Merging position evaluation device and method for vehicle

Abstract

To properly perform evaluation of a merging position in a short time, in a scene where a vehicle merges.SOLUTION: A merging position evaluation device comprises: an obtaining part (12) that obtains a traffic environment around an own vehicle; an extracting part (12) that extracts merging position candidates that are candidates for cut-in destination gaps for the own vehicle cuts in an other vehicle group; a simulating part (13) that repeatedly simulates future behavior of the own vehicle and of the other vehicle group, using an operation behavior model for predicting behavior of the own vehicle and of the other vehicle group, while applying variation to a parameter of the model; and an evaluating part (14) that determines a distribution of evaluation values for each merging position candidate on the basis of the simulated result and evaluates superiority or inferiority of the merging position candidates on the basis of the distribution of the evaluation values.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus and method for evaluating a merging position when a vehicle passes through a branch line and merges into a main line. [Background technology]

[0002] In recent years, as part of research into vehicle driving assistance or autonomous driving, assistance or automation of a merging operation of a vehicle merging from a branch line onto a main line has been considered. For example, Patent Document 1 below discloses that in a behavior plan generation device that generates a behavior plan for a vehicle merging onto a main line, a learning model generated from driving data obtained through a simulator function that allows a user to experience simulated vehicle driving is used to calculate a yielding degree that indicates the likelihood that other vehicles traveling on the main line will yield to the user's vehicle, and a behavior plan for the user's vehicle merging onto the main line is generated based on the calculated yielding degree. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-146576 Summary of the Invention [Problem to be solved by the invention]

[0004] When the vehicle merges onto the main lane, it is necessary to determine one of a plurality of gaps (vehicle gaps) in a group of other vehicles traveling on the main lane as a target merging position. However, in the above-mentioned Patent Document 1, the determination of whether or not the vehicle can actually merge at the target merging position, that is, the evaluation of the merging position, is performed based on the output value (degree of yielding) of a learning model obtained from repeated experiments by subjects using a simulator function, which results in the problem of time and effort required to establish the evaluation logic.

[0005] The present invention has been made in consideration of the above circumstances, and has an object to provide a vehicle merging position evaluation device and method that can appropriately evaluate a merging position in a short amount of time. [Means for solving the problem]

[0006] In order to solve the above problem, one aspect of the present invention provides a vehicle merging position evaluation device that evaluates a merging position when a host vehicle passes through a branch line and merges onto a main line, and includes: an acquisition unit that acquires a traffic environment around the host vehicle, including the positions and speeds of a group of other vehicles traveling on the main line, and road shape; an extraction unit that extracts merging position candidates that are candidates for cut-in gaps when the host vehicle cuts in into the group of other vehicles, based on the traffic environment acquired by the acquisition unit; a simulation unit that uses a driving behavior model that predicts the behavior of the host vehicle and the group of other vehicles, and repeatedly simulates the future behavior of the host vehicle and the group of other vehicles while varying model parameters of the driving behavior model; and an evaluation unit that calculates a distribution of evaluation values ​​for each of the merging position candidates extracted by the extraction unit, based on the results of the simulation performed by the simulation unit, and evaluates the merits of the merging position candidates based on the distribution of evaluation values.

[0007] According to the present invention, each potential merging location is evaluated through a simulation using a driving behavior model that predicts the behavior of the vehicle itself and other vehicles. This eliminates the need for complex processes such as machine learning or reinforcement learning to calculate the evaluation value, thereby reducing the time required for evaluation.

[0008] Furthermore, simulations are repeatedly performed while varying the model parameters of the driving behavior model, and the distribution of evaluation values ​​for each merging position candidate is determined from the results of the repeated simulations. This allows the merits and demerits of the merging position candidates to be appropriately evaluated based on the distribution of evaluation values, and enables statistically valid merging position candidates to be identified.

[0009] Preferably, the evaluation unit calculates a mean and a standard deviation of the evaluation values ​​for each of the meeting position candidates as the distribution of the evaluation values, and evaluates the merits and demerits of the meeting position candidates based on the mean and standard deviation.

[0010] In this embodiment, a comprehensive evaluation can be performed based on both the average and standard deviation of the evaluation values.

[0011] Preferably, the evaluation unit calculates an overall evaluation index Eg for each of the merging position candidates, which is determined by the following formula (1) from the average and standard deviation of the evaluation values, and evaluates the merging position candidates with a large overall evaluation index Eg as being better than the merging position candidates with a small overall evaluation index Eg. Eg=μ+k×σ ‥‥(1) Here, μ is the average of the evaluation values, σ is the standard deviation of the evaluation values, and k is a coefficient between −1 and +1.

[0012] In this embodiment, it is possible to appropriately evaluate the merging position candidates based on the magnitude of the comprehensive evaluation index defined by both the average and the standard deviation. Also, it is possible to adjust the coefficient k, for example, by making it negative when careful judgment is required and by making it zero or greater when not, thereby enabling the merging position candidates to be evaluated with appropriate caution depending on the situation.

[0013] Preferably, the simulation unit applies the variation based on statistical appearance frequency distribution data to a characteristic parameter of the model parameters that is determined according to driver characteristics or vehicle performance of the other vehicle group.

[0014] In this embodiment, it is possible to appropriately evaluate merge position candidates while taking into consideration variations in driver characteristics or vehicle performance.

[0015] Preferably, the evaluation unit calculates, as the evaluation value, a merging margin, which is the remaining distance or remaining time to the end of the branch line at the time when the host vehicle has completed merging or is expected to complete merging.

[0016] The merging margin, which is the remaining distance or time to the end of the branch line, is a value that can change continuously depending on the situation. Therefore, evaluation based on this value can determine not only whether the merging was successful or not, but also how much time was available for the merging. Furthermore, since the merging margin can be calculated as a negative value even in the case of a failed merging, it is possible to determine from this value how close the merging was to success. In this way, by using the merging margin, which can change continuously from positive to negative, as an evaluation value, the merits and demerits of each merging location candidate can be accurately evaluated.

[0017] Preferably, the driving behavior model includes a following driving model that predicts the behavior of the group of other vehicles and outputs acceleration required to drive while maintaining an appropriate inter-vehicle distance from the preceding vehicle.

[0018] Furthermore, the driving behavior model includes a proportional model that outputs acceleration proportional to the difference between a predetermined target position and a predetermined target speed as a model for predicting the behavior of the host vehicle.

[0019] In these aspects, the future behavior of the other vehicle group and the host vehicle can be appropriately simulated through calculations with a relatively light load using specified calculation formulas.

[0020] A method for evaluating a merging position for a vehicle according to another aspect of the present invention is a method for evaluating a merging position when a host vehicle merges onto a main line via a branch line, the method including the steps of: acquiring a traffic environment around the host vehicle, including the positions and speeds of a group of other vehicles traveling on the main line, and road shape; extracting merging position candidates, which are candidates for cut-in gaps when the host vehicle cuts in into the group of other vehicles, based on the acquired traffic environment; repeatedly simulating the future behavior of the host vehicle and the group of other vehicles using a driving behavior model that predicts the behavior of the host vehicle and the group of other vehicles while varying model parameters of the driving behavior model; and determining a distribution of evaluation values ​​for each of the extracted merging position candidates based on the results of the simulation, and evaluating the merits of the merging position candidates based on the distribution of evaluation values.

[0021] According to the invention of the merging position evaluation method, similar to the invention of the merging position evaluation device described above, it is possible to appropriately evaluate the merging position in a short time. [Effects of the Invention]

[0022] As described above, according to the merging position evaluation device or method of the present invention, it is possible to appropriately evaluate a merging position in a short time. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a functional block diagram showing the configuration of a vehicle control system to which a merging position evaluation device according to an embodiment of the present invention is applied. [Figure 2] FIG. 1 is a schematic diagram illustrating an example of a merging scene in which a vehicle merges from a branch line onto a main line. [Figure 3A] FIG. 10 is a schematic diagram for explaining a situation in which the merging margin distance becomes positive. [Figure 3B] FIG. 10 is a schematic diagram for explaining a situation in which the merging margin distance becomes negative. [Figure 4] 10 is an equation showing the contents of a driving behavior model that predicts the behavior of the host vehicle and other vehicles when merging. [Figure 5]10 is a flowchart showing a procedure for evaluating a meeting position candidate. [Figure 6] 6 is a subroutine showing details of step S4 in FIG. 5. [Figure 7] 7 is a subroutine showing details of step S15 in FIG. 6. [Figure 8A] 3A and 3B are schematic diagrams showing examples of setting a target position and a target speed of a host vehicle; [Figure 8B] 10A and 10B are schematic diagrams showing other examples of setting the target position and target speed of the host vehicle. [Figure 9] 1 is a graph showing the relationship between the value of a model parameter and the frequency of occurrence thereof; [Figure 10] 10 is a graph showing the relationship between the merging margin distance calculated by the above simulation and the frequency of occurrence thereof. [Figure 11] 10 is a graph showing the relationship between the coefficient used in calculating the comprehensive evaluation index and the average merging margin distance. [Figure 12] 10 is a graph for explaining how the overall evaluation index changes depending on the coefficient. [Figure 13] 10 is a graph showing a comparison of the overall evaluation indexes of three candidate merging positions. DETAILED DESCRIPTION OF THE INVENTION

[0024] Hereinafter, preferred embodiments of the vehicle merging position evaluation device and method of the present invention will be described in detail with reference to the drawings. The vehicle to which the present invention is applied may be any of an engine vehicle powered by an internal combustion engine, an electric vehicle powered by an electric motor, and a hybrid vehicle powered by both an internal combustion engine and an electric motor. Furthermore, the merging position evaluation device and method may be used to evaluate a merging position during a merging operation of an autonomous vehicle that does not require driver operation, or may be used to evaluate a merging position during a merging operation of a vehicle with a driving assistance function that assists the driver in driving.

[0025] (1) Overall structure Fig. 1 is a functional block diagram showing the configuration of a vehicle control system to which a merging position evaluation device according to one embodiment of the present invention is applied. As shown in the diagram, the vehicle control system includes a controller 10 that controls the vehicle, a group of internal sensors 30 that detect the vehicle's driving state, a group of external sensors 31 that detect the vehicle's surrounding conditions, a GNSS receiver 32 that identifies the vehicle's position, and a group of actuators 40 that drive the vehicle. The vehicle control system is mounted on a vehicle 1 shown in Fig. 2. Hereinafter, the vehicle 1 may be referred to as the host vehicle 1 to distinguish it from another vehicle 2.

[0026] The controller 10 is configured with a microcomputer as its main components, including an arithmetic unit 11 including a processor such as a CPU, a storage unit 20 including a ROM, a RAM, and an HDD, and peripheral circuits such as an I / O interface.

[0027] The controller 10 is electrically connected to the internal sensor group 30, the external sensor group 31, the GNSS receiver 32, and the actuator group 40. That is, the controller 10 receives various information output from the sensor groups 30, 31 and the GNSS receiver 32, and outputs control signals to the actuator group 40.

[0028] The internal sensor group 30 is a collective term for sensors for detecting various information representing the traveling state of the host vehicle 1. The internal sensor group 30 includes a vehicle speed sensor for detecting the speed (traveling speed) of the host vehicle 1 and an acceleration sensor for detecting the acceleration of the host vehicle 1.

[0029] The GNSS receiver 32 is a receiver for determining the vehicle's own position using the Global Navigation Satellite System (GNSS). The GNSS receiver 32 receives and processes radio signals transmitted from GNSS satellites to determine the position of the vehicle 1 on Earth.

[0030] The external sensor group 31 is a collective term for sensors for recognizing targets around the host vehicle 1, and includes at least one of an optical sensor and an imaging sensor. Examples of optical sensors include radar such as millimeter-wave radar or a ranging device using LiDAR (light detection and ranging). Examples of imaging sensors include cameras including imaging elements such as CCDs and CMOSs. Alternatively, the external sensor group 31 may be a sensor fusion system including multiple types of sensors including optical sensors and imaging sensors and integration means for integrating and processing signals obtained from the sensors. Note that at least a portion of the external sensor group 31 may be optical sensors or imaging sensors installed on the road on which the host vehicle 1 travels. In this case, the controller 10 of the host vehicle 1 acquires information detected by the sensors on the road via appropriate communication means.

[0031] The actuator group 40 is a general term for actuators for driving that enable the vehicle 1 to drive. The actuator group 40 includes, for example, a power source such as an engine or a motor that generates power for driving, and a motor (steering motor) that drives a steering mechanism for changing the direction of travel.

[0032] The memory unit 20 stores various data necessary for driving control of the host vehicle 1. The data stored in the memory unit 20 includes road map data M1 and a driving behavior model M2. The road map data M1 is, for example, high-precision three-dimensional map data (HD map). In this case, the road map data M1 includes, for example, information on the position, shape, gradient, etc. of the road, position information on traffic lights, signs, etc. on the road, and information on the width and position of lanes, etc. The driving behavior model M2 is a mathematical model for simulating the future behavior of the host vehicle 1 and the other vehicle 2 in a merging scene (FIG. 2) described later. At least one of the road map data M1 and the driving behavior model M2 does not have to be stored in the memory unit 20 in advance, but may be input from an external server via a communication device (not shown) and temporarily stored in the memory unit 20.

[0033] The calculation unit 11 functionally includes a recognition unit 12, a simulation unit 13, an evaluation unit 14, a route generation unit 15, and a travel control unit 16.

[0034] The recognition unit 12 is a module that recognizes the state of the host vehicle 1 and the state of the surroundings of the host vehicle 1, including the other vehicle 2. For example, the recognition unit 12 acquires the speed and acceleration of the host vehicle 1 and the position of the host vehicle 1 on the road based on information input from the internal sensor group 30 and the GNSS receiver 32. The recognition unit 12 also acquires the position and speed of the other vehicle 2 based on information input from the external sensor group 31. Furthermore, the recognition unit 12 acquires the shape of the road around the host vehicle 1 from the road map data M1. The recognition unit 12 corresponds to an example of the "acquisition unit" and the "extraction unit" in the present invention.

[0035] The simulation unit 13 is a module that uses the driving behavior model M2 to simulate the future behavior of the host vehicle 1 and the other vehicle 2. Specifically, the simulation unit 13 performs a simulation to determine the merging operation of the host vehicle 1 at the time of merging shown in Fig. 2, that is, at the time of merging when the host vehicle 1 passes through the branch line 102 and merges onto the main line 101.

[0036] In the example of FIG. 2, the host vehicle 1 is traveling on a branch line 102 including a parallel section that extends parallel to the main line 101 in order to merge onto the main line 101. Furthermore, a plurality of other vehicles 2 (hereinafter also referred to as the other vehicle group 2) are traveling on the main line 101. A gap 3 is formed between each of the vehicles adjacent to each other in the fore-and-aft direction (travel direction) in the other vehicle group 2. When merging onto the main line 101, the host vehicle 1 determines which gap 3 in the other vehicle group 2 the host vehicle 1 will enter, and moves toward the determined gap 3. In order to determine the merging behavior of the host vehicle 1 in advance, the simulation unit 13 repeatedly simulates the future behavior of the host vehicle 1 and the other vehicles 2 using the driving behavior model M2.

[0037] The evaluation unit 14 is a module that evaluates the gap 3 into which the host vehicle 1 will cut in, i.e., the merging position, based on the results of the simulation performed by the simulation unit 13. That is, the evaluation unit 14 regards each of the multiple gaps 3 into which the host vehicle 1 may cut in as a merging position candidate, and evaluates each of the merging position candidates based on the results of the simulation in order to compare the merits of these merging position candidates.

[0038] Specifically, in the example of FIG. 2, a group of other vehicles 2 includes a first vehicle 2A, a second vehicle 2B, a third vehicle 2C, and a fourth vehicle 2D traveling on the main road 101 in this order from the front in the traveling direction. In this case, a first gap 3A between the first vehicle 2A and the second vehicle 2B, a second gap 3B between the second vehicle 2B and the third vehicle 2C, and a third gap 3C between the third vehicle 2C and the fourth vehicle 2D are respectively candidate merging positions. Based on this, the simulation unit 13 repeatedly simulates the future behavior of the host vehicle 1 and the other vehicles 2 (2A-2D) using the driving behavior model M2 for each case in which the host vehicle 1 is forced to cut into the first to third gaps 3A-3C. From the results of this simulation, an evaluation value representing the appropriateness of each of the first to third gaps 3A-3C as a merging position is obtained for each of the first to third gaps 3A-3C. The evaluation unit 14 evaluates the merits or demerits of each of the gaps 3A-3C based on the obtained evaluation value.

[0039] As the evaluation value, the simulation unit 13 calculates a merging margin, which is the remaining distance or remaining time to the end 102a of the branch line 102 (hereinafter also referred to as the branch line end 102a) at the time when the host vehicle 1 has completed merging or when the completion of merging is expected. Specifically, in this embodiment, as shown in FIG. 3A, the merging margin is calculated as a merging margin distance Lm, which is the distance from the host vehicle 1 to the end 102a of the branch line at the time when the completion of merging is expected. Here, the time when the completion of merging is expected is the time when the host vehicle 1 will be able to complete merging by simply changing lanes, moving laterally from the branch line 102 to the main line 101. As will be described in detail later, in this embodiment, it is determined that the completion of merging is expected when merging possible conditions are met, including the following conditions: the size of the gap at the cut-in destination (second gap 3B in the example of FIG. 3A) is larger than a predetermined value, and the host vehicle 1 is traveling near the gap at a speed close to that of the other vehicle 2.

[0040] The merging margin distance Lm can be calculated as a negative value. In other words, in the above simulation, even if the merging condition is not yet met when the host vehicle 1 approaches the branch line terminal end 102a and merging completion is not expected, in other words, even if it is determined that merging will fail, the calculation using the driving behavior model M2 continues, assuming that there is another lane beyond the branch line terminal end 102a. The calculation continues until the merging condition is met (merging completion is expected), and the negative merging margin distance Lm shown in FIG. 3B is calculated. In other words, the situation in FIG. 3B is a situation in which merging is not possible unless the host vehicle 1 moves beyond the branch line terminal end 102a, which does not actually exist, so the merging margin distance Lm is negative. Conversely, if the merging condition is met just before the branch line terminal end 102a as shown in FIG. 3A, the merging margin distance Lm is calculated as a positive value. Thus, the merging margin distance Lm can be calculated regardless of whether merging is successful or not, and is an evaluation value that can continuously change from positive to negative.

[0041] The evaluation unit 14 evaluates each of the merging position candidates (gaps 3A to 3C) using the merging margin distance Lm calculated as described above as an evaluation value. The larger the merging margin distance Lm, the more margin there is for merging. Therefore, roughly speaking, the evaluation of the merging position candidates can be performed in such a way that the merging position candidate with a larger merging margin distance Lm is given a higher evaluation. However, in this embodiment, a simulation is repeatedly performed for each merging position candidate, the merging margin distance Lm is calculated each time, and the merging position candidates are statistically evaluated based on the distribution (mean μ and standard deviation σ) of the merging margin distance Lm obtained from the simulation results. This will be described in detail later.

[0042] The route generation unit 15 is a module that generates a movement route for the host vehicle 1 to a target merging position, i.e., a merging target. That is, the route generation unit 15 determines one of the merging position candidates with the highest evaluation as the merging target based on the evaluation of each of the merging position candidates by the evaluation unit 14. Then, assuming that the host vehicle 1 will move to the determined merging target, the route generation unit 15 generates a movement route for the host vehicle 1 required for this purpose.

[0043] The traveling control unit 16 is a module that controls the movement of the host vehicle 1 along the travel route generated by the route generation unit 15. That is, the traveling control unit 16 controls the actuator group 40 that causes the host vehicle 1 to travel, thereby moving the host vehicle 1 along the travel route and leading it to the merging target.

[0044] (2) Driving behavior model 4 shows the equations of the driving behavior model M2 used in the above simulation. The driving behavior model M2 shown in this figure includes an own vehicle model equation F1 that predicts the behavior of the own vehicle 1, and an other vehicle model equation F2 that predicts the behavior of the other vehicle 2.

[0045] The vehicle model formula F1 is a model formula that outputs acceleration ACCx proportional to the difference between the target position and the target speed, and expresses a proportional model such as a spring mass model. In this vehicle model formula F1, Δx is the difference between the target position and the current position, and Δv is the difference between the target speed and the current speed. These Δx and Δv are variables that change with time. Also, a max is the upper limit acceleration, a min is the lower limit acceleration, and c1 and c2 are weighting coefficients. max ,a min , c1, and c2 are parameters that are determined in advance. Note that the weighting coefficients c1 and c2 may be changed as appropriate depending on the situation of the host vehicle 1 or the other vehicle 2, etc.

[0046] The acceleration ACCx of the host vehicle 1 calculated by such host vehicle model formula F1 is basically calculated as the sum of a value proportional to the difference (Δx) between the target position and the current position and a value proportional to the difference (Δv) between the target speed and the current vehicle speed. However, the acceleration ACCx includes a lower limit acceleration a min and the upper limit acceleration a max A limiter is applied to prevent it from exceeding this.

[0047] The other vehicle model formula F2 is a model formula that outputs the acceleration ACCy required to travel while maintaining an appropriate distance from the preceding vehicle, and represents a following driving model generally known as the IDM (Intelligent Driver Model). In this other vehicle model formula F2, s is the distance from the preceding vehicle, v is the speed, and Δv is the relative speed from the preceding vehicle. These s, v, and Δv are variables that change over time. Also, v0 is the desired speed, s0 is the safe distance from the preceding vehicle (in other words, the distance between vehicles when stopped), T is the minimum time between vehicles (reaction time), a is the maximum acceleration, b is the maximum deceleration, and δ is the power of the acceleration term (smoothness of acceleration). These v0, s0, T, a, b, and δ are characteristic parameters that can change depending on the driver's characteristics and the vehicle's performance.

[0048] Simply put, this other vehicle model formula F2 (follow-up driving model) calculates the appropriate inter-vehicle distance (s * ) and calculates the acceleration ACCy from the calculated inter-vehicle distance. As a result, the acceleration of the other vehicle 2 is adjusted so as to maintain an appropriate inter-vehicle distance from the preceding vehicle.

[0049] (3) Details of evaluation of candidate merging locations Next, the details of the evaluation of the merging position candidate performed by the evaluation unit 14 will be described. FIG. 5 is a flowchart showing the procedure for evaluating the merging position candidate. As a premise for starting the control shown in this figure, it is assumed that the host vehicle 1 is traveling on the branch line 102 (FIG. 2), and that multiple other vehicles 2 are traveling within the range of the main line 101 that the host vehicle 1 can recognize. When this control starts, the recognition unit 12 acquires the traveling state of the host vehicle 1 and the traffic environment around the host vehicle 1 (step S1). That is, the recognition unit 12 acquires information including the position and speed of the host vehicle 1 as information representing the traveling state of the host vehicle 1. The recognition unit 12 also acquires information including the road shape around the host vehicle 1 and the position and speed of the other vehicles 2 as information representing the traffic environment around the host vehicle 1. This information is determined from the detection values ​​of the internal sensor group 30 and the external sensor group 31, the road map data M1 stored in the memory unit 20, and the received signal of the GNSS receiver 32.

[0050] More specifically, the recognition unit 12 acquires information including the speed of the vehicle 1 and the position of the vehicle 1 on the branch line 102 based on the detection values ​​of the internal sensor group 30 and the received signal of the GNSS receiver 32. The recognition unit 12 also acquires information about the road shape around the vehicle 1 based on the acquired position (current position) of the vehicle 1 and detailed road map data M1 stored in the memory unit 20. This information may include the length of an acceleration section, which is the distance from the current position of the vehicle 1 traveling on the branch line 102 to the branch line end 102a, and information about lane change prohibited sections, which are sections where changing lanes from the branch line 102 to the main line 101 is prohibited. If a lane change prohibited section exists, the position of the branch line end 102a may be set to the end of the branch line 102 excluding the lane change prohibited section, in other words, the end of the section where changing lanes from the branch line 102 to the main line 101 is permitted. Furthermore, the recognition unit 12 acquires information including the position and speed of each of a plurality of other vehicles 2 (other vehicle group) traveling on the main road 101 in a range from diagonally ahead to diagonally behind the host vehicle 1, based on the detection values ​​of the external sensor group 31. In this case, the acquired positions of the other vehicle group 2 are relative positions with the host vehicle 1 as the reference.

[0051] Next, based on the information about the other vehicle group 2 acquired in step S1, the recognition unit 12 extracts candidate merging positions, which are candidates for gaps into which the host vehicle 1 will cut in when cutting into the other vehicle group 2 (step S2). For example, if the other vehicle group 2 recognized in step S1 is made up of four vehicles, namely, first to fourth vehicles 2A to 2D, as shown in Fig. 2, the recognition unit 12 extracts three gaps, consisting of a first gap 3A between the first vehicle 2A and the second vehicle 2B, a second gap 3B between the second vehicle 2B and the third vehicle 2C, and a third gap 3C between the third vehicle 2C and the fourth vehicle 2D, as candidate merging positions.

[0052] Next, the evaluation unit 14 designates one merging position candidate to be evaluated from the merging position candidates extracted in step S2 (step S3). For example, if the extracted merging position candidates are the first to third gaps 3A to 3C as in the example of Fig. 2, the evaluation unit 14 designates an appropriate one of these three gaps 3A to 3C as the target for evaluation.

[0053] Next, the evaluation unit 14 evaluates the merging position candidate designated in step S3 (step S4). The evaluation here is performed based on the results of a simulation performed by the simulation unit 13 using the driving behavior model M2.

[0054] 6 is a subroutine showing detailed procedures for evaluating merge position candidates in step S4 above. When the control shown in this figure starts, the simulation unit 13 sets the initial positions and initial velocities of the host vehicle 1 and the other vehicle group 2 (step S11). The initial positions and initial velocities are the positions and velocities of the vehicles 1 and 2 at the start of the simulation. The simulation unit 13 sets the position and speed of the host vehicle 1 acquired in step S1 above as the initial position and initial speed of the host vehicle 1, and sets the position and speed of the other vehicle group 2 acquired in step S1 above as the initial position and initial speed of the other vehicle group 2.

[0055] Next, the simulation unit 13 sets the acceleration section length at the start of the simulation based on the information acquired in step S1 (step S12). The acceleration section length is the distance from the initial position of the vehicle 1 to the branch line end 102a.

[0056] Next, the simulation unit 13 sets a target position and a target speed of the host vehicle 1 (step S13). The target position and the target speed are the position and the speed that the host vehicle 1 aims to achieve in the host vehicle model formula F1 of the driving behavior model M2 described above, and are determined according to the merge position candidate specified in step S3 (FIG. 5).

[0057] For example, as shown in FIG. 8A, if the specified candidate merging position is a first gap 3A between a first vehicle 2A and a second vehicle 2B, the target position is set to the side of the first gap 3A. Also, as shown in FIG. 8B, if the specified candidate merging position is a third gap 3C between a third vehicle 2C and a fourth vehicle 2D, the target position is set to the side of the third gap 3C. In the former case (FIG. 8A), the target position is set in front of the host vehicle 1, so the host vehicle 1 moves toward the target position while accelerating. On the other hand, in the latter case (FIG. 8B), the target position is set behind the host vehicle 1, so the host vehicle 1 moves toward the target position while suppressing acceleration (or decelerating in some cases).

[0058] The target position of the vehicle 1 may be approximately to the side of the gap 3 designated as the candidate merging position in step S3 (hereinafter referred to as designated gap 3), and various specific methods for setting the target position are conceivable. For example, the target position may be to the side of the center of the designated gap 3, or to the side of another vehicle 2 (leading vehicle) located in front of the designated gap 3.

[0059] The target speed of the host vehicle 1 is set based on the speeds of the other vehicles 2 that form the gap 3 of the candidate merging position, in other words, the speeds of the other vehicles 2 before and after the gap 3. For example, if the candidate merging position is a first gap 3A as shown in FIG. 8A , the target speed of the host vehicle 1 is set based on the speeds of the first vehicle 2A in front of the first gap 3A and the second vehicle 2B behind the first gap 3A. There are various specific methods for setting the target speed, but for example, the average speed of the first vehicle 2A and the second vehicle 2B may be set as the target speed of the host vehicle 1. This is also true when the candidate merging position is another gap (the second gap 3B or the third gap 3C).

[0060] Next, the simulation unit 13 randomly sets the model parameters of the other vehicle model formula F2 described above that predicts the behavior of the other vehicle 2 (step S14). Specifically, in this embodiment, four parameters included in the other vehicle model formula F2, namely, the desired speed (v0), the minimum inter-vehicle time (T), the maximum acceleration (a), and the maximum deceleration (b), are randomly set based on statistical occurrence frequency distribution data. On the other hand, the remaining parameters, namely, the exponent (δ) of the acceleration term and the minimum inter-vehicle distance (s0), are maintained at fixed values. This is because it is known that sufficient accuracy can be obtained even if these two parameters are treated as fixed values.

[0061] Here, the statistical occurrence frequency distribution data that forms the basis for random setting is statistical data that defines the relationship between parameter values ​​and occurrence frequencies, as shown in FIG. 9, and is obtained in advance by observing actual vehicles traveling at merging sections on expressways, etc. The four model parameters described above depend on the characteristics of the driver of the other vehicle 2 and the performance of the other vehicle 2, and therefore cannot be known by the own vehicle 1. Therefore, in step S14, the model parameters are randomly set based on the occurrence frequency distribution data of FIG. 9 obtained from observation of actual traffic. This is equivalent to statistically inferring the driver characteristics of the other vehicle 2 from the observation results of actual traffic. Note that there are already several publicly known occurrence frequency distribution data (statistical data) such as that shown in FIG. 9, and it is possible to obtain them without independently observing actual traffic.

[0062] For example, suppose the occurrence frequency distribution data in FIG. 9 is data on the occurrence frequency of each parameter in the range from P1 to P2, and the mode is Px. In this case, the simulation unit 13 randomly sets the model parameters within the range from P1 to P2 and varies the occurrence probability based on the distribution curve. That is, the model parameter value generated by the random setting is most likely to be Px. Conversely, the further a value is from Px, the less likely it is to be set as a model parameter. Thus, in step S14, the simulation unit 13 sets the model parameters with probabilities according to the distribution curve in FIG. 9. Therefore, when step S14 is repeated and model parameters are randomly set many times, the occurrence frequency will be higher for parameters closer to the mode Px in FIG. 9 and lower for parameters farther from the mode Px.

[0063] Furthermore, the random setting of the model parameters in step S14 above is performed individually for each other vehicle 2. That is, the random setting of the model parameters for one other vehicle 2 is performed independently of the random setting of the model parameters for the other other vehicles 2. For this reason, in most cases, different model parameters are set for each other vehicle 2.

[0064] As will be described later, the random setting of the model parameters in step S14 is repeated until a predetermined number of sampling times N1 (S16) is reached, and the model parameters set each time are used in the next merging simulation (S15). In other words, the values ​​of the model parameters used in the merging simulation vary as the random setting in step S14 is repeated. For this reason, the processing in step S14 can be said to be processing that imparts fluctuations to the model parameters based on statistical occurrence frequency distribution data.

[0065] When the random setting of the model parameters of the other vehicle model formula F2 is completed as described above, the simulation unit 13 performs a merging simulation using the set model parameters (step S15). The merging simulation is a process of model predicting the future behavior of each vehicle 1, 2 in a merging scene where the host vehicle 1 cuts in to a group of other vehicles 2. In this merging simulation, a simulation is performed using the driving behavior model M2 including the host vehicle model formula F1 and the other vehicle model formula F2 described above. At this time, the parameters randomly set in step S14 above are used as the model parameters (v0, T, a, b) of the other vehicle model formula F2.

[0066] 7 is a subroutine showing the detailed procedure for performing the merging simulation in step S15. When the control shown in this figure starts, the simulation unit 13 determines the variables of each of the model formulas F1 and F2 from the initial positions and initial velocities of the host vehicle 1 and the other vehicle group 2, and the target position of the host vehicle 1 (step S21).

[0067] Specifically, the simulation unit 13 determines, for each other vehicle 2, the values ​​of the speed (v), the relative speed (Δv) from the preceding vehicle, and the inter-vehicle distance (s) from the preceding vehicle, which are variables of the other vehicle model formula F2, from the position (initial position) and speed (initial speed) of the other vehicle group 2 acquired in step S1 (FIG. 5). For example, for the second vehicle 2B shown in FIG. 2, the simulation unit 13 determines the speed of the second vehicle 2B acquired in step S1 as the speed (v) of the other vehicle model formula F2. Furthermore, the simulation unit 13 calculates the relative speed and inter-vehicle distance of the second vehicle 2B with respect to the first vehicle 2A from the positions and speeds of the first vehicle 2A and second vehicle 2B acquired in step S1, and determines the calculated values ​​as the relative speed (Δv) and inter-vehicle distance (s) of the other vehicle model formula F2. The simulation unit 13 performs this process for the other other vehicles 2 in the same manner. Note that for the first vehicle 2A, the above variables can be determined using information on other vehicles (not shown) located further ahead. However, if no other vehicles are recognized ahead of the first vehicle 2A, the above variables can be determined under an appropriate assumption, such as, for example, that there is another vehicle sufficiently ahead of the first vehicle 2A traveling at the same speed as the desired speed (v0) of the first vehicle 2A.

[0068] Furthermore, the simulation unit 13 determines the difference (Δx) between the target position and the current position and the difference (Δv) between the target speed and the current speed, which are variables of the host vehicle model formula F1, based on the position (initial position) and speed (initial speed) of the host vehicle 1 acquired in step S1 and the target position and target speed of the host vehicle 1 set in step S13 (FIGS. 8A and 8B). For example, the simulation unit 13 determines the difference (Δx) between the target position and the current position in the host vehicle model formula F1 based on the position of the host vehicle 1 acquired in step S1 and the target position of the host vehicle set in step S13. Furthermore, the simulation unit 13 determines the difference (Δv) between the target speed and the current speed in the host vehicle model formula F1 based on the speed of the host vehicle 1 acquired in step S1 and the target speed of the host vehicle set in step S13.

[0069] Next, the simulation unit 13 calculates the acceleration ACCy of the other vehicle group 2 from the other vehicle model formula F2 (step S22). That is, the simulation unit 13 performs calculations for each other vehicle 2 using the other vehicle model formula F2 using the variables (v, Δv, s) determined for each other vehicle 2 in step S21 above, thereby calculating the acceleration ACCy of each other vehicle 2. At this time, the values ​​randomly set for each other vehicle 2 in step S14 above are used as the model parameters (v0, T, a, b) of the other vehicle model formula F2.

[0070] Next, the simulation unit 13 calculates the position and speed of each of the other vehicles 2 at the time when the small time period Δt has elapsed, using the acceleration ACCy calculated for each other vehicle 2 in step S22 (step S23). That is, the simulation unit 13 calculates the position and speed of each other vehicle 2 after Δt has elapsed, based on the current position and speed of each other vehicle 2 obtained in the previous step and the acceleration ACCy of each other vehicle 2 calculated in step S22.

[0071] Next, the simulation unit 13 calculates the acceleration ACCx of the host vehicle 1 from the host vehicle model formula F1 (step S24). That is, the simulation unit 13 performs calculations using the host vehicle model formula F1 using the variables (Δx, Δv) determined for the host vehicle 1 in step S21, thereby calculating the acceleration ACCx of the host vehicle 1.

[0072] Next, the simulation unit 13 calculates the position and speed of the host vehicle 1 at the time when the small time Δt has elapsed, using the acceleration ACCx of the host vehicle 1 calculated in the above step S24 (step S25). That is, the simulation unit 13 calculates the position and speed of the host vehicle 1 after the elapse of Δt, based on the current position and speed of the host vehicle 1 obtained in the previous step and the acceleration ACCx of the host vehicle 1 calculated in the above step S24.

[0073] Next, the simulation unit 13 updates the positions and velocities of the host vehicle 1 and the other vehicle group 2, as well as the target position and target speed of the host vehicle 1 (step S26). That is, the simulation unit 13 updates the positions and velocities of the host vehicle 1 and the other vehicle group 2 to the positions and velocities after Δt has elapsed, which were calculated in steps S23 and S25. The simulation unit 13 also updates the target position and target speed of the host vehicle 1 based on the updated position and speed of the other vehicle group 2.

[0074] Next, the simulation unit 13 determines whether or not the merging possible condition is satisfied (step S27). The merging possible condition is a condition under which the vehicle 1 can start changing lanes, moving laterally from the branch lane 102 to the main lane 101. Once the merging possible condition is satisfied, merging can be completed by simply changing lanes, and therefore, it can be considered that the completion of merging is expected at this point. In other words, determining whether or not the merging possible condition is satisfied is equivalent to determining whether or not the completion of merging is expected.

[0075] Specifically, the confluence enabling conditions may include, for example, the following requirements (i) to (iv). (i) The vehicle 1 is located near the gap 3 designated as a candidate merging position, i.e., the target position set to the side of the designated gap 3. For example, the vehicle 1 is located within a range of ±5 m of the target position. (ii) The vehicle 1 is traveling at a speed close to the target speed set so that it can travel alongside other vehicles 2 before and after the designated gap 3. For example, the vehicle 1 is traveling within a range of ±5 km / h of the target speed. (iii) The above requirements (i) and (ii) continue for a predetermined period of time (for example, approximately 3 seconds) or more. (iv) The distance between vehicles in designated gap 3 is sufficient. For example, the distance between vehicles in designated gap 3 is a distance equivalent to a time gap of 1.5 seconds or more.

[0076] If the determination in step S27 above is NO and it is confirmed that the merging condition is not met, the simulation unit 13 updates the variables of the model formulas F1 and F2 described above (step S28). That is, the simulation unit 13 calculates the variables (v, Δv, s) of the other vehicle model formula F2 and the variables (Δx, Δv) of the host vehicle model formula F1, respectively, from the positions and velocities of the host vehicle 1 and the other vehicle group 2 updated in step S26 above and the target position and target velocity of the host vehicle 1, in the same manner as in step S21 above. Then, using the calculated values ​​as the updated variables, the simulation unit 13 performs the calculations in steps S22 to S25 above to calculate the positions and velocities of the host vehicle 1 and the other vehicle group 2 after Δt has elapsed. The simulation unit 13 repeats this calculation to calculate the position and velocity of each vehicle every Δt until the merging condition in step S27 above is met.

[0077] It should be noted that, even if the position of the vehicle 1 approaches the branch line terminal end 102a during the repetition of the above calculations, the calculations continue unless the merging condition (S27) is met at that point. In other words, the calculations indicate that the vehicle 1 may move beyond the branch line terminal end 102a. However, if the merging condition is not met even after the vehicle 1 has significantly passed the branch line terminal end 102a, the calculations may be terminated at that point and the merging condition may be deemed to be met.

[0078] If the determination in step S27 above is YES and it is confirmed that the merging condition is met, the simulation unit 13 ends the above calculations for determining the position and speed of each vehicle every Δt (step S29), and calculates the merging margin distance Lm using the conditions at the time of completion (step S30). That is, the simulation unit 13 calculates the merging margin distance Lm (FIGS. 3A and 3B), which is the distance from the host vehicle 1 to the branch line end 102a, based on the position of the host vehicle 1 on the branch line 102 when the merging condition is met, i.e., the position of the host vehicle 1 on the branch line 102 calculated in the last of the repeated calculations.

[0079] The merging margin distance Lm calculated here can be considered the remaining distance to the branch line terminal end 102a at the time when merging is expected to be completed, and as described above, is a value that can be either positive or negative. That is, if the position of the host vehicle 1 at the time when the merging condition is met is before the branch line terminal end 102a, a positive merging margin distance Lm is calculated. On the other hand, if the position of the host vehicle 1 at the time when the merging condition is met is beyond the branch line terminal end 102a, a negative merging margin distance Lm is calculated. The larger the positive merging margin distance Lm, the more leeway there is for merging. Furthermore, a negative merging margin distance Lm means that merging is not possible using behavior according to the model formula.

[0080] When the calculation of the merging margin distance Lm is completed in the above manner, the simulation unit 13 returns to the flow of FIG. 6 and determines whether the number of times the model parameters of the other vehicle model formula F2 have been randomly set has reached a predetermined number of sampling times N1 (step S16).

[0081] If the determination in step S16 above is NO and it is confirmed that the number of random settings has not reached the sampling number N1, the simulation unit 13 returns to step S14 above and randomly sets new model parameters for the other vehicle group 2. Then, using the randomly set model parameters here, a merging simulation (S15) is performed and the merging margin distance Lm is calculated. The simulation unit 13 repeats this merging simulation (calculation of the merging margin distance Lm) for each condition of the model parameters until the number of random settings reaches the sampling number N1.

[0082] If the determination in step S16 above is YES and it is confirmed that the number of random settings has reached the sampling number N1, the evaluation unit 14 obtains the distribution of the many merging margin distances Lm obtained by repeating the merging simulation in step S15 above, that is, the distribution of merging margin distances Lm corresponding to various conditions with varying model parameters (step S17). Specifically, the evaluation unit 14 obtains the mean μ and standard deviation σ shown in FIG. 10 as the distribution of merging margin distances Lm. As is well known, the mean μ is a value obtained by dividing the sum of the data of the obtained merging margin distances Lm by the number of data. The standard deviation σ is a value indicating the degree of variation relative to the mean value μ, and is expressed as the square root of the value (variance) obtained by dividing the sum of the squares of the differences (deviations) between the value of the target data and the mean μ by the number of data.

[0083] Next, the evaluation unit 14 calculates a comprehensive evaluation index Eg of the merging position candidate from the distribution of the merging margin distance Lm obtained in step S17, i.e., the mean μ and standard deviation σ (step S18). In this embodiment, the comprehensive evaluation index Eg is a value defined by the following formula (1) using the mean μ and standard deviation σ of the merging margin distance Lm.

[0084] Eg=μ+k×σ ‥‥(1) Here, k is a coefficient between -1 and +1.

[0085] The coefficient k in the above formula (1) may be set appropriately based on the values ​​that are emphasized, and may be a constant value regardless of conditions, or may be a value that varies depending on conditions. As an example, in this embodiment, the coefficient k is set variably depending on the average μ value of the merging margin distance Lm.

[0086] FIG. 11 is a graph showing the relationship between the average μ of the merging margin distance Lm (hereinafter also referred to as the average merging margin distance μ) and the coefficient k. As shown in this figure, the coefficient k is set to zero when the average merging margin distance μ is between a predetermined first threshold μa and a second threshold μb (>μa). In the range in which the average merging margin distance μ exceeds the second threshold μb, the coefficient k is greater than zero, and its value increases as the average merging margin distance μ increases. However, once the average merging margin distance μ increases until the coefficient k becomes 1, the coefficient k remains at 1 even if the average merging margin distance μ further increases. Furthermore, in the range in which the average merging margin distance μ is below the first threshold μa, the coefficient k becomes less than zero, and its value decreases as the average merging margin distance μ decreases. However, once the average merging margin distance μ decreases until the coefficient k becomes -1, the coefficient k remains at 1 even if the average merging margin distance μ further decreases.

[0087] Setting the coefficient k according to the above tendency means that the distribution of the merging margin distance Lm is interpreted optimistically when there is ample margin and pessimistically when there is little margin. That is, when the average merging margin distance μ is greater than the second threshold μb and the remaining distance to the branch line end 102a is sufficiently secured when the merging condition (S27) is met, the coefficient k becomes positive, and a value greater than the average merging margin distance μ is adopted as the overall evaluation index Eg. This is an optimistic approach, in which a value greater than the average merging margin distance μ is adopted as a reasonable evaluation value. On the other hand, when the average merging margin distance μ is smaller than the first threshold μa and the remaining distance to the branch line end 102a is not sufficiently secured when the merging condition is met, the coefficient k becomes negative, and a value less than the average merging margin distance μ is adopted as the overall evaluation index Eg. This is a pessimistic approach, in which a value less than the average merging margin distance μ is adopted as a reasonable evaluation value. In other words, the above setting of coefficient k leads to more careful judgment regarding the likelihood of successful merging in situations with less margin.

[0088] FIG. 12 is a graph showing the range of the comprehensive evaluation index Eg obtained by the above formula (1). As shown in this figure, the comprehensive evaluation index Eg becomes the maximum Egb (= μ + σ) when the coefficient k is +1, and becomes the minimum Ega (= μ - σ) when the coefficient k is -1. Thus, the comprehensive evaluation index Eg is calculated so as to vary within the range from Ega to Egb depending on the conditions (here, depending on the value of μ).

[0089] When the calculation of the comprehensive evaluation index Eg is completed as described above, the evaluation unit 14 returns to the flow chart of FIG. 5 and determines whether the evaluation of all the confluence position candidates has been completed (step S5). For example, when there are three confluence position candidates in total (the first to third gaps 3A to 3C) as in the example of FIG. 2, the evaluation unit 14 determines whether the calculation of the comprehensive evaluation index Eg (FIG. 6) has been completed for all of these three gaps 3A to 3C.

[0090] If it is determined as NO in step S5 above and it is confirmed that there are unevaluated confluence position candidates remaining, the evaluation unit 14 designates the next confluence position candidate to be evaluated (step S6). Then, the designated confluence position candidate is newly evaluated (S4), and the comprehensive evaluation index Eg of that confluence position candidate is obtained. The evaluation unit 14 repeats the designation and evaluation (S4, S6) of the confluence position candidate until such evaluation (calculation of the comprehensive evaluation index Eg) is performed for all the confluence position candidates.

[0091] If it is determined as YES in step S5 above and it is confirmed that the evaluation of all the confluence position candidates has been completed, the evaluation unit 14 identifies the confluence position candidate with the highest comprehensive evaluation index Eg (step S7).

[0092] FIG. 13 is a graph showing, as an example, the difference in the comprehensive evaluation index Eg when there are three confluence position candidates, candidates 1 to 3. When the comprehensive evaluation index Eg of candidate 1 is Eg1, the comprehensive evaluation index Eg of candidate 2 is Eg2, and the comprehensive evaluation index Eg of candidate 3 is Eg3, in the example of FIG. 13, the relationship Eg1 < Eg3 < Eg2 holds. In this case, the evaluation unit 14 identifies candidate 2 corresponding to the highest comprehensive evaluation index Eg2.

[0093] When the graph in Figure 13 is associated with the example layout of each vehicle shown in Figure 2, candidate 1 may correspond to the first gap 3A, candidate 2 may correspond to the second gap 3B, and candidate 3 may correspond to the third gap 3C. Of course, other correspondences are possible depending on the situation.

[0094] Furthermore, in step S7, if there are two or more candidates with the highest overall evaluation index Eg, one of the candidates may be narrowed down by an appropriate method and identified as the candidate with the highest evaluation. Various methods for narrowing down the candidates may be considered, for example, a method of narrowing down the candidates to those closest to the vehicle 1 at the time of evaluation may be considered.

[0095] Next, the route generation unit 15 determines the merging position candidate identified in step S7 above, i.e., the merging position candidate with the highest overall evaluation index Eg, as the merging target for the host vehicle 1 (step S8). For example, if the merging position candidate identified in step S7 above is candidate 2, which corresponds to the second gap 3B shown in Fig. 2, the route generation unit 15 determines the second gap 3B as the merging target. As a result, the host vehicle 1 will travel along the travel route that leads to the second gap 3B and will cut into the second gap 3B.

[0096] (4) Action and effect As described above, in this embodiment, when the host vehicle 1 merges into the other-vehicle group 2, multiple candidate merging positions (e.g., gaps 3A to 3C) that are candidates for the cut-in destination are each evaluated through a simulation using the driving behavior model M2. Specifically, the future behavior of the host vehicle 1 and the other-vehicle group 2 is repeatedly simulated while applying fluctuations based on statistical random settings to the model parameters included in the other-vehicle model formula F2 of the driving behavior model M2, and the merits and demerits of the candidate merging positions are evaluated based on the distribution of the merging margin distance Lm (evaluation value) obtained from the simulation. This configuration has the advantage that each candidate merging position can be appropriately evaluated in a short time.

[0097] In other words, in this embodiment, evaluation of each potential merging position is performed through a simulation using a driving behavior model M2 that predicts the behavior of the vehicle 1 and the group of other vehicles 2, so there is no need to go through complex processes such as machine learning or reinforcement learning to calculate the merging margin distance Lm as an evaluation value, and the time required for evaluation can be shortened.

[0098] Furthermore, simulations are repeatedly performed while varying the model parameters of the driving behavior model M2, and the distribution of the merging margin distance Lm for each merging position candidate is obtained from the results of the repeated simulations. This makes it possible to appropriately evaluate the merits and demerits of the merging position candidates based on the distribution of the merging margin distance Lm, and to identify statistically valid merging position candidates.

[0099] Specifically, in this embodiment, the mean μ and standard deviation σ of the distribution of the merging margin distance Lm are calculated, and the merits of the merging position candidates are evaluated based on these mean μ and standard deviation σ. With this configuration, a comprehensive evaluation can be performed based on both the mean μ and standard deviation σ of the merging margin distance Lm.

[0100] More specifically, in this embodiment, an overall evaluation value that takes into account both the mean μ and standard deviation σ of the merging margin distance Lm is calculated as an overall evaluation index Eg (= μ + k × σ), which is the sum of the mean μ and the standard deviation σ multiplied by a coefficient k (-1≦k≦+1), and a merging location candidate with a large overall evaluation index Eg is evaluated as superior to a merging location candidate with a small overall evaluation index Eg. This configuration allows merging location candidates to be appropriately evaluated based on the size of the overall evaluation index Eg, which is defined from both the mean μ and the standard deviation σ.

[0101] Furthermore, by adjusting the coefficient k depending on the situation, it is possible to evaluate merge position candidates with appropriate caution. That is, the closer the coefficient k is to +1, the higher the calculated overall evaluation index Eg will be, and the closer the coefficient k is to -1, the lower the calculated overall evaluation index Eg will be. For this reason, it is possible to make adjustments such as setting the coefficient k to a negative value when careful judgment is required, or to set the coefficient k to zero or greater when this is not the case, allowing merge position candidates to be evaluated with appropriate caution depending on the situation.

[0102] Furthermore, in this embodiment, during the repeated simulation described above, among the model parameters included in other vehicle model formula F2, the characteristic parameters (v0, T, a, b) determined according to the driver characteristics or vehicle performance of the other vehicle group 2 are given variations based on statistical appearance frequency distribution data ( FIG. 9 ). With this configuration, it is possible to appropriately evaluate merge position candidates while taking into account variations in driver characteristics or vehicle performance.

[0103] In this embodiment, the evaluation value calculated by the simulation is the merging margin distance Lm, which is the remaining distance to the branch line end 102a at the time when the host vehicle 1 is expected to complete merging (when the merging condition is met). This configuration can improve the evaluation accuracy compared to a dichotomous evaluation such as success / failure.

[0104] That is, the merging margin distance Lm, which is the remaining distance to the branch line end 102a, is a value that can continuously change depending on the situation, so evaluation based on this value can determine not only whether the merging will succeed or fail, but also how much margin of error the merging will have. Furthermore, because the merging margin distance Lm can be calculated as a negative value even in the case of a failed merging attempt, this value can also be used to determine how close the merging attempt was to success. In this way, according to this embodiment, which uses the merging margin distance Lm, which can continuously change from positive to negative, as an evaluation value, the merits and demerits of each merging location candidate can be accurately evaluated.

[0105] In this embodiment, the driving behavior model M2 includes an other vehicle model formula F2 that predicts the behavior of the other vehicle group 2, and a host vehicle model formula F1 that predicts the behavior of the host vehicle 1. The other vehicle model formula F2 corresponds to a following driving model that outputs the acceleration required to drive while maintaining an appropriate inter-vehicle distance from the preceding vehicle, and the host vehicle model formula F1 corresponds to a proportional model that outputs acceleration proportional to the difference between a predetermined target position and a predetermined target speed. With this configuration, the future behavior of the other vehicle group 2 and the host vehicle 1 can be appropriately simulated through relatively light calculations using specified calculation formulas.

[0106] (5) Variations Although the preferred embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various modifications are possible without departing from the spirit of the present invention.

[0107] For example, in the above embodiment, when repeatedly simulating the future behavior of the host vehicle 1 and the other vehicle group 2 at the time of merging, variations based on statistical occurrence frequency distribution data are imparted to the model parameters of the driving behavior model M2 (other vehicle model formula F2), but the method of imparting variations to the model parameters is not limited to this. For example, normal distribution data that approximates occurrence frequency distribution data obtained from observation of actual traffic may be prepared, and variations may be imparted based on the normal distribution data. Alternatively, an occurrence frequency table that discretely expresses the relationship between parameter values ​​and occurrence frequencies may be prepared, and interpolation using appropriate random numbers may be performed so that parameter values ​​appear evenly within each discrete section.

[0108] Furthermore, when vehicle type information such as standard vehicles, large vehicles, and motorcycles is available for the other vehicle group 2, the appearance frequency distribution data may be used separately for each vehicle type. In this way, parameter setting that is more in line with reality can be realized.

[0109] In the above embodiment, the simulation is continued until the specified merging conditions are met and merging is expected to be completed, and the distance from the vehicle 1 to the end of the branch line 102a at that time, in other words the remaining distance to the end of the branch line 102a, is calculated as the merging margin distance Lm. However, the simulation may also be continued until the vehicle 1 actually enters the specified gap 3 of the group of other vehicles 2 and merging is completed, and the remaining distance to the end of the branch line 102a at that time (the time of merging completion) is calculated as the merging margin distance Lm.

[0110] Furthermore, instead of the merging margin distance Lm as described above, a merging margin, which is the remaining time until the branch line end 102a at the time when merging has been completed or is expected to be completed, may be calculated by simulation, and a merging position candidate may be evaluated based on the merging margin. In other words, when a value indicating how much margin the vehicle 1 has to merge, i.e., a merging margin, is used as an evaluation value of a merging position candidate, this merging margin may be a value expressed in terms of either distance or time.

[0111] Furthermore, the evaluation value for evaluating the merits and demerits of the merging position candidate may be any value related to the success or failure of merging, and is not limited to the merging margin (merging margin distance or merging time). For example, an evaluation value may be used that integrates multiple index values, including a first index value that indicates whether or not merging can be performed before the branch line end 102a, and a second index value that indicates the degree of burden on the driver, such as the smoothness of acceleration and deceleration.

[0112] In the above embodiment, the overall evaluation index Eg determined from the distribution (mean μ and standard deviation σ) of the merging margin distance Lm is calculated for each merging position candidate, and the larger the overall evaluation index Eg, the higher the evaluation of the merging position candidate, but if the overall evaluation index Eg or the merging margin distance Lm is excessively large, it can also be interpreted as meaning that the vehicle 1 is not accelerating sufficiently on the branch line 102, in other words, that the length of the branch line 102 is not being used effectively. Therefore, for example, a positive threshold value may be set in advance for the merging margin distance Lm, and the evaluation may be increased as the merging margin distance Lm increases within a range below the threshold, and the evaluation may be decreased as the merging margin distance Lm increases within a range above the threshold.

[0113] In the above embodiment, a following-traveling model (other vehicle model formula F2) is used as a model for predicting the behavior of the other vehicle 2, and a proportional model (subject vehicle model formula F1) is used as a model for predicting the behavior of the host vehicle 1, but the behavior of the host vehicle 1 and the other vehicle 2 may be predicted using the same model. For example, the behavior of both the host vehicle 1 and the other vehicle 2 may be predicted using a following-traveling model. Furthermore, since various models with a similar purpose have already been proposed as the following-traveling model (IDM), it goes without saying that a following-traveling model other than the model formula (other vehicle model formula F2) shown in FIG. 4 can be used as appropriate.

[0114] In the above embodiment, a simulation was performed while driving to predict the future behavior of the host vehicle 1 and the other vehicle group 2 in an actual merging scene in which the host vehicle 1 cuts into one of the gaps 3 in the other vehicle group 2, and the merits of the merging position candidates, which are candidates for the cut-in gap, were evaluated based on the results of the simulation, but a similar evaluation may also be performed to generate a regression model. That is, by performing a large number of simulations under various virtual initial conditions with different positions and speeds of the host vehicle 1 and the other vehicle group 2, a large number of data sets including initial conditions and evaluation values ​​(for example, merging margins) may be created as training data, and a regression model may be generated based on this training data. [Explanation of symbols]

[0115] 1. Your vehicle 2 Other vehicles (groups of other vehicles) 3. Gap 12 Recognition unit (acquisition unit, extraction unit) 13 Simulation Department 14 Evaluation Section 101 Main Line 102 branch line 102a (branch line) termination Lm Merging margin distance (merging margin) M2 driving behavior model

Claims

1. A device for evaluating a merging position when a vehicle passes through a branch line and merges into a main line, an acquisition unit that acquires a traffic environment around the vehicle, including the positions and speeds of other vehicles traveling on the main road and road shapes; an extraction unit that extracts merge position candidates that are candidates for a gap to be cut in when the host vehicle cuts in to the group of other vehicles, based on the traffic environment acquired by the acquisition unit; a simulation unit that uses a driving behavior model that predicts the behavior of the host vehicle and the other vehicle group, and repeatedly simulates future behaviors of the host vehicle and the other vehicle group while varying model parameters of the driving behavior model; an evaluation unit that calculates a distribution of evaluation values ​​for each of the merging position candidates extracted by the extraction unit based on the results of the simulation performed by the simulation unit, and evaluates the merits and demerits of the merging position candidates based on the distribution of evaluation values.

2. 2. The vehicle merging position evaluation device according to claim 1, The evaluation unit calculates the average and standard deviation of the evaluation values ​​for each of the merging position candidates as a distribution of the evaluation values, and evaluates the merits and demerits of the merging position candidates based on the average and standard deviation.

3. 3. The vehicle merging position evaluation device according to claim 2, The evaluation unit calculates an overall evaluation index Eg for each of the merging position candidates using the average and standard deviation of the evaluation values, and evaluates the merging position candidates with a large overall evaluation index Eg as being better than the merging position candidates with a small overall evaluation index Eg. Eg=μ+k×σ ‥‥(1) Here, μ is the average of the evaluation values, σ is the standard deviation of the evaluation values, and k is a coefficient between −1 and +1.

4. The vehicle merging position evaluation device according to any one of claims 1 to 3, The simulation unit applies the fluctuation based on statistical occurrence frequency distribution data to characteristic parameters among the model parameters that are determined according to the driver characteristics or vehicle performance of the other vehicle group.

5. The vehicle merging position evaluation device according to any one of claims 1 to 3, The evaluation unit calculates the merging margin, which is the remaining distance or remaining time to the end of the branch line at the time when the vehicle has completed merging or is expected to complete merging, as the evaluation value.

6. The vehicle merging position evaluation device according to any one of claims 1 to 3, The driving behavior model is a model that predicts the behavior of the group of other vehicles, and includes a following driving model that outputs the acceleration required to drive while maintaining an appropriate distance from the preceding vehicle.

7. 7. The vehicle merging position evaluation device according to claim 6, The vehicle merging position evaluation device, wherein the driving behavior model includes a proportional model that outputs acceleration proportional to the difference between a predetermined target position and a predetermined target speed as a model for predicting the behavior of the vehicle.

8. A method for evaluating a merging position when a vehicle passes through a branch line and merges into a main line, comprising: acquiring a traffic environment around the vehicle, including the positions and speeds of other vehicles traveling on the main road and road shapes; extracting, based on the acquired traffic environment, merge position candidates that are candidates for gaps into which the host vehicle will cut in when cutting into the group of other vehicles; a step of repeatedly simulating future behaviors of the subject vehicle and the other vehicle group while varying model parameters of a driving behavior model that predicts behaviors of the subject vehicle and the other vehicle group; a step of calculating a distribution of evaluation values ​​for each of the extracted merging position candidates based on the results of the simulation, and evaluating the merits and demerits of the merging position candidates based on the distribution of evaluation values.

Images