JP2019175492A - Predictor, prediction system, prediction method, and prediction program - Google Patents

Abstract

To enable a behavior of another vehicle to be predicted on the basis of route information.SOLUTION: A predictor 100 includes an acquisition unit 101 that acquires, from another vehicle, a movement history of the other vehicle, a prediction unit 102 that predicts a behavior of the other vehicle on the basis of the movement history, and an output unit 103 that outputs driving support information on the basis of the prediction. The acquisition unit 101 acquires the movement history from the other vehicle within a communication range for inter-vehicle communication, and the prediction unit 102 predicts the behavior of the other vehicle within the communication range for inter-vehicle communication. The acquisition unit 101 acquires information that can be used for prediction of the behavior of the other vehicle, and the prediction unit 102 predicts the behavior of the other vehicle using a plurality of pieces of information together with the movement history.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a prediction device, a prediction system, a prediction method, and a prediction program for predicting the behavior of another vehicle. However, utilization of this invention is not restricted to a prediction apparatus, a prediction system, a prediction method, and a prediction program.

  Conventionally, a technique for acquiring route information from another vehicle and predicting the behavior of the other vehicle based on the acquired route information has been disclosed (see, for example, Patent Document 1 below).

JP 2011-242887 A

  In the above conventional technique, when another vehicle has not set a route, a problem that the behavior of the other vehicle cannot be predicted is given as an example.

  In order to solve the above-described problem and achieve the object, the prediction device according to the invention of claim 1 is based on an acquisition unit that acquires a movement history of the moving body from another moving body, and the movement history. The apparatus includes: a prediction unit that predicts the behavior of the moving body; and an output unit that outputs driving support information based on the prediction.

  The prediction system according to the invention of claim 8 is a prediction system in which a host vehicle, another vehicle, and a server are communicatively connected. The server includes a current position of the host vehicle and a movement history of the other vehicle. Obtaining means for obtaining, prediction means for predicting the behavior of the other vehicle based on the current position and the movement history, and output means for outputting driving support information to the host vehicle based on the prediction. It is characterized by providing.

  According to a ninth aspect of the present invention, there is provided a prediction method according to a prediction method implemented by a prediction device, wherein the moving body is obtained based on an acquisition step of acquiring a movement history of the moving body from another moving body, and the movement history. A prediction step of predicting the behavior of the vehicle, and an output step of outputting driving support information based on the prediction.

  A prediction program according to a tenth aspect of the invention causes a computer to execute the prediction method according to the ninth aspect.

FIG. 1 is a block diagram illustrating an example of a functional configuration of the prediction apparatus according to the embodiment. FIG. 2 is a flowchart illustrating an example of a processing procedure of the prediction apparatus according to the embodiment. FIG. 3 is a block diagram illustrating an example of a hardware configuration of the navigation device according to the embodiment of the prediction device. FIG. 4 is a chart illustrating an example of information acquired from the other vehicle by the navigation device according to the embodiment. FIG. 5 is a chart for explaining a communication example of inter-vehicle communication according to the embodiment. FIG. 6 is a diagram for explaining an example of predicting the behavior of another vehicle according to the embodiment. FIG. 7 is a chart for explaining an example of driving support according to the prediction accuracy according to the embodiment. FIG. 8A is a flowchart illustrating an example of a prediction process performed by the vehicle according to the embodiment. FIG. 8B is a flowchart illustrating a processing example of another vehicle related to the prediction processing according to the embodiment. FIG. 9 is a diagram illustrating a system configuration example of a prediction apparatus according to another embodiment. FIG. 10 is a diagram illustrating a functional configuration example of a system of a prediction device according to another embodiment.

(Embodiment)
Exemplary embodiments of a prediction device, a prediction system, a prediction method, and a prediction program according to the present invention will be explained below in detail with reference to the accompanying drawings. In the following description, the own vehicle is a vehicle (moving body) such as an automobile equipped with a prediction device, and the other vehicle is a vehicle (moving body) that runs around the own vehicle, for example, in front of the own vehicle. is there.

  FIG. 1 is a block diagram illustrating an example of a functional configuration of the prediction apparatus according to the embodiment. The prediction device 100 includes an acquisition unit 101, a prediction unit 102, and an output unit 103.

  The acquisition unit 101 acquires a movement history of another vehicle. The movement history is acquired directly from another vehicle by inter-vehicle communication. The communication unit for inter-vehicle communication transmits and receives information to and from other vehicles within the communication range of the own vehicle. At this time, the own vehicle broadcasts vehicle information to an unspecified number of other vehicles, and receives vehicle information broadcast from other vehicles. The vehicle information includes vehicle identification information (vehicle ID), latitude / longitude information indicating the position of the vehicle, vehicle speed information indicating the travel speed of the vehicle, travel direction information indicating the travel direction of the vehicle, and travel of the vehicle. Traveling road information indicating the road number (including the lane number) of the middle road. A plurality of vehicles (other vehicles) can be identified based on the received vehicle information, and the movement history can be identified for each other vehicle.

  The acquisition part 101 of embodiment can acquire a movement history from the other vehicle which drive | works ahead of the own vehicle by vehicle-to-vehicle communication, for example. The movement history of the other vehicle is not limited to the inter-vehicle communication that directly communicates between the own vehicle and the other vehicle, and the own vehicle can also acquire from the other vehicle via a network in which the own vehicle and the other vehicle communicate and connect.

  However, in the case of inter-vehicle communication, the movement history can be easily acquired from other vehicles within a predetermined communication range centered on the own vehicle. In other words, if inter-vehicle communication is used, the own vehicle can acquire the movement history by focusing on other vehicles in the vicinity of the own vehicle without designating other vehicles.

  Other vehicles hold a route on the road that has traveled in the past. This route is a past movement history of other vehicles and has information such as latitude and longitude, speed, and time.

  In addition, the other vehicle can hold attached information related to the past route as the movement history. The attached information includes, for example, facility and place visit histories (convenience stores, supermarkets, gas stations, parking lots, etc. that are frequently used) and favorite points (registered places and on the route display screen when visiting in the past) ), Parking lot entrance (auto parking memory position information), direction indicator operation information, and the like. The acquisition unit 101 can acquire the attached information held by the other vehicle together with the movement history.

  The acquisition unit 101 can also acquire current driving information of other vehicles. Other vehicles obtain information such as gasoline remaining amount, continuous operation time, sudden braking (presence / absence and level of sudden braking), passenger's conversation information collected in the vehicle, automatic driving status, etc. as driving information The acquisition unit 101 can acquire the driving information. The continuous operation time is not limited to information on the current continuous operation, but may be information when continuously operated in the past.

  The prediction unit 102 predicts the behavior of the other vehicle based on the movement history of the other vehicle acquired by the acquisition unit 101. The output unit 103 outputs driving support information that supports safe driving of the host vehicle based on the prediction of the prediction unit 102. For example, the driving assistance information can be output to the driver (driver) driving the vehicle with a screen display or voice. In addition, the driving support information can be output as control information for the vehicle control unit of the host vehicle.

  When the prediction unit 102 predicts the behavior of another vehicle traveling in front of the host vehicle, the host vehicle can safely drive the host vehicle. For example, when the acquisition unit 101 acquires a past movement history of “turning left at the next intersection” from another vehicle, the prediction unit 102 performs the behavior of the other vehicle at the next intersection (for example, for deceleration and left turn). Change of driving lane).

  Here, even if the other vehicle is moving without setting a route, the past movement history can be acquired from the other vehicle. This makes it possible to predict the behavior of other vehicles that are moving without setting the route. In addition, even if other vehicles are moving without setting a stop (such as a convenience store or a gas station), the behavior of other vehicles including the stop of other vehicles can be determined based on the past movement history. Be able to predict. In addition, even if there is unevenness in the operation of the direction indicator in another vehicle (for example, when the operation of the direction indicator at the intersection is slow or not operated), based on the past movement history, Can be predicted.

  When the vehicle approaches the next intersection, the output unit 103 displays, on the screen, the behavior of another vehicle (for example, change of the driving lane for deceleration and left turn) as predicted driving assistance information, Output by voice. Thereby, the behavior of the other vehicle can be notified in advance to the driver of the own vehicle. Further, the vehicle control unit can use the driving support information as information for automatic control such as deceleration, and can perform deceleration by automatic braking or the like.

  Further, the output unit 103 can change the content of the driving support according to the accuracy of the driving support information based on the accuracy of the prediction (accuracy) by the prediction unit 102. For example, when the prediction accuracy is high, the predicted behavior is positively communicated to the driver using a plurality of outputs (for example, screen display and audio output). On the other hand, as accuracy decreases, attention should be paid to the output, and the output should be weakened to the extent that either screen display or audio output is performed. In addition, for driving support information for the vehicle control unit, for example, if the prediction accuracy is high, the driver can perform vehicle control (e.g. deceleration by brake braking) to the extent that the driver can understand, and as the accuracy decreases, the driver does not know The degree of vehicle control can be changed, for example, the vehicle control is performed and the vehicle control is not performed with the lowest accuracy (however, other radar detection is performed).

  The above driving information is also used to predict the behavior of other vehicles. The prediction process using the driving information can be performed by another vehicle or the own vehicle. For example, the remaining amount of gasoline itself is constantly detected by other vehicles. In this case, the acquisition unit 101 of the own vehicle acquires the gasoline remaining amount information from the other vehicle, and based on the gasoline remaining amount information acquired by the prediction unit 102, the other vehicle is located at the next gas station on the traveling route of the own vehicle. The output unit 103 outputs the prediction result to the driver of the own vehicle. If the other vehicle is configured to perform the prediction process, the acquisition unit 101 acquires the information on the gas station that the other vehicle predicted to stop from the other vehicle, and the output unit 103 outputs the information.

  Further, the prediction unit 102 may predict the behavior of other vehicles in combination with not only the movement history but also driving information. Thereby, the accuracy of prediction can be improved.

  FIG. 2 is a flowchart illustrating an example of a processing procedure of the prediction apparatus according to the embodiment. The example of the prediction process of the behavior of the other vehicle which the prediction apparatus 100 of the own vehicle performs is shown. First, the prediction device 100 acquires a movement history from another vehicle by the acquisition unit 101 (step S201). This movement history includes the driving information.

  Next, the prediction device 100 predicts the behavior of the other vehicle based on the movement history by the prediction unit 102 (step S202). And the output part 103 outputs the driving assistance information based on prediction (step S203), and the above process is complete | finished.

  For example, in step S201, the acquisition unit 101 acquires a past movement history that “turned left at the next intersection” from another vehicle, and in step S202, the prediction unit 102 causes the behavior of the other vehicle at the next intersection. (For example, change of traveling lane for deceleration and left turn, etc.) is predicted. In step S203, the output unit 103 displays the behavior of the other vehicle (for example, change of the driving lane for deceleration and left turn) as the predicted driving assistance information when the own vehicle approaches the next intersection. Output in the upper display or audio.

  In addition, in step S203, the output unit 103 outputs to the vehicle control unit, as driving support information, a lane change of another vehicle (for example, a lane change to the left lane immediately before the left turn) or a prediction that the vehicle will decelerate. To do. The vehicle control unit can perform vehicle control such as brake braking of the host vehicle corresponding to the predicted behavior of the other vehicle.

  As another example, in step S201, the acquisition unit 101 of the own vehicle acquires the gasoline remaining amount of the other vehicle. In step S202, the prediction unit 102 determines that the gasoline remaining amount of the other vehicle is equal to or less than a predetermined remaining amount. Predict that another vehicle will stop at the next petrol station on your route. In step S <b> 203, when the host vehicle approaches the next gas station, the output unit 103 provides the driver with the driver's driving assistance information as a driving assistance information (when another vehicle stops at the next gas station). Behavior) is displayed on the screen or output as audio. Further, the output unit 103 outputs driving support information to the vehicle control unit, so that the vehicle control unit can perform vehicle control such as brake braking of the own vehicle in response to the predicted behavior of the other vehicle. it can.

  As yet another example, when another vehicle collects the conversation information in the vehicle, the acquisition unit 101 of the own vehicle acquires the conversation information in step S201. In step S <b> 202, the prediction unit 102 analyzes the speech information and predicts a stop-by place. For example, the predicting unit 102 analyzes the voice of the conversation “I want to stop at a convenience store” in another vehicle, and predicts that the other vehicle stops at the next convenience store on the travel route of the own vehicle. In step S203, the output unit 103 displays the predicted behavior of another vehicle (behavior when another vehicle stops at the next convenience store) to the driver when the own vehicle approaches the next convenience store. Output in the upper display or audio. Further, the output unit 103 outputs driving support information to the vehicle control unit, so that the vehicle control unit can perform vehicle control such as brake braking of the own vehicle in response to the predicted behavior of the other vehicle. it can.

  By the way, when the present driving information is acquired together with the past movement history of the other vehicle in Step S201, the prediction unit 102 can predict by combining the driving information with the movement history of the other vehicle in Step S202. For example, in step S202, if the past movement history is “stop to the next gas station” information, but the remaining amount of gasoline in the current driving information is “full” and there is no need to refill the gasoline, In step S203, the output from the output unit 103 is not performed.

  In addition, in step S203, the output unit 103 determines whether the prediction unit 102 performs the determination process, that is, “stops to the next gas station in the past but the current gasoline level is full. "You don't need to stop and stop at the next gas station." At this time, the output unit 103 may not output driving support information based on the remaining amount of gasoline to the vehicle control unit.

  According to the above embodiment, the prediction device outputs driving support information in which the behavior of the other vehicle is predicted based on the movement history of the other vehicle to the driver or the vehicle control unit. As a result, the driver of the own vehicle and the vehicle control unit can know the behavior of the other vehicle in advance, and perform appropriate driving (for example, risk avoidance) corresponding to the behavior before the predicted behavior of the other vehicle actually occurs. You can do it. For example, the vehicle can be driven with a margin for the behavior of other vehicles, and safe driving can be performed.

  For example, even if another vehicle is moving without setting the route to the destination or stopover location, the other vehicle does not set the route by acquiring the past movement history from the other vehicle. The behavior of other vehicles moving to can be predicted. In addition, additional information included in the movement history of other vehicles, such as frequently used facilities, favorite points, facility logo marks displayed on the route display screen when visiting in the past), parking lot information The behavior of other vehicles can be predicted based on the operation information of the entrance and the direction indicator. Furthermore, the behavior of the other vehicle can be predicted by combining the current driving information together with the past movement history of the other vehicle. As a result, the accuracy of predicting the behavior of other vehicles can be increased.

  In addition, the driving support information can change the degree of notification to the driver and the driving control unit in accordance with the accuracy of the prediction of the behavior of the other vehicle. If the prediction accuracy is high, for example, the driver can be actively notified in advance of a dangerous state, while the driver assistance information is weakened and notified to the driver as the prediction accuracy decreases. . The driving support information may not be notified with the lowest accuracy. As a result, unnecessary prediction information is provided while providing reliable prediction information to the driver, so that the complexity of notification of prediction information is eliminated, and the reliability of the prediction device can be improved.

  Next, examples of the present invention will be described. In the embodiment, an example in which the navigation device 300 is mounted on the own vehicle and the navigation device 300 executes the function of the prediction device 100 will be described.

(Hardware configuration of navigation device 300)
FIG. 3 is a block diagram illustrating an example of a hardware configuration of the navigation device according to the embodiment of the prediction device. In FIG. 3, a navigation device 300 includes a CPU 301, ROM 302, RAM 303, magnetic disk drive 304, magnetic disk 305, optical disk drive 306, optical disk 307, audio I / F (interface) 308, microphone 309, speaker 310, input device 311, A video I / F 312, a display 313, a communication I / F 314, a GPS unit 315, various sensors 316, and a camera 317 are provided. Each component 301 to 317 is connected by a bus 320.

  The CPU 301 governs overall control of the navigation device 300. The ROM 302 records various programs including a boot program and a prediction program. The RAM 303 is used as a work area for the CPU 301. That is, the CPU 301 controls the entire navigation device 300 by executing various programs recorded in the ROM 302 while using the RAM 303 as a work area.

  The magnetic disk drive 304 controls the reading / writing of the data with respect to the magnetic disk 305 according to control of CPU301. The magnetic disk 305 records data written under the control of the magnetic disk drive 304. As the magnetic disk 305, for example, an HD (hard disk) or an FD (flexible disk) can be used.

  The optical disk drive 306 controls reading / writing of data with respect to the optical disk 307 according to the control of the CPU 301. The optical disk 307 is a detachable recording medium from which data is read according to the control of the optical disk drive 306. As the optical disc 307, a writable recording medium can be used. In addition to the optical disk 307, an MO, a memory card, or the like can be used as a removable recording medium.

  Examples of information recorded on the magnetic disk 305 and the optical disk 307 include map data, vehicle information, road information, movement history, and the like. Map data is used when searching for routes in car navigation systems. Background data that represents features (features) such as buildings, rivers, ground surfaces, and energy supply facilities, and road shapes that represent road shapes with links and nodes. It is vector data including data.

  The audio I / F 308 is connected to a microphone 309 for audio input and a speaker 310 for audio output. The sound received by the microphone 309 is A / D converted in the sound I / F 308. For example, the microphone 309 is installed in a dashboard portion of a vehicle, and the number thereof may be one or more. From the speaker 310, a sound obtained by D / A converting a predetermined sound signal in the sound I / F 308 is output.

  Examples of the input device 311 include a remote controller having a plurality of keys for inputting characters, numerical values, various instructions, and the like, a keyboard, and a touch panel. The input device 311 may be realized by any one form of a remote control, a keyboard, and a touch panel, but may be realized by a plurality of forms.

  The video I / F 312 is connected to the display 313. Specifically, the video I / F 312 is output from, for example, a graphic controller that controls the entire display 313, a buffer memory such as a VRAM (Video RAM) that temporarily records image information that can be displayed immediately, and a graphic controller. And a control IC for controlling the display 313 based on the image data to be processed.

  The display 313 displays icons, cursors, menus, windows, or various data such as characters and images. As the display 313, for example, a TFT liquid crystal display, an organic EL display, or the like can be used.

  The camera 317 captures an image including a road outside the vehicle. The image may be either a still image or a moving image. For example, the outside of the vehicle is photographed by the camera 317, and the photographed image is analyzed by the CPU 301, or a recording medium such as the magnetic disk 305 or the optical disk 307 via the video I / F 312. Or output to

  The communication I / F 314 is connected to a network via wireless and functions as an interface between the navigation device 300 and the CPU 301. Communication networks that function as networks include in-vehicle communication networks such as CAN and LIN (Local Interconnect Network), public line networks and mobile phone networks, DSRC (Dedicated Short Range Communication), LAN, and WAN. The communication I / F 314 is, for example, a public line connection module, an ETC (non-stop automatic fee payment system, registered trademark) unit, an FM tuner, a VICS (Vehicle Information and Communication System) / beacon receiver, or the like.

  The GPS unit 315 receives radio waves from GPS satellites and outputs information indicating the current position of the vehicle. The output information of the GPS unit 315 is used when the CPU 301 calculates the current position of the vehicle together with output values of various sensors 316 described later. The information indicating the current position is information for specifying one point on the map data such as latitude / longitude and altitude.

  The various sensors 316 output information for determining the position and behavior of the vehicle, such as a vehicle speed sensor, an acceleration sensor, an angular velocity sensor, and a tilt sensor. The output values of the various sensors 316 are used for the calculation of the current position of the vehicle by the CPU 301 and the amount of change in speed and direction.

  The CPU 301 executes a predetermined program using the programs and data recorded in the ROM 302, the RAM 303, the magnetic disk 305, the optical disk 307, etc., shown in FIG. 3, so that the acquisition units 101 to 101 of the prediction apparatus 100 shown in FIG. A function related to information processing in the output unit 103 is realized.

  Further, using the communication I / F 314 in FIG. 3, vehicle-to-vehicle communication is performed with other vehicles by short-range wireless communication using radio waves. With this communication, the function of the acquisition unit 101 in FIG. 1 can be realized. Further, the function of the output unit 103 in FIG. 1 can be realized by using the display 313, the speaker 310, and the like in FIG. The communication I / F 314 may communicate with other vehicles via a network such as the Internet.

(Example of information obtained from other vehicles)
FIG. 4 is a chart illustrating an example of information acquired from the other vehicle by the navigation device according to the embodiment. The navigation apparatus 300 acquires past information 401 and current information 402 regarding vehicle travel of other vehicles from other vehicles by inter-vehicle communication.

  The past information 401 is information relating to vehicle travel that is stored in a memory or the like by another vehicle. The past information 401 is, for example, a travel history (latitude / longitude, speed, time, etc.) of a road on which another vehicle has traveled in the past. In addition, if other vehicles store and hold attached information attached to the movement history, the attached information can also be acquired.

  Attached information, for example, visit history of facilities and places (frequently used convenience stores, supermarkets, gas stations, parking lots, etc.), favorite points (registered locations, and displayed on the route display screen when visiting in the past) And a parking lot entrance (auto parking memory position information), direction indicator operation information (latitude and longitude when operating the direction indicator, and direction of operation), and the like.

  Current information 402 is driving information of other vehicles. Current information 402 includes, for example, current gasoline remaining amount, continuous operation time, information on sudden braking (existence and degree of sudden braking, etc.) (latitude / longitude and degree of sudden braking), and boarding that is picked up in the vehicle Conversation information, automatic driving status, etc. The continuous driving time and the conversation information are not limited to the current continuous driving information, but may include past information held by other vehicles.

  The navigation device 300 predicts the behavior of the other vehicle currently traveling in the vicinity of the current vehicle (for example, forward in the traveling direction) based on the past information 401 and the current information 402 acquired from the other vehicle. The past information 401 shown in FIG. 4 indicates the behavior actually performed by other vehicles in the past. For this reason, the navigation apparatus 300 can use the past information 401 acquired from the other vehicle as it is for predicting the behavior of the other vehicle.

  On the other hand, the current information 402 indicates the current state (behavior) of the other vehicle. For this reason, the navigation apparatus 300 performs a predetermined analysis process on the current information 402 before performing the prediction process on a part of the current information 402 acquired from the other vehicle.

  For example, regarding the remaining amount of gasoline, the distance that can be traveled in the future with the remaining amount of gasoline is analyzed based on the fuel consumption of other vehicles. At this time, the navigation device 300 acquires the fuel consumption information of the other vehicle and analyzes the distance that can be traveled in the future corresponding to the remaining amount of gasoline. Then, the navigation device 300 performs prediction processing using the analysis result, and when the travelable distance falls below a certain threshold value (or when the corresponding gasoline remaining amount becomes a predetermined amount or less), the navigation device 300 arrives in the traveling direction. Predict possible gas stations.

  In addition, for continuous operation time, an analysis based on the average speed that is different between when driving on a general road and when driving on a highway is performed. Do. Further, for the sudden braking information, a prediction process is performed after analyzing the place (latitude and longitude) where the other vehicle suddenly braked and the degree of sudden braking (rate of speed change due to sudden braking). Further, the analysis may include the number of times of sudden braking in the past at the same location. Moreover, about the conversation information in a vehicle, a prediction process is performed after analyzing the content of conversation. Moreover, about an automatic driving | running state, after acquiring the state of automatic driving | running | working of other vehicles, for example, level information (for example, levels 1-4) of automatic driving from other vehicles, prediction processing is performed.

  These analyzes are not limited to the navigation device 300 of the host vehicle, but are performed by devices on the other vehicle side (for example, the same navigation device 300), and the navigation device 300 of the host vehicle acquires the analysis result from the other vehicle. May be used for prediction processing. For example, the remaining amount of gasoline is information to be analyzed for future travel on the other vehicle side, and the result analyzed on the other vehicle side can be used. Sudden braking and conversation information may also be analyzed in driving assistance on the other vehicle side.

(Vehicle-to-vehicle communication example)
FIG. 5 is a chart for explaining a communication example of inter-vehicle communication according to the embodiment. The efficiency of data transmission / reception in inter-vehicle communication will be described with reference to FIG. When the navigation apparatus 300 performs various types of information (see FIG. 4) acquired from other vehicles for prediction in constant communication, the amount of communication increases.

  In the embodiment, in order to prevent an increase in the amount of communication between vehicles, as shown in FIG. 5A, first, the navigation device 300 of the own vehicle 500 uses, for example, information used for prediction with respect to the other vehicle 501. Request. At this time, the navigation device 300 of the own vehicle 500 determines whether the communication with the other vehicle 501 has not been performed or has already been performed based on the identification information of the vehicle of the other vehicle 501. And the navigation apparatus 300 of the own vehicle 500 is the information of a certain time (for example, several minutes later) from the last communication about the other vehicle 501 which has not communicated yet, and the other vehicle 501 which has already communicated. Send a request.

  In the embodiment, the navigation device 300 requests the other vehicle 501 to transmit at least a movement history. For the other information shown in FIG. 4, for example, a part or all of the information that can be collected by the other vehicle 501 is requested.

  Accordingly, as shown in FIG. 5B, the other vehicle 501 collects information that can be used for behavior prediction after receiving the request, and transmits the information to the own vehicle 500 (navigation device 300). At this time, if information on a collection target used for behavior prediction is defined in advance between the own vehicle 500 and the other vehicle 501 (see, for example, FIG. 4), the other vehicle 501 collects information corresponding to the request, Can be sent.

  At this time, the other vehicle 501 transmits at least movement history information to the own vehicle 500. Of the past information 401 and the current information 402, the collected information is also transmitted. At this time, by extracting and transmitting information related to the vicinity of the current position of the other vehicle 501, data necessary for prediction can be narrowed down and transmitted. If the amount of data to be transmitted is large, information related to the vicinity of the current position of the other vehicle 501 (intersection in the example of FIG. 5) is extracted and transmitted. Alternatively, the amount of data can be reduced by transmitting some predetermined information.

  Thereby, the navigation apparatus 300 of the own vehicle 500 can acquire the information for predicting the behavior of the other vehicle 501 from the other vehicle 501 as shown in FIG.5 (c). In addition, the navigation apparatus 300 of the own vehicle 500 repeats transmission of a request | requirement with respect to the other vehicle 501 again, when the information acquisition from the other vehicle 501 fails.

  By the way, the inter-vehicle communication is not performed only between one own vehicle 500 and one other vehicle 501, and the request of the own vehicle 500 is a plurality of vehicles located within the communication range of the inter-vehicle communication. Broadcast transmission is made to the other vehicle 501. Similarly, the other vehicle 501 also broadcasts information for prediction to a plurality of other vehicles 501 (including the own vehicle 500) located within the communication range.

  The own vehicle 500 that made the request can select and discard the information so that only the prediction information corresponding to the transmitted request is received from the other vehicle 501. For example, by attaching an identifier to the request and transmitting it to the other vehicle 501, only the information having the same identifier as the request among the received information can be selected and received from the other vehicle 501.

(An example of predicting the behavior of other vehicles)
FIG. 6 is a diagram illustrating an example of predicting the behavior of another vehicle according to the embodiment. An example in which the navigation device 300 of the host vehicle 500 acquires the past movement history of the other vehicle 501 and predicts the behavior of the other vehicle 501 will be described.

  In the example shown in FIG. 6, the navigation device 300 of the host vehicle 500 uses the movement history 600 acquired from the other vehicle 501 (in the figure, ○ is, for example, the transition of the position of the other vehicle 501 every predetermined time) in the past. The information that the other vehicle 501 turns right at the next intersection 601 in the traveling direction is included. In this case, the navigation apparatus 300 predicts, as the behavior of the other vehicle 501 based on the acquired movement history, that “the other vehicle 501 makes a right turn at the next intersection 601 in the traveling direction”. Note that the navigation device 300 does not output the movement history 600 shown in FIG. 6 at the time when the movement history 600 is acquired (before the prediction process is executed).

  If the time information is given to the movement history 600, the navigation device 300 can obtain the accuracy of prediction based on the past time when the other vehicle 501 indicated by the movement history 600 makes a right turn and the current time. become able to.

  If the past time when the other vehicle 501 makes a right turn is close to the current time, the prediction accuracy becomes high, and the prediction time becomes lower as the past time when the other vehicle 501 makes a right turn greatly differs from the current time. For example, when the past time when the other vehicle 501 turns right is a morning commute time zone (for example, AM 8:00) and the current time is substantially the same time (AM: 7:55), the accuracy of prediction is high. . On the other hand, when the current time is the daytime time (PM: 1:15), the prediction accuracy is low. When the current time is night time (PM: 6:30), the accuracy of prediction is further reduced.

  Moreover, the accuracy of prediction can be calculated | required based on the frequency according to the advancing direction of the past movement history 600 of the acquired other vehicle 501 in the intersection 601. FIG. For example, if the ratio of the number of times the other vehicle 501 makes a right turn at the intersection 601 is high, the accuracy of the right turn prediction can be increased. By combining the frequency and the time, the prediction accuracy can be further increased.

  The navigation device 300 outputs the predicted behavior of the other vehicle 501 as driving support information. For example, the navigation device 300 outputs the driving support information for the driver of the own vehicle 500. In this case, the navigation device 300 displays that the other vehicle 501 turns right at the intersection 601 as the prediction information 600 of the behavior of the other vehicle 501 on the display screen. The prediction information 600 is the same as the travel locus 600, but as shown in FIG. 6, the navigation device 300 displays and outputs on the display screen for the first time after the prediction. The navigation device 300 may output “Other vehicle (front vehicle) will turn right at the next intersection” or the like in a text or voice along with the display.

  As a result, the driver of the host vehicle 500 is connected to the other vehicle 501 in advance before the other vehicle 501 decelerates at the intersection 601 or operates the direction indicator based on the display of the prediction information performed by the navigation device 300. For example, the vehicle 500 can be decelerated to widen the distance between the vehicles. In this way, the future behavior of the other vehicle 501 is predicted, and the behavior of the other vehicle 501 is notified to the driver of the own vehicle 500 before the time when the other vehicle 501 actually performs the behavior. Therefore, an appropriate driving operation can be performed before the actual behavior of the other vehicle 501 occurs, and driving safety can be achieved.

  Further, the navigation device 300 may output the behavior prediction information 600 of the other vehicle 501 to the vehicle control unit of the host vehicle 500. In this case, the vehicle control unit decelerates the host vehicle 500 in advance to increase the inter-vehicle distance from the other vehicle 501 before the other vehicle 501 decelerates at the intersection 601 or operates the direction indicator. The operation control can be performed.

  In the behavior prediction described above, the navigation device 300 may acquire route information from the other vehicle 501 when the other vehicle 501 sets the route. However, the other vehicle 501 may not travel along the set route even when the route is set. In the example of FIG. 6, even when the route is set to turn right at the intersection 601, there are actually cases where the other vehicle 501 goes straight or turns left.

  In such a case, the navigation device 300 predicts the behavior of the other vehicle 501 by combining various information acquired from the other vehicle 501 (see FIG. 4) and the set route information. Further, at least the past movement history of the other vehicle 501 has predetermined reliability, and the behavior is predicted and determined in combination with the route information. As a result, the navigation device 300 can predict the behavior of the other vehicle 501 with accuracy as accurately as possible regardless of whether the other vehicle 501 has a route set.

  In addition, the navigation device 300 can improve the accuracy of prediction by acquiring a past movement history from the other vehicle 501 and combining it with other information. As other information, as shown in FIG. 4, there is attached information (past information 401) of travel history and driving information (current information 402). The greater the number of these other information combined with the movement history, the higher the accuracy of prediction.

  For example, when the navigation apparatus 300 is in an automatic driving state and a route is set as other information acquired from the other vehicle 501, the behavior of the other vehicle 501 is determined to travel according to the route. Will be more accurate. On the other hand, in the case of manual driving, as described above, even if route information is acquired from the other vehicle 50, there is a case where the vehicle does not travel according to the route, so the prediction accuracy is low. For this reason, in the case of manual operation, the accuracy can be increased by acquiring a plurality of pieces of information.

  In addition, as an analysis process before prediction for other information acquired from the other vehicle 501, continuous operation time will be described as an example. When the other vehicle 501 is continuously driving for a predetermined time (for example, two hours) on an expressway or the like, the navigation device 300 displays the behavior of the other vehicle 501 as “the next service area (SA) Stop at the parking area (PA).

  In this case, the navigation apparatus 300 performs a predetermined analysis on the increase in the stop time of the continuous operation time due to traffic jams. For example, if it is a stop due to traffic on an expressway, refer to the road map. If it is a stop on an expressway, it is determined that the other vehicle 501 is located within the traffic jam, and the stop time is included in the continuous operation time. It is analyzed that it is not a stop for the end (end of continuous operation time). In addition, if the other vehicle 501 is located in the traffic jam section based on the beacon and traffic jam information acquired from the outside, the stop time is included in the continuous driving time and it is not a stop for the break (end of the continuous driving time). And analyze. By performing such an analysis, the accuracy of subsequent prediction can be increased.

  Furthermore, the case where the other vehicle 501 is in-vehicle conversation information will be described as an analysis process before prediction for other information acquired from the other vehicle 501. The other vehicle 501 transmits the conversation information (voice data) collected inside the other vehicle 501 to the own vehicle 500. The navigation device 300 of the host vehicle 500 analyzes the acquired conversation information and uses it for behavior prediction. For example, the navigation apparatus 300 analyzes the voice of the conversation “I want to stop at a convenience store” in the other vehicle 501 and predicts that the other vehicle stops at the next convenience store on the travel route of the own vehicle 500. Then, the navigation device 300 displays the predicted behavior of the other vehicle (behavior when another vehicle stops at the next convenience store) on the screen when the own vehicle 500 approaches the next convenience store. Outputs to, and outputs with sound. Such voice analysis may be performed on the other vehicle 501 side, and the navigation apparatus 300 of the own vehicle 500 may perform prediction of the other vehicle 501 based on the voice analysis result.

(Example of driving support according to the accuracy of prediction)
FIG. 7 is a chart for explaining an example of driving support according to the prediction accuracy according to the embodiment. The vertical axis represents the driving state of the host vehicle 500, and the horizontal axis represents the accuracy of prediction of the behavior of the other vehicle 501. The driving state indicates that the own vehicle 500 has either manual driving or automatic driving. In the manual driving, the navigation apparatus 300 indicates the output contents notified to the driver, and in the automatic driving, the control contents performed by the vehicle control unit.

  The accuracy of behavior prediction can be determined according to the number of pieces of information acquired from the other vehicle 501, for example. It can also be determined based on whether the other vehicle 501 is in an automatic driving state or a manual driving state. For example, when the information acquired from the other vehicle is only one of the movement histories, it is determined that the accuracy is “low”. In addition, when the information acquired from the other vehicle includes the movement history and one or more other information, it is determined that the accuracy is “medium”. The accuracy may be increased within the accuracy range as the number of other information increases. When the information acquired from the other vehicle is automatic traveling, it is determined that the accuracy is “high” because the traveling route is determined even if there is no movement history. In addition, when there is no movement history in the information acquired from other vehicles (including cases where there are multiple other information other than the movement history), the accuracy is judged to be “minimum” and the output of driving assistance information (behavior of behavior) (Prediction) may not be performed.

  When the accuracy of the prediction of the behavior of the other vehicle 501 is “low”, the navigation device 300 notifies either the display screen or sound during manual operation. For example, weaken the message to “Let's pay attention to other cars (cars ahead)”. During automatic driving, the vehicle control unit performs vehicle control based on other vehicle control radars and the like, without performing vehicle control based on the prediction, based on a prediction that the behavior accuracy is “low”.

  When the accuracy of the prediction of the behavior of the other vehicle 501 is “medium”, the navigation device 300 performs notification in combination with the display screen and sound during manual driving. For example, please pay attention to other vehicles "to alert the driver. In the example of FIG. 6, it notifies that “the other vehicle (the vehicle ahead) will turn right at the next intersection”. During automatic driving, the vehicle control unit performs vehicle control based on a prediction that the behavior prediction accuracy is “medium”. For example, in addition to decelerating (brake braking) to the extent that the driver does not know (time before the other vehicle 501 behaves), control (brake braking, lane change, etc.) that increases the distance between the other vehicle 501 is performed. Can do.

  When the accuracy of the prediction of the behavior of the other vehicle 501 is “high”, the navigation device 300 performs a combination of a display screen and sound during manual driving. For example, “Beware of other cars (front cars)” is communicated to the driver about the predicted behavior. At this time, the screen display is highlighted. In addition, notification may be made with more emphasis by raising the audio volume and outputting. During automatic driving, the vehicle control unit performs vehicle control based on prediction that the accuracy of behavior prediction is “high”. For example, the vehicle is decelerated (brake braking) to an extent known to the driver (before the other vehicle 501 behaves). At this time, control (brake braking, lane change, etc.) that increases the inter-vehicle distance from the other vehicle 501 can also be performed.

(Example of prediction process of other vehicle behavior)
FIG. 8A is a flowchart illustrating an example of a prediction process performed by the vehicle according to the embodiment. The navigation device 300 of the host vehicle 500 first transmits a request for information used for predicting the behavior of the other vehicle 501 to the other vehicle 501 through inter-vehicle communication (step S801). The other vehicle that has received the request from the own vehicle 500 performs processing such as collection of information used by the own vehicle 500 for prediction (FIG. 8B) (step S802).

  Next, the navigation device 300 of the own vehicle 500 receives information used for predicting the behavior of the other vehicle from the other vehicle 501 by inter-vehicle communication (step S803). Next, the navigation apparatus 300 determines whether or not the received information is information that can be used for predicting the behavior of the other vehicle 501 (step S804). If the information can be used for predicting the behavior of the other vehicle 501 (step S804: Yes), the navigation device 300 predicts the behavior of the other vehicle 501 (step 805). The information that can be used for predicting the behavior of the other vehicle 501 is, for example, the various types of information shown in FIG. 4 and includes at least movement history information.

  If the information is not usable for predicting the behavior of the other vehicle 501 (step S804: No), the process proceeds to step S808. Information that cannot be used to predict the behavior of the other vehicle 501 is, for example, various information other than that shown in FIG. Further, if movement history information is not included in the transmitted information, it may be determined that the information is not usable for predicting the behavior of the other vehicle 501.

  After predicting the behavior of the other vehicle 501 in step S805, the navigation apparatus 300 determines whether or not to provide driving assistance according to the accuracy of the prediction (step S806). When the prediction is unsuccessful or the prediction accuracy is “minimum” (step S806: No), the process proceeds to step S808. When the prediction process can be performed and the accuracy is “low” or higher, it is determined that driving assistance is performed (step S806: Yes), and the process proceeds to step S807.

  In step S807, the navigation apparatus 300 provides driving assistance for the host vehicle 500 (step S807). At this time, as shown in FIG. 7, the navigation apparatus 300 performs display or voice notification to the driver of the own vehicle. It is also possible to control automatic driving performed by the vehicle control unit.

  In step S808, the prediction is impossible or the prediction accuracy is “minimum”, and the navigation apparatus 300 does not perform driving support because it cannot be used for driving support (step S808). After the processing of Step S807 and Step S808, the navigation device 300 of the host vehicle 500 ends the above processing performed on the host vehicle 500 side.

  FIG. 8B is a flowchart illustrating a processing example of another vehicle related to the prediction processing according to the embodiment. The processing of the other vehicle 501 may be performed by a predetermined control unit having a function of inter-vehicle communication, or may be performed by a device having a function equivalent to the navigation device 300 of the host vehicle 500.

  The other vehicle 501 side receives a request for information used for predicting the behavior transmitted from the own vehicle 500 by inter-vehicle communication (step S811). On the other vehicle 501 side as well, for example, a device having a function equivalent to that of the navigation device 300 equivalent to that of the own vehicle 500 (a configuration capable of holding at least a movement history and transmitting to the own vehicle 500 through inter-vehicle communication) executes the following processing. .

  Next, the other vehicle 501 collects information used for predicting the behavior that can be transmitted in response to the request (step S812). At this time, the other vehicle 501 collects various information such as past information 401 stored in a memory or the like, current information 402 (see FIG. 4), and the like.

  Next, the other vehicle 501 determines whether or not the information used for behavior prediction has been successfully collected (step S813). If the collection is successful (step S813: Yes), the process proceeds to step S814, and if the collection fails (step S813: No), the process proceeds to step S815. As described above, at least the past movement history of the other vehicle 501 is required as information used for behavior prediction, and when there is no movement history, it is determined that the collection has failed.

  In step S814, the prediction information that has been successfully collected is transmitted to the host vehicle 500 (step S814). This prediction information includes at least the movement history of the other vehicle 501. In step S815, since the collection is failed, the prediction information is not transmitted to the other vehicle 501 (step S815). After the processing of step S814 and step S815, the other vehicle 501 ends the above processing performed on the other vehicle 501 side.

(Another configuration example of the prediction device)
In the above embodiment, the configuration example in which the navigation device 300 of the host vehicle 500 functions as the prediction device has been described. Not only this but the prediction of the behavior of the other vehicle 501 by the prediction device may be performed by an external device.

  FIG. 9 is a diagram illustrating a system configuration example of a prediction apparatus according to another embodiment. The own vehicle 500 and the other vehicles 501 (501a to 501c) may have a configuration equivalent to the navigation device 300. The own vehicle 500 transmits the current position of the own vehicle 500 to the server 901 via the network (NW) 900. In addition, the other vehicle 501 transmits information (see FIG. 4) used for prediction of behavior including the current position and past movement history to the server 901 via the NW 900. The server 901 predicts the behavior of the other vehicle 501 based on the movement history received from the other vehicle 501 located around the own vehicle 500 corresponding to the current position of the own vehicle 500, and sends the prediction result via the NW 900. It transmits to the own vehicle 500.

  In the case where the host vehicle 500 and the other vehicle 501 are connected to the server 901 via the network, the server 901 sequentially detects the current position for each vehicle. As a result, as shown in FIG. 9, even if there are a plurality of other vehicles 501, the own vehicle 500 and the plurality of other vehicles 501 can be identified with a predetermined positional accuracy. The server 901 can further identify each vehicle using identification information unique to each vehicle or wireless identification information, and can predict the behavior of a plurality of other vehicles 501 with respect to the own vehicle 500 and transmit it to the own vehicle 500. For example, the behavior can be predicted by distinguishing the other vehicle 501a in the same traveling direction from the own vehicle 500 and the other vehicle 501c approaching from a different direction.

  FIG. 10 is a diagram illustrating a functional configuration example of a system of a prediction device according to another embodiment. The own vehicle 500 and the other vehicle 501 can be configured to include an equivalent navigation device 300, for example.

  The own vehicle 500 receives the acquisition unit 1001 that acquires the current position, the communication unit 1002 that transmits the current position to the server 901, and the prediction result that is predicted by the server 901 via the communication unit 1002, and outputs the display and the like. An output unit 1003.

  The other vehicle 501 includes an acquisition unit 1021 that acquires information (see FIG. 4) that is used to predict behavior including the current position and past movement history, and a communication unit 1022 that transmits information such as movement history to the server 901. Is provided. If the other vehicle 501 has the same configuration as that of the own vehicle 500, the other party's behavior prediction can be received from the server 901.

  The server 901 can include a communication unit 1011 that transmits and receives information between the host vehicle 500 and the other vehicle 501 and a prediction unit 1012. The prediction unit 1012 has the same function as in FIG. 1, predicts the behavior of the other vehicle 501, and transmits the prediction result to the host vehicle 500.

  Also in the above configuration, when the own vehicle 500 requests the server 901 to predict the behavior of the other vehicle 501, the server 901 predicts the behavior of the other vehicle 501 based on the movement history and transmits the prediction result to the own vehicle 500. .

  As described above, in another embodiment, the own vehicle 500 and the other vehicle 501 transmit information necessary for predicting the behavior of the other vehicle 501 to the central server 901. Thereby, since the server 901 performs the prediction process which requires a predetermined processing load, the processing load of the own vehicle 500 and the other vehicle 501 can be reduced. Further, since the information of the plurality of other vehicles 501 is collected in the server 901, the behavior of the plurality of other vehicles 501 with respect to the own vehicle 500 can be collectively predicted, and information can be provided to the own vehicle 500. In addition, prediction processing can be performed without performing inter-vehicle communication that directly communicates between the own vehicle 500 and the other vehicle 501.

  In the embodiment described above, the navigation device is used as the prediction device, and the configuration in which the navigation device is mounted on the moving body (vehicle) is described as an example. However, the vehicle on which the prediction device (navigation device) is mounted is an automobile. Not limited to this, it can be mounted on bicycles and motorcycles as well.

  Moreover, although the Example demonstrated as a structure which provides a navigation apparatus in the own vehicle or another vehicle, terminal devices, such as a smart phone and a tablet, can also be used besides this.

  Note that the prediction method described in this embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. This program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. The program may be a transmission medium that can be distributed via a network such as the Internet.

DESCRIPTION OF SYMBOLS 100 Prediction apparatus 101,1001,1021 Acquisition part 102,1012 Prediction part 103,1003 Output part 300 Navigation apparatus 301 CPU
302 ROM
303 RAM
500 own vehicle 501 other vehicle 901 server 1001,1021 acquisition unit 1002,1011,1022 communication unit

Claims (1)

Acquisition means for acquiring a movement history of the moving object from another moving object;
Prediction means for predicting the behavior of the moving body based on the movement history;
An output means for outputting driving support information based on the prediction;
A prediction apparatus comprising:

Images