system

Abstract

Identify the end of the traffic jam in a way that matches the driver's perception. [Solution] The system (10) includes an acquisition means (11) that acquires vehicle information, including hazard information regarding hazard lights, from each of multiple vehicles; an intention estimation unit (12) that determines whether or not the turn signals were activated within a first predetermined period centered on the time when the hazard lights were turned ON, based on the turn signal information of the vehicle information, which includes hazard information indicating that the hazard lights are ON; an identification means (13) that identifies the end of a traffic jam using the hazard information included in the vehicle information; and a distribution unit (14) that distributes traffic jam start information and traffic jam prediction information generated by the identification means (13) to the road administrator and vehicles traveling around the target vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of a system for identifying the end of traffic congestion.

Background Art

[0002] As this type of system, for example, based on the measurement results by a millimeter-wave radar, it is determined whether each of a plurality of sections is in a traffic congestion state or a non-traffic congestion state, the determination result is corrected based on the arrangement of the traffic congestion state and the non-traffic congestion state, and a system for estimating the end of traffic congestion based on the state of each section after correction has been proposed (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technique described in Patent Document 1, it is determined whether it is in a traffic congestion state or a non-traffic congestion state based on the traffic congestion threshold speed. There may be a deviation between the determination result of determining whether there is traffic congestion using a numerical value and the driver's feeling. In addition, a technique has been proposed in which AI (Artificial Intelligence) detects traffic congestion by analyzing an image of a road captured. Also in this case, there may be a deviation between the detection result by AI and the driver's feeling.

[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide a system capable of identifying the end of traffic congestion that matches the driver's feeling.

Means for Solving the Problems

[0006] A system according to one aspect of the present invention comprises an acquisition means for acquiring vehicle information, including hazard information relating to hazard lights, from each of a plurality of vehicles, and an identification means for identifying the end of a traffic jam using the hazard information contained in the vehicle information. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the configuration of the system according to the embodiment. [Figure 2] A flowchart illustrating an example of the operation of the system according to the embodiment. [Figure 3] A flowchart illustrating another example of the operation of the system according to the embodiment. [Figure 4] This figure shows an example of how a vehicle's position changes over time. [Figure 5] This figure shows an example of a method for identifying the end of a traffic jam. [Modes for carrying out the invention]

[0008] Embodiments of the system will be described with reference to Figures 1 to 5. In Figure 1, the system 10 comprises a data acquisition unit 11, an intention estimation unit 12, a congestion end identification unit 13, a distribution unit 14, and a database 15. For example, the system 10 may be implemented by a server on a network. The server on the network may be a cloud server. Furthermore, the system 10 is not limited to a single server, but may be implemented by multiple servers.

[0009] The data acquisition unit 11 acquires vehicle information from multiple vehicles. These multiple vehicles may be connected cars. The data acquisition unit 11 may store the acquired vehicle information in the database 15. For example, the vehicle information may include time information, location information (e.g., latitude, longitude), hazard information related to hazard lights, turn signal information related to turn signals, speed, and acceleration.

[0010] For example, hazard lights may be used by a driver of a vehicle that is forced to park on the street due to a breakdown or other reason, to warn other drivers of the presence of danger. For example, hazard lights may be used by a driver of a vehicle approaching the end of a congested area to warn following drivers of the presence of congestion. For example, hazard lights may be used to express gratitude to a following driver who has yielded the right of way by changing lanes, etc. In this way, vehicle drivers may use hazard lights in different ways depending on the situation. In other words, vehicle drivers use hazard lights with a certain intention (or purpose).

[0011] The intention estimation unit 12 estimates the intention of the driver of the vehicle in question when the hazard information included in the vehicle information indicates that the hazard lights are ON (in other words, the hazard lights are activated). Here, the operation of the intention estimation unit 12 will be explained with reference to the flowchart in Figure 2.

[0012] In Figure 2, the intention estimation unit 12 determines whether or not the turn signals were activated within a first predetermined period, centered on the time when the hazard lights were turned ON, based on the turn signal information of the vehicle information, which includes hazard information indicating that the hazard lights are ON (step S101).

[0013] In the process of step S101, if it is determined that the turn signal was activated within a first predetermined period centered on the time when the hazard lights were turned ON (step S101: No), the intention estimation unit 12 estimates that the driver used the hazard lights with the intention of expressing gratitude to the following driver (so-called thank you hazard) (step S102).

[0014] In the process of step S101, if it is determined that the turn signal was not activated within a first predetermined period centered on the time when the hazard lights were turned ON (step S101: Yes), the intention estimation unit 12 determines whether the hazard lights have been ON for a long period of time (step S103). Alternatively, the intention estimation unit 12 may determine whether the hazard lights have been ON for a long period of time by determining whether the period during which the hazard lights have been ON is equal to or greater than a second predetermined period.

[0015] In step S103, if it is determined that the hazard lights have not been ON for an extended period of time (step S103: No), the intention estimation unit 12 estimates that the driver used the hazard lights with the intention of informing following drivers of the presence of traffic congestion (step S104). It should be noted that the end of a congested section can be considered the entrance to the congested section for drivers of vehicles about to enter it. Therefore, the "intention to inform following drivers of the presence of traffic congestion" can be rephrased as the "intention to inform following drivers of the point where the congestion begins."

[0016] In the process of step S103, if it is determined that the hazard lights have been ON for a long time (step S103: Yes), the intention estimation unit 12 estimates that the driver used the hazard lights with the intention of informing other drivers that the vehicle had made an emergency stop due to a malfunction or the like (step S105).

[0017] Returning to Figure 1, the traffic congestion end identification unit 13 identifies the end of the traffic congestion when the intention estimation unit 12 estimates that "the hazard lights were used with the intention of informing following drivers of the presence of traffic congestion." Here, the operation of the traffic congestion end identification unit 13 will be explained by referring to the flowchart in Figure 3.

[0018] For example, the intention estimation unit 12 may transmit vehicle information related to a vehicle (hereinafter, appropriately referred to as the "target vehicle") in which the hazard lamp has been operated in a predetermined manner, that is, "using the hazard lamp with the intention of informing the following driver of the existence of traffic congestion", to the traffic congestion end specifying unit 13. Here, the "predetermined manner" is a manner in which the direction indicator has not been operated within the first predetermined period centered on the time when the hazard lamp is turned on, and the hazard lamp is not in the ON state for a long time.

[0019] Based on the vehicle information related to the target vehicle, the traffic congestion end specifying unit 13 may specify the position of the target vehicle when the hazard lamp has been operated in a predetermined manner. For example, the position where the target vehicle has operated the hazard lamp in a predetermined manner may be the position p1 in FIG. 4. Here, the position p1 is relatively likely to be the end of the traffic congestion. However, depending on the timing when the driver of the target vehicle operates the hazard lamp, there is also a possibility that the position p1 is not the end of the traffic congestion.

[0020] Therefore, the traffic congestion end specifying unit 13 sets a spatio-temporal area W including the position p1 and the time t1 in a graph (time-space diagram) showing the relationship between the vehicle positions and times shown in FIG. 4 (step S201). That is, by setting the spatio-temporal area W, the traffic congestion end specifying unit 13 narrows down the spatio-temporal area including the end of the traffic congestion. Narrowing down the spatio-temporal area including the end of the traffic congestion may be referred to as area aggregation. Here, the size of the spatio-temporal area W may be fixed or may change according to some parameters. Further, the spatio-temporal area W may be set using a learned model (in other words, AI) generated by machine learning.

[0021] Next, based on the vehicle information related to one or more vehicles included in the spatio-temporal area W, the traffic congestion end specifying unit 13 may generate a speed distribution in the spatio-temporal area W. Based on the speed distribution, the traffic congestion end specifying unit 13 may calculate a speed difference (in other words, a change amount of speed) in the vicinity of the position p1. The traffic congestion end specifying unit 13 determines whether or not the speed difference is equal to or greater than a predetermined value in the vicinity of the position p1 (step S202).

[0022] The speed of the vehicle in the traffic jam area is significantly lower than the speed of the vehicle in the non-traffic jam area. Therefore, at the boundary between the non-traffic jam area and the traffic jam area (in other words, the end of the traffic jam), the speed difference becomes relatively large. The above-mentioned "predetermined value" may be a value for determining whether the end of the traffic jam is included in the spatio-temporal area W. For example, the predetermined value in the case of a highway may be 40 kilometers per hour. For example, the predetermined value in the case of an ordinary road may be 10 kilometers per hour.

[0023] In the process of step S202, when it is determined that the speed difference is not greater than the predetermined value (step S202: No), the process shown in FIG. 3 ends. On the other hand, in the process of step S202, when it is determined that the speed difference is greater than or equal to the predetermined value (step S202: Yes), the traffic jam end specifying unit 13 may determine that one or more vehicles included in the spatio-temporal area W are a group of vehicles traveling near the end of the traffic jam. Then, the traffic jam end specifying unit 13 extracts the traffic jam end position (step S203).

[0024] Here, it is not the driver's obligation to activate the hazard lights to inform following drivers of the presence of congestion. For this reason, some drivers do not activate their hazard lights when approaching the end of a traffic jam. For example, if there is only one location where the hazard lights were activated within the spatiotemporal area W, the traffic jam end identification unit 13 may extract that location as the traffic jam end location. For example, if there are multiple locations where the hazard lights were activated within the spatiotemporal area W, the traffic jam end identification unit 13 may extract the upstream location within the spatiotemporal area W from among the multiple locations as the traffic jam end location. For example, the black circles in Figure 5(a) indicate locations where the hazard lights were activated within the spatiotemporal area W. In this way, if there are multiple locations where the hazard lights were activated within the spatiotemporal area W, the traffic jam end identification unit 13 may extract location p2 as the traffic jam end location. Alternatively, if the spatiotemporal area W includes multiple locations where the hazard lights were activated, the congestion end identification unit 13 may extract (identify) the congestion end location based on at least one of the following: the average location where the hazard lights were activated, the location where the hazard lights were activated most frequently, and the location where the hazard lights were activated least frequently.

[0025] Next, the congestion end identification unit 13 predicts the future location of the end of the congestion (step S204). Traffic conditions propagate from downstream to upstream of the traffic flow. Therefore, the end of the congestion also changes over time. For example, the operation shown in Figure 3 may be repeated. In this case, the congestion end identification unit 13 may predict the future location of the end of the congestion based on the spatiotemporal area W set this time and the spatiotemporal area Wp set last time. For example, the relationship between spatiotemporal area W and spatiotemporal area Wp may be as shown in Figure 5(b). The black circles in Figure 5(b) indicate the locations where the hazard lights were activated. For example, the congestion end identification unit 13 may perform a linear regression analysis based on multiple locations where the hazard lights were activated. Then, the congestion end identification unit 13 may use the results of the linear regression analysis and the spatiotemporal area Wf set in the future to predict the future location of the end of the congestion (for example, location p3).

[0026] Subsequently, the congestion end identification unit 13 may generate congestion start information indicating the spatiotemporal area W set in step S201 and the congestion end position (e.g., position p2) extracted (in other words, identified) in step S203, and congestion prediction information indicating the predicted future congestion end position (e.g., position p3) and the results of linear regression analysis in step S204.

[0027] Returning to Figure 1, the distribution unit 14 may distribute the congestion start information and congestion forecast information generated by the congestion end identification unit 13 to the road administrator and to vehicles traveling around the target vehicle. Alternatively, the distribution unit 14 may distribute the congestion start information and congestion forecast information to vehicles traveling around the target vehicle by transmitting the congestion start information and congestion forecast information to a connected center that sequentially distributes information to connected cars.

[0028] (Technical effects) System 10 identifies the end of a traffic jam using information from hazard lights used with the intention of informing following drivers of the presence of congestion. Therefore, the location corresponding to the end of the traffic jam identified by System 10 is expected to be close to the location that drivers perceive as the end of a traffic jam. Thus, System 10 can identify the end of a traffic jam in a way that matches the driver's perception.

[0029] For example, accidents can occur on highways when another vehicle collides with a slow-moving vehicle from behind. In response to this, system 10 predicts the future end position of a traffic jam. System 10 then distributes traffic jam prediction information indicating the predicted future end position of the traffic jam. By distributing traffic jam prediction information, it is expected that drivers of vehicles approaching the end of a traffic jam will be more likely to notice the congestion. As a result, it is expected that the occurrence of collision accidents at the end of traffic jams will be suppressed.

[0030] The embodiments of the invention derived from the above-described embodiments are described below.

[0031] A system according to one aspect of the invention includes an acquisition means for acquiring vehicle information, including hazard information relating to hazard lights, from each of a plurality of vehicles, and a identification means for identifying the end of a traffic jam using the hazard information contained in the vehicle information. In the above embodiment, the "data acquisition unit 11" corresponds to an example of the "acquisition means," and the "traffic jam end identification unit 13" corresponds to an example of the "identification means."

[0032] In one example of the system, the vehicle information may include location information indicating the location, and the identifying means may use the hazard information and the location information to identify the location of a vehicle whose hazard lights have been activated in a predetermined manner, thereby identifying an area including the end of a traffic jam.

[0033] In this embodiment, if there are multiple vehicles with their hazard lights activated within the identified area, the identification means may identify the upstreammost location within the identified area among the multiple locations where the hazard lights were activated as the end of the traffic jam.

[0034] The present invention is not limited to the embodiments described above, and can be modified as appropriate without contradicting the gist or idea of ​​the invention as can be read from the claims and specification as a whole. Systems involving such modifications are also included within the technical scope of the present invention. [Explanation of Symbols]

[0035] 10...System, 11...Data acquisition unit, 12...Intention estimation unit, 13...Traffic congestion end identification unit, 14...Distribution unit, 15...Database

Claims

1. A means for acquiring vehicle information, including hazard information related to hazard lights, from each of multiple vehicles, A means for identifying the end of a traffic jam using the hazard information included in the vehicle information, A system equipped with these features.

2. The aforementioned vehicle information includes location information indicating the location, The aforementioned specifying means is, By using the hazard information and location information to identify the location of a vehicle whose hazard lights were activated in a predetermined manner, the area including the end of the traffic jam can be identified. The system according to claim 1.

3. If there are multiple vehicles with their hazard lights on within the identified area, the identification means identifies the upstreammost location within the identified area among the multiple locations where the hazard lights were on as the end of the traffic jam. The system according to claim 2.

Images