Operation assistance device

Abstract

An operation assistance device (100) comprises: a situation acquisition unit (101) that acquires information on the surrounding environment (203) of a moving body; and a determination delay prediction unit (104) that predicts, on the basis of the information on the surrounding environment (203) of the moving body, whether or not the determination of an autonomous action of the moving body will be delayed.

Description

Operation support device

[0001] The present disclosure relates to a driving assistance device that assists driving of a moving body that operates autonomously, such as an autonomous driving vehicle.

[0002] In transportation services that utilize autonomous driving, the autonomous driving system is designed to be safe, which can result in longer decision-making times for autonomous driving compared to human drivers. For example, when an autonomous vehicle attempts to turn right at an intersection and encounters an oncoming vehicle, even if a human driver would initiate the right turn, the system performance, such as the recognition performance and processing speed of the autonomous driving system's sensors, as well as the safety design of the autonomous driving system, may determine that the vehicle should wait, resulting in a longer turn. Such long waiting times for autonomous vehicles can lead to congestion and delays for following vehicles, which could hinder cooperative driving behavior with other vehicles and the smooth operation of transportation services.

[0003] One solution to this problem is for a human operator to temporarily intervene in the driving operation. A remote operator can monitor the autonomous vehicle and manually operate it from a remote location if the autonomous vehicle becomes idle for a long time, preventing operational delays.

[0004] For example, Patent Document 1 below discloses a monitoring system that determines that a situation requiring remote operation has occurred when an autonomous vehicle remains stopped for a period of time equal to or longer than a threshold, and calls an operator. The monitoring system of Patent Document 1 prevents the operator from being called every time the autonomous vehicle stops, thereby reducing the burden on the operator.

[0005] Japanese Patent Application Laid-Open No. 2021-56621

[0006] In the monitoring system of Patent Document 1, whether remote operation is necessary is determined based on the length of time the vehicle has been stopped. Therefore, even in situations where operator intervention is not required, such as when an autonomous vehicle is turning right at an intersection and it is taking a long time to turn because there is a constant stream of oncoming vehicles, an operator is called if the length of time the vehicle has been stopped reaches a threshold. Furthermore, even if a situation arises where operator intervention is required, the operator may not be called until the length of time the vehicle has been stopped reaches the threshold, which could result in a delay in operator intervention.

[0007] The present disclosure has been made to solve the above-mentioned problems, and aims to provide an operation assistance device that supports the operation of a mobile body by enabling an operator to appropriately determine whether or not a situation requires remote control of an autonomously operating mobile body.

[0008] The operation assistance device according to the present disclosure includes a situation acquisition unit that acquires information about the surrounding environment of a mobile body, and a judgment delay prediction unit that predicts whether a judgment about the autonomous operation of the mobile body will be delayed based on the information about the surrounding environment of the mobile body.

[0009] The travel assistance device according to the present disclosure allows an operator to appropriately determine whether or not a situation requires remote control of an autonomously operating moving object.

[0010] FIG. 1 is a diagram illustrating the configuration of a travel assistance device according to a first embodiment. FIG. 2 is a diagram illustrating an example of the configuration of a judgment delay recording unit. FIG. 3 is a diagram illustrating an example of information acquired by a short-distance prediction unit from the judgment delay recording unit. FIG. 4 is a diagram illustrating an example of information acquired by a long-distance prediction unit from the judgment delay recording unit. FIG. 5 is a conceptual diagram of information acquired by a long-distance prediction unit from the situation acquisition unit and the judgment delay prediction unit. FIG. 6 is a flowchart illustrating the operation of the short-distance prediction unit. FIG. 7 is a flowchart illustrating the operation of the long-distance prediction unit. FIG. 8 is a flowchart illustrating the operation of the judgment delay recording unit. FIG. 9 is a flowchart illustrating the operation of the judgment delay recording unit for calculating the normal length of a target vehicle's stop duration and the autonomous driving judgment time. FIG. 10 is a flowchart illustrating the operation of a recommended route creation unit. FIG. 11 is a conceptual diagram illustrating the relationship between a travel assistance device and multiple operators. FIG. 12 is a diagram illustrating the configuration of an allocation unit. FIG. 13 is a diagram illustrating an example of a calculation table for the time required for an operator to respond to a task. FIG. 14 is a diagram illustrating the configuration of a travel assistance device according to a second embodiment. FIG. 15 is a diagram illustrating an example of a highlighted display on a map. FIG. 16 is a flowchart showing the operation of the travel assistance device to highlight a map. FIG. 17 is a flowchart showing the operation of the highlighting condition sharing unit to update and share a judgment time model. FIG. 18 is a flowchart showing the operation of the travel assistance device to present candidates to be added to the highlighting to an operator. FIG. 19 is a flowchart showing the operation of the travel assistance device to notify an operator that manual driving is appropriate. FIG. 20 is a diagram showing the configuration of a travel assistance device according to embodiment 3. FIG. 21 is a diagram showing an example display of processing content related to determination of autonomous driving of a target vehicle. FIG. 22 is a diagram showing an example of information on the ideal driving position of a service. FIG. 23 is a diagram showing an example of an ideal driving position table. FIG. 24 is a diagram showing an example display of the driving status of a service that is a target vehicle. FIG. 25 is a flowchart showing the operation of the ideal driving position calculation unit. FIG. 26 is a flowchart showing the operation of the ideal driving position calculation unit to correct the ideal driving position. FIG. 27 is a diagram showing an example of the hardware configuration of a travel assistance device. FIG. 28 is a diagram showing an example of the hardware configuration of a travel assistance device.

[0011] In the following embodiments, an autonomously operating vehicle (e.g., an autonomously operating bus) will be described as an example of an autonomously operating moving body. However, the autonomously operating moving body is not limited to a vehicle. As the autonomously operating moving body, various artificial objects that move automatically, such as an air vehicle (e.g., a drone, a probe, etc.), a mobility robot, etc., can be envisioned.

[0012] <First Embodiment> Fig. 1 is a diagram showing the configuration of a travel assistance device 100 according to a first embodiment. The travel assistance device 100 assists in the travel of a vehicle, which is an autonomously operating mobile body, and is operated by an operator 205. Hereinafter, a vehicle that is the target of travel assistance by the travel assistance device 100 will be referred to as a "target vehicle."

[0013] The travel assistance device 100 is operated by an operator 205. The operator 205 remotely monitors the target vehicle through the travel assistance device 100, determines whether the target vehicle is in a situation requiring remote control, and remotely controls the target vehicle if it determines that remote control is necessary. As will be described later, the travel assistance device 100 predicts whether the target vehicle will be in a situation requiring remote control, and if it predicts that a situation requiring remote control will occur, notifies the operator 205 to that effect. Therefore, the operator 205 does not need to constantly monitor the target vehicle, and can be in charge of multiple target vehicles at the same time.

[0014] As shown in Figure 1, the operation assistance device 100 includes a status acquisition unit 101, a status presentation unit 102, an operation information acquisition unit 103, a decision delay prediction unit 104, a decision delay occurrence status presentation unit 105, a decision delay recording unit 106, a recommended route creation unit 107, and an allocation unit 108.

[0015] The situation acquisition unit 101 acquires information on the surrounding environment 203 of the target vehicle and information on the target vehicle's autonomous driving system 204. The surrounding environment 203 of the target vehicle includes not only the surrounding environment of the current position of the target vehicle, but also the surrounding environment of the points where the target vehicle is scheduled to pass (i.e., the surrounding environment of the planned driving route of the target vehicle).

[0016] Specific examples of the surrounding environment 203 include road conditions (e.g., road surface conditions, conditions of objects such as obstacles on the road, road construction locations, etc.), conditions of other traffic participants (positions, movements, etc.), weather conditions (sunny, rainy, cloudy, snowy, etc.), and surrounding sound conditions. The other traffic participants also include other vehicles present around the target vehicle. The information about the surrounding environment 203 may also include fixed information (information that does not change over time), such as the type of road (general road, expressway, etc.), the type of road surface (paved road, gravel road, etc.), the location of pedestrian crossings, and the location of traffic lights. The situation acquisition unit 101 may acquire the information about the surrounding environment 203 from a sensor mounted on the target vehicle, or may acquire it via communication from infrastructure sensors (cameras, LiDAR, etc.) installed on the road.

[0017] Specific examples of information from the autonomous driving system 204 of the target vehicle include information on decisions made by the autonomous driving system 204 regarding the autonomous driving of the target vehicle (autonomous operation of a mobile body), and information acquired by the autonomous driving system 204 from devices and sensors of the target vehicle (for example, the driving status and interior status of the target vehicle). Information on autonomous driving decisions includes, for example, the content of the decision, the decision result, and the decision time (the time required to make the decision). Examples of the driving status of the target vehicle include position, speed, acceleration, duration of stopping, engine RPM, steering angle, accelerator / brake status, turn signal status, and horn status. Examples of the interior status include the status of the occupants, the status of cargo such as luggage, and the status of the interior space (temperature, sound, etc.).

[0018] The status presentation unit 102 displays the information acquired by the status acquisition unit 101 on the display device 201 to present it to an operator 205 who is a user.

[0019] The operation information acquisition unit 103 acquires operation information, which is information relating to the operation of the target vehicle, such as the target vehicle's operation schedule and operation route (planned driving route), from the target vehicle's operation management system 202.

[0020] The decision delay prediction unit 104 predicts whether it will take a long time for the autonomous driving system 204 of the target vehicle to make an autonomous driving decision, based on the information about the surrounding environment 203 acquired by the situation acquisition unit 101. Hereinafter, the time it takes to make a decision will be referred to as a "delay" in decision. Note that the time it takes to make a decision not only includes the time it takes for the system to process and calculate, but also the time it takes to take action before moving on to the next task, such as the waiting time to wait for the timing to start turning right when making a right turn. In other words, a delay in decision does not only mean that it takes a long time to process and calculate for the decision, but also includes a case where it does not take a long time to process and calculate for the decision but takes a long time to take action before moving on to the next task.

[0021] The decision delay prediction unit 104 includes a short-distance prediction unit 104a and a long-distance prediction unit 104b. The short-distance prediction unit 104a predicts whether the decision to engage in autonomous driving will be delayed at positions close to the current position of the target vehicle (including the current position of the target vehicle) based on information about the target vehicle's surrounding environment 203 and information about the target vehicle's state. On the other hand, the long-distance prediction unit 104b predicts whether a situation will arise in which the decision to engage in autonomous driving will be delayed at positions on the planned driving route away from the current position of the target vehicle, based on information about the target vehicle's surrounding environment 203 and information about the target vehicle's planned driving route.

[0022] The judgment delay occurrence status presenting unit 105 presents the notification transmitted from the judgment delay prediction unit 104 (the short distance prediction unit 104a and the long distance prediction unit 104b) to the user, that is, the operator 205. Here, the judgment delay occurrence status presenting unit 105 displays the notification on the display device 201, but the notification may also be output as audio.

[0023] The decision delay recording unit 106 records the situation when a decision delay in autonomous driving actually occurs in the autonomous driving system 204. In other words, the decision delay recording unit 106 accumulates information on decision delays in autonomous driving that have occurred in the past. The decision delay recording unit 106 may record continuous data for sections in which a decision delay in autonomous driving occurred.

[0024] When the autonomous driving decision by the autonomous driving system 204 is delayed, the decision delay recording unit 106 records, as information about the situation at that time, information about the driving state of the target vehicle (such as location and duration of stoppage), information about the autonomous driving system 204 (such as the autonomous driving decision time), and information about the surrounding environment 203 (such as information about other traffic participants). Specifically, the decision delay recording unit 106 calculates the duration of stoppage of the target vehicle or the calculation time of each system (recognition, judgment, control, etc.) of the autonomous driving system 204, and if these times are longer than the average time, determines that the autonomous driving decision was delayed. The "average time" here may be, for example, the average time across all situations, the average time when the vehicle has traveled to the same location in the past, or the average time when the vehicle has traveled in the same situation in the past (such as turning right at an intersection, turning left at an intersection, a crosswalk, or near a construction zone).

[0025] Fig. 2 shows an example of the configuration of the decision delay recording unit 106. In the example of Fig. 2, the decision delay recording unit 106 is made up of an average time calculation unit 106a, a comparison unit 106b, and a recording unit 106c.

[0026] The average time calculation unit 106a calculates the above-mentioned "average time" from the target vehicle's stop duration acquired from the situation acquisition unit 101, the calculation times of each system (recognition, judgment, control, etc.) of the autonomous driving system 204, the target vehicle's position, information on the surrounding environment 203, etc. The comparison unit 106b compares the target vehicle's stop duration or the calculation times of each system of the autonomous driving system 204 with the average time to determine whether the autonomous driving decision has been delayed. The recording unit 106c records information on the driving state of the target vehicle, information on the autonomous driving system 204, and information on the surrounding environment 203 when it is determined that the autonomous driving decision has been delayed.

[0027] The recommended route creation unit 107 identifies locations and road environments where automated driving decisions are likely to be delayed based on the information recorded in the decision delay recording unit 106 (information on past automated driving decision delays) and the prediction results from the decision delay prediction unit 104 (information on predicted automated driving decision delays), and creates at least one of a route recommended for smooth operation (hereinafter referred to as a "recommended route") and a route not recommended (hereinafter referred to as a "non-recommended route"). Specifically, the recommended route creation unit 107 identifies locations where automated driving decisions are frequently delayed and locations where the long-distance prediction unit 104b predicts that a situation where automated driving decisions will be delayed will occur, and calculates a route that avoids these locations as much as possible as a recommended route. In addition, the recommended route creation unit 107 calculates a route that passes through many of these locations as a non-recommended route. At least one of the recommended route and non-recommended route created by the recommended route creation unit 107 is transmitted to the display device 201 or another system.

[0028] When there are multiple operators 205, the allocation unit 108 determines the operator 205 to present and the timing of the presentation, taking into consideration the work status of the operators 205, the status of the target vehicle, the difficulty of the task, and the time required to complete the task. The term "task" here refers to an action that the target vehicle traveling in autonomous driving should take (e.g., turning right at an intersection). Furthermore, "responding to a task" refers to the operator 205 intervening in the driving behavior of the target vehicle to enable the target vehicle to complete the task. Here, driving behavior refers to the "cognition," "judgment," and "control" required for autonomous driving. An example of the operator 205 intervening in the "cognition" of autonomous driving is when the operator 205 changes the sensing range of a sensor that acquires information about the surrounding environment 203. More specifically, the operator 205 changes the sensing range so as not to include surrounding vehicles that may cause delays in judgment. An example of operator 205's intervention in the "judgment" of automated driving is when the target vehicle turns right at an intersection, and the automated driving system 204 judges to wait, but the operator 205 judges that a right turn is possible and gives a voice command to the automated driving system 204 to start the right turn (manual operation to start a right turn corresponds to intervention in "control"). In this case, a voice recognition means (not shown) of the travel assistance device 100 recognizes the voice of the operator 205, and a control unit (not shown) of the travel assistance device 100 sends a command to start a right turn to the automated driving system 204. Intervention in the "control" of automated driving by the operator 205 is the operator 205's intervention in the driving of the target vehicle, that is, remote operation of the target vehicle. In this way, the operator 205's intervention in the driving behavior of the target vehicle includes not only remote operation of the target vehicle (intervention in "control") but also operational support of the automated driving system 204 (intervention in "cognition" or "judgment"). Note that responding to a task includes not only the operator 205 actually intervening in the driving behavior of the target vehicle, but also determining whether or not to intervene in the driving behavior.

[0029] The input receiving unit 109 is a means for the operator 205 to input information necessary for the processing performed by the allocation unit 108. The allocation unit 108 and the input receiving unit 109 will be described in detail later.

[0030] Here, the short-distance prediction unit 104a and the long-distance prediction unit 104b will be described in detail.

[0031] The short-distance prediction unit 104a predicts whether the autonomous driving decision will be delayed at the position of the target vehicle or at a position close to the target vehicle, based on the driving state of the target vehicle and information on the surrounding environment 203. The surrounding environment 203 here includes the positional relationship between the target vehicle and traffic participants (pedestrians, other vehicles, etc.) and objects (obstacles, etc.) around the target vehicle, as well as the movements of the traffic participants and objects. Specifically, the short-distance prediction unit 104a calculates the traveling direction of the target vehicle from the planned traveling route of the target vehicle acquired from the operation information acquisition unit 103. Furthermore, the decision delay prediction unit 104 calculates the relative positions (distance and direction from the target vehicle) of traffic participants and objects present in the traveling direction of the target vehicle, based on information on the surrounding environment 203 and the autonomous driving system 204 acquired by the situation acquisition unit 101.

[0032] For example, if the distance to a traffic participant or object in the target vehicle's direction of travel is less than a predetermined threshold and the traffic participant or object is not stationary, the short-distance prediction unit 104a predicts that the decision to perform autonomous driving will be delayed. For example, if the number of vehicles traveling in a certain section of the oncoming lane is greater than or equal to a predetermined threshold when the target vehicle turns right at an intersection, the decision delay prediction unit 104 predicts that the decision to perform autonomous driving will be delayed. For example, if the number of traffic participants (pedestrians, cyclists, etc.) present in a certain section of the sidewalk to the left of the target vehicle is greater than or equal to a predetermined threshold when the target vehicle is turning left at an intersection, the short-distance prediction unit 104a predicts that the decision to perform autonomous driving will be delayed. For example, if the number of vehicles traveling in a certain section of the road is greater than or equal to a predetermined threshold when the target vehicle merges onto a road from a parking lot, or if the number of traffic participants present on the sidewalk between the parking lot and the road is greater than or equal to a predetermined threshold, the short-distance prediction unit 104a predicts that the decision to perform autonomous driving will be delayed.

[0033] Furthermore, the short-distance prediction unit 104a appropriately modifies each of the thresholds based on information recorded in the decision delay recording unit 106 (e.g., the situation of automated driving when a decision delay occurred in the past, and information about other traffic participants and objects when the decision delay occurred). By modifying each threshold, the short-distance prediction unit 104a can predict decision delays that were previously unpredictable, or can determine a situation in which a decision delay was erroneously predicted as a situation in which a decision delay will not occur, thereby improving the accuracy of decision delay prediction. For example, if the short-distance prediction unit 104a references the information recorded in the decision delay recording unit 106 and finds that automated driving decision delays frequently occurred even in situations in which the distance from the target vehicle to a traffic participant or object was greater than the threshold, the short-distance prediction unit 104a can increase the accuracy of decision delay prediction by decreasing the threshold. Conversely, if it finds that automated driving decision delays rarely occurred even in situations in which the distance from the target vehicle to a traffic participant or object was shorter than the threshold, the short-distance prediction unit 104a can increase the threshold to reduce the frequency of erroneous decision delay predictions. FIG. 3 shows an example of information that the short distance prediction unit 104a acquires from the decision delay recording unit 106.

[0034] The long-distance prediction unit 104b predicts whether a situation will occur in which the decision to perform autonomous driving will be delayed, based on the status of traffic participants present in the vicinity of the planned driving route of the target vehicle and information about the roads on the planned driving route. Specifically, the long-distance prediction unit 104b acquires information about the surrounding environment 203 of the planned driving route at positions distant from the target vehicle (e.g., several hundred meters ahead) from the situation acquisition unit 101, based on the planned driving route of the target vehicle acquired from the operation information acquisition unit 103. The information about the surrounding environment 203 at positions distant from the target vehicle can be acquired, for example, by communication from infrastructure sensors installed on the road.

[0035] For example, if there are a large number of pedestrians around an intersection where the target vehicle is scheduled to turn right or left, the long-distance prediction unit 104b predicts that a situation will arise in which the decision to perform autonomous driving will be delayed.The long-distance prediction unit 104b also predicts that a situation will arise in which the decision to perform autonomous driving will be delayed in construction sections, accident locations, locations with parked vehicles on the road, locations with traffic controllers, etc. on the planned driving route of the target vehicle.

[0036] Furthermore, the long-distance prediction unit 104b analyzes the information recorded in the decision delay recording unit 106 and increases the number of situations that are determined to cause a delay in autonomous driving decisions. For example, if a certain situation causes a delay in autonomous driving decisions more than a certain number of times, the long-distance prediction unit 104b adds that situation as a new situation that causes a delay in autonomous driving decisions. Figure 4 shows an example of information that the long-distance prediction unit 104b acquires from the decision delay recording unit 106.

[0037] 5 shows an image diagram of the information that the long-distance prediction unit 104b acquires from the situation acquisition unit 101 and the operation information acquisition unit 103. As shown in FIG. 5, the estimation of whether a situation will occur in which a decision to perform autonomous driving will be delayed is based on information about roads and traffic participants related to the planned driving route, and therefore the long-distance prediction unit 104b does not need to acquire information about roads and traffic participants located away from the planned driving route.

[0038] 6 is a flowchart showing the operation of the short distance prediction unit 104a. The operation of the short distance prediction unit 104a will be described with reference to FIG.

[0039] First, the short-distance prediction unit 104a acquires information about the planned driving route (driving route) of the target vehicle from the driving information acquisition unit 103 (step S101). The short-distance prediction unit 104a also acquires information about the positions and movements of other traffic participants and other objects present around the target vehicle from the situation acquisition unit 101 (step S102).

[0040] Next, the short-distance prediction unit 104a predicts whether the decision to engage in autonomous driving of the target vehicle will be delayed based on the planned driving route of the target vehicle and information on the positions and movements of other traffic participants and other objects (step S103).

[0041] If it is predicted that the autonomous driving decision of the target vehicle will be delayed (YES in step S104), the short-distance prediction unit 104a presents the status of the target vehicle and the surrounding environment and a notification that the autonomous driving decision will be delayed to the operator 205 via the decision delay occurrence status presentation unit 105 (step S105).If it is not predicted that the autonomous driving decision of the target vehicle will be delayed (NO in step S104), step S105 is not performed and the process returns to step S101.

[0042] The short distance prediction unit 104a repeatedly executes the above operations.

[0043] 7 is a flowchart showing the operation of the long distance prediction unit 104b. The operation of the long distance prediction unit 104b will be described with reference to FIG.

[0044] First, the long-distance prediction unit 104b acquires information about the planned driving route (driving route) of the target vehicle from the driving information acquisition unit 103 (step S201). The long-distance prediction unit 104b also acquires information about the positions and movements of other traffic participants and other objects present around the planned passage point of the target vehicle from the situation acquisition unit 101 (step S202).

[0045] Next, the long-distance prediction unit 104b predicts whether a situation will arise in which the decision to drive the target vehicle automatically will be delayed at the point where the target vehicle is scheduled to pass, based on the planned route of the target vehicle and information on the positions and movements of other traffic participants and other objects (step S203).

[0046] If it is predicted that a situation will occur in which the target vehicle's decision to perform autonomous driving will be delayed (YES in step S204), the long-distance prediction unit 104b presents the situation of the target vehicle and the surrounding environment, and a notification that a situation will occur in which the target vehicle's decision to perform autonomous driving will be delayed, to the operator 205 via the decision delay occurrence situation presentation unit 105 (step S205).If it is not predicted that a situation will occur in which the target vehicle's decision to perform autonomous driving will be delayed (NO in step S204), step S205 is not performed, and the process returns to step S201.

[0047] The long distance prediction unit 104b repeatedly executes the above operations.

[0048] 8 is a flowchart showing the operation of the decision delay recording unit 106. The operation of the decision delay recording unit 106 will be described with reference to FIG.

[0049] The judgment delay recording unit 106 acquires from the situation acquisition unit 101 the driving state of the target vehicle, the time taken by the autonomous driving system 204 to determine whether the target vehicle is driving autonomously (hereinafter referred to as the "autonomous driving decision time"), and information on the surrounding environment 203 (step S301).

[0050] Next, the judgment delay recording unit 106 classifies the situation of the target vehicle by the position of the target vehicle and the surrounding environment 203 (step S302). Then, the judgment delay recording unit 106 determines whether the target vehicle's stop duration or the autonomous driving decision time is longer than a normal length (e.g., average time) for the classified situation of the target vehicle (step S303). The "normal length" may be defined in any way. In this embodiment, the average time is used as the normal length.

[0051] If the target vehicle's stop duration or the autonomous driving decision time is longer than usual (YES in step S303), the decision delay recording unit 106 records the target vehicle's stop duration and the autonomous driving decision time together with information on the surrounding environment 203 and information on the autonomous driving system 204 (step S304). If the target vehicle's stop duration and the autonomous driving decision time are both shorter than usual (NO in step S303), step S304 is not performed and the process returns to step S301.

[0052] The decision delay recording unit 106 repeatedly executes the above operations.

[0053] 9 is a flowchart showing the operation of the determination delay recording unit 106 to calculate an average time as a normal length of the target vehicle's stop duration and the automatic driving determination time. The operation of calculating the normal length (average time) will be described with reference to FIG.

[0054] The decision delay recording unit 106 acquires the driving state of the target vehicle, the time taken by the automatic driving system 204 to decide automatic driving of the target vehicle, and information on the surrounding environment 203 from the situation acquisition unit 101 (step S401).

[0055] Next, the judgment delay recording unit 106 classifies the situation of the target vehicle by the position of the target vehicle and the surrounding environment 203 (step S402).The judgment delay recording unit 106 then updates the average times for the target vehicle's stop duration and autonomous driving determination time using the past average times for the target vehicle's stop duration and autonomous driving determination time in the classified situation of the target vehicle and the current target vehicle's stop duration and autonomous driving determination time acquired in step S401 (step S403).

[0056] The decision delay recording unit 106 executes the above operations together with the operations shown in FIG.

[0057] 10 is a flowchart showing the operation of the recommended route generating unit 107. The operation of the recommended route generating unit 107 will be described with reference to FIG.

[0058] The recommended route creation unit 107 identifies locations and road environments where there is a high possibility of automated driving decisions being delayed based on the information recorded in the decision delay recording unit 106 (information on past automated driving decision delays) and the prediction results by the decision delay prediction unit 104 (information on predicted automated driving decision delays) (step S501).

[0059] The recommended route creation unit 107 also creates at least one of a recommended route and a non-recommended route for smooth operation based on the current location and destination of the target vehicle and map information, taking into account the points and road environment identified in step S501 (step S502).The recommended route creation unit 107 transmits the created at least one of the recommended route and the non-recommended route to the display device 201 or another system (step S503).

[0060] Next, a detailed description will be given of the allocation unit 108. The allocation unit 108 allocates the operators 205 when there are multiple operators 205 for one travel assistance device 100 as shown in FIG.

[0061] Fig. 12 is a diagram showing the configuration of the allocation unit 108. As shown in Fig. 12, the allocation unit 108 includes a task understanding unit 108a, a difficulty level estimation unit 108b, and an allocation determination unit 108c.

[0062] The work understanding unit 108a understands the work status of the operator 205 based on the information of the operator 205 input to the input receiving unit 109 (referred to as "input information of the operator 205"). The work status of the operator 205 includes the current status and future plans.

[0063] The current status of the operator 205 is, for example, “on call,” “on standby,” “unavailable” (e.g., away from their desk), etc. Whether the operator 205 is on call or on standby may be determined by the task understanding unit 108a based on the history of task allocation to the operator 205 and the current status of the traffic assistance device 100.

[0064] The future schedule of the operator 205 includes, for example, the waiting time until the next task to be handled, the time until the task currently being handled is completed, the time until the situation in which the operator is unable to handle the situation is over, and the like.

[0065] The future schedule of the operator 205 is the time until the status of the operator 205 (working, waiting, or unavailable) changes. The time until the operator 205 becomes working or waiting is automatically determined by the task understanding unit 108a by calculating it from the estimated time required to work on a task and the estimated time when the task occurs. The time until the operator 205 becomes "unavailable" is determined based on information input by the operator 205. A method may be adopted in which the operator 205 inputs all of the current work status and future schedule.

[0066] The difficulty level estimation unit 108b calculates the difficulty level of the task, the time required for response, and the expected time of occurrence from information about the surrounding environment 203 of the target vehicle acquired from the situation acquisition unit 101 (e.g., the degree of congestion in the surrounding area, the weather, the current time of day, etc.) and information about the decision delay in the autonomous driving of the target vehicle predicted by the short-distance prediction unit 104a and the long-distance prediction unit 104b (the situation of the decision delay, the expected time of occurrence, etc.). In this embodiment, the difficulty level of the task is expressed by a number from 1 to 3, with the higher the number, the higher the difficulty level.

[0067] The difficulty level estimation unit 108b calculates the time required for the operator 205 to respond to a task based on the status of the corresponding vehicle. Specifically, the difficulty level estimation unit 108b calculates the time required for the operator 205 to respond from the status of the corresponding vehicle and the task of the corresponding vehicle, based on a calculation table such as that shown in Fig. 13. When the status of the corresponding vehicle includes a situation requiring greater caution in driving the vehicle, such as a high number of surrounding vehicles, bad weather, or nighttime, the difficulty level of the task is determined to be high.

[0068] The allocation determination unit 108c determines the operator 205 corresponding to the task and the timing corresponding to the task, and notifies the operator 205 corresponding to the task by displaying it on the display device 201 via the judgment delay occurrence status presentation unit 105.

[0069] The allocation determination unit 108c calculates an expected value of the time it will actually take to respond to a task (hereinafter referred to as "expected response time") using a formula such as "time required for response + difficulty of task × coefficient", and selects a corresponding operator 205 taking the expected response time into consideration. Furthermore, the allocation determination unit 108c changes the rules for allocating operators 205 between tasks for which a delay is predicted by the short-distance prediction unit 104a and tasks for which a delay is predicted by the long-distance prediction unit 104b.

[0070] For example, if the task is one for which a delay is predicted by the long-distance prediction unit 104b, the first candidate is an operator 205 whose current status is waiting and whose waiting time until the next scheduled response is within the expected response time, and the second candidate is an operator 205 whose current status is currently responding or unable to respond but whose waiting time until the next wait is within the expected response time.

[0071] On the other hand, if the task is one for which a delay has been predicted by the long-distance prediction unit 104b, the first candidate is an operator 205 whose current status is waiting, who is not scheduled to respond by the time the task is expected to occur, and whose expected response time falls within the waiting time until the next scheduled response, and the second candidate is an operator 205 whose current status is currently responding or who is unable to respond, who is not scheduled to respond by the time the task is expected to occur, and whose expected response time falls within the waiting time until the next scheduled response.

[0072] After allocating a task to an operator 205, if a safety-related notification is issued from the autonomous driving system 204 regarding the task, and the operator 205 scheduled to handle the task is currently handling another task, the allocation determination unit 108c may reallocate the task to another waiting operator 205. This allows priority to be given to handling safety-related tasks.

[0073] In addition, if an operator 205 takes a long time to handle the previous task and does not complete the previous task by the expected time of the next task, and the operator 205 who is scheduled to handle the task is still in the process of handling the task or is still unavailable even when the expected time of the task arrives, the task may be reallocated to another operator 205 who is waiting to handle the task.

[0074] <Embodiment 2> Figure 14 is a diagram showing the configuration of a travel assistance device according to embodiment 2. The configuration of travel assistance device 100 according to embodiment 2 is obtained by adding, to the configuration of embodiment 1 (Figure 1), an intervention operation receiving unit 110, a control unit 111, a map database 112, a highlighted road recording unit 113, a judgment time prediction unit 114, a highlighting judgment unit 115, a highlighting unit 116, a highlighting condition recommendation unit 117, a remote driving history storage unit 118, a manual response time prediction unit 119, a response time comparison unit 120, and a highlighting condition sharing unit 121. However, for convenience of illustration, elements not directly related to the added elements among those shown in Figure 1 are omitted in Figure 14.

[0075] The intervention operation reception unit 110 receives input when the operator 205 intervenes in the driving behavior of the target vehicle. The operator 205 inputs commands and messages (including voice input) for operational support of the automated driving system 204 of the target vehicle (intervention in "cognition" or "judgment"), operations for remote driving of the target vehicle (intervention in "control"), and the like to the intervention operation reception unit 110.

[0076] The control unit 111 transmits to the automatic driving system 204 of the target vehicle the commands and messages input by the operator 205 to the intervention operation reception unit 110, as well as the steering amount and pedal depression amount corresponding to the remote driving of the operator 205. As a result, the target vehicle operates in accordance with the operator's 205 intervention instruction for the driving behavior.

[0077] The map database 112 is a database that stores map information. The highlighted road recording unit 113 records road types (e.g., intersections, merging points, traffic light locations, etc.) and locations (e.g., locations where waiting times have been long in the past) where target vehicles are likely to wait, in association with the map information.

[0078] The decision time prediction unit 114 calculates a predicted decision time, which is a predicted value of the time (decision time) required to make a decision on autonomous driving of the target vehicle based on information on the current situation of the target vehicle acquired by the situation acquisition unit 101. The predicted decision time is calculated using a decision time model, which is a model of the relationship between situations in which autonomous driving will wait and the predicted decision time in those situations, derived from the operational design domain (ODD) of the autonomous driving of the target vehicle. The decision time model derives the predicted decision time from the positional relationship between the target vehicle and traffic participants and the actions of the traffic participants based on the surrounding environmental conditions in which the target vehicle can travel defined in the ODD. Specifically, the decision time prediction unit 114 determines that autonomous driving will wait and calculates the predicted decision time when the positional relationship between the target vehicle and traffic participants satisfies certain conditions and the current actions of the traffic participants are predicted to interfere with the driving of the target vehicle with a certain probability or higher. The "situation of the target vehicle" here refers to the traffic conditions around the target vehicle and the driving state of the target vehicle (speed, direction of travel, etc.). The information on the traffic conditions around the target vehicle may be acquired from a sensor mounted on the target vehicle, or may be acquired from a sensor of infrastructure installed on the road.

[0079] In addition, since a long predicted decision time corresponds to a high possibility that the autonomous driving decision will be delayed, the decision delay prediction unit 104 described in embodiment 1 may take into account the predicted decision time calculated by the decision time prediction unit 114 to predict whether the autonomous driving decision will be delayed.

[0080] The highlighting determination unit 115 determines an object to be highlighted on a map displayed on the display device 201 to be presented to the operator 205. The highlighting determination unit 115 stores in advance highlighting rules based on the train schedule of the target vehicle, road information for the road on which the target vehicle is traveling, and the predicted judgment time for the autonomous driving of the target vehicle, and determines an object to be highlighted on the map based on the highlighting rules and the current status of the target vehicle. Specifically, the highlighting determination unit 115 determines the range and extent of highlighting on the map based on the predicted judgment time calculated by the judgment time prediction unit 114, information on the extent to which road types and locations where waiting is likely to occur stored in the highlighted road recording unit 113 are included in the road on which the target vehicle is traveling, and information on the extent to which the target vehicle is delayed relative to the train schedule. Hereinafter, the object to be highlighted determined by the highlighting determination unit 115 will be referred to as the "highlighted object."

[0081] The range of highlighting is, for example, the position of the target vehicle, the range of roads including the highlighted target, etc. Possible methods for determining the degree of highlighting include a method of highlighting points with longer expected judgment times, a method of highlighting points with more road types where waiting is likely to occur, a method of highlighting points with more road types where waiting is likely to occur, a method of highlighting points with more road types where waiting is likely to occur, etc. Note that if the planned driving route of the target vehicle does not include points with long expected judgment times or road types where waiting is likely to occur, there is no need to highlight the target vehicle more strongly even if the target vehicle is delayed from the bus schedule.

[0082] The highlighting unit 116 displays a map on the display device 201 that highlights locations where the decision delay prediction unit 104 predicts that the autonomous driving decision will be delayed. Specifically, the highlighting unit 116 performs a coloring process on the portion of the map that includes the highlight target (highlighting range) according to the degree of highlighting, and displays the map on the display device 201, thereby performing highlighting.

[0083] An example of map highlighting is shown in Figure 15. In the example of Figure 15, the location of the target vehicle is highlighted by an image of a car. Also highlighted are points with long predicted judgment times (before a merging point), points where waiting times have been long in the past (before a traffic light), and types of roads where waiting is likely to occur (intersections, merging points, and points where traffic lights are installed). The intersection shown in Figure 15 in particular is heavily highlighted because it is also a point where a traffic light is installed and contains two types of roads where waiting is likely to occur.

[0084] In this embodiment, points with long predicted decision times are highlighted, but as described above, a long predicted decision time corresponds to a high possibility of a delay in the autonomous driving decision, so points where the decision delay prediction unit 104 described in embodiment 1 predicts that the autonomous driving decision will be delayed may also be highlighted.

[0085] The highlighting condition recommendation unit 117 recommends to the operator 205, as candidates to be added to the highlighting targets, situations that match some of the conditions of the highlighting rules stored in the highlighting determination unit 115 but do not qualify as highlighting targets (for example, a specific road segment, a specific positional relationship between the target vehicle and a traffic participant, a specific action of a traffic participant, etc.). The operator 205 can manually make the candidates recommended by the highlighting condition recommendation unit 117 into highlighting targets.

[0086] The remote driving history storage unit 118 stores the remote driving history (log) of the operator 205. The manual response time prediction unit 119 predicts the time required for the operator 205 to respond by manual driving to the current situation of the target vehicle, based on the remote driving history of the operator 205 stored in the remote driving history storage unit 118 and the information on the situation of the target vehicle acquired by the situation acquisition unit 101. The response time required for the operator 205 to respond by manual driving is referred to as the "manual response time."

[0087] The response time comparison unit 120 compares the manual response time calculated by the manual response time prediction unit 119 with the response time (referred to as the "automatic response time") that would be required if the automated driving system 204 were to respond to the current situation of the target vehicle through automated driving. The automatic response time is calculated as the sum of the predicted judgment time calculated by the judgment time prediction unit 114 and the time required for the target vehicle to travel a specific distance through automated driving (the "specific distance" corresponds to the distance that the target vehicle will travel when the operator 205 responds through manual driving). Furthermore, if the manual response time is shorter as a result of comparing the manual response time with the automatic response time, the response time comparison unit 120 determines that it is appropriate for the operator 205 to respond through manual driving, and notifies the operator 205 of this by, for example, increasing the degree of highlighting of the position of the target vehicle on the map.

[0088] When the emphasis condition sharing unit 121 observes from the status of the target vehicle acquired by the status acquisition unit 101 that the target vehicle has been waiting for a certain period of time or more, it updates the judgment time model used by the judgment time prediction unit 114 to calculate the predicted judgment time and the information stored in the emphasis road recording unit 113 based on the status of the target vehicle at that time and information on the surrounding environment 203.

[0089] Furthermore, in an environment where multiple travel assistance devices 100 are installed, such as an environment in which multiple operators 205 use different travel assistance devices 100 to monitor different target vehicles, the emphasis condition sharing unit 121 also shares the information acquired by the situation acquisition unit 101 with the other travel assistance devices 100, and updates the judgment time model of the judgment time prediction unit 114 and the information stored in the emphasis road recording unit 113. Sharing information among multiple travel assistance devices 100 can efficiently improve the functionality of the travel assistance devices 100. One emphasis condition sharing unit 121 may manage multiple travel assistance devices 100, in which case only one emphasis condition sharing unit 121 may be provided for the multiple travel assistance devices 100.

[0090] 16 is a flowchart showing the operation of highlighting a map performed by the travel assistance device 100. The operation of highlighting a map performed by the travel assistance device 100 will be described with reference to FIG.

[0091] First, the situation acquisition unit 101 acquires information on the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S601). Then, the decision time prediction unit 114 calculates a predicted decision time for autonomous driving of the target vehicle based on the information on the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S602).

[0092] The highlighting determination unit 115 determines the highlighting target based on the predicted determination time calculated by the determination time prediction unit 114, the map information acquired from the map database 112, and the bus schedule acquired by the operation information acquisition unit 103, and determines which area on the map to highlight and to what extent (step S603).Then, the highlighting unit 116 displays on the display device 201 the map in which the highlighting range determined by the highlighting determination unit 115 has been colored according to the degree of highlighting (step S604).

[0093] 17 is a flowchart showing the operation of updating and sharing the judgment time model by the emphasis condition sharing unit 121. The operation of updating and sharing the judgment time model by the emphasis condition sharing unit 121 will be described with reference to FIG.

[0094] The emphasis condition sharing unit 121 first acquires information on the surrounding environment 203 of the target vehicle and the autonomous driving system 204 from the situation acquisition unit 101 (step S701). Then, when the emphasis condition sharing unit 121 observes that the autonomous driving decision time is longer than normal (for example, average time), that is, that the autonomous driving decision has been delayed (step S702), it determines whether the decision delay could have been predicted by the decision time model (step S703).

[0095] If the judgment delay observed in step S702 cannot be predicted by the judgment time model (NO in step S703), the emphasis condition sharing unit 121 updates the judgment time model so that the delay can be predicted, uploads the updated model to a shared server (not shown), and also updates the judgment time model on the shared server (step S704).The emphasis condition sharing unit 121 then notifies the other travel assistance devices 100 that the judgment time model on the shared server has been updated (step S705).

[0096] 18 is a flowchart showing the operation of the travel assistance device 100 to present candidates to be added to the highlighting to the operator 205. The operation of the travel assistance device 100 to present candidates to be added to the highlighting to the operator 205 will be described with reference to FIG.

[0097] First, the situation acquisition unit 101 acquires information on the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S801). Then, the decision time prediction unit 114 calculates a predicted decision time for autonomous driving of the target vehicle based on the information on the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S802).

[0098] The highlighting condition recommendation unit 117 checks whether the surrounding environment of the target vehicle, information about the autonomous driving system, and the predicted judgment time match some of the conditions of the highlighting rules held by the highlighting judgment unit 115, but are not enough to be highlighted (step S803).

[0099] If the surrounding environment of the target vehicle, information about the autonomous driving system, and the predicted judgment time match some of the conditions of the highlighting rules but do not qualify as a highlight target (YES in step S803), the highlighting condition recommendation unit 117 confirms with the operator 205 whether the status of the target vehicle and the road status corresponding to the information obtained in step S801 should be added as a highlight target (step S804).

[0100] 19 is a flowchart showing the operation of the travel assistance device 100 notifying the operator 205 that manual driving is appropriate. With reference to FIG. 19 , the operation of the travel assistance device 100 notifying the operator 205 that manual driving is appropriate will be described.

[0101] First, the situation acquisition unit 101 acquires information about the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S901). The decision time prediction unit 114 calculates an expected decision time for autonomous driving of the target vehicle based on the information about the surrounding environment 203 of the target vehicle and the autonomous driving system 204 (step S902). The manual response time prediction unit 119 calculates a manual response time for the current situation of the target vehicle based on the remote driving history of the operator 205 stored in the remote driving history storage unit 118 and information about the situation of the target vehicle (step S903).

[0102] Thereafter, the response time comparison unit 120 compares the manual response time calculated by the manual response time prediction unit 119 with the automatic response time calculated from the predicted judgment time calculated by the judgment time prediction unit 114 (step S904). If the manual response time is shorter (YES in step S904), the response time comparison unit 120 determines that it is appropriate for the operator 205 to respond by manual driving, and notifies the operator 205 of this by, for example, increasing the degree of highlighting of the position of the target vehicle on the map (step S905).

[0103] 20 is a diagram showing the configuration of a travel assistance device 150 according to Embodiment 3. The travel assistance device 150 includes a status acquisition unit 151, a processing status visualization unit 152, a travel information acquisition unit 153, an ideal travel position calculation unit 154, an operation status visualization unit 155, and an information presentation unit 156.

[0104] The situation acquisition unit 151 acquires information about the autonomous driving system 204 of the target vehicle.

[0105] The processing status visualization unit 152 visualizes the processing content related to the autonomous driving determination of the target vehicle by displaying it on the display device 201. Specifically, the processing status visualization unit 152 determines the state of the autonomous driving system 204, such as the "system processing item," its "status," "processing time," and "next action" (next autonomous operation), from the information on the autonomous driving system 204 acquired by the status acquisition unit 151, and displays it on the display device 201 via the information presentation unit 156.

[0106] Note that automated driving decisions include planning such as which route to take, HMI (Human Machine Interface) such as what to present to the driver, and information communication-related decisions. However, this embodiment focuses only on decisions related to the Dynamic Driving Task (DDT). Generally, DDTs are classified into "cognition," "judgment," and "control," so "system processing items" may be expressed at that level of abstraction. Alternatively, the level of abstraction may be lowered even further, and specific processing contents (in functional block units) may be used as "system processing items."

[0107] 21 is a display example of processing details related to determining whether a target vehicle is autonomously driving. In FIG. 21, "system processing items" are classified into "recognition," "determination," and "control."

[0108] The operation information acquisition unit 153 acquires operation information, which is information relating to the operation of the target vehicle, such as the target vehicle's operation schedule and operation route (planned driving route), from the target vehicle's operation management system 202.

[0109] The ideal running position calculation unit 154 calculates the ideal running position (operation position) of the target vehicle based on the operation information of the target vehicle. Specifically, the ideal running position calculation unit 154 calculates the ideal running position of the target vehicle based on the operation information of the target vehicle (flight name, departure time, arrival time, location of departure point, location of destination, etc.) acquired from the operation information acquisition unit 153. Note that the flight name can be uniquely identified from the departure time, arrival time, location of departure point, and location of destination. Therefore, two flights that have exactly the same departure time, arrival time, location of departure point, and location of destination will have the same flight name.

[0110] The ideal travel position calculation unit 154 calculates the travel time from the departure time and arrival time of the target vehicle, and maps the ideal travel positions at equal intervals so that travel from the departure point to the destination can be achieved at a constant speed within the travel time. Information about a flight that has been calculated once does not need to be calculated every time, and previously calculated results can be used.

[0111] Furthermore, the ideal running position calculation unit 154 may correct the ideal running position by taking into consideration the actual position of the target vehicle acquired by the situation acquisition unit 151. For example, the ideal running position may be corrected based on the position of the target vehicle at each time when the target vehicle is able to run along the running route at the departure and arrival times according to the bus schedule.

[0112] An example of information on the ideal running position of a service is shown in Figure 22. A table that compiles information on the ideal running positions of multiple services, as shown in Figure 23, is called an "ideal running position table." When there is only one service, the "ideal running position table" is made up of information on the ideal running position of that single service.

[0113] The operation status visualization unit 155 visualizes the operation status of the target vehicle by displaying it on the display device 201 based on the information on the state of the target vehicle and the operation information. In the present embodiment, the operation status visualization unit 155 visualizes the difference between the ideal running position and the actual running position of the target vehicle, and the difference between the arrival time on the bus schedule and the actual scheduled arrival time. Specifically, the operation status visualization unit 155 displays, on the display device 201 via the information presentation unit 156, the current position of the target vehicle acquired by the status acquisition unit 151, the ideal running position of the target vehicle obtained from the ideal running position table, the arrival time on the bus schedule acquired by the operation information acquisition unit 153, the scheduled arrival time predicted from the current position of the target vehicle, and the difference between the arrival time on the bus schedule and the scheduled arrival time.

[0114] An example of displaying the running status of a target vehicle is shown in Fig. 24. The color of the icon indicating the current location of the target vehicle may be changed depending on the difference between the arrival time and the scheduled arrival time on the bus schedule.

[0115] The estimated arrival time may be calculated by the autonomous driving system 204, or may be calculated from the current position of the target vehicle by the operation status visualization unit 155. The estimated arrival time may be calculated by a general method, such as a method of calculating the estimated arrival time based on the average speed of the target vehicle.

[0116] The information presentation unit 156 performs processing to display the information of the processing state visualization unit 152 and the operation status visualization unit 155 on the display device 201 in order to present the information to the operator 205 .

[0117] 25 is a flowchart showing the operation of the ideal traveling position calculation unit 154. The operation of the ideal traveling position calculation unit 154 will be described with reference to FIG.

[0118] First, the ideal running position calculation unit 154 acquires information on the schedule of the target vehicle from the operation information acquisition unit 153 (step S1001). The ideal running position calculation unit 154 also checks whether the target vehicle's service is included in the ideal running position table (step S1002).

[0119] If the ideal driving position table includes a flight (YES in step S1002), the ideal driving position calculation unit 154 obtains information about the flight of the target vehicle from the ideal driving position table and transmits it to the operation status visualization unit 155 (step S1003).

[0120] If the flight is not included in the ideal traveling position table (NO in step S1002), the ideal traveling position calculation unit 154 calculates the traveling time from the departure time and arrival time of the flight of the target vehicle, and sets ideal traveling positions at equal intervals so that travel from the departure point to the destination can be achieved at a constant speed within the traveling time (step S1004).The ideal traveling position calculation unit 154 then transmits the set ideal traveling positions of the flight of the target vehicle to the operation status visualization unit 155 (step S1005).The ideal traveling position calculation unit 154 also updates the ideal traveling position table to add information about the set ideal traveling positions of the flight of the target vehicle (step S1006).

[0121] 26 is a flowchart showing the operation of correcting the ideal running position by the ideal running position calculation unit 154. The operation of correcting the ideal running position by the ideal running position calculation unit 154 will be described with reference to FIG.

[0122] First, the ideal traveling position calculation unit 154 acquires information on the bus schedule of the target vehicle from the operation information acquisition unit 153 (step S1101). The ideal traveling position calculation unit 154 also acquires information on the current location of the target vehicle from the situation acquisition unit 151 (step S1102). Then, the ideal traveling position calculation unit 154 calculates and records the departure time of the target vehicle from the departure point based on the bus schedule and current location of the target vehicle (step S1103).

[0123] Next, the ideal driving position calculation unit 154 records the position and time of the target vehicle at predetermined time intervals until the target vehicle arrives at the destination (step S1104), and when the target vehicle arrives at the destination, records the arrival time at the destination (step S1105).

[0124] Thereafter, the ideal traveling position calculation unit 154 checks whether there is a discrepancy between the departure time and arrival time of the target vehicle and the departure time and arrival time on the bus schedule (step S1106). If there is no discrepancy between the departure time and arrival time of the target vehicle and the departure time and arrival time on the bus schedule (NO in step S1106), the ideal traveling position calculation unit 154 searches the ideal traveling position table for the target vehicle's flight and updates the ideal traveling position of that flight based on the target vehicle's position recorded in steps S1104 and S1105 (step S1107). If there is a discrepancy between the departure time and arrival time of the target vehicle and the departure time and arrival time on the bus schedule (YES in step S1106), the information recorded in steps S1104 and S1105 is discarded (step S1108).

[0125] The traffic assistance device 150 of the third embodiment can be combined with the traffic assistance device 100 of the first or second embodiment. For example, an ideal driving position calculation unit 154 and an operation status visualization unit 155 may be added to the traffic assistance device 100, and information on the driving status of the target vehicle shown in Fig. 24 (information such as the ideal driving position of the target vehicle, the arrival time on the bus schedule, and the estimated arrival time) may be superimposed on the map screen shown in Fig. 15 and displayed.

[0126] <Hardware Configuration Example> FIGS. 27 and 28 are diagrams illustrating examples of the hardware configuration of the travel assistance device 100. The functions of the components of the travel assistance device 100 illustrated in FIG. 1 are realized by, for example, a processing circuit 500 illustrated in FIG. 27 . That is, the travel assistance device 100 includes a processing circuit 500 that acquires information about the surrounding environment 203 of the mobile object and predicts whether a decision on the autonomous operation of the mobile object will be delayed based on the information about the surrounding environment 203 of the mobile object. The processing circuit 500 may be dedicated hardware, or may be configured using a processor (also referred to as a central processing unit (CPU), processing device, arithmetic device, microprocessor, microcomputer, or DSP (Digital Signal Processor)) that executes a program stored in a memory.

[0127] When the processing circuit 500 is dedicated hardware, the processing circuit 500 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. Each function of the components of the travel assistance device 100 may be realized by a separate processing circuit, or these functions may be realized together by a single processing circuit.

[0128] FIG. 28 shows an example of the hardware configuration of the travel assistance device 100 when the processing circuit 500 is configured using a processor 501 that executes a program. In this case, the functions of the components of the travel assistance device 100 are realized by software, etc. (software, firmware, or a combination of software and firmware). The software, etc. is written as a program and stored in memory 502. The processor 501 realizes the functions of each unit by reading and executing the program stored in memory 502. In other words, the travel assistance device 100 includes memory 502 for storing a program that, when executed by the processor 501, results in the following: acquiring information about the surrounding environment 203 of the mobile object; and predicting whether a decision on the mobile object's autonomous operation will be delayed based on the information about the surrounding environment 203 of the mobile object. In other words, this program can be said to cause a computer to execute the procedures and methods of the operations of the components of the travel assistance device 100.

[0129] Here, the memory 502 may be, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically Erasable Programmable Read Only Memory), a HDD (Hard Disk Drive), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disc), and a drive device for such a disk, or any other storage medium that will be used in the future.

[0130] Similarly, the travel assistance device 150 shown in Fig. 20 can be realized with the hardware configuration shown in Fig. 27 or Fig. 28. When the functions of the components of the travel assistance device 150 in Fig. 20 are realized with the processing circuit 500 shown in Fig. 27, the travel assistance device 150 includes the processing circuit 500 for displaying processing details related to the determination of the autonomous operation of the mobile object based on the state of the mobile object and information on the surrounding environment 203 of the mobile object.

[0131] Furthermore, when the functions of the components of the operation assistance device 150 in FIG. 20 are realized by the processor 501 and memory 502 shown in FIG. 28, the operation assistance device 150 includes a memory 502 for storing a program that, when executed by the processor 501, results in the execution of a process for displaying processing content related to determining the autonomous operation of the mobile body based on the state of the mobile body and information on the surrounding environment 203 of the mobile body.

[0132] The above describes a configuration in which the functions of the components of the travel assistance devices 100 and 150 are realized either by hardware or software, etc. However, this is not a limitation, and the travel assistance devices 100 and 150 may be configured such that some of the components are realized by dedicated hardware and other components are realized by software, etc. For example, the functions of some of the components may be realized by the processing circuit 500 as dedicated hardware, and the functions of other components may be realized by the processing circuit 500 as the processor 501 reading and executing a program stored in the memory 502.

[0133] As described above, the travel assistance devices 100 and 150 can realize the above-described functions by hardware, software, or a combination of these.

[0134] It is possible to freely combine the embodiments, and to modify or omit the embodiments as appropriate.

[0135] <Supplementary Notes> Various aspects of the present disclosure will be summarized below as supplementary notes.

[0136] (Supplementary Note 1) A driving assistance device comprising: a situation acquisition unit that acquires information about the surrounding environment of a moving body; and a decision delay prediction unit that predicts whether a decision on the autonomous operation of the moving body will be delayed based on the information about the surrounding environment of the moving body.

[0137] (Supplementary Note 2) The travel assistance device according to Supplementary Note 1, wherein the decision delay prediction unit predicts whether the decision of the mobile body will be delayed based on information about the surrounding environment of the mobile body and information about a state of the mobile body.

[0138] (Supplementary Note 3) The navigation assistance device according to Supplementary Note 1 or Supplementary Note 2, wherein the decision delay prediction unit predicts whether the decision will be delayed at a position on the planned movement route away from a current position of the moving body, based on information on the surrounding environment of the moving body and information on the planned movement route of the moving body.

[0139] (Supplementary Note 4) The travel assistance device according to any one of Supplementary Note 1 to Supplementary Note 3, further comprising a decision-delay occurrence status notification unit that notifies a user when the decision-delay prediction unit predicts that the decision will be delayed.

[0140] (Supplementary Note 5) The travel assistance device according to any one of Supplementary Note 1 to Supplementary Note 4, further comprising a judgment delay recording unit that records the surrounding environment of the moving object and a state of the moving object when the judgment delay actually occurs.

[0141] (Supplementary Note 6) The travel assistance device according to Supplementary Note 5, further comprising: a recommended route creation unit that creates at least one of a recommended route and a non-recommended route for the moving object based on the information recorded in the decision delay recording unit.

[0142] (Supplementary Note 7) The travel assistance device according to any one of Supplementary Note 1 to Supplementary Note 6, further comprising an allocation unit that allocates an operator to remotely operate the moving object when the decision delay prediction unit predicts that the decision will be delayed.

[0143] (Supplementary Note 8) The navigation assistance device according to any one of Supplementary Note 1 to Supplementary Note 7, further comprising: a highlighting unit that displays a map highlighting a location where the decision delay prediction unit predicts that the decision will be delayed.

[0144] (Supplementary Note 9) The navigation assistance device according to Supplementary Note 8, further comprising a judgment time prediction unit that predicts a time required for the judgment, and the highlighting unit changes a degree of highlighting of a location where the judgment is predicted to be delayed depending on the time required for the judgment.

[0145] (Supplementary Note 10) The operation assistance device according to Supplementary Note 8 or Supplementary Note 9, comprising: an operation information acquisition unit that acquires operation information of the mobile body; and an operation status visualization unit that displays the operation status of the mobile body by superimposing it on the map based on information on the state of the mobile body and the operation information.

[0146] (Supplementary Note 11) The travel assistance device according to Supplementary Note 10, wherein the operation status visualization unit displays an ideal operation position of the moving object by superimposing it on the map based on the operation information and information on a state of the moving object.

[0147] (Supplementary Note 12) A navigation assistance device comprising: a processing state visualization unit that displays processing details relating to a determination of an autonomous operation of a moving object based on a state of the moving object and information on a surrounding environment of the moving object.

[0148] (Supplementary Note 13) The navigation assistance device according to Supplementary Note 12, wherein the processing content displayed by the processing status visualization unit includes a processing item, a status and processing time of the processing item, and a next autonomous operation.

[0149] (Supplementary Note 14) The operation assistance device according to Supplementary Note 12 or Supplementary Note 13, comprising: an operation information acquisition unit that acquires operation information of the mobile body; and an operation status visualization unit that displays the operation status of the mobile body based on information on the state of the mobile body and the operation information.

[0150] (Supplementary Note 15) The travel assistance device according to Supplementary Note 14, wherein the operation status visualization unit displays an ideal operation position of the moving object based on the operation information and information on a state of the moving object.

[0151] 100 Operation assistance device, 101 Status acquisition unit, 102 Status presentation unit, 103 Operation information acquisition unit, 104 Judgment delay prediction unit, 104a Short distance prediction unit, 104b Long distance prediction unit, 105 Judgment delay occurrence status presentation unit, 106 Judgment delay recording unit, 106a Average time calculation unit, 106b Comparison unit, 106c Recording unit, 107 Recommended route creation unit, 108 Allocation unit, 108a Business understanding unit, 108b Difficulty estimation unit, 108c Allocation determination unit, 109 Input reception unit, 110 Intervention operation reception unit, 111 Control unit, 112 Map database, 113 Highlighted road recording unit, 114 Judgment time prediction unit, 115 Highlight display judgment unit, 116 Highlight display unit, 117 Highlight condition recommendation unit, 118 Remote driving history storage unit, 119 Manual response time prediction unit, 120 response time comparison unit, 121 emphasis condition sharing unit, 150 operation support device, 151 situation acquisition unit, 152 processing status visualization unit, 153 operation information acquisition unit, 154 ideal driving position calculation unit, 155 operation status visualization unit, 156 information presentation unit, 201 display device, 202 operation management system, 203 surrounding environment, 204 automatic driving system, 205 operator, 500 processing circuit, 501 processor, 502 memory.

Claims

1. A situation acquisition unit that acquires information about the surrounding environment of a moving object, A decision delay prediction unit predicts whether the decision on autonomous operation of the mobile body will be delayed based on information about the surrounding environment of the mobile body, An operation support device equipped with the following features.

2. The judgment delay prediction unit predicts whether the judgment of the moving body will be delayed, based on information about the surrounding environment of the moving body and information about the state of the moving body. The operation support device according to claim 1.

3. The decision delay prediction unit predicts whether the decision will be delayed at a location on the planned movement path, away from the current location of the moving object, based on information about the surrounding environment of the moving object and information about the planned movement path of the moving object. The operation support device according to claim 1 or claim 2.

4. The system includes a unit that notifies the user of the status of the occurrence of a decision delay when the decision delay prediction unit predicts that the decision will be delayed. The operation support device according to claim 1 or claim 2.

5. The system includes a determination delay recording unit that records the surrounding environment of the moving body and the state of the moving body when the aforementioned determination delay actually occurs. The operation support device according to claim 1 or claim 2.

6. The system includes a recommended route creation unit that generates at least one of a recommended route and a non-recommended route for the moving object based on the information recorded in the judgment delay recording unit. The operation support device according to claim 5.

7. If the decision delay prediction unit predicts that the decision will be delayed, the system includes an assignment unit that assigns an operator to remotely control the mobile body. The operation support device according to claim 1 or claim 2.

8. The system includes a highlighting unit that displays a map highlighting locations where the judgment is predicted to be delayed by the judgment delay prediction unit. The operation support device according to claim 1 or claim 2.

9. It includes a decision time prediction unit that predicts the time required for the aforementioned decision, The highlighting unit changes the degree to which it highlights locations where a delay in the judgment is predicted, according to the time required for the judgment. The operation support device according to claim 8.

10. A unit for acquiring operational information of the aforementioned mobile body, Based on the information on the state of the moving object and the operation information, the operation status visualization unit displays the operation status of the moving object superimposed on the map, Equipped with, The operation support device according to claim 8.

11. The operation status visualization unit displays the ideal operating position of the mobile body superimposed on the map, based on the operation information and the information on the state of the mobile body. The operation support device according to claim 10.

12. The mobile unit further comprises a processing state visualization unit that displays the processing content related to the determination of autonomous operation of the mobile unit based on information about the state of the mobile unit and information about the surrounding environment of the mobile unit. The operation support device according to claim 1 or claim 2.

13. The processing content displayed by the processing status visualization unit includes a processing item, the status of the processing item, the processing time, and the next autonomous action. The operation support device according to claim 12.

14. A unit for acquiring operational information of the aforementioned mobile body, Based on the information on the state of the moving body and the operation information, the operation status visualization unit displays the operating status of the moving body. Equipped with, The operation support device according to claim 12.

15. The operation status visualization unit displays the ideal operating position of the moving object based on the operation information and the information on the state of the moving object. The operation support device according to claim 14.