JP2020095334A - Congestion prediction device, congestion prediction system, and congestion prediction method - Google Patents

Abstract

To provide a congestion prediction device, a congestion prediction system, and a congestion prediction method capable of improving accuracy in predicting a congestion on a road where vehicles travel.SOLUTION: A congestion prediction device includes a generation section, an acquisition section, and a calculation section. The generation section generates prediction information indicating prediction of a congestion on a road where vehicles travel. The acquisition section acquires vehicle information related to automatic operations of the vehicles traveling on the road. The calculation section calculates a correction value based on the vehicle information acquired by the acquisition section. The generation section corrects the prediction information based on the correction value calculated by the calculation section.SELECTED DRAWING: Figure 1

Description

The present invention relates to a traffic jam prediction device, a traffic jam prediction system, and a traffic jam prediction method.

BACKGROUND ART Conventionally, a traffic congestion prediction device that predicts traffic congestion on a road on which a vehicle travels has been proposed (for example, see Patent Document 1). The traffic congestion prediction apparatus according to the related art acquires the traffic volume of a vehicle traveling on a road and predicts the traffic congestion based on the acquired traffic volume.

JP, 2007-179166, A

However, the conventional technique has room for further improvement in improving the accuracy of traffic congestion prediction.

The present invention has been made in view of the above, and an object thereof is to provide a traffic jam prediction device, a traffic jam prediction system, and a traffic jam prediction method that can improve the accuracy of traffic jam prediction on a road on which a vehicle travels. To do.

In order to solve the above-mentioned subject and to achieve an object, the present invention is provided with a generating part, an acquiring part, and a calculating part in a traffic jam prediction device. The generation unit generates prediction information indicating prediction of traffic congestion on the road on which the vehicle travels. The acquisition unit acquires vehicle information regarding automatic driving of a vehicle traveling on a road. The calculation unit calculates a correction value based on the vehicle information acquired by the acquisition unit. Further, the generation unit corrects the prediction information based on the correction value calculated by the calculation unit.

According to the present invention, it is possible to improve the accuracy of traffic congestion prediction on a road on which a vehicle travels.

FIG. 1 is a diagram showing an outline of a traffic jam prediction method according to the embodiment. FIG. 2 is a block diagram showing a configuration example of a traffic congestion prediction system including a traffic congestion prediction device. FIG. 3 is a block diagram showing a configuration example of an in-vehicle device. FIG. 4 is a block diagram showing a configuration example of the traffic congestion prediction device. FIG. 5 is a diagram showing correction value information. FIG. 6 is a diagram illustrating an example of correction of prediction information by the generation unit. FIG. 7 is a flowchart showing a processing procedure executed by the traffic jam prediction apparatus.

Hereinafter, embodiments of a traffic jam prediction apparatus, a traffic jam prediction system, and a traffic jam prediction method disclosed in the present application will be described in detail with reference to the accompanying drawings. The present invention is not limited to the embodiments described below.

<1. Outline of traffic congestion prediction method>
Hereinafter, first, an outline of the traffic congestion prediction method according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an outline of a traffic congestion prediction method according to the embodiment.

The traffic congestion prediction method according to the embodiment is executed by the traffic congestion prediction device 10 included in the traffic congestion prediction system 1, for example. Specifically, as shown in FIG. 1, the traffic congestion prediction system 1 includes the traffic congestion prediction device 10 and the vehicle-mounted device 100 described above.

The traffic jam prediction device 10 is a server that can process various types of information. For example, the traffic congestion prediction device 10 first generates prediction information indicating prediction of traffic congestion on the road on which the vehicle C travels (step S1). For example, the traffic jam prediction apparatus 10 accumulates actual data of traffic jams that have actually occurred in the past, and uses the actual data and the weather information of the day acquired from an external server (not shown) or the like, and nearby event information. Based on this, prediction information is generated.

By the way, in recent years, a vehicle capable of automatic driving that does not require a driver's driving operation (hereinafter, may be referred to as “automatic driving vehicle”) is known. An autonomous vehicle, for example, can travel at a constant speed or can travel while maintaining a constant distance between the vehicle and a preceding vehicle, so that traveling on the road is smooth. If there is traffic congestion on the road you are driving, you can expect to alleviate the traffic congestion.

In addition, when multiple autonomous driving vehicles run continuously, it is possible to perform so-called platooning, in which multiple autonomous driving vehicles run in a row with a short inter-vehicle distance. As a result, we can expect further relief from traffic congestion. Thus, the presence of self-driving vehicles on the road can affect traffic congestion prediction.

Therefore, in the traffic jam prediction apparatus 10 according to the present embodiment, the previously generated prediction information is corrected according to the presence of the autonomous driving vehicle on the road, thereby improving the traffic jam prediction accuracy. ..

More specifically, the traffic jam prediction apparatus 10 acquires vehicle information regarding automatic driving from the vehicle-mounted apparatus 100 of the vehicle C (step S2). Here, the vehicle-mounted device 100 is mounted on the vehicle C. The vehicle C may be an automatic driving vehicle, or may be a manually driven vehicle that requires a driver's driving operation (hereinafter, may be referred to as “manual driving vehicle”).

Therefore, the above-mentioned vehicle information regarding automatic driving is information indicating whether or not the own vehicle is an automatic driving vehicle. The vehicle information is not limited to this, and is, for example, information indicating whether or not the vehicle is currently traveling in the automatic driving mode when the vehicle can switch between the automatic driving mode and the manual driving mode. May be. Further, the vehicle information may be information indicating whether or not the vehicle has a part of the automatic driving function such as keeping the speed constant, performing platooning, etc., instead of the fully autonomous autonomous driving. That is, the vehicle information related to automatic driving is information indicating whether the vehicle can take a running state peculiar to automatic driving, which is a prerequisite for correcting the prediction information such as the above-described platooning. Further, the traffic jam prediction device 10 may acquire other information such as the position information of the own vehicle by GPS (Global Positioning System) together with the vehicle information.

Next, the traffic jam prediction device 10 calculates a correction value based on the acquired vehicle information and position information (step S3). The calculation of the correction value will be described later with reference to FIGS. 4 and 5.

Then, the traffic jam prediction device 10 corrects the prediction information based on the calculated correction value (step S4). In this way, the prediction information is corrected based on the correction value calculated according to the existence of the autonomous driving vehicle, which may affect the prediction of the traffic congestion, thereby predicting the traffic congestion on the road on which the vehicle C travels. The accuracy of can be improved.

<2. Constitution of traffic congestion prediction system including traffic congestion prediction device>
Next, the configuration of the traffic congestion prediction system 1 including the traffic congestion prediction device 10 according to the embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing a configuration example of the traffic congestion prediction system 1 including the traffic congestion prediction device 10. Note that in the block diagrams such as FIG. 2, only the components necessary for explaining the features of the present embodiment are represented by functional blocks, and the description of general components is omitted.

In other words, each component illustrated in the block diagram of FIG. 2 and the like is functionally conceptual and does not necessarily have to be physically configured as illustrated. For example, the specific form of distribution/integration of each functional block is not limited to that shown in the figure, and all or part of the functional block may be functionally or physically distributed in arbitrary units according to various loads and usage conditions. -It is possible to integrate and configure.

As shown in FIG. 2, the traffic congestion prediction system 1 includes the on-vehicle device 100, the terminal device 200, and the traffic congestion prediction device 10 described above, which are communicably connected via a communication network N such as the Internet network. It

Next, the configurations of the on-vehicle device 100, the terminal device 200, and the traffic jam prediction device 10 described above will be specifically described.

<3. In-vehicle device configuration>
FIG. 3 is a block diagram showing a configuration example of the in-vehicle apparatus 100. As shown in FIG. 3, the in-vehicle device 100 includes a communication unit 101, an in-vehicle sensor group 102, a display unit 103, a vehicle control device 110, a drive source control device 141, a brake control device 142, and a steering mechanism control. And a device 143. In addition, in FIG. 3, the vehicle-mounted device 100 mounted in the autonomous vehicle will be described as an example.

The communication unit 101 is a communication interface that is connected to the communication network N so as to be capable of bidirectional communication, and transmits and receives information to and from the traffic congestion prediction device 10 and the like.

The in-vehicle sensor group 102 includes, for example, various sensors that detect information necessary for traveling control of the vehicle C (see FIG. 1). For example, the vehicle-mounted sensor group 102 includes a vehicle speed sensor that detects a vehicle speed, an accelerator sensor that detects an accelerator operation amount, a brake sensor that detects a brake operation amount, a steering angle sensor that detects a steering angle of a steering wheel, and the like.

The in-vehicle sensor group 102 also includes various devices that detect information necessary for automatic driving of the vehicle C. For example, the vehicle-mounted sensor group 102 includes a GPS receiver that detects the current location of the vehicle based on a signal from a GPS satellite, a camera that can image other vehicles existing around the vehicle, and electromagnetic waves around the vehicle. A radar or the like that measures the distance and direction from the reflected wave obtained by radiating to another vehicle existing in the vicinity may be included. Note that, for example, when the vehicle-mounted device 100 is mounted on a manually driven vehicle, a camera, a radar, etc. may not be included.

The on-vehicle sensor group 102 described above outputs information indicating the obtained vehicle speed, vehicle position, etc. to the vehicle control device 110.

The display unit 103 is, for example, a liquid crystal display, and can display route guidance information from the navigation unit 123, which will be described later.

The drive source control device 141 is a device that controls a drive source such as an engine or an electric motor of the vehicle C, the brake control device 142 is a device that controls a brake of the vehicle C, and the steering mechanism control device 143 is a steering mechanism that steers the vehicle C. It is a device that controls.

The vehicle control device 110 includes a control unit 120 and a storage unit 130. The control unit 120 is a microcomputer that includes an acquisition unit 121, a vehicle control unit 122, a navigation unit 123, and a transmission unit 124, and has a CPU (Central Processing Unit) and the like.

The storage unit 130 is a storage unit configured by a storage device such as a non-volatile memory or a hard disk drive. The storage unit 130 stores vehicle information 131, various programs, setting data, and the like.

The vehicle information 131 is information about automatic driving, that is, information indicating whether or not the own vehicle is an automatic driving vehicle. Here, since the vehicle-mounted device 100 is mounted on the self-driving vehicle, the vehicle information 131 includes information indicating that the own vehicle is the self-driving vehicle. Therefore, for example, when the vehicle-mounted device 100 is mounted in a manually-operated vehicle, the vehicle information 131 includes information indicating that the vehicle is not an automatically-operated vehicle, in other words, a manually-operated vehicle.

The acquisition unit 121 of the control unit 120 acquires each sensor signal output from the in-vehicle sensor group 102 and outputs the sensor signal to the vehicle control unit 122 and the transmission unit 124. For example, the acquisition unit 121 outputs the position information of the vehicle detected by the GPS receiver of the on-vehicle sensor group 102 to the transmission unit 124.

Further, the acquisition unit 121 receives and acquires the prediction information output from the traffic congestion prediction device 10 via the communication unit 101, and outputs the acquired prediction information to the navigation unit 123.

The vehicle control unit 122 controls the driving of the vehicle C. More specifically, the vehicle control unit 122 outputs from the accelerator sensor, the brake sensor, and the steering angle sensor of the in-vehicle sensor group 102 when, for example, the driver manually operates the accelerator, the brake, and the steering wheel (all not shown). Various information to be input is input via the acquisition unit 121. The vehicle control unit 122 controls the drive source control device 141, the brake control device 142, and the steering mechanism control device 143 based on the information, and controls the manual operation of the vehicle C.

The vehicle control unit 122 can also perform automatic driving control of the vehicle C. For example, the vehicle control unit 122 controls the drive source control device 141 and the like based on GPS information, camera information, radar information, and the like output from the vehicle-mounted sensor group 102, and executes automatic driving control.

When the destination is set by the user such as the driver of the vehicle C, the navigation unit 123 superimposes the route information indicating the traveling route of the vehicle C from the current position to the destination on the map information and displays the route information on the display unit 103. Can be made As a result, the navigation unit 123 provides route guidance to the user.

Here, the navigation unit 123 may provide route information to the destination of the vehicle C based on the prediction information output from the traffic congestion prediction device 10. As described above, the prediction information is corrected by the correction value, and the accuracy of the prediction is improved. By using such prediction information, for example, it is possible to improve the accuracy of route search to the destination and route re-search (reroute search) during guidance.

The transmission unit 124 can transmit various types of information and the like to the traffic congestion prediction device 10. For example, the transmission unit 124 reads the vehicle information 131 stored in the storage unit 130, and transmits the vehicle information 131 to the traffic congestion prediction device 10 via the communication unit 101.

The transmission unit 124 may also transmit the position information of the vehicle input from the acquisition unit 121 to the traffic congestion prediction device 10 via the communication unit 101. In addition, the transmission unit 124 may transmit the destination information set by the user of the vehicle C to the traffic congestion prediction device 10.

<4. Configuration of terminal device>
The terminal device 200 shown in FIG. 2 is configured to have a function of providing route guidance to the user, for example. As the terminal device 200, for example, a smartphone, a tablet terminal, a personal computer, or the like can be used, but the terminal device 200 is not limited to this.

For example, the terminal device 200 may receive and acquire the prediction information output from the traffic jam prediction device 10, and provide route information to the destination of the vehicle C based on the acquired prediction information. That is, the terminal device 200 may include a navigation unit (not shown) that provides route information based on the prediction information. As described above, since the prediction information has improved accuracy of prediction, by using the prediction information, for example, a route search to a destination in the terminal device 200 or a route re-search during the guidance (reroute) is performed. The accuracy of search) can also be improved.

In this way, the in-vehicle device 100 and the terminal device 200 described above can function as a receiving device capable of receiving the prediction information predicted by the traffic jam prediction device 10. That is, the in-vehicle device 100 and the terminal device 200 are examples of the receiving device.

<5. Congestion prediction device configuration>
Next, the traffic jam prediction apparatus 10 will be described with reference to FIG. FIG. 4 is a block diagram showing a configuration example of the traffic congestion prediction device 10. As shown in FIG. 4, the traffic congestion prediction device 10 includes a communication unit 11 and a control device 20.

The communication unit 11 is a communication interface that connects to the communication network N so as to be capable of bidirectional communication, and transmits and receives information to and from the vehicle-mounted device 100, the terminal device 200, and the like.

The control device 20 includes a control unit 30 and a storage unit 40. The control unit 30 is a server including a generation unit 31, an acquisition unit 32, a calculation unit 33, and a transmission unit 34, and having a CPU, a RAM (Random Access Memory), and the like.

The storage unit 40 is a storage unit configured by a storage device such as a non-volatile memory or a hard disk, and stores vehicle information 41, prediction information 42, and correction value information 43.

The vehicle information 41 is information indicating whether the vehicle C is an autonomous driving vehicle, and more specifically, the vehicle information 131 for each vehicle C transmitted from each vehicle C. For example, the vehicle information 41 may include accumulated past vehicle information 131, present vehicle information 131, and the like.

The prediction information 42 is information indicating prediction of traffic congestion on the road on which the vehicle C travels. For example, the prediction information 42 may include a traffic jam level indicating the degree of traffic jam. The traffic congestion level is shown step by step, for example, traffic congestion levels A, B, C, D, E... (see FIG. 6), but is not limited to this. Here, for the sake of explanation, the congestion level A is set to have the highest degree of congestion, and as the congestion levels B, C,... I can't.

The correction value information 43 is information on a correction value used for correcting the prediction information 42. The correction value information 43 will be described later with reference to FIG.

The generation unit 31 of the control unit 30 generates prediction information 42 indicating prediction of traffic congestion on the road on which the vehicle C travels. For example, as described above, the generation unit 31 generates the prediction information 42 based on the actual data of the traffic jam that has actually occurred in the past, the weather information of the day acquired from an external server (not shown), and the event information of the surroundings. can do. The generation unit 31 can correct the generated prediction information 42 based on the correction value, which will be described in detail later.

The acquisition unit 32 acquires the vehicle information 131 transmitted from the vehicle C via the communication unit 11 and stores it in the storage unit 40 as the vehicle information 41.

In addition, the acquisition unit 32 can acquire, as the vehicle information 41, continuity information indicating the continuity in which the autonomous vehicle continuously travels. The continuous information is information indicating how many autonomous driving vehicles are traveling in the space. Alternatively, the continuous information is information indicating how much the automatic driving vehicle and the manual driving vehicle are mixed. For example, when there are many autonomous driving vehicles that continuously run on the same road, that is, when the automatically driving vehicles and the manually driving vehicles do not mix and only a large number of automatically driving vehicles run in series, the continuous information in the continuous information is Will be more likely. On the contrary, when the number of automatically driving vehicles that run continuously is small, the continuity of the continuous information is low.

Here, as described above, the acquisition unit 32 acquires the continuous information because it becomes possible to perform the platooning in the case where a plurality of autonomous driving vehicles continuously run, and predict the congestion. This may have a relatively large effect on

The calculation unit 33 reads out the vehicle information 41 and the correction value information 43 stored in the storage unit 40, and calculates the correction value based on the vehicle information 41 and the correction value information 43. Since the vehicle information 41 includes information indicating whether or not the vehicle C is an autonomous driving vehicle, the calculation unit 33 calculates the number of autonomous driving vehicles on the road and sets the correction value according to the number of vehicles. It can be calculated.

Further, since the vehicle information 41 includes the above-described continuity information, the calculation unit 33 can calculate the correction value according to the level of continuity in the continuity information.

Then, for example, the calculation unit 33 can calculate the correction value from the correction value information 43 based on the accumulated past vehicle information 41 and the current vehicle information 41.

FIG. 5 is a diagram showing the correction value information 43. The correction value information 43 determines the correction value based on a combination of the number (none, small, or large) of automatically driving vehicles and continuity (low or high) for each time axis (current or past) of vehicle information. Configured as a table. In addition, in FIG. 5, “small”, “medium”, and “large” represent correction values, and as the correction value increases, the prediction information 42 is corrected to reduce traffic congestion. Further, in FIG. 5, “small”, “medium”, and “large” with black triangles at the beginning also show the correction values, but as the correction values become larger, this is on the side that increases the traffic congestion with respect to the prediction information 42. to correct.

For example, if the past vehicle information 41 is “no autonomous driving vehicle” and the current vehicle information 41 is “many autonomous driving vehicles and high continuity”, it is estimated that the congestion is alleviated by the above-mentioned platooning or the like. Therefore, the correction value is set to “large”. That is, the correction value is set to a value that corrects the prediction information 42 to the side that significantly reduces the congestion.

Further, for example, when the past vehicle information 41 is “no autonomous driving vehicle” and the current vehicle information 41 is “many autonomous driving vehicles and low continuity”, the congestion can be alleviated by the above-mentioned platooning or the like. Although it is unlikely to be expected, the correction value is set to "medium" because it is expected to alleviate the traffic congestion due to many autonomous vehicles traveling. That is, the correction value is set to a value that corrects the prediction information 42 to the side that moderates the traffic congestion.

In addition, for example, when the past vehicle information 41 is “no automatic driving vehicle” and the current vehicle information 41 is “there are few automatic driving vehicles and high continuity”, the above-mentioned platooning or the like can reduce congestion. The correction value is set to "medium" because the number of autonomous vehicles is small, although it can be expected.

Further, for example, when the past vehicle information 41 is “no automatic driving vehicle” and the current vehicle information 41 is “the number of automatic driving vehicles is low and the continuity is low”, the above-mentioned automatic driving vehicles are traveling. The correction value is set to "small" because it is unlikely that the congestion will be alleviated. That is, the correction value is set to a value that corrects the prediction information 42 to the side that slightly alleviates the congestion.

Further, for example, when the past vehicle information 41 is “no automatic driving vehicle” and the current vehicle information 41 is also “no automatic driving vehicle”, there is no change in the road condition related to the automatic driving vehicle, and Since it is not possible to alleviate the congestion caused by the driving vehicle traveling, the correction value is set to “no correction”, that is, zero.

Further, for example, when the past vehicle information 41 is “there are many self-driving vehicles and the continuity is high” and the current vehicle information 41 is “no self-driving vehicle”, the congestion is alleviated by the above-mentioned platooning or the like. Therefore, the correction value is set to “large” with a black triangle at the beginning. That is, the correction value is set to a value for correcting the prediction information 42 to a side that significantly increases traffic congestion.

In this way, the calculation unit 33 can calculate an appropriate correction value according to the situation of the autonomous driving vehicle by using the past vehicle information 41 and the current vehicle information 41.

Further, the calculation unit 33 can similarly calculate an appropriate correction value according to the situation of the autonomous driving vehicle by using the continuity information indicating the continuity in which the autonomous driving vehicle continuously travels.

In the present embodiment, the correction value information 43 is configured as a table, but the table is not limited to this. That is, in the correction value information 43, the correction value is calculated as a function with the current number of autonomous driving vehicles, the present continuity, the number of past autonomous driving vehicles, and the past continuity as variables. May be described in. In this case, the number and continuity of the autonomous driving vehicles may be the number of vehicles themselves. Further, the number and continuity of the autonomous driving vehicles may be continuous values standardized by a predetermined number of vehicles, such as an estimated number of vehicles that do not cause congestion on the road.

Returning to the description of FIG. 4, the calculation unit 33 calculates the correction value, and then outputs information indicating the calculated correction value to the generation unit 31. Then, the generation unit 31 corrects the prediction information 42 based on the correction value. FIG. 6 is a diagram illustrating an example of correction of the prediction information 42 by the generation unit 31. Note that FIG. 6 shows the prediction information 42 of a predetermined area.

In FIG. 6, for example, the traffic congestion level included in the prediction information 42 before correction is “level A” at 12:00 and 13:00, “level B” at 14:00, and “level C” at 15:00. Shows. That is, in a predetermined area, it is predicted that the congestion is highest at 12:00 and 13:00, and the congestion is alleviated with the passage of time.

Here, if the correction value is set to “large” at 12:00, for example, the generation unit 31 applies the correction value in a predetermined time range to correct the traffic jam level of the prediction information 42. In the example shown in FIG. 6, the generation unit 31 corrects the traffic jam level of the prediction information 42 from 13:00 to 15:00. As a result, the traffic congestion level after correction is corrected to "level C" at 13:00, "level D" at 14:00, and "level E" at 15:00, which is a prediction that the traffic congestion will be significantly reduced.

As described above, by using the correction value, it is possible to correct the prediction information 42 according to the situation of the autonomous driving vehicle traveling on the road, and thus the accuracy of the prediction of the congestion on the road on which the vehicle C is traveling is improved. Can be made

In addition, in the present embodiment, the generation of the pre-correction prediction information 42 does not necessarily need to consider the presence of the autonomous driving vehicle. Therefore, it becomes possible to consider the autonomous driving vehicle as a so-called additional function to the conventional prediction portion. In other words, since it is not necessary to correct the conventional prediction portion, it is possible to significantly reduce the time and effort of correction when constructing the traffic jam prediction device 10 that supports automatic driving.

In the above description, the generation unit 31 applies the correction value in the predetermined time range, but the predetermined time range can be set arbitrarily. That is, for example, the predetermined time range can be set to a range of time in which the vehicle C that outputs the current vehicle information 41 when the correction value is set to “large” is estimated to travel on the road. .. The time range in which the vehicle C is estimated to travel on the road may be calculated from, for example, destination information transmitted from the vehicle C.

Further, the generation unit 31 may correct the prediction information 42 on the road on which the vehicle C, which has acquired the vehicle information 41 by the acquisition unit 32, is scheduled to travel based on the correction value. That is, for example, the road on which the vehicle C, which has output the current vehicle information 41 when the correction value is set to “large”, is scheduled to travel can be expected to significantly reduce congestion. Therefore, the generation unit 31 can apply the correction value to the prediction information 42 on the road. As a result, the accuracy of traffic congestion prediction on the road on which the vehicle C is scheduled to travel can be improved. The road on which the vehicle C will travel may be calculated from the destination information transmitted from the vehicle C, for example.

In addition, for example, in the case where there is a branch road in the middle of the road on which the vehicle C is going to travel and it is estimated that the platooning formation of a plurality of autonomous vehicles will collapse at this branch road, the generation unit 31, the correction value can be applied to the prediction information 42 up to the branch road. That is, if the platooning formation collapses, the congestion cannot be alleviated. Therefore, the correction value is not applied to the prediction information 42 on the road ahead of the branch road.

As a result, it is possible to further improve the accuracy of traffic congestion prediction on the road on which the vehicle C will travel. The collapse of the formation of a plurality of autonomous driving vehicles on the branch road can be estimated from, for example, destination information transmitted from the vehicle C.

Returning to FIG. 4, the transmission unit 34 can transmit the prediction information 42 corrected by the correction value to the vehicle-mounted device 100, the terminal device 200, or the like via the communication unit 11. As described above, the vehicle-mounted device 100, the terminal device 200, and the like perform route search using the corrected prediction information 42 as described above.

<6. Control Processing of Vehicle Management Device According to Embodiment>
Next, a specific processing procedure in the traffic jam prediction apparatus 10 will be described with reference to FIG. FIG. 7 is a flowchart showing a processing procedure executed by the traffic congestion prediction device 10.

As shown in FIG. 7, the control unit 30 of the traffic congestion prediction device 10 generates prediction information 42 indicating prediction of traffic congestion on the road on which the vehicle C travels (step S10). Next, the control unit 30 acquires the vehicle information regarding the automatic driving of the vehicle C traveling on the road (step S11).

Next, the control unit 30 calculates a correction value based on the acquired vehicle information (step S12). Then, the control unit 30 corrects the previously generated prediction information 42 based on the calculated correction value (step S13).

As described above, the traffic jam prediction device 10 according to the embodiment includes the generation unit 31, the acquisition unit 32, and the calculation unit 33. The generation unit 31 generates prediction information 42 indicating prediction of traffic congestion on the road on which the vehicle C travels. The acquisition unit 32 acquires vehicle information regarding automatic driving of the vehicle C traveling on the road. The calculation unit 33 calculates the correction value based on the vehicle information acquired by the acquisition unit 32. Further, the generation unit 31 corrects the prediction information 42 based on the correction value calculated by the calculation unit 33. As a result, the accuracy of traffic congestion prediction on the road on which the vehicle C travels can be improved.

Further effects and modifications can be easily derived by those skilled in the art. Therefore, the broader aspects of the present invention are not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept defined by the appended claims and their equivalents.

1 Traffic Congestion Prediction System 10 Traffic Congestion Prediction Device 30 Control Unit 31 Generation Unit 32 Acquisition Unit 33 Calculation Unit 42 Prediction Information 100 In-vehicle Device 123 Navigation Unit 200 Terminal Device C Vehicle

Claims (7)

A generation unit that generates prediction information indicating prediction of traffic congestion on the road on which the vehicle travels,
An acquisition unit that acquires vehicle information about automatic driving of a vehicle traveling on a road,
A calculation unit that calculates a correction value based on the vehicle information acquired by the acquisition unit,
The generator is
A traffic jam prediction apparatus, which corrects the prediction information based on the correction value calculated by the calculation unit. The calculation unit
The vehicle information is accumulated, and the correction value is calculated based on the accumulated vehicle information in the past and the current vehicle information acquired by the acquisition unit. Congestion prediction device. The acquisition unit is
Obtaining continuous information indicating the continuity in which the automatically operated vehicle continuously travels as the vehicle information,
The calculation unit
The traffic congestion prediction device according to claim 1 or 2, wherein the correction value is calculated based on the continuation information acquired by the acquisition unit. The generator is
The congestion information according to any one of claims 1 to 3, wherein the prediction information on a road on which the vehicle, which has acquired the vehicle information by the acquisition unit, is to be corrected based on the correction value. Prediction device. A traffic congestion prediction device according to any one of claims 1 to 4,
And a receiving device capable of receiving the prediction information predicted by the traffic congestion predicting device. The receiving device is
The traffic congestion prediction system according to claim 5, further comprising: a navigation unit that provides route information indicating a route to a destination of the vehicle based on the prediction information corrected by the generation unit. A generation step of generating prediction information indicating prediction of traffic congestion on the road on which the vehicle travels;
An acquisition step of acquiring vehicle information regarding automatic driving of a vehicle traveling on a road;
A calculation step of calculating a correction value based on the vehicle information acquired in the acquisition step,
The generation step is
A traffic congestion prediction method, comprising: correcting the prediction information based on the correction value calculated in the calculation step.

Images