changes the first processing result to the third processing result according to the difference determined by the automatic driving vehicle itself.

[0117] The remote automatic driving server 100 is a computer including a processor, a memory, a communication interface, etc. The remote automatic driving server 100 is an example of a device external to the information processing device 200. The memory is a ROM, a RAM, etc., and can store programs executed by the processor. The remote automatic driving server 100 includes a sensing data acquisition unit 101, a pseudo-automatic driving system 102, and a second processing result transmission unit 103. The functions of the sensing data acquisition unit 101, the pseudo-automatic driving system 102, and the second processing result transmission unit 103 are realized by a processor or the like that executes programs stored in the memory. Note that the components constituting the remote automatic driving server 100 may be distributed and arranged in a plurality of servers.

[0118] Since the functions of the sensing data acquisition unit 101 and the pseudo-automatic driving system 102 are basically the same as the functions of the sensing data acquisition unit 11 and the pseudo-automatic driving system 12 in the first embodiment, the description is omitted.

[0119] The second processing result transmission unit 103 transmits the second processing result, which is the result of the second preprocessing executed by the pseudo-automatic driving system 102, to the autonomous vehicle. The second processing result transmission unit 103 transmits the second processing result to the autonomous vehicle via a communication interface or the like provided in the remote autonomous driving server 100.

[0120] In the second embodiment, the second processing result is transmitted from the remote autonomous driving server 100 to the autonomous vehicle, and the determination of the difference between the first processing result and the second processing result is not performed by the remote autonomous driving server 100 but by the autonomous vehicle.

[0121] Next, the operation of the autonomous vehicle will be described with reference to FIG. 7.

[0122] FIG. 7 is a flowchart showing an example of the operation of the autonomous vehicle (specifically, the information processing device 200) according to the second embodiment.

[0123] First, the autonomous vehicle determines whether the autonomous vehicle is communicatively connected to the remote autonomous driving server 100 (step S41).

[0124] When the autonomous vehicle is not communicatively connected to the remote autonomous driving server 100 (No in step S41), the autonomous vehicle restricts its driving (step S42). When the autonomous vehicle is not communicatively connected to the remote autonomous driving server 100, the autonomous vehicle cannot obtain the second processing result, that is, cannot determine the difference between the first processing result and the second processing result, and cannot change the first processing result to the third processing result. For this reason, when the autonomous vehicle is not communicatively connected to the remote autonomous driving server 100, there is a risk that the autonomous vehicle will enter a dangerous state, so the driving of the autonomous vehicle is restricted. Therefore, even when the communication between the autonomous vehicle and the remote autonomous driving server 10 is interrupted, safety can be ensured in the autonomous vehicle.

[0125] When the autonomous vehicle is communicatively connected to the remote autonomous driving server 100 (Yes in step S41), based on the sensing data, the autonomous vehicle executes a first preprocessing which is a preprocessing for the driving control process in the autonomous driving of the autonomous vehicle to obtain a first processing result (step S43). For example, the autonomous vehicle performs a detection process of obstacles around the autonomous vehicle (such as detecting the number of obstacles or the position of obstacles, etc.) from the sensing data to obtain the detection process result. Also, for example, the autonomous vehicle performs an estimation process of the position of the autonomous vehicle from the sensing data to obtain the estimation process result. Also, for example, the autonomous vehicle performs a driving determination process (such as determining whether to continue driving or stop, etc.) from the sensing data to obtain the driving determination process result.

[0126] Next, the autonomous vehicle outputs the sensing data acquired by the autonomous vehicle to the remote autonomous driving server 100 (step S44). The remote autonomous driving server 100 that has received the sensing data executes a second preprocessing which is a preprocessing more advanced than the first preprocessing based on the sensing data to obtain a second processing result. Then, the remote autonomous driving server 100 transmits the acquired second processing result to the autonomous vehicle.

[0127] Next, the autonomous vehicle determines whether it has acquired the second processing result transmitted from the remote autonomous driving server 100 without delay (step S45). For example, when the autonomous vehicle acquires the second processing result after a predetermined time or more has elapsed since the output of the sensing data or the output of the request, it determines that the second processing result cannot be acquired without delay. When a communication delay occurs between the autonomous vehicle and the remote autonomous driving server 100, the second processing result may not be acquired without delay.

[0128] If the automated vehicle fails to obtain the second processing result without delay (No in step S45), it does not perform the difference determination and restricts the running of the automated vehicle (step S42). Similar to the case where there is a processing delay in the second preprocessing described in Embodiment 1, the automated vehicle cannot effectively utilize the third processing result even if it changes the first processing result to the third processing result, and there is a risk that the automated vehicle may enter a dangerous state.

[0129] If the automated vehicle obtains the second processing result without delay (Yes in step S45), it determines the difference between the first processing result and the second processing result (step S46), and determines whether the determined difference satisfies a predetermined condition (step S47). The processing in steps S46 and S47 is the same as the processing in steps S15 and S16 described in FIG. 2 except that it is performed by the automated vehicle, so the description is omitted.

[0130] When the determined difference satisfies a predetermined condition (Yes in step S47), the automated vehicle executes a process of changing the first processing result to the third processing result (step S48). Then, the driving control process is executed using the third processing result. In this way, the first processing result is not used for the driving control process of the automated vehicle, and the third processing result based on the second processing result, which is the result of advanced second preprocessing, is used for the driving control of the automated vehicle, thereby improving the performance of the automated driving.

[0131] Note that when the determined difference satisfies a predetermined condition (Yes in step S47), the automated vehicle may restrict the running of the automated vehicle. Also, in this case, the automated vehicle may notify an abnormality to a remote monitor or a passenger of the automated vehicle.

[0132] When the determined difference does not satisfy a predetermined condition (No in step S47), the automated vehicle does not execute the above-described changing process (step S49). In this case, for example, the first processing result is not inferior to the second processing result, and the automated vehicle may not need to change the first processing result to the third processing result, and can perform the driving control of the automated vehicle using the first processing result that is not inferior to the second processing result.

[0133] Then, the autonomous vehicle determines whether it has arrived at the destination (step S50). If it has not arrived at the destination (No in step S50), the processes from step S41 to step S49 are repeated until it arrives at the destination. If it has arrived at the destination (Yes in step S50), the autonomous vehicle is stopped and the process ends.

[0134] As described above, separately from the first preprocessing executed in an autonomous vehicle with limitations on the computer that can be mounted from the viewpoints of cost, power consumption, space, etc., a second preprocessing more advanced than the first preprocessing is executed in an external device (for example, the remote autonomous driving server 100) with fewer limitations on cost, power consumption, space, etc., and the second processing result that is the result of the second preprocessing is transmitted to the autonomous vehicle. The difference between the first processing result that is the result of the first preprocessing and the second processing result that is the result of the second preprocessing is determined in the autonomous vehicle. Then, according to the difference, the first processing result that is the result of the first preprocessing, which is the preprocessing of the driving control process of the autonomous vehicle, is changed to a third processing result based on the second processing result that is the result of the above-mentioned advanced second preprocessing. Alternatively, according to the difference, the first processing result is changed to a third processing result obtained by correcting or restricting the first processing result. Thereby, since a third processing result more advanced than the first processing result is used for the driving control process of the autonomous vehicle, the performance of autonomous driving can be improved. For example, by improving the performance of autonomous driving, the drivable area of the autonomous vehicle can be expanded.

[0135] (Modification Example of Embodiment 2) For example, the execution of the second preprocessing in the remote autonomous driving server or the like may be started when there is a request from the autonomous vehicle. This will be described as a modification example of Embodiment 2 with reference to FIGS. 8 and 9.

[0136] FIG. 8 is a block diagram showing an example of an autonomous vehicle (specifically, the information processing device 200a mounted on the autonomous vehicle), a remote autonomous driving server 100a, and a remote processing management server 30 according to a modification example of Embodiment 2.

[0137] The information processing device 200a further includes a remote processing request unit 210, and is different from the information processing device 200 in Embodiment 2 in that it includes a sensing data acquisition unit 201a and a sensing data transmission unit 202a instead of the sensing data acquisition unit 201 and the sensing data transmission unit 202. Since other points are the same as those in the information processing device 200, the description thereof is omitted. Note that the remote processing request unit 210 is realized by a processor or the like that executes a program stored in a memory in the same manner as other components.

[0138] The remote processing request unit 210 outputs a request for executing the second preprocessing to the remote automatic driving server 100a via the remote processing management server 30. Since the remote processing management server 30 has basically the same functions as those in the modification of Embodiment 1, the description thereof is omitted. For example, the remote processing request unit 210 may output a request to the remote automatic driving server 100a based on at least one of the resources of the autonomous vehicle, the moving state of the autonomous vehicle, the external environment of the autonomous vehicle, the time, and the response time to an inquiry to the remote automatic driving server 100a. For example, when the resources of the autonomous vehicle are insufficient, when the moving state of the autonomous vehicle is, for example, a state where the vehicle speed is high, the acceleration is large, or the steering angle is large, when the external environment of the autonomous vehicle is an environment where the position of an obstacle is close, the number is large, or the type is a moving object, when the position of the autonomous vehicle is in a place with a large traffic volume (for example, an intersection, etc.), when the surrounding brightness is dark, when the weather is rainy or cloudy, when the time is night time, when the response time to the request is short, etc., a request is output. Also, for example, when the resources of the autonomous vehicle are sufficient, when the moving state of the autonomous vehicle is, for example, a state where the vehicle speed is low, the acceleration is small, or the steering angle is small, when the external environment of the autonomous vehicle is an environment where the position of an obstacle is far, the number is small, or the type is an object that does not move, when the position of the autonomous vehicle is in a place with a small traffic volume, when the surrounding brightness is bright, when the weather is sunny, when the time is daytime, when the response time to the request is long, etc., a request is not output.

[0139] Thus, depending on the situation, even if the second preprocessing is executed, the performance of the autonomous driving may not be improved. For example, depending on the resources of the autonomous vehicle, the moving state of the autonomous vehicle, the external environment of the autonomous vehicle, the time, or the response time to a request, even if the second preprocessing is executed and the driving control of the autonomous vehicle is performed using the third processing result, the performance of the autonomous driving may not be improved. In such a case, the autonomous vehicle can refrain from outputting a request. In other words, depending on the situation, the performance of the autonomous driving may be improved by executing the second preprocessing. When the situation where the performance of such autonomous driving can be improved occurs, the autonomous vehicle can output a request.

[0140] The remote processing request unit 210 instructs the sensing data acquisition unit 201a to acquire sensing data, and instructs the sensing data transmission unit 202a to transmit the sensing data to the remote autonomous driving server 100a selected by the remote processing management unit 31.

[0141] The sensing data acquisition unit 201a acquires sensing data from sensors provided in the autonomous vehicle in response to an instruction from the remote processing request unit 210. Since other aspects regarding the sensing data acquisition unit 201a are the same as those of the sensing data acquisition unit 201, the description thereof is omitted.

[0142] The sensing data transmission unit 202a transmits the sensing data acquired by the sensing data acquisition unit 201a to the selected remote autonomous driving server 100a. Since other aspects regarding the sensing data transmission unit 202a are the same as those of the sensing data transmission unit 202, the description thereof is omitted.

[0143] The remote automatic driving server 100a further includes a request acquisition unit 104 and a second preprocessing execution determination unit 105, and is different from the remote automatic driving server 100 in Embodiment 2 in that it includes a sensing data acquisition unit 101a and a pseudo-automatic driving system 102a instead of the sensing data acquisition unit 101 and the pseudo-automatic driving system 102. Other points are the same as those in the remote automatic driving server 100, so the description is omitted. Note that the request acquisition unit 104 and the second preprocessing execution determination unit 105 are realized by a processor or the like that executes a program stored in a memory in the same manner as other components.

[0144] The request acquisition unit 104 is basically the same as the request acquisition unit 16 in the modification of Embodiment 1, so the description is omitted.

[0145] The second preprocessing execution determination unit 105 is basically the same as the second preprocessing execution determination unit 17 in the modification of Embodiment 1, so the description is omitted.

[0146] When the sensing data acquisition unit 101a receives a request from the autonomous vehicle, it acquires sensing data when it is determined that the second preprocessing is to be executed. Other points regarding the sensing data acquisition unit 101a are the same as those of the sensing data acquisition unit 101, so the description is omitted.

[0147] When the pseudo-automatic driving system 102a receives a request from the autonomous vehicle, it executes the second preprocessing based on the sensing data acquired by the sensing data acquisition unit 101a when it is determined that the second preprocessing is to be executed, and obtains a second processing result. Other points regarding the pseudo-automatic driving system 102a are the same as those of the pseudo-automatic driving system 102, so the description is omitted.

[0148] Next, the operation of the autonomous vehicle will be described with reference to FIG. 9.

[0149] The flowchart shown in FIG. 9 is different from the flowchart shown in FIG. 7 in that step S51 is added instead of step S41. Other points (i.e., steps S42 to S50) are the same as those shown in FIG. 7 and thus the description thereof is omitted.

[0150] The autonomous vehicle outputs a request for execution of the second preprocessing to the remote autonomous driving server 100a (step S51). For example, after outputting the request, the autonomous vehicle receives a notification from the remote processing management server 30 indicating to which remote autonomous driving server 100a it should output the sensing data as a server capable of executing the second preprocessing. Then, as a response to the request, the second processing result is acquired in step S45. Note that, after outputting the request, if there is no response to the request, the autonomous vehicle may determine that it is not connected to the remote processing management server 30 or the like and restrict the driving of the autonomous vehicle.

[0151] Note that the request for execution of the second preprocessing may include information specifying a specific process among the second preprocessing. This is because depending on the moving state of the autonomous vehicle or the external environment, etc., there may be cases where it is only necessary to perform a difference determination for a specific process (for example, only an obstacle detection process, only a driving determination process, etc.). Thereby, the autonomous vehicle can selectively execute a specific process by specifying, for example, a specific process desired by the autonomous vehicle from among the second preprocessing to the remote autonomous driving server 100a. In this case, the autonomous vehicle acquires the second processing result, which is the result obtained by executing the specific process in steps S45 and S46, and performs a difference determination only for the specific process.

[0152] Note that even when the automated vehicle obtains the second processing result after a lapse of a predetermined time or more from the output of the sensing data or the output of the request (that is, even if the answer in step S45 is No), the process proceeds to step S46, and the difference between a part of the first processing result and the processing result corresponding to the part of the second processing result may be determined. For example, the part of the processing result is a part that is less affected by delay. For example, the part of the processing result is the result of the surrounding recognition process, and the result of the surrounding recognition process is less affected by delay. For example, since the result of the self-position estimation process is easily affected by delay, it may not be necessary to execute the difference determination for the processing result. Then, the automated vehicle may change the part of the first processing result to the third processing result according to the determined difference. In this way, when the second processing result is obtained after a lapse of a predetermined time or more from the output of the sensing data or the output of the request, there may be a communication delay with the remote automated driving server 100a. In such a case, by not executing the difference determination or by executing the difference determination only for a part of the processing results that are not affected by the delay, the processing load on the automated vehicle (specifically, the information processing device 200a) can be reduced.

[0153] As described above, by outputting a request from the automated vehicle, the execution of the second preprocessing in the remote automated driving server and the like may be started. Thereby, the second preprocessing can be executed at the timing when the automated vehicle desires to execute the advanced second preprocessing.

[0154] (Modifications common to each embodiment) In each of the above embodiments, it is assumed that the instruction or control for changing the preprocessing result is performed according to whether there is a delay in the second preprocessing. However, it may be performed according to whether correction processing for the delay is possible when there is a delay.

[0155] In addition, the instruction or control for changing the preprocessing result and the instruction or restriction for driving restriction may be performed according to the ODD (Operational Design Domain) corresponding to the above delay and difference, in addition to the difference between the first processing result and the second processing result. The ODD is set with elements such as, for example, time zone, region, driving state (speed, acceleration, steering angle, etc.), and environment (weather, illuminance, etc.).

[0156] The above processing will be described with reference to FIG. 10. FIG. 10 is a flowchart showing an example of an information processing method according to a modification common to each embodiment. Note that the description of the processing substantially the same as that in each of the above embodiments will be omitted.

[0157] When there is a delay in the second preprocessing (Yes in step S13), the server (for example, a remote automatic driving server) determines whether a correction process for the delay is possible (step S60). Specifically, when there is a communication delay between the server and the autonomous vehicle or a processing delay as described above, the server determines whether it is possible to correct (suppress, reduce) the time shift in the processing result due to the delay. For example, it is determined whether the delay amount is equal to or less than a threshold value.

[0158] When the correction process for the delay is possible (Yes in step S60), the server executes the correction process (step S61). Specifically, when the delay amount is equal to or less than the threshold value, the server executes a correction process for the second preprocessing result.

[0159] When there is no delay in the second preprocessing (No in step S60), or after executing the correction process, the process proceeds to steps S15 and S16.

[0160] When the correction process for the delay is not possible (No in step S60), the server determines whether the first ODD is satisfied (step S62). Specifically, the first ODD is an ODD set for the automatic driving in the autonomous vehicle. For example, the first ODD is that the region is other than an intersection, the speed is 20 km / h or less, and the weather is sunny.

[0161] When the first ODD is satisfied, the server does not output a change instruction (step S18). In this case, the driving control process in the autonomous driving is performed using the result of the first preprocessing executed in the autonomous vehicle.

[0162] When the difference between the first preprocessing and the second preprocessing satisfies a predetermined condition (Yes in step S16), the server determines whether the second ODD is satisfied (step S63). Specifically, the second ODD is an ODD different from the first ODD set for the autonomous driving in the autonomous vehicle. For example, the second ODD is that the area is the whole area, the speed is 15 km / h or less, and the weather is sunny or rainy. In this way, at least a part of the second ODD is relaxed compared to the first ODD. On the other hand, when using the second processing result, communication is used, so the items affected by the delay in the second ODD are the same as or stricter than the first ODD.

[0163] When the above difference satisfies a predetermined condition and the second ODD is satisfied (Yes in step S63), the server outputs a change instruction (step S17). In this case, the driving control process in the autonomous driving is performed using the result of the second preprocessing executed in the server or the corrected result of the first preprocessing.

[0164] When the difference between the first preprocessing and the second preprocessing does not satisfy a predetermined condition (No in step S16), the server determines whether the second ODD is satisfied (step S64). This process is substantially the same as the process of step S63.

[0165] When the above difference does not satisfy a predetermined condition and the second ODD is satisfied (Yes in step S64), the server does not output a change instruction (step S18). The reason for using the second ODD when the above difference does not satisfy a predetermined condition is that the difference between the result of the preprocessing in the server and the result of the preprocessing in the autonomous vehicle does not satisfy the predetermined condition enough. In other words, it is because the result of the preprocessing in the autonomous vehicle can be treated equivalently to the result of the preprocessing in the server.

[0166] If the first ODD is not satisfied (No in step S62), or if the second ODD is not satisfied (No in step S63 or S64), the server outputs a driving restriction instruction (step S14).

[0167] Note that in FIG. 10, an example is shown in which the server determines whether correction processing for delay is possible and determines a change instruction for the preprocessing result and a driving restriction instruction according to the ODD corresponding to the delay and the difference. However, the autonomous vehicle may determine whether correction processing for delay is possible and execute change control of the preprocessing result and driving restriction according to the ODD corresponding to the delay and the difference.

[0168] In addition, the change instruction or change control of the preprocessing result may be performed according to whether there is a communication failure related to the second preprocessing. Specifically, the communication failure is communication data loss. For example, the change instruction or change control of the preprocessing result may be performed according to whether the packet loss rate is equal to or higher than a threshold value. Note that the above-mentioned communication delay may be included in the communication failure.

[0169] In addition, the change instruction or change control of the preprocessing result may be performed according to whether correction processing for the communication failure is possible when there is a communication failure. Specifically, the change instruction or change control of the preprocessing result is performed according to whether the data missing due to communication data loss can be supplemented. For example, the change instruction or change control of the preprocessing result is performed according to the ratio at which the lost packets can be supplemented.

[0170] (Other Embodiments) As described above, the information processing method, information processing system (for example, a remote autonomous driving server), and information processing apparatus according to one or more aspects of the present disclosure have been described based on the embodiments. However, the present disclosure is not limited to these embodiments. As long as the gist of the present disclosure is not deviated from, various modifications conceived by those skilled in the art applied to each embodiment, and forms constructed by combining components in different embodiments may also be included within the scope of one or more aspects of the present disclosure.

[0171] For example, the steps included in the information processing method can be realized as a program for causing a processor to execute. Further, the present disclosure can be realized as a non-transitory computer-readable recording medium such as a CD-ROM on which the program is recorded.

[0172] For example, when the present disclosure is realized by a program (software), each step is executed by using hardware resources such as a CPU, a memory, and an input / output circuit of a computer to execute the program. That is, each step is executed by the CPU acquiring data from the memory or the input / output circuit or the like and performing calculations, or outputting the calculation result to the memory or the input / output circuit or the like.

[0173] Note that in the above embodiment, each component included in the information processing system and the information processing apparatus may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0174] Part or all of the functions of the information processing system and the information processing apparatus according to the above embodiment are typically realized as an LSI which is an integrated circuit. These may be individually formed into one chip, or may be formed into one chip so as to include part or all of them. Further, the integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.

[0175] Furthermore, various modifications obtained by making changes within the scope conceivable by those skilled in the art to each embodiment of the present disclosure are also included in the present disclosure as long as they do not depart from the gist of the present disclosure.

Industrial Applicability

[0176] The present disclosure can be applied to a remote control system for an autonomous vehicle.

Explanation of Signs

[0177] 10, 10a, 100, 100a Remote autonomous driving server 11, 11a, 21, 21a, 101, 101a, 201, 201a Sensing data acquisition unit 12, 12a, 102, 102a Pseudo-autonomous driving system 13 First processing result acquisition unit 14, 205 Difference determination unit 15 Change instruction output unit 16, 104 Request acquisition unit 17, 105 Second preprocessing execution determination unit 20, 20a, 200, 200a Information processing device 22, 22a, 202, 202a Sensing data transmission unit 23, 203 Vehicle autonomous driving system 24, 24a First processing result transmission unit 25, 206 Processing result change unit 26, 207 Communication confirmation unit 27, 208 Driving restriction unit 28, 210 Remote processing request unit 30 Remote processing management server 31 Remote processing management unit 103 Second processing result transmission unit 204 Second processing result acquisition unit

Claims

1. An information processing method for causing an information processing device mounted on an autonomous mobile body to execute, comprising: executing a first preprocessing, which is a preprocessing of a travel control process in the autonomous driving of the autonomous mobile body, based on sensing data acquired by the autonomous mobile body to obtain a first processing result; outputting the sensing data to an external device; acquiring a second processing result obtained by executing a second preprocessing, which is a preprocessing more advanced than the first preprocessing, based on the sensing data, wherein the second preprocessing is executed by an external device connected to the autonomous mobile body via a network and having higher processing capability than the information processing device; restricting the travel of the autonomous mobile body when there is a communication delay between the autonomous mobile body and the external device or when there is a processing delay in the second preprocessing; performing travel control of the autonomous mobile body based on the first processing result or the third processing result when there is no communication delay between the autonomous mobile body and the external device or when there is no processing delay in the second preprocessing, wherein the third processing result is the second processing result or a processing result obtained by correcting the first processing result. Information processing method.

2. When a change instruction for changing the first processing result to the third processing result is received, if the reception of the change instruction is delayed due to the communication delay, the received change instruction is ignored and the travel of the autonomous mobile body is restricted. The information processing method according to claim 1.

3. When the second processing result cannot be acquired without delay due to the communication delay, the travel of the autonomous mobile body is restricted. The information processing method according to claim 1.

4. When the second processing result cannot be acquired without delay due to the communication delay or when there is a processing delay in the second preprocessing, and correction for the delay is possible, travel control of the autonomous mobile body is performed based on the first processing result or the third processing result. The information processing method according to claim 1.

5. When the second processing result cannot be acquired without delay due to the communication delay or when there is a processing delay in the second preprocessing, and correction for the delay is not possible, when a predetermined ODD (Operational Design Domain) is satisfied, travel control of the autonomous mobile body is performed based on the first processing result, and when the predetermined ODD is not satisfied, the travel of the autonomous mobile body is restricted. The information processing method according to claim 1.

6. Furthermore, when there is no communication delay between the autonomous mobile body and the external device, or when there is no processing delay in the second preprocessing, determine the difference between the first processing result and the second processing result, change the first processing result to the third processing result according to the determined difference, and perform travel control of the autonomous mobile body based on the third processing result The information processing method according to claim 1.

7. When the difference satisfies a predetermined condition, change the first processing result to the third processing result, and perform travel control of the autonomous mobile body based on the third processing result The information processing method according to claim 6.

8. When the difference satisfies the predetermined condition, when a predetermined ODD is satisfied, change the first processing result to the third processing result, and perform travel control of the autonomous mobile body based on the third processing result; when the predetermined ODD is not satisfied, limit the travel of the autonomous mobile body The information processing method according to claim 7.

9. When the difference satisfies a predetermined condition, limit the travel of the autonomous mobile body The information processing method according to claim 6.

10. When the difference satisfies a predetermined condition, notify an abnormality The information processing method according to claim 6.

11. When the weather is not suitable for the autonomous driving of the autonomous mobile body, without determining the difference, change the first processing result to the third processing result, and perform travel control of the autonomous mobile body based on the third processing result The information processing method according to claim 6.

12. When the second processing result is obtained after a lapse of a predetermined time or more from the output of the sensing data, determine the difference between a part of the first processing result and a part of the second processing result The information processing method according to claim 6.

13. Furthermore, output a request for execution of the second preprocessing to the external device based on at least one of the resources of the autonomous mobile body, the movement state of the autonomous mobile body, the external environment of the autonomous mobile body, the time, and the response time to an inquiry to the external device The information processing method according to claim 1.

14. An information processing device mounted on an autonomous mobile body, execute a first preprocessing which is a preprocessing of a travel control process in the autonomous driving of the autonomous mobile body based on sensing data acquired by the autonomous mobile body to obtain a first processing result, output the sensing data to an external device, Obtain a second processing result obtained by performing a second preprocessing, which is a preprocessing more advanced than the first preprocessing, based on the sensing data, from the external device. Here, the second preprocessing is executed by the external device that is connected to the autonomous mobile body via a network and has a higher processing capacity than the information processing device. When there is a communication delay between the autonomous mobile body and the external device, or when there is a processing delay in the second preprocessing, restrict the travel of the autonomous mobile body. When there is no communication delay between the autonomous mobile body and the external device, or when there is no processing delay in the second preprocessing, perform travel control of the autonomous mobile body based on the first processing result or the third processing result. The third processing result is the second processing result or a processing result obtained by correcting the first processing result. Information processing device.

15. An information processing method for causing an external device connected to an autonomous mobile body via a network to execute, Obtain a first processing result, which is a result of a first preprocessing that is a preprocessing of a travel control process in the autonomous movement process of the autonomous mobile body, and sensing data acquired by the autonomous mobile body, from the autonomous mobile body. Here, the first preprocessing is executed based on the sensing data by an information processing device provided in the autonomous mobile body. Execute a second preprocessing, which is a preprocessing more advanced than the first preprocessing, based on the sensing data to obtain a second processing result. Here, the external device has a higher processing capacity than the information processing device. When there is a communication delay between the autonomous mobile body and the external device, or when there is a processing delay in the second preprocessing, output a travel restriction instruction for restricting the travel of the autonomous mobile body to the autonomous mobile body. When there is no communication delay between the autonomous mobile body and the external device, or when there is no processing delay in the second preprocessing, output a change instruction for changing the first processing result to a third processing result to the autonomous mobile body. The third processing result is the second processing result or a processing result obtained by correcting the first processing result. Information processing method.

16. When there is a communication delay between the autonomous mobile body and the external device, or when there is a processing delay in the second preprocessing, and correction for the delay is not possible, when a predetermined ODD (Operational Design Domain) is satisfied, the change instruction is not output to the autonomous mobile body, and when the predetermined ODD is not satisfied, the travel restriction instruction is output to the autonomous mobile body The information processing method according to claim 15

17. Furthermore When there is no communication delay between the autonomous mobile body and the external device, or when there is no processing delay in the second preprocessing, the difference between the first processing result and the second processing result is determined According to the determined difference, the change instruction is output to the autonomous mobile body The information processing method according to claim 15

18. When the difference satisfies a predetermined condition, the change instruction is output to the autonomous mobile body The information processing method according to claim 17

19. When the difference satisfies the predetermined condition, when a predetermined ODD is satisfied, the change instruction is output to the autonomous mobile body, and when the predetermined ODD is not satisfied, the travel restriction instruction is output to the autonomous mobile body The information processing method according to claim 18

20. When a request for execution of the second preprocessing is received from a plurality of the autonomous mobile bodies, based on at least one of the resources of the plurality of autonomous mobile bodies, the moving states of the plurality of autonomous mobile bodies, the external environments of the plurality of autonomous mobile bodies, the time, and the response time for the request, an autonomous mobile body that preferentially accepts the request is selected from among the plurality of autonomous mobile bodies The information processing method according to claim 15

Images