Remote support system and remote support method

Abstract

The present disclosure relates to a remote support system and a remote support method that reduce the load on an operator who applies remote support to travel of an automated driving vehicle. The remote support system includes an achievement database. The achievement database shows, for each scenario, an achievement of a support request process performed by an automated driving vehicle. The remote support system requests an operator for an instruction for a target automated driving vehicle in response to a support request from the target automated driving vehicle. The support process is a vehicle process performed by the operator instead of the target automated driving vehicle. On the other hand, the entrustment process is a process entrusted by the operator to the target automated driving vehicle. The remote support system decides a recommended option of a combination of the support process and the entrustment process in accordance with the achievement database. Then, the remote support system prompts the recommended option to the operator.

Description

TECHNICAL FIELD

[0001] The present application relates to a technology of remotely assisting travel of an automated vehicle. BACKGROUND

[0002] Patent Literature 1 discloses a regulation device that remotely controls an automated vehicle. After implementing remote control for a certain object vehicle, the regulation device registers location data including position information and sensing data of the object vehicle. In a case where remote control is performed, the regulation device determines whether similar registered location data to current location data acquired from the object vehicle is available. In a case where similar registered location data is available, the regulation device performs first remote control using the similar registered location data and without intervention of an operator. On the other hand, in a case where similar registered location data is not available, the regulation device performs second remote control with intervention of the operator.

[0003] Patent Literature 2 discloses a management device that manages a vehicle. The vehicle creates surrounding information indicating a situation of a surrounding using a sensor, and performs automated driving based on the surrounding information. In a situation where automated driving is difficult, the management device acquires the surrounding information from the vehicle, and selects one of remote operation of the vehicle and alternative processing based on the surrounding information. The alternative processing is a change of the used sensor or a change of a route of the automated driving.

[0004] Patent Literature 3 discloses a vehicle remote operation support system. The vehicle remote operation support system includes a vehicle that performs automated driving and a regulation center that has an operator. The vehicle transmits surrounding information to the regulation center and calls the operator in a case where automated driving is difficult. The operator inputs a parameter for selecting a travel mode in remote operation of the vehicle based on the surrounding information. The regulation center selects the travel mode based on the input parameter, and generates a path of the vehicle using the selected travel mode and the surrounding information.

[0005] PRIOR ART DOCUMENTS

[0006] PATENT LITERATURE

[0007] Patent Literature 1: Japanese Patent Application Publication No. 2019-185280

[0008] Patent Literature 2: Japanese Patent Application Publication No. 2019-207539

[0009] Patent Literature 3: Japanese Patent Application Publication No. 2019-191982 SUMMARY

[0010] A situation is considered in which an operator remotely assists travel of an automated vehicle in response to an assistance request from the automated vehicle. At this time, in a case where a load on the operator increases, there is a possibility that efficiency of the remote assistance decreases.

[0011] An object of the present application is to provide a technology capable of reducing the load on an operator who remotely supports the travel of an autonomous vehicle.

[0012] A first aspect relates to a remote support system that remotely supports the travel of an autonomous vehicle.

[0013] The autonomous vehicle executes:

[0014] a plurality of vehicle processes including recognition and determination in autonomous driving; and

[0015] a support request process that sends a support request requesting support for at least one of the plurality of vehicle processes to the remote support system.

[0016] The remote support system includes:

[0017] one or more processors; and

[0018] a performance database that shows, for each scenario, a performance of the support request process executed by the autonomous vehicle.

[0019] The one or more processors are configured to execute:

[0020] an operator instruction request process that, in response to a support request sent from a target autonomous vehicle in a first scenario, requests an instruction for the target autonomous vehicle from an operator; and

[0021] an operator instruction notification process that notifies the target autonomous vehicle of the instruction from the operator.

[0022] The support process is a vehicle process in the plurality of vehicle processes in the first scenario that is performed by the operator instead of the target autonomous vehicle.

[0023] The delegation process is a vehicle process in the plurality of vehicle processes in the first scenario that is delegated by the operator to the target autonomous vehicle.

[0024] In the operator instruction request process, the one or more processors

[0025] retrieve, from the performance database, a performance of the support request process associated with the first scenario,

[0026] determine, from the performance associated with the first scenario, a recommended option for the operator from among a plurality of options of combinations of the support process and the delegation process,

[0027] and at least the recommended option is prompted to the operator.

[0028] A second aspect relates to a remote support method that remotely supports the travel of an autonomous vehicle.

[0029] The automated driving vehicle performs:

[0030] a plurality of vehicle processes including recognition and determination in automated driving; and

[0031] a support request process that sends a support request requesting support for at least one of the plurality of vehicle processes to a remote support system.

[0032] The performance database shows, for each scenario, a performance of the support request process performed by the automated driving vehicle.

[0033] The remote support method includes:

[0034] an operator instruction request process that, in response to a support request sent from a subject automated driving vehicle in a first scenario, requests an instruction for the subject automated driving vehicle from an operator; and

[0035] an operator instruction notification process that notifies the subject automated driving vehicle of the instruction from the operator.

[0036] The support process is a vehicle process in the plurality of vehicle processes in the first scenario that is performed by the operator instead of the subject automated driving vehicle.

[0037] The delegation process is a vehicle process in the plurality of vehicle processes in the first scenario that is delegated to the subject automated driving vehicle by the operator.

[0038] The operator instruction request process includes:

[0039] a process of obtaining, from the performance database, a performance of the support request process associated with the first scenario;

[0040] a process of determining, from the performance of the support request process associated with the first scenario, a recommended option of a plurality of options of combinations of the support process and the delegation process to recommend to the operator; and

[0041] a process of at least prompting the recommended option to the operator.

[0042] According to the present application, in response to a support request from a subject automated driving vehicle, an instruction for the subject automated driving vehicle is requested from an operator. The support process is a vehicle process performed by the operator instead of the subject automated driving vehicle. On the other hand, the delegation process is a process delegated to the subject automated driving vehicle by the operator. When the delegation process is increased and the support process is decreased, accordingly, the matters that the operator should determine are reduced. This contributes to reducing the load on the operator.

[0043] Further, according to the present application, a recommended option of a combination of the support processing and the commission processing is determined from a result database that indicates results of support request processing. Then, the recommended option is prompted to the operator. The operator can shorten the time for studying which vehicle processing to be the commission processing by referring to the recommended option. Thus, the load of the operator is reduced.

[0044] Since the load of the operator is reduced, the time required for the operator to deal with a single support request (i.e., a single target autonomous vehicle) is shortened. As a result, the efficiency of remote support is improved. In addition, this means that more support requests (target autonomous vehicles) can be dealt with by a limited number of operators. From the viewpoint of cost, this is preferable. According to the present application, it is possible to improve the efficiency of remote support while suppressing an increase in cost. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is a conceptual diagram for explaining an outline of remote support of an embodiment of the present application.

[0046] Figure 2 is a conceptual diagram for explaining an outline of a remote support system of an embodiment of the present application.

[0047] Figure 3 is a conceptual diagram for explaining a remote support processing performed by a remote support system of an embodiment of the present application.

[0048] Figure 4 is a conceptual diagram for explaining one example of an operator instruction request processing performed by a remote support system of an embodiment of the present application.

[0049] Figure 5 is a block diagram showing a structure example of an autonomous driving system mounted on an autonomous vehicle of an embodiment of the present application.

[0050] Figure 6 is a block diagram showing an example of driving environment information of an embodiment of the present application.

[0051] Figure 7 is a block diagram showing a structure example of a remote support system of an embodiment of the present application.

[0052] Figure 8 is a conceptual diagram showing one example of a result database of an embodiment of the present application.

[0053] Figure 9 is a conceptual diagram showing another example of a result database of an embodiment of the present application.

[0054] Figure 10is a block diagram showing an example of various information associated with the remote support processing of the embodiment of the present application.

[0055] Figure 11 is a flowchart showing the operator instruction request processing in the remote support processing of the embodiment of the present application.

[0056] Figure 12 is a flowchart showing the operator instruction notification processing in the remote support processing of the embodiment of the present application.

[0057] (Symbol explanation)

[0058] 1: autonomous vehicle; 1T: target autonomous vehicle; 10: autonomous driving system; 20: recognition sensor; 25: camera; 50: communication device; 70: control device; 80: driving environment information; 100: remote support system; 110: information processing device; 111: processor; 112: memory; 120: communication device; 130: display device; 140: input device; 200: performance database; 300: vehicle-side information; 400: reference information; 410: performance information; 430: autonomous driving system information; 440: environmental condition information; 500: option information; IMG: image information; INS: operator instruction; OPT1: recommended option; REQ: support request. DETAILED DESCRIPTION

[0059] With reference to the drawings, an embodiment of the present application will be described.

[0060] 1. Outline of remote support

[0061] Figure 1 is a conceptual diagram for explaining the outline of the remote support of the present embodiment. The autonomous vehicle 1 is a vehicle that can be autonomously driven. As the autonomous driving here, driving is assumed in which a driver can not have to concentrate on driving by 100% (so-called level 3 or more autonomous driving). The autonomous vehicle 1 can also be a level 4 or more autonomous vehicle that does not need a driver. As such an autonomous vehicle 1, for example, an autonomous bus that runs within a limited area can be cited.

[0062] The remote support system 100 is provided, for example, in an autonomous driving center in an area where a large number of autonomous vehicles 1 travel. The autonomous vehicle 1 and the remote support system 100 can communicate with each other. The remote support system 100 communicates with the autonomous vehicle 1 and remotely supports the travel of the autonomous vehicle 1. More specifically, a human operator remotely supports the travel of the autonomous vehicle 1 via the remote support system 100. The remote support system 100 can also be referred to as a system that assists the remote support of the autonomous vehicle 1 by the operator.

[0063] As shown in FIG. 1, for example, the remote support system 100 includes a monitor. In the monitor, information such as a situation of a region, a position and a state of each of the automated vehicles 1 is displayed. An operator monitors the information displayed in the monitor. Also, the operator remotely supports the travel of the automated vehicles 1 as necessary. Figure 2

[0064] Typically, a situation in which remote support needs to be implemented by the operator is a situation in which automated driving is difficult. In automated driving, the automated vehicle 1 performs various vehicle processes. As representative vehicle processes in automated driving, the following examples can be given.

[0065] (1) Recognition process: The automated vehicle 1 recognizes a situation of the periphery of the automated vehicle 1 using a recognition sensor. For example, the automated vehicle 1 recognizes a signal display of a signal light (example: green signal, yellow signal, red signal, right turn signal, and the like) using a camera.

[0066] (2) Action judgment process: The automated vehicle 1 judges whether or not to perform an action on the basis of a result of the recognition process. As the action of the automated vehicle 1, examples are start, stop, right turn, left turn, lane change, and the like.

[0067] (3) Timing judgment process: The automated vehicle 1 judges a timing of performing the above-mentioned action.

[0068] For example, when sunlight is shining on a signal light provided at an intersection, there is a possibility that the recognition accuracy of the signal display is reduced. In a case where the signal display cannot be correctly discriminated by the recognition process, the automated vehicle 1 needs remote support by the operator with respect to signal recognition. In addition, in a case where the signal display cannot be discriminated, it is also difficult to judge what kind of action should be performed at which timing. Therefore, with respect to the action judgment process and the timing judgment process, the automated vehicle 1 also needs remote support by the operator.

[0069] A situation in which it is also difficult to judge whether or not the action can be actually performed even if the signal display is discriminated is also considered. For example, even after the signal display observed from the automated vehicle 1 is "right turn possible", there is a case where an oncoming vehicle enters the intersection or the oncoming vehicle or a preceding vehicle is stalled in the intersection. In such a case, the automated vehicle 1 can directly stop, and with respect to the action judgment process and the timing judgment process, remote support by the operator is requested.

[0070] ​As still another example, a situation where it is difficult to determine whether to perform a lane change is also considered, although there is a parked vehicle on a travel lane ahead of the automated driving vehicle 1. For example, in a situation where there is a sign of a parked vehicle starting, it is difficult to determine whether to perform a lane change. In addition, in a section where lane changing is prohibited, there is no action that can be taken other than parking. In such a case, the automated driving vehicle 1 can also stop right in front of the parked vehicle, and regarding the action determination process, request remote assistance by an operator to be performed.

[0071] As still another example, the automated driving vehicle 1 can also request remote assistance by an operator to be performed in an engineering section. As still another example, the automated driving vehicle 1 can also request remote assistance by an operator to be performed when the automated driving vehicle 1 has a failure.

[0072] In a case where remote assistance by an operator is required, the automated driving vehicle 1 delivers a "support request REQ" to the remote assistance system 100. The support request REQ requests assistance of at least one of the above-described plurality of vehicle processes (recognition process, action determination process, and timing determination process). Hereinafter, the process performed by the automated driving vehicle 1 will be referred to as a "support request process". In addition, hereinafter, the automated driving vehicle 1 that performs the support request process will be referred to as an "object automated driving vehicle 1T". The support request REQ can also include a result of the vehicle process in the object automated driving vehicle 1T as reference information.

[0073] The remote assistance system 100 accepts the support request REQ from the object automated driving vehicle 1T. The remote assistance system 100 notifies the operator of the accepted support request REQ, and requests an instruction to the object automated driving vehicle 1T from the operator. Hereinafter, the process performed by the remote assistance system 100 will be referred to as an "operator instruction request process".

[0074] The operator decides an "operator instruction INS" as an instruction to the object automated driving vehicle 1T in accordance with the content of the support request REQ. The operator inputs the operator instruction to the remote assistance system 100. The remote assistance system 100 communicates with the object automated driving vehicle 1T, and notifies the object automated driving vehicle 1T of the operator instruction INS. Hereinafter, the process performed by the remote assistance system 100 will be referred to as an "operator instruction notification process".

[0075] The remote assistance process performed by the remote assistance system 100 includes the above-described "operator instruction request process" and "operator instruction notification process".

[0076] The subject autonomous vehicle 1T receives the operator instruction INS from the remote support system 100. Then, the subject autonomous vehicle 1T starts autonomous driving again in accordance with the operator instruction INS.

[0077] Further, a case where autonomous driving is still difficult after receiving the operator instruction INS is also considered. In this case, the subject autonomous vehicle 1T can also re-send the support request REQ to the remote support system 100 without following the received operator instruction INS. Hereinafter, this processing is referred to as "re-support request processing".

[0078] 2. Reducing the load applied to the operator

[0079] 2-1. Overview

[0080] As described above, the operator performs remote support for the travel of the subject autonomous vehicle 1T in response to the support request REQ from the subject autonomous vehicle 1T. At this time, when the load applied to the operator increases, there is a possibility that the efficiency of remote support decreases.

[0081] For example, a case where support requests REQ are sequentially sent from a large number of subject autonomous vehicles 1T is considered. The operator needs to quickly respond to the sequentially occurring support requests REQ. When the handling of the support requests REQ is delayed, the efficiency of remote support decreases.

[0082] It is also considered that a large number of operators are prepared, and the support requests REQ are divided and handled by the large number of operators. However, the operators who perform remote support are high-skilled personnel who require specialized techniques. From the viewpoint of cost and training, there are limitations to increasing such high-skilled operators.

[0083] In order to improve the efficiency of remote support, it is important to reduce the load applied to the operator. To this end, it is effective to reduce the matters that the operator needs to research and judge for a single support request REQ. As a result, the time required for the operator to handle a single support request REQ (i.e., a single subject autonomous vehicle 1T) is shortened. As a result, the efficiency of remote support is improved.

[0084] According to the above viewpoint, according to the present embodiment, the concepts of "support processing" and "delegation processing" are introduced. The support processing refers to the vehicle processing in the above-described multiple vehicle processing (recognition processing, action judgment processing, and timing judgment processing) that is performed by the operator instead of the subject autonomous vehicle 1T. On the other hand, the delegation processing refers to the processing in the above-described multiple vehicle processing (recognition processing, action judgment processing, and timing judgment processing) that is delegated to the subject autonomous vehicle 1T by the operator.

[0085] When the number of commission processes increases and the number of support processes decreases, the matters that the operator should judge decrease accordingly. This is preferable from the viewpoint of the reduction of the load imposed on the operator. However, in order to decide which vehicle process is to be a commission process, it is necessary to comprehensively study various kinds of information. Moreover, the various kinds of information to be studied differ for each subject autonomous vehicle 1T, and also differ depending on the situation in which the subject autonomous vehicle 1T is placed. As a result, this study becomes a load for the operator.

[0086] Therefore, the remote support system 100 of the present embodiment, in the operator instruction request process, prompts the operator with useful information that contributes to the reduction of the study time of the operator. Among the combinations of support processes and commission processes, there are a plurality of options OPT. The remote support system 100 automatically decides one of the plurality of options OPT recommended for the operator as a "recommended option OPT1". Then, the remote support system 100 at least prompts the recommended option OPT1 to the operator. The operator, by referring to the recommended option OPT1, is able to reduce the time for studying which vehicle process is to be a commission process. As a result, the load imposed on the operator is reduced.

[0087] 2-2. Remote support process based on performance database

[0088] Figure 3 is a conceptual diagram for explaining the remote support process executed by the remote support system 100 of the present embodiment. The remote support system 100 includes a performance database 200. The performance database 200 shows, at least for each scenario, the past performance of the support request process executed by each autonomous vehicle 1.

[0089] The scenario is the situation in which the autonomous vehicle 1 is placed. Specifically, the scenario includes a location in which there is a possibility that a support request process is performed by the autonomous vehicle 1. As the location in which a support request process is performed, a crossroad, a merging section, a construction section, and the like are exemplified. Each location is specified by a range of latitude and longitude. The scenario is not only the location, but can also include the behavior of the autonomous vehicle 1. As an example of a scenario that includes a location and a behavior, "right turn at a crossroad", "perform lane change in a merging section", and the like can be given.

[0090] The past performance of the support request processing for a certain scenario includes, for example, a probability that a vehicle requests support of the vehicle processing in the scenario. For example, assume that a certain automated vehicle 1 has passed a certain intersection 100 times in the past. Assume that recognition processing for recognizing a signal display at the intersection has succeeded 98 times and failed 2 times. In the case where the recognition processing fails to recognize the signal display, the automated vehicle 1 requests support of the recognition processing. Thus, the past support request probability for the recognition processing at the intersection is 2%. It is generally considered that, in the case where the past support request probability for the recognition processing is low, it is less likely that a problem occurs even if the recognition processing is allocated to the delegated processing.

[0091] Thus, in order to decide the recommendation option OPT1, the performance database 200 that shows the past performance of the support request processing for each scenario is useful. Furthermore, in the above example, the support request probability is 2% and the recognition success probability is 98%. The "performance of the support request processing" and the "performance of the vehicle processing" are in a reversed relationship and can be said to be equivalent. Thus, the performance database 200 can also be said to show the performance of a plurality of vehicle processes performed by the automated vehicle 1 for each scenario.

[0092] Each automated vehicle 1 sends information indicating a scenario and results of each vehicle process (recognition processing, action judgment processing, and timing judgment processing) to the remote support system 100 each time the scenario is experienced. In the case where the support request processing is performed, each automated vehicle 1 sends information indicating contents of the support request processing (which vehicle process is requested to be supported) to the remote support system 100. The remote support system 100 collects these pieces of information from each automated vehicle 1. Then, the remote support system 100 updates the performance database 200 by registering the collected information in the performance database 200. As shown in FIG. 2, the performance database 200 shows a correspondence relationship among the identification information of each automated vehicle 1, a scenario, and the performance of the support request processing. Figure 3

[0093] On the other hand, from the subject automated vehicle 1T in a certain scenario, a support request REQ is sent to the remote support system 100. For convenience, the scenario in which the subject automated vehicle 1T is located is referred to as "the first scenario". In response to the support request REQ, the remote support system 100 performs an operator instruction request processing that requests an instruction to the subject automated vehicle 1T from an operator.

[0094] ​In the operator instruction request processing, the remote support system 100 first acquires, from the performance database 200, a performance of the support request processing associated with the 1st scenario. The support request processing associated with the 1st scenario includes the support request processing in the 1st scenario itself. The support request processing associated with the 1st scenario can also include the support request processing of a similar scenario similar to the 1st scenario. For example, in the case where the 1st scenario is "right turn at intersection A", "right turn at intersection B of the same configuration as intersection A" is a similar scenario.

[0095] The performance of the support request processing acquired from the performance database 200 includes at least the performance of the support request processing performed by the subject autonomous vehicle 1T itself. That is, the remote support system 100 acquires, from the performance database 200, the performance of the support request processing associated with the 1st scenario performed by the subject autonomous vehicle 1T.

[0096] As a modification, the remote support system 100 can also acquire, in addition to the performance of the support request processing performed by the subject autonomous vehicle 1T, the performance of the support request processing performed by other autonomous vehicles 1. In this case, the remote support system 100 weights and combines the performances of the support request processing performed by each of the autonomous vehicles 1 different from the subject autonomous vehicle 1T. At this time, the weight for the subject autonomous vehicle 1T is set to be greater than the weight for the other autonomous vehicles 1.

[0097] Next, the remote support system 100 decides, from the performance of the support request processing associated with the 1st scenario, a "recommended option OPT1" related to the combination of the support processing and the delegation processing. The support processing is the vehicle processing in the plurality of vehicle processes of the 1st scenario, which is performed by the operator instead of the subject autonomous vehicle 1T. On the other hand, the delegation processing is the processing in the plurality of vehicle processes of the 1st scenario, which is delegated by the operator to the subject autonomous vehicle 1T. Further, the remote support system 100 at least prompts the recommended option OPT1 to the operator. The remote support system 100 can also prompt the operator with a plurality of options OPT including the recommended option OPT1.

[0098] Figure 4 is a conceptual diagram for explaining one example of the operator instruction request processing of the present embodiment. Specifically, Figure 4 One example of information displayed on a monitor observed by an operator is shown. In the monitor, an image (video) captured by a camera mounted on the subject autonomous vehicle 1T is displayed. The image information is transmitted from the subject autonomous vehicle 1T to the remote support system 100 in real time via communication. The remote support system 100 displays the image information in the monitor.

[0099] In Figure 4In the example shown, the subject autonomous vehicle 1T outputs a request for assistance REQ when making a right turn at the 1st intersection. That is, the 1st scenario is a right turn at the 1st intersection. The subject autonomous vehicle 1T performs recognition processing to recognize the signal display of the signal light provided at the 1st intersection. In this example, the subject autonomous vehicle 1T recognizes the signal display as a "right arrow" with high accuracy. Therefore, the subject autonomous vehicle 1T determines that, with respect to the signal recognition, remote assistance by an operator is not needed.

[0100] On the other hand, the subject autonomous vehicle 1T cannot confidently determine whether to perform a right turn. As a result, it also cannot determine the timing of performing the right turn. In such a situation, the subject autonomous vehicle 1T sends a request for assistance REQ to the remote assistance system 100. The request for assistance REQ requests assistance for the action determination processing (right turn determination processing) and the timing determination processing. The request for assistance REQ can also include the results of the respective recognition processing (signal recognition), action determination processing, and timing determination processing in the subject autonomous vehicle 1T. In this case, as shown in FIG. 6, the respective results are also displayed on the monitor. Figure 4

[0101] In the operator instruction request processing, the remote assistance system 100 acquires the results of the request for assistance processing associated with the 1st scenario from the performance database 200. For example, the results of the respective vehicle processing and the request for assistance processing performed by the subject autonomous vehicle 1T for the 1st scenario are as follows.

[0102] [Recognition processing (signal recognition)] success probability = 98%, request for assistance probability = 2%

[0103] [Action determination processing (right turn determination)] success probability = 40%, request for assistance probability = 60%

[0104] [Timing determination processing] success probability = 95%, request for assistance probability = 5%

[0105] With respect to vehicle processing for which the past request for assistance probability is sufficiently low, it is generally considered that there is no problem even if it is delegated to the subject autonomous vehicle 1T. Therefore, the remote assistance system 100 recommends to the operator that the timing determination processing be delegated to the subject autonomous vehicle 1T. On the other hand, with respect to vehicle processing for which the past request for assistance probability is high, it is preferable that the operator perform assistance. Therefore, the remote assistance system 100 recommends to the operator that the action determination processing be assisted. That is, the recommended option OPT1 is "assist the action determination processing, but delegate the timing determination processing to the subject autonomous vehicle 1T".

[0106] The remote assistance system 100 at least prompts the recommended option OPT1 to the operator. For example, as shown in FIG. 7, the recommended option OPT1 is displayed on the monitor. Figure 4 ​As shown, the recommended option OPT1 is displayed on the operator's instruction screen. The text "recommended" can also be added to the recommended option OPT1. By referring to the recommended option OPT1, operators can reduce the time spent determining which vehicle to process as the assigned task. This reduces the workload on the operator.

[0107] Furthermore, operators are not required to strictly follow the recommended option OPT1. Depending on the circumstances, operators may also issue instructions different from the recommended option OPT1. Even in this case, the same effect of reduced study time and workload can still be achieved.

[0108] like Figure 4 As shown, multiple OPT options, including the recommended option OPT1, can also be presented to the operator. For example, option OPT2 is "Support both action decision processing and timing decision processing." Option OPT3 is "Support all of identification processing, action decision processing, and timing decision processing." In option OPT3, support is also recommended for the operator regarding identification processing that was not requested from the target autonomous vehicle 1T. Presenting the operator with multiple OPT options, including the recommended option OPT1, allows the operator to easily compare the various options. This also helps to shorten the research time.

[0109] When presenting operators with multiple options (OPT), it is recommended that option OPT1 be presented in a more prominent manner than other options. For example, as... Figure 4 As shown, the text size of the recommended option OPT1 is larger than that of the other options OPT2 and OPT3. The text of the recommended option OPT1 can also be bolder than that of the other options OPT2 and OPT3. Therefore, it is easier for operators to understand the recommended option OPT1.

[0110] 2-3. Effects

[0111] As explained above, according to this embodiment, the remote support system 100 responds to a support request (REQ) from the target autonomous vehicle 1T and requests instructions from the operator for the target autonomous vehicle 1T. Support processing is vehicle handling performed by the operator on behalf of the target autonomous vehicle 1T. On the other hand, delegated processing is processing delegated by the operator to the target autonomous vehicle 1T. When delegated processing increases and support processing decreases, the number of matters that the operator must judge decreases accordingly. This helps to reduce the burden on the operator.

[0112] Further, according to the present embodiment, the remote support system 100 determines the recommended option OPT1 of the combination of the support processing and the assignment processing, based on the performance database 200 that indicates the performance of the support request processing. Then, the remote support system 100 prompts the recommended option OPT1 to the operator. The operator can shorten the time for studying which vehicle processing to be the assignment processing, with reference to the recommended option OPT1. Thus, the load imposed on the operator is reduced.

[0113] Since the load imposed on the operator is reduced, the time required for the operator to deal with a single support request REQ (i.e., a single target autonomous vehicle 1T) is shortened. As a result, the efficiency of the remote support is improved. In addition, this means that a larger number of support requests REQ (target autonomous vehicles 1T) can be dealt with by a limited number of operators. From the viewpoint of cost, this is preferable. According to the present embodiment, it is possible to improve the efficiency of the remote support while suppressing an increase in cost.

[0114] Furthermore, the remote support system 100 of the present embodiment does not perform remote support completely automatically without bypassing the operator. The final instruction content (operator instruction INS) for the target autonomous vehicle 1T is determined by the operator. Therefore, the accuracy of the remote support is ensured. In addition, the operator does not necessarily have to follow the recommended option OPT1. Depending on the situation, the operator can also make an instruction different from the recommended option OPT1. Thus, the flexibility of the remote support is ensured.

[0115] Hereinafter, specific examples of the autonomous vehicle 1 and the remote support system 100 of the present embodiment will be described in detail.

[0116] 3. Autonomous vehicle

[0117] 3-1. Configuration example

[0118] Figure 5 is a block diagram showing a configuration example of the autonomous driving system 10 mounted on the autonomous vehicle 1 of the present embodiment. The autonomous driving system 10 includes a recognition sensor 20, a vehicle state sensor 30, a position sensor 40, a communication device 50, a travel device 60, and a control device 70.

[0119] The recognition sensor 20 recognizes (detects) the situation around the autonomous vehicle 1. The recognition sensor 20 includes at least a camera 25. The recognition sensor 20 can also include a LIDAR (Laser Imaging Detection and Ranging), a radar, or the like.

[0120] The vehicle state sensor 30 detects a state of the automated driving vehicle 1. For example, the vehicle state sensor 30 includes a vehicle speed sensor, an acceleration sensor, a yaw rate sensor, a rudder angle sensor, and the like.

[0121] The position sensor 40 detects a position and an orientation of the automated driving vehicle 1. As the position sensor 40, a GPS (Global Positioning System) sensor is exemplified.

[0122] The communication device 50 communicates with the outside of the automated driving vehicle 1. For example, the communication device 50 communicates with the remote support system 100.

[0123] The travel device 60 includes a steering device, a drive device, and a brake device. The steering device turns a wheel of the automated driving vehicle 1. For example, the steering device includes an EPS (Electric Power Steering) device. The drive device is a power source that generates a driving force. As the drive device, an engine, an electric motor, a hub motor, and the like are exemplified. The brake device generates a braking force.

[0124] The control device 70 controls the automated driving vehicle 1. The control device 70 includes one or a plurality of processors 71 (hereinafter, simply referred to as processors 71) and one or a plurality of memories 72 (hereinafter, simply referred to as memories 72). The processor 71 executes various processes. For example, the processor 71 includes a CPU (Central Processing Unit). The memory 72 stores various information. As the memory 72, a volatile memory, a non-volatile memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), and the like are exemplified. By the processor 71 executing a control program that is a computer program, various processes executed by the processor 71 (the control device 70) are realized. The control program is stored in the memory 72 or recorded in a computer-readable recording medium. The control device 70 can also include one or a plurality of ECUs (Electronic Control Units). A part of the control device 70 can also be an information processing device outside the automated driving vehicle 1. In this case, a part of the control device 70 communicates with the automated driving vehicle 1 and remotely controls the automated driving vehicle 1.

[0125] 3-2. Information Acquisition Process

[0126] The processor 71 acquires driving environment information 80 that indicates a driving environment of the automated driving vehicle 1. The driving environment information 80 is stored in the memory 72.

[0127] Figure 6This is a block diagram illustrating an example of driving environment information 80. Driving environment information 80 includes map information 81, surrounding conditions information 82, vehicle status information 83, and vehicle location information 84.

[0128] Map information 81 indicates lane configuration, road shape, etc. Processor 71 retrieves necessary map information for the area from the map database. The map database can be stored either in a predetermined storage device installed in the autonomous vehicle 1 or in a management server external to the autonomous vehicle 1. In the latter case, processor 71 communicates with the management server to obtain the necessary map information.

[0129] Surrounding conditions information 82 is information representing the conditions surrounding the autonomous vehicle 1. Surrounding conditions information 82 includes information obtained from the identification sensor 20. For example, surrounding conditions information 82 includes image information (IMG) captured by the camera 25. As other examples, surrounding conditions information 82 includes measurement information measured by LIDAR or radar.

[0130] Additionally, the surrounding environment information 82 includes object information related to objects surrounding the autonomous vehicle 1. Examples of objects surrounding the autonomous vehicle 1 include pedestrians, other vehicles (vehicles in front, parked vehicles, etc.), signs, white lines, roadside structures, and obstacles. The object information represents the relative position and relative speed of the object relative to the autonomous vehicle 1. For example, by analyzing the image information IMG obtained from the camera 25, objects can be identified and their relative positions calculated. Furthermore, objects can also be identified and their relative positions and relative speeds calculated based on measurement information obtained from LIDAR or radar.

[0131] Furthermore, the surrounding situation information 82 includes signal display information indicating the recognition result of the traffic light signal display. The processor 71 detects traffic lights around the autonomous vehicle 1 based on the image information IMG captured by the camera 25. Then, the processor 71 identifies the signal display of the traffic lights (e.g., green signal, yellow signal, red signal, right turn signal, etc.) based on the image information IMG. Image analysis methods for detecting (extracting) traffic lights from images and identifying signal displays are known.

[0132] Vehicle state information 83 represents the state of the autonomous vehicle 1. Examples of the state of the autonomous vehicle 1 include vehicle speed, yaw rate, lateral acceleration, and rudder angle. The processor 71 obtains the vehicle state information 83 from the detection results obtained by the vehicle state sensor 30.

[0133] The vehicle position information 84 indicates the position and the orientation of the automated vehicle 1. The vehicle position information 84 is obtained by the position sensor 40. In addition, the processor 71 can also obtain high-precision vehicle position information 84 by using a known self-position estimation process (Localization) using the map information 81 and the surrounding situation information 82 (object information).

[0134] 3-3. Vehicle Travel Control

[0135] The processor 71 executes "vehicle travel control" that controls the travel of the automated vehicle 1. The vehicle travel control includes steering control, acceleration control, and deceleration control. The processor 71 executes the vehicle travel control by controlling the travel device 60. Specifically, the processor 71 executes the steering control by controlling the steering device. In addition, the processor 71 executes the acceleration control by controlling the drive device. In addition, the processor 71 executes the deceleration control by controlling the brake device.

[0136] 3-4. Automated Driving Control

[0137] The processor 71 executes automated driving control based on the driving environment information 80. As the automated driving here, driving in which the driver does not have to concentrate on driving 100% (so-called automated driving of Level 3 or higher) is assumed.

[0138] During the automated driving, the processor 71 executes the above-described vehicle processing. As the vehicle processing, the following examples can be given.

[0139] (1) Recognition Processing: The processor 71 recognizes the situation of the surroundings of the automated vehicle 1 using the recognition sensor 20. For example, the processor 71 recognizes the signal display of a signal light (example: green signal, yellow signal, red signal, right-turn signal, and the like) using the camera 25.

[0140] (2) Action Judgment Processing: The processor 71 judges whether to execute an action based on the result of the recognition processing. As the action of the automated vehicle 1, starting, stopping, right-turning, left-turning, lane changing, and the like are exemplified.

[0141] (3) Timing Judgment Processing: The processor 71 judges the execution timing of the above-described action.

[0142] When the above-described action is executed, the processor 71 generates a target trajectory line of the automated vehicle 1 based on the driving environment information 80. The target trajectory line includes a target position and a target speed. Then, the processor 71 executes the vehicle travel control in such a manner that the automated vehicle 1 traces the target trajectory line.

[0143] 3-5. Support Request Processing

[0144] In a case where remote support by an operator is required, the processor 71 sends a support request REQ to the remote support system 100. More specifically, the processor 71 communicates with the remote support system 100 via the communication device 50, and sends the support request REQ to the remote support system 100. Typically, a situation where remote support by an operator is required is a situation where automatic driving is difficult. Therefore, the support request REQ requests support for at least one of the above-described vehicle processes (recognition process, action judgment process, and timing judgment process). The support request REQ can also include a result of the vehicle process as reference information.

[0145] The processor 71 sends driving environment information 80 required for remote support to the remote support system 100 together with the support request REQ. The driving environment information 80 required for remote support includes at least image information IMG captured by the camera 25. The processor 71 sends the latest image information IMG to the remote support system 100. In addition, the processor 71 can also send image information IMG in a certain period before the support request REQ occurs to the remote support system 100. In addition, the processor 71 can also send necessary vehicle state information 83 and the like to the remote support system 100.

[0146] 3-6. Automatic driving control corresponding to operator instruction

[0147] After sending the support request REQ, the processor 71 accepts an operator instruction INS from the remote support system 100 via the communication device 50. The operator instruction INS includes an instruction from an operator in relation to the support process. In addition, the operator instruction INS also includes a case where a delegation process is designated. The processor 71 starts automatic driving control again in accordance with the operator instruction INS. At this time, with respect to a vehicle process designated as a delegation process, the processor 71 performs recognition or judgment by itself without depending on an instruction from an operator.

[0148] 3-7. Re-support request process

[0149] A case where automatic driving is still difficult after the operator instruction INS is accepted is also considered. In this case, the processor 71 sends the support request REQ to the remote support system 100 again without following the accepted operator instruction INS. The support request REQ can also indicate "this is a re-support request".

[0150] 4. Remote support system

[0151] 4-1. Configuration example

[0152] Figure 7is a block diagram showing a configuration example of the remote support system 100 of the present embodiment. The remote support system 100 includes an information processing apparatus 110, a communication apparatus 120, a display apparatus 130, an input apparatus 140, and a performance database 200.

[0153] The information processing apparatus 110 performs various information processing. The information processing apparatus 110 includes one or a plurality of processors 111 (hereinafter referred to simply as processors 111) and one or a plurality of memories 112 (hereinafter referred to simply as memories 112). The processors 111 execute various processing. For example, the processors 111 include CPUs. The memories 112 store various information. As the memories 112, volatile memories, non-volatile memories, HDDs, SSDs, and the like are exemplified. The functions of the information processing apparatus 110 are realized by the processors 111 executing a remote support program as a computer program. The remote support program is stored in the memories 112. The remote support program can also be recorded on a recording medium that is readable by a computer. The remote support program can also be provided via a network.

[0154] The communication apparatus 120 communicates with the outside. For example, the communication apparatus 120 communicates with the autonomous vehicle 1.

[0155] The display apparatus 130 displays various information. As the display apparatus 130, liquid crystal displays, organic EL displays, head-mounted displays, touch panels, and the like are exemplified. Further, the display apparatus 130 corresponds to the monitor illustrated in Figure 2

[0156] The input apparatus 140 is an interface for accepting input from an operator. As the input apparatus 140, touch panels, keyboards, mice, and the like are exemplified.

[0157] 4-2. Performance Database

[0158] The information processing apparatus 110 can access the performance database 200. The performance database 200 shows, for each scenario, the performance of the vehicle processing and the support request processing performed by each autonomous vehicle 1.

[0159] Figure 8 is a conceptual diagram showing one example of the performance database 200. The performance database 200 indicates the correspondence relationship of vehicle ID information, scenarios, and performance.

[0160] The vehicle ID information includes an ID number given to each autonomous vehicle 1. The vehicle ID information can also include the vehicle type (for example, normal, medium, large, bus, and the like) of each autonomous vehicle 1.

[0161] ​The scenario includes a location where there is a possibility of support request processing by the automated vehicle 1. As the location where support request processing is performed, a crossroad, a merging section, a construction section, and the like are exemplified. Each location is specified by a range of latitude and longitude. The scenario not only is the location, but also can further include the behavior of the automated vehicle 1.

[0162] The performance, for example, includes a support request probability relating to each vehicle processing of the plurality of vehicle processes. The support request probability is a ratio of the number of occurrences of support request processing to the number of times the automated vehicle 1 experiences the scenario. Further, the support request probability and the success probability of the vehicle processing are in a relationship of inversion, and can be said to be equivalent. In the case where the support request probability is higher than the success probability of the vehicle processing, the support request probability is higher than the success probability of the vehicle processing. Figure 8 In the example shown, the performance indicates the success probability of each of the plurality of vehicle processes.

[0163] As another example, the performance can include a support request frequency relating to each vehicle processing of the plurality of vehicle processes. The support request frequency is calculated from the number of occurrences of support request processing in a certain period in the past.

[0164] Figure 9 is a conceptual diagram showing another example of the performance database 200. In Figure 9 In the example shown, the performance shown in the performance database 200 further includes the performance of re-support request processing. For example, the performance of re-support request processing is a re-support request probability. The re-support request probability is a ratio of the number of occurrences of re-support request processing to the number of times the operator instructs the INS.

[0165] As another example, the performance of re-support request processing can include a re-support request frequency. The re-support request frequency is calculated from the number of occurrences of re-support request processing in a certain period in the past.

[0166] Each automated vehicle 1 sends information indicating the scenario and the result of each vehicle processing to the remote support system 100 every time it experiences the scenario. In the case where support request processing is performed, each automated vehicle 1 sends information indicating the content of the support request processing (which vehicle processing to request support for) to the remote support system 100. The processor 111 accepts the information from the automated vehicle 1 via the communication device 120. The processor 111 updates the performance database 200 by registering the collected information to the performance database 200.

[0167] 4-3. Remote Support Processing

[0168] The processor 111 executes remote support processing. The remote support processing includes "operator instruction request processing" of requesting an operator to request an instruction to the subject autonomous vehicle 1T in response to a support request REQ sent from the subject autonomous vehicle 1T. In addition, the remote support processing includes "operator instruction notification processing" of notifying the subject autonomous vehicle 1T of an operator instruction INS from the operator.

[0169] Figure 10 Fig. 27 is a block diagram showing various information associated with the remote support processing of the present embodiment. The various information is stored in the memory 112.

[0170] The support request REQ is sent from the subject autonomous vehicle 1T. The processor 111 accepts the support request REQ via the communication device 120.

[0171] The vehicle-side information 300 is the driving environment information 80 required for remote support. The vehicle-side information 300 includes at least the image information IMG captured by the camera 25. The vehicle-side information 300 can include not only the latest image information IMG but also image information IMG in a certain period before the support request REQ occurs. The vehicle-side information 300 can include the vehicle state information 83. The vehicle-side information 300 is sent from the subject autonomous vehicle 1T. The processor 111 accepts the vehicle-side information 300 via the communication device 120.

[0172] The reference information 400 is information for reference in deciding the recommendation option OPT1.

[0173] The reference information 400 includes performance information 410. The performance information 410 is information obtained from the performance database 200. Specifically, the performance information 410 indicates a performance associated with the 1st scenario in which the subject autonomous vehicle 1T is located. The processor 111 accesses the performance database 200, and obtains the performance information 410 from the performance database 200.

[0174] The reference information 400 can include autonomous driving system information 430. The autonomous driving system information 430 indicates a state of the autonomous driving system 10. For example, the autonomous driving system information 430 indicates whether the autonomous driving software is just after being updated. The autonomous driving system information 430 can indicate the accuracy of the sensors such as the recognition sensor 20. The autonomous driving system information 430 can indicate whether the traveling device 60 is normal. The autonomous driving system information 430 is sent from the subject autonomous vehicle 1T. The processor 111 accepts the autonomous driving system information 430 via the communication device 120.

[0175] The reference information 400 can also include environment condition information 440. The environment condition information 440 indicates an environment in which the subject automated vehicle 1T is located. As the environment, weather, meteorological conditions, time, season, congestion conditions, and the like are exemplified. The environment condition information 440 is provided from an information service server or the subject automated vehicle 1T. The processor 111 accepts the environment condition information 440 via the communication device 120.

[0176] The option information 500 indicates a plurality of options OPT of a combination of the support processing and the entrustment processing. The plurality of options OPT includes a recommended option OPT1. The processor 111 generates the option information 500 by the processing described later.

[0177] The operator instruction INS is an instruction made by an operator to the subject automated vehicle 1T. The operator instruction INS includes an instruction from the operator in relation to the support processing. In addition, the operator instruction INS also includes a case where the designation of the entrustment processing is included. The operator inputs the operator instruction INS using the input device 140. The processor 111 accepts the operator instruction INS via the input device 140.

[0178] Figure 11 is a flowchart showing an operator instruction request processing in the remote support processing.

[0179] In step S110, the processor 111 determines whether the support request REQ is accepted from the subject automated vehicle 1T. In a case where the support request REQ is accepted (step S110, "Yes"), the processing proceeds to step S120. In a case other than this (step S110, "No"), the processing of this time is ended.

[0180] In step S120, the processor 111 acquires the vehicle side information 300 and the reference information 400.

[0181] In step S130, the processor 111 displays the vehicle side information 300 on the display device 130. In particular, the processor 111 displays the image information IMG on the display device 130 (refer to Figure 4 ).

[0182] In step S140, the processor 111 sets a plurality of options OPT of a combination of the support processing and the entrustment processing. Further, the processor 111 decides a recommended option OPT1 recommended to the operator among the plurality of options OPT. Here, the processor 111 decides the recommended option OPT1 in accordance with the reference information 400 described above. Various examples of deciding the recommended option OPT1 based on the reference information 400 are described later. The processor 111 generates the option information 500 by this processing.

[0183] In step S150, the processor 111 displays the option information 500 on the display device 130. At this time, the processor 111 displays at least the recommended option OPT1. The processor 111 can also display a plurality of options OPT including the recommended option OPT1. The processor 111 can also display a plurality of options OPT in a manner that makes the recommended option OPT1 stand out from the other options OPT (see FIG. 6). Figure 4

[0184] Figure 12 FIG. 10 is a flowchart showing an operator instruction notification process in the remote support process.

[0185] In step S160, the processor 111 determines whether an operator instruction INS has been input by the operator. In the case where the operator instruction INS has been input (step S160, YES), the process proceeds to step S170. In the case other than this (step S160, NO), the process of this time ends.

[0186] In step S170, the processor 111 communicates with the target autonomous vehicle 1T via the communication device 120, and notifies the target autonomous vehicle 1T of the operator instruction INS.

[0187] 4-4. Example of recommended option decision process

[0188] Hereinafter, various examples of the recommended option decision process (step S140) will be described.

[0189] 4-4-1. First example

[0190] In the first example, the processor 111 decides the recommended option OPT1 based on the performance information 410. The performance information 410 indicates a performance associated with the first scenario in which the target autonomous vehicle 1T is located.

[0191] For example, the performance includes a support request probability or a support request frequency with respect to each of a plurality of vehicle processes. For convenience, an arbitrary process among the plurality of vehicle processes is referred to as a "first vehicle process". The processor 111 acquires a support request probability or a support request frequency with respect to the first vehicle process from the performance information 410. Then, based on the support request probability or the support request frequency with respect to the first vehicle process, the processor 111 decides to set the first vehicle process as a support process in the recommended option OPT1 or as a delegation process.

[0192] ​For example, as the probability of a request for assistance or the frequency of requests for assistance for the 1st vehicle processing decreases, the probability that the 1st vehicle processing is set to the delegated processing in the recommended option OPT1 increases. Conversely, as the probability of a request for assistance or the frequency of requests for assistance for the 1st vehicle processing increases, the probability that the 1st vehicle processing is set to the assistance processing in the recommended option OPT1 increases.

[0193] As another example, the probability of a request for assistance or the frequency of requests for assistance can be compared with a predetermined threshold value. In a case where the probability of a request for assistance or the frequency of requests for assistance for the 1st vehicle processing is equal to or higher than the predetermined threshold value, the processor 111 sets the 1st vehicle processing to the assistance processing in the recommended option OPT1. On the other hand, in a case where the probability of a request for assistance or the frequency of requests for assistance for the 1st vehicle processing is lower than the predetermined threshold value, the processor 111 sets the 1st vehicle processing to the delegated processing in the recommended option OPT1.

[0194] In this way, the content of the recommended option OPT1 is decided based on the performance information 410. The performance information 410 indicates past performance related to the request for assistance processing, so an appropriate recommended option OPT1 can be decided.

[0195] 4-4-2. 2nd Example

[0196] In the 2nd example, the performance of the re-request for assistance processing is considered. The processor 111 acquires the performance information 410 including the performance of the re-request for assistance processing (refer to Figure 9 ), and decides the recommended option OPT1 based on the performance of the re-request for assistance processing.

[0197] For example, the performance of the re-request for assistance processing includes the probability of a re-request for assistance or the frequency of re-requests for assistance. The processor 111 acquires the probability of a re-request for assistance or the frequency of re-requests for assistance from the performance information 410. Then, the processor 111 sets the assistance processing and the delegated processing in the recommended option OPT1 based on the probability of a re-request for assistance or the frequency of re-requests for assistance. For example, as the probability of a re-request for assistance or the frequency of re-requests for assistance increases, the proportion of the assistance processing in the recommended option OPT1 increases and the proportion of the delegated processing decreases. Conversely, as the probability of a re-request for assistance or the frequency of re-requests for assistance decreases, the proportion of the delegated processing in the recommended option OPT1 increases and the proportion of the assistance processing decreases.

[0198] 4-4-3. 3rd Example

[0199] In the 3rd example, the processor 111 decides the recommended option OPT1 based on the automatic driving system information 430.

[0200] For example, in a case where the automatic driving software has just been updated, the reliability of past performance decreases. Therefore, in this case, the processor 111 increases the proportion of support processing in the recommendation option OPT1 and decreases the proportion of delegation processing.

[0201] As another example, in a case where the accuracy of the sensor such as the recognition sensor 20 decreases, the accuracy of the automatic driving control also decreases. Therefore, in this case, the processor 111 increases the proportion of support processing in the recommendation option OPT1 and decreases the proportion of delegation processing.

[0202] 4-4-4. 4th example

[0203] In the 4th example, the processor 111 decides the recommendation option OPT1 in accordance with the environmental condition information 440.

[0204] For example, in a case where the weather is bad, there is a possibility that the accuracy of the recognition processing decreases and the accuracy of the automatic driving control also decreases. Therefore, the processor 111 increases the proportion of support processing in the recommendation option OPT1 and decreases the proportion of delegation processing.

[0205] 4-4-5. 5th example

[0206] It is also possible to combine a plurality of examples in the 1st example to the 4th example.

Claims

1. A remote support system that remotely supports travel of an autonomous vehicle, wherein the autonomous vehicle executes: a plurality of vehicle processes including recognition and determination in autonomous driving; and a support request process that, in a situation in which autonomous driving is difficult, sends a support request that requests support of at least one vehicle process of the plurality of vehicle processes to the remote support system, the remote support system includes: one or more processors; and a performance database that shows, for each scenario, a performance of the support request process executed by the autonomous vehicle, the performance including a probability or frequency of a request for the support of each vehicle process of the plurality of vehicle processes, the one or more processors are configured to execute: an operator instruction request process that, in response to the support request sent from a subject autonomous vehicle in a first scenario, requests an instruction for the subject autonomous vehicle from an operator; and an operator instruction notification process that notifies the subject autonomous vehicle of the instruction from the operator, a support process is a vehicle process of the plurality of vehicle processes of the first scenario that is performed by the operator instead of the subject autonomous vehicle, a delegation process is a vehicle process of the plurality of vehicle processes of the first scenario that is delegated to the subject autonomous vehicle by the operator, in the operator instruction request process, the one or more processors acquire, from the performance database, the performance of the support request process associated with the first scenario, a recommended option of a plurality of options of a combination of the support process and the delegation process is decided as a recommended option for the operator in accordance with the performance associated with the first scenario, at least the recommended option is prompted to the operator, in the operator instruction request process, the one or more processors: acquire, from the performance associated with the first scenario, the probability or the frequency of a request for the support of each vehicle process of the plurality of vehicle processes, and decide each vehicle process of the plurality of vehicle processes as the support process in the recommended option or as the delegation process in accordance with the acquired probability or frequency.

2. The remote support system according to claim 1, wherein the one or more processors prompt the plurality of options including the recommended option to the operator.

3. The remote support system according to claim 2, wherein the one or more processors prompt the plurality of options to the operator in a manner in which the recommended option is more noticeable than an option other than the recommended option.

4. The remote support system according to claim 1, wherein as the probability or the frequency of a request for the support of the first vehicle process becomes lower, a probability that the first vehicle process is decided as the delegation process in the recommended option becomes higher.

5. The remote support system according to claim 1, wherein the one or more processors ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ in a case where the probability or the frequency of the request for the support for the first vehicle process is equal to or higher than a threshold value, the first vehicle process is set to the support process among the recommended options, in a case where the probability or the frequency of the request for the support for the first vehicle process is lower than the threshold value, the first vehicle process is set to the delegation process among the recommended options.

6. The remote support system according to any one of claims 1 to 5, wherein the plurality of vehicle processes include: an identification process that identifies a situation of a periphery of the automated vehicle; an action determination process that determines whether to perform an action based on a result of the identification process; and a timing determination process that determines a timing of performing the action.

7. A remote support system that remotely supports travel of an automated vehicle, wherein the automated vehicle performs: a plurality of vehicle processes including identification and determination in automated driving; and a support request process that, in a situation where automated driving is difficult, sends a support request that requests support for at least one of the plurality of vehicle processes to the remote support system, the remote support system includes: one or more processors; and a performance database that shows, for each scenario, a performance of the support request process performed by the automated vehicle, the one or more processors are configured to perform: an operator instruction request process that, in response to the support request sent from a subject automated vehicle in a first scenario, requests an instruction for the subject automated vehicle from an operator; and an operator instruction notification process that notifies the subject automated vehicle of the instruction from the operator, a support process is a vehicle process, among the plurality of vehicle processes of the first scenario, that is performed by the operator instead of the subject automated vehicle, a delegation process is a vehicle process, among the plurality of vehicle processes of the first scenario, that is delegated to the subject automated vehicle by the operator, in the operator instruction request process, the one or more processors: obtain, from the performance database, the performance of the support request process associated with the first scenario, determine, from the performance associated with the first scenario, a recommended option recommended to the operator among a plurality of options of a combination of the support process and the delegation process, at least prompt the operator of the recommended option, the support request process performed by the automated vehicle includes a re-support request process that, after the instruction is accepted from the operator, sends the support request again to the remote support system without following the accepted instruction, the performance includes a probability or a frequency of the re-support request process, the one or more processors: obtain, from the performance associated with the first scenario, the probability or the frequency of the re-support request process, determine, from the obtained probability or frequency, the support process and the delegation process among the recommended options.

8. The remote support system according to claim 7, wherein ​ ​ The proportion of the support processing in the recommended options increases as the probability or the frequency of the support request processing increases.

9. The remote support system according to claim 7 or 8, wherein the plurality of vehicle processes include: a recognition process that recognizes a situation of a periphery of the automated vehicle; an action determination process that determines whether to perform an action based on a result of the recognition process; and a timing determination process that determines a timing of performing the action.

10. A remote support method of remotely supporting travel of an automated vehicle, wherein the automated vehicle performs: a plurality of vehicle processes including recognition and determination in automated driving; and a support request process that, in a situation in which automated driving is difficult, sends a support request that requests support of at least one vehicle process of the plurality of vehicle processes to a remote support system, a performance database shows, for each scenario, a performance of the support request process performed by the automated vehicle, the performance including a probability or a frequency that each vehicle process of the plurality of vehicle processes requests the support, the remote support method includes: an operator instruction request process that, in response to the support request sent from a subject automated vehicle in a first scenario, requests an instruction for the subject automated vehicle from an operator; and an operator instruction notification process that notifies the subject automated vehicle of the instruction from the operator, a support process is a vehicle process of the plurality of vehicle processes of the first scenario that is performed by the operator instead of the subject automated vehicle, a delegation process is a vehicle process of the plurality of vehicle processes of the first scenario that is delegated to the subject automated vehicle by the operator, the operator instruction request process includes: a process of acquiring, from the performance database, the performance of the support request process associated with the first scenario; a process of deciding, from the performance of the support request process associated with the first scenario, a recommended option of the plurality of options of combinations of the support process and the delegation process to recommend to the operator; and a process of at least prompting the operator of the recommended option, in the operator instruction request process: the probability or the frequency that each vehicle process of the plurality of vehicle processes requests the support is acquired from the performance associated with the first scenario, each vehicle process of the plurality of vehicle processes is decided to be the support process in the recommended option or to be the delegation process based on the acquired probability or frequency.

11. A remote support method of remotely supporting travel of an automated vehicle, wherein the automated vehicle performs: a plurality of vehicle processes including recognition and determination in automated driving; and a support request process that, in a situation in which automated driving is difficult, sends a support request that requests support of at least one vehicle process of the plurality of vehicle processes to a remote support system, a performance database shows, for each scenario, a performance of the support request process performed by the automated vehicle, ​ ​ The remote assistance method includes: operation-personnel instruction request processing that, in response to the assistance request from the object autonomous vehicle in the first scenario, requests an instruction for the object autonomous vehicle from an operation personnel; and operation-personnel instruction notification processing that notifies the object autonomous vehicle of the instruction from the operation personnel, the assistance processing is the vehicle processing in the plurality of vehicle processes of the first scenario, which is performed by the operation personnel instead of the object autonomous vehicle, the commission processing is the vehicle processing in the plurality of vehicle processes of the first scenario, which is commissioned by the operation personnel to the object autonomous vehicle, the operation-personnel instruction request processing includes: processing that acquires the performance of the assistance request processing associated with the first scenario from the performance database; processing that determines a recommended option of the combination of the assistance processing and the commission processing from the performance of the assistance request processing associated with the first scenario, and recommends the recommended option to the operation personnel; and processing that at least prompts the recommended option to the operation personnel, the assistance request processing performed by the autonomous vehicle includes re-assistance request processing that, after accepting the instruction from the operation personnel, re-sends the assistance request to the remote assistance system without following the accepted instruction, the performance includes a probability or frequency of the re-assistance request processing, the operation-personnel instruction request processing includes processing that: acquires the probability or frequency of the re-assistance request processing from the performance associated with the first scenario, sets the assistance processing and the commission processing in the recommended option based on the acquired probability or frequency.

Images