Merging prediction device, vehicle control device, and merging prediction method

Abstract

To provide a merging prediction device, a vehicle control device, and a merging prediction method that can predict a merging position of a merging vehicle relative to a target vehicle, and evaluate an accuracy of a prediction result of the merging position.SOLUTION: A merging prediction device predicts a merging position of a merging vehicle, either in front of or behind a target vehicle, based on movement information of the target vehicle, movement information of the merging vehicle, lane information of a target lane, and lane information of a merging lane. The merging prediction device calculates the reliability of the merging position, and calculates a probability of the merging vehicle merging in front of the target vehicle, and a probability of the merging vehicle merging behind the target vehicle based on the merging position and the reliability.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a merging prediction device, a vehicle control device, and a merging prediction method. [Background technology]

[0002] The technology of Patent Document 1 calculates the predicted probability of the behavior of a merging vehicle based on the ratio between the time required for the merging vehicle to reach the merging point and the time required for the vehicle itself to reach the merging point.

[0003] The technology of Patent Document 2 calculates the probability that a nearby vehicle will cut in front of the vehicle, and exponentially increases the cutting in probability as the nearby vehicle approaches the merging point. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6984172 [Patent Document 2] Patent No. 6738957 Summary of the Invention [Problem to be solved by the invention]

[0005] Merging vehicles may accelerate to merge in front of the host vehicle or decelerate to merge behind the host vehicle. However, whether a merging vehicle accelerates or decelerates varies depending on the merging vehicle. Therefore, as the distance to the merging point of the merging vehicle at the time of prediction increases, the amount of fluctuation in the merging position due to the variation in the acceleration and deceleration of the merging vehicle increases, and the accuracy of the predicted merging position of the merging vehicle decreases. Therefore, it is necessary to evaluate the accuracy of the merging position prediction result.

[0006] The technology of Patent Document 1 takes into consideration the current relative position and relative speed between the vehicle and the merging vehicle, as well as the distance to the merging point, but does not take into consideration the accuracy of the predicted merging position.

[0007] The technology of Patent Document 2 predicts only the lane change probability of a merging vehicle, and does not take into consideration the relative position between the host vehicle and the merging vehicle, or the merging position of the merging vehicle relative to the host vehicle.

[0008] Therefore, the present disclosure aims to provide a merging prediction device, a vehicle control device, and a merging prediction method that can predict the merging position of a merging vehicle relative to a target vehicle and evaluate the accuracy of the merging position prediction result. [Means for solving the problem]

[0009] The confluence prediction device according to the present disclosure comprises: an information acquisition unit that acquires movement information of a target vehicle, movement information of a merging vehicle traveling in a merging lane that merges into a target lane in which the target vehicle is traveling, lane information of the target lane, and lane information of the merging lane; a merging position prediction unit that predicts a merging position of the merging vehicle ahead of or behind the target vehicle based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a reliability calculation unit that calculates the reliability of the merging position based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; and a merging probability calculation unit that calculates the merging probability of the merging vehicle in front of the target vehicle and the merging probability of the merging vehicle in rear of the target vehicle based on the merging position and the reliability.

[0010] The vehicle control device according to the present disclosure includes: The above-mentioned confluence prediction device; a vehicle control unit that controls the running of the target vehicle, The vehicle control unit controls the traveling of the target vehicle based on the probability of merging ahead and the probability of merging behind.

[0011] The confluence prediction method according to the present disclosure includes: an information acquisition step of acquiring movement information of a target vehicle, movement information of a merging vehicle traveling in a merging lane that merges into a target lane in which the target vehicle is traveling, lane information of the target lane, and lane information of the merging lane; a merging position prediction step of predicting a merging position of the merging vehicle ahead of or behind the target vehicle based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a reliability calculation step of calculating a reliability of the merging position based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; and a merging probability calculation step of calculating the merging probability of the merging vehicle in front of the target vehicle and the merging probability of the merging vehicle in rear of the target vehicle based on the merging position and the reliability. [Effects of the Invention]

[0012] The merging prediction device, vehicle control device, and merging prediction method according to the present disclosure can calculate not only the merging position but also the reliability of the merging position, and can calculate the probability of merging ahead and the probability of merging behind based on the merging position and the reliability. Thus, the accuracy of the merging position prediction result can be evaluated taking the reliability of the merging position into consideration. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a schematic block diagram of a vehicle control device and a merging prediction device according to a first embodiment. [Figure 2] 1 is a schematic hardware configuration diagram of a vehicle control device and a merging prediction device according to a first embodiment. [Figure 3] 1 is a schematic hardware configuration diagram of a vehicle control device and a merging prediction device according to a first embodiment. [Figure 4] FIG. 2 is a diagram for explaining a coordinate system of a host vehicle according to the first embodiment. [Figure 5] FIG. 2 is a schematic diagram for explaining merging onto an expressway or the like according to the first embodiment. [Figure 6] FIG. 2 is a schematic diagram for explaining merging due to travel restrictions according to the first embodiment. [Figure 7] FIG. 2 is a schematic diagram for explaining merging at an intersection according to the first embodiment. [Figure 8] 4 is a schematic diagram for explaining the front-rear relationship when the angle between the own lane and the merging lane is small according to the first embodiment. FIG. [Figure 9] 4 is a schematic diagram for explaining the front-rear relationship when the angle between the own lane and the merging lane is large according to the first embodiment. FIG. [Figure 10] FIG. 2 is a schematic diagram for explaining a prediction model using a boundary line according to the first embodiment. [Figure 11] FIG. 10 is a diagram for explaining calculation of a third reliability according to the first embodiment. [Figure 12] FIG. 10 is a diagram for explaining calculation of a third reliability when the merging position is on the front side of the vehicle according to the first embodiment. [Figure 13] FIG. 10 is a diagram for explaining calculation of a third reliability when the merging position is behind the vehicle according to the first embodiment. [Figure 14] 10A and 10B are diagrams for explaining calculation of a probability of merging to the front side and a probability of merging to the rear side according to the first embodiment. [Figure 15] FIG. 4 is a diagram for explaining setting of a maximum deceleration rate and a maximum deceleration jerk based on the probability of merging ahead according to the first embodiment. [Figure 16] 10A and 10B are diagrams for explaining setting of maximum acceleration and maximum acceleration jerk based on the probability of merging at the rear according to the first embodiment. [Figure 17] 4 is a flowchart for explaining the processing of the merging prediction device and the vehicle control device according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] 1. First Embodiment A merging prediction device 1 according to a first embodiment will be described with reference to the drawings. In this embodiment, the merging prediction device 1 is provided in a target vehicle (host vehicle). The merging prediction device 1 is incorporated in a vehicle control device 50 provided in the target vehicle (host vehicle).

[0015] As shown in FIG. 1, the target vehicle (own vehicle) is equipped with a surroundings monitoring device 31, a position detection device 32, a vehicle state detection device 33, a map information database 34, a wireless communication device 35, a vehicle control device 50, a drive control device 36, a power plant 8, an electric steering device 7, an electric braking device 9, and a human interface device 37, etc.

[0016] The periphery monitoring device 31 is a device such as a camera or radar that monitors the periphery of the vehicle. The radar may be a millimeter wave radar, a laser radar, an ultrasonic radar, or the like. The wireless communication device 35 performs wireless communication with a base station using a cellular wireless communication standard such as 4G or 5G. The wireless communication device 35 may also perform wireless communication with surrounding vehicles or roadside devices, etc.

[0017] The position detection device 32 is a device that detects the current position (latitude, longitude, altitude) of the vehicle, and uses a GPS antenna or the like that receives signals output from artificial satellites such as the Global Navigation Satellite System (GNSS). Note that various methods may be used to detect the current position of the vehicle, such as a method using the lane number of the vehicle, a map matching method, a dead reckoning method, or a method using detected information around the vehicle.

[0018] The map information database 34 stores road information such as road shapes (for example, the number of lanes, the position of each lane, the shape of each lane, the type of each lane, the road type, speed limits, etc.), signs, traffic lights, etc. The map information database 34 is mainly composed of a storage device. The map information database 34 may be provided in a server outside the vehicle connected to a network, and the vehicle control device 50 may obtain necessary road information from the server outside the vehicle via the wireless communication device 35.

[0019] The drive control device 36 includes a power control device, a brake control device, an automatic steering control device, a light control device, etc. The power control device controls the output of a power machine 8 such as an internal combustion engine or a motor. The brake control device controls the braking operation of an electric brake device 9. The automatic steering control device controls the electric steering device 7. The light control device controls turn signals, hazard lights, etc.

[0020] The vehicle state detection device 33 is a detection device that detects the state of the host vehicle, which is the driving state and running state of the host vehicle. In this embodiment, the vehicle state detection device 33 detects the speed, acceleration, yaw rate, steering angle, lateral acceleration, etc. of the host vehicle as the running state of the host vehicle. For example, the vehicle state detection device 33 may be provided with a speed sensor, an acceleration sensor, an angular velocity sensor, a steering angle sensor, etc. that detect the rotational speed of the wheels.

[0021] The driving state of the vehicle is detected by detecting acceleration / deceleration operations, steering angle operations, and lane change operations by the driver. For example, the vehicle state detection device 33 is provided with an accelerator position sensor, a brake position sensor, a steering angle sensor (handle angle sensor), a steering torque sensor, a turn signal position switch, and the like.

[0022] The human interface device 37 is a device that receives input from the driver through a speaker, a display screen, an input device, etc., and transmits information to the driver.

[0023] 1-1. Vehicle control device 50 The vehicle control device 50 includes functional units such as an information acquisition unit 51, a merging position prediction unit 52, a reliability calculation unit 53, a merging probability calculation unit 54, and a vehicle control unit 55. Each function of the vehicle control device 50 is realized by a processing circuit included in the vehicle control device 50. Specifically, as shown in Fig. 2, the vehicle control device 50 includes an arithmetic processing device 90 such as a CPU (Central Processing Unit), a storage device 91, an input / output device 92 that inputs and outputs external signals to the arithmetic processing device 90, and the like.

[0024] The arithmetic processing device 90 may be an ASIC (Application Specific Integrated Circuit), an IC (Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), a GPU (Graphics Processing Unit), an AI (Artificial Intelligence) chip, various logic circuits, various signal processing circuits, etc. Furthermore, the arithmetic processing device 90 may be a plurality of the same or different types, and each process may be shared and executed. The storage device 91 may be a variety of storage devices, such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a hard disk, etc.

[0025] The input / output device 92 is equipped with a communication device, an A / D converter, an input / output port, a drive circuit, etc. The input / output device 92 is connected to the surroundings monitoring device 31, the position detection device 32, the vehicle state detection device 33, the map information database 34, the wireless communication device 35, the drive control device 36, the human interface device 37, etc., and communicates with these devices.

[0026] The functions of the functional units 51 to 55 of the vehicle control device 50 are realized by the arithmetic processing device 90 executing software (programs) stored in the storage device 91 and cooperating with other hardware of the vehicle control device 50, such as the storage device 91 and the input / output device 92. Setting data such as parameters and thresholds of the prediction models used by the functional units 51 to 55 are stored in the storage device 91, such as an EEPROM.

[0027] Alternatively, the vehicle control device 50 may be provided with dedicated hardware 93 as a processing circuit, such as a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, a GPU, an AI chip, or a circuit that combines these, as shown in Fig. 3. Each function of the vehicle control device 50 will be described in detail below.

[0028] 1-1-1. Information acquisition section 51 The information acquisition unit 51 acquires movement information of the subject vehicle (target vehicle). In this embodiment, the information acquisition unit 51 acquires the position, movement direction, speed, acceleration, etc. of the subject vehicle based on the position information of the subject vehicle acquired from the position detection device 32 and the subject vehicle state acquired from the vehicle state detection device 33.

[0029] The information acquisition unit 51 acquires movement information of surrounding vehicles present around the vehicle. The surrounding vehicles also include merging vehicles, which will be described later. In this embodiment, the information acquisition unit 51 acquires the positions, movement directions, speeds, accelerations, etc. of the surrounding vehicles based on the detection information acquired from the periphery monitoring device 31 and the position information of the vehicle acquired from the position detection device 32. In addition to the surrounding vehicles, the information acquisition unit 51 also acquires information on obstacles, pedestrians, signs, traffic regulations such as lane restrictions, etc.

[0030] The information acquisition unit 51 can acquire movement information of surrounding vehicles and lane information of surrounding vehicles through communication from outside the vehicle. Surrounding vehicles also include merging vehicles. For example, the information acquisition unit 51 may acquire movement information of surrounding vehicles (position, movement direction, speed, etc. of surrounding vehicles) from surrounding vehicles through wireless communication or the like. Furthermore, the information acquisition unit 51 may acquire movement information of surrounding vehicles present in a monitoring area (position, movement direction, speed, acceleration, etc. of surrounding vehicles), information on obstacles and pedestrians, road shape, traffic regulations, traffic conditions, etc., from roadside devices such as cameras that monitor road conditions, etc., through wireless communication or the like.

[0031] In this embodiment, the information acquisition unit 51 acquires the relative positions and relative speeds of surrounding vehicles and the like with respect to the host vehicle in a coordinate system of the host vehicle based on the current position of the host vehicle. As shown in FIG. 4, the host vehicle coordinate system is a coordinate system having axes in the longitudinal direction X of the current host vehicle and the lateral direction Y of the host vehicle. Note that the information acquisition unit 51 may also acquire the relative positions and relative speeds of surrounding vehicles in a coordinate system in the longitudinal and lateral directions of the host vehicle's lane (target lane) in which the host vehicle is traveling. The information acquisition unit 51 may also acquire the absolute position (latitude, longitude), absolute movement direction (orientation), absolute speed, absolute acceleration, etc. of each vehicle.

[0032] The information acquisition unit 51 acquires road information around the vehicle from the map information database 34 based on the vehicle's position information acquired from the position detection device 32. The acquired road information includes information such as the number of lanes, the position of each lane, the shape of each lane, the type of each lane, the road type, and the speed limit. The types of each lane include merging lanes, main lanes, etc. The information acquisition unit 51 also acquires information on traffic regulations such as lane restrictions due to construction work, etc. from an external server, etc.

[0033] The information acquisition unit 51 also detects the shape and type of road dividing lines, etc., based on detection information of dividing lines such as white lines and road shoulders acquired from the periphery monitoring device 31, and determines the shape and position of each lane, the number of lanes, and the type of each lane, etc., based on the detected shape and type of road dividing lines, etc. The type of each lane includes merging lanes, etc. The information acquisition unit 51 also determines whether or not there are traffic regulations, such as lane restrictions.

[0034] The information acquisition unit 51 acquires lane information corresponding to the lane in which the vehicle is traveling, based on the position of the vehicle. The information acquisition unit 51 also acquires lane information corresponding to the lane in which each of the surrounding vehicles is traveling, based on the positions of each of the surrounding vehicles. The acquired lane information includes the shape, position, and type of the lane, as well as lane information for the surrounding lanes.

[0035] <Definition of confluence, etc.> A merge refers to a road shape where lanes intersect, and includes merges on expressways (see Figure 5), merges from additional lanes, merges due to a reduction in the number of lanes, merges due to temporary travel restrictions such as construction (see Figure 6), and intersections (see Figure 7). The lane in which the subject vehicle (target vehicle) is traveling is defined as the subject lane (target lane), and the lane merging into the subject vehicle lane is defined as the merging lane. A merge point is a point where the merging lane and the subject vehicle lane merge. For example, the merge point may be set at the point where the center line of the subject vehicle lane intersects with the center line of the merging lane, or it may be set at a specific point before or after the intersection of the center lines. For example, the merge point may be set at the start of a tapered portion where the lane width of the merging lane gradually narrows. In the case of a temporary driving restriction, a virtual center line may be set in the driveable lane area of ​​the lane (merging lane) where the driving restriction is imposed, and the point where the center line of the restricted lane intersects with the center line of the merging lane may be set as the merging point, or the start point of the driving restriction may be set as the merging point.

[0036] The information acquisition unit 51 determines the merging lane that merges into the lane in which the vehicle is traveling (target lane), determines the merging vehicle traveling in the merging lane from the surrounding vehicles, and acquires the movement information of the merging vehicle and the lane information of the merging lane as described above.

[0037] <Getting merging distance> The information acquisition unit 51 acquires a merging distance, which is the distance the merging vehicle takes to reach the merging point where the merging lane and the own vehicle lane merge, based on the movement information of the merging vehicle and the lane information of the merging lane.

[0038] <Obtaining relative position Xr and relative velocity Vr> The information acquisition unit 51 acquires the relative position Xr and relative speed Vr between the own vehicle and the merging vehicle based on the movement information of the own vehicle, the movement information of the merging vehicle, the lane information of the own lane, and the lane information of the merging lane.

[0039] As shown in Fig. 8, when the angle between the own lane and the merging lane is small, the information acquisition unit 51 calculates the relative position Xr by subtracting the distance X2 of the merging vehicle from the merging point from the distance X1 of the own vehicle from the merging point. Alternatively, the information acquisition unit 51 may calculate the relative position Xr by subtracting the position of the own vehicle from the position of the merging vehicle in the forward / backward direction X of the own vehicle or the own lane. The information acquisition unit 51 calculates the relative speed Vr by subtracting the speed V1 of the own vehicle from the speed V2 of the merging vehicle. When the acceleration a2 of the merging vehicle can be obtained, the information acquisition unit 51 calculates the relative acceleration ar by subtracting the acceleration a1 of the own vehicle from the acceleration a2 of the merging vehicle.

[0040] 9, even when the angle between the own vehicle's lane and the merging lane is large, such as at an intersection, the information acquisition unit 51 calculates the relative position Xr by subtracting the distance X2 of the merging vehicle from the merging point from the distance X1 of the own vehicle from the merging point. The information acquisition unit 51 calculates the relative speed Vr by subtracting the speed V1 of the own vehicle from the speed V2 of the merging vehicle. If the acceleration a2 of the merging vehicle can be obtained, the information acquisition unit 51 calculates the relative acceleration ar by subtracting the acceleration a1 of the own vehicle from the acceleration a2 of the merging vehicle.

[0041] <Acquisition of information about surrounding vehicles> The information acquisition unit 51 acquires information on whether there are any vehicles ahead of the merging vehicle in the merging lane, whether there are any vehicles following the merging vehicle in the merging lane, whether there are any vehicles ahead of the vehicle in the current lane, and whether there are any vehicles following the vehicle in the current lane.

[0042] In addition, the information acquisition unit 51 acquires the inter-vehicle distance and relative speed between the merging vehicle and the vehicle preceding the merging vehicle, the inter-vehicle distance and relative speed between the merging vehicle and the vehicle following the merging vehicle, the inter-vehicle distance and relative speed between the host vehicle and the vehicle preceding the host vehicle, and the inter-vehicle distance and relative speed between the host vehicle and the vehicle following the host vehicle.

[0043] 1-1-2. Vehicle control unit 55 When autonomous driving is performed, the vehicle control unit 55 determines a target driving trajectory that is suited to the state of surrounding vehicles, obstacles, and pedestrians detected by the information acquisition unit 51, as well as the shape of the road around the vehicle. The target driving trajectory is a time-series driving plan that includes the vehicle's position, vehicle's traveling direction, vehicle speed, driving lane, and lane change positions at each future point in time. The vehicle control unit 55 generates a target driving trajectory that performs deceleration or acceleration, lane changes, etc. based on the merge probability Pf ahead and the merge probability Pr behind.

[0044] The vehicle control unit 55 controls the vehicle so that it travels along a target travel trajectory of the vehicle. For example, the vehicle control unit 55 determines a target speed, a target steering angle, a turn signal operation command, etc., and transmits each determined command value to the drive control devices 36, such as a power control device, a brake control device, an automatic steering control device, and a light control device.

[0045] The power control device controls the output of a power machine 8 such as an internal combustion engine or a motor so that the speed of the vehicle follows a target speed. The brake control device controls the braking operation of an electric brake device 9 so that the speed of the vehicle follows a target speed. The automatic steering control device controls the electric steering device 7 so that the steering angle follows a target steering angle. The light control device controls the turn signal according to an operation command for the turn signal.

[0046] Alternatively, when the driver is driving manually or semi-automatically, the vehicle control unit 55 transmits commands to the power control device and the brake control device to perform deceleration or acceleration based on the merging probability Pf at the front and the merging probability Pr at the rear, thereby controlling the output of the power machine 8 and controlling the braking operation of the electric brake device 9. At this time, the steering angle may also be controlled by the electric steering device 7.

[0047] 1-1-3. Merging position prediction unit 52 The merging position prediction unit 52 predicts the merging position of a merging vehicle in front of or behind the vehicle based on movement information of the vehicle itself, movement information of a merging vehicle, lane information of the vehicle's own lane (target lane), and lane information of the merging lane.

[0048] In this embodiment, the merging position predicting unit 52 predicts the merging position of a merging vehicle ahead or behind the host vehicle based on the relative position Xr and relative speed Vr of the merging vehicle with respect to the host vehicle.

[0049] As shown in Fig. 8, when the angle between the own vehicle lane and the merging lane is small, the longitudinal relationship between the own vehicle and the merging vehicle is determined in the fore-and-aft direction X of the own vehicle or the own lane. When the own lane is curved, the curve of the own lane may be taken into consideration.

[0050] On the other hand, as shown in Figure 9, when the angle between the own vehicle's lane and the merging lane is large, such as at an intersection, the front-to-rear relationship between the merging vehicle and the own vehicle is determined based on the distance to the merging point. If the merging vehicle arrives at the merging point before the own vehicle, it is predicted that the merging vehicle will merge in front of the own vehicle, and if the merging vehicle arrives at the merging point after the own vehicle, it is predicted that the merging vehicle will merge behind the own vehicle. The merging position in this case is the distance between the own vehicle and the merging vehicle when the merging vehicle reaches the merging point (when merging is complete).

[0051] <Prediction using boundaries> As shown in FIG. 10, the merging position prediction unit 52 sets a boundary line in a two-dimensional coordinate system having axes of relative position Xr and relative speed Vr, and predicts the merging position of a merging vehicle in front of or behind the vehicle based on the relative positional relationship between the boundary line and the detected value Xrdet of the relative position of the merging vehicle and the detected value Vrdet of the relative speed of the merging vehicle relative to the vehicle.

[0052] A boundary line is set such that the relative position Xr decreases from 0 as the relative speed Vr increases from 0, and a boundary line is set such that the relative position Xr increases from 0 as the relative speed Vr decreases from 0. The boundary line may be designed and tuned using a statistical method, or a boundary line model learned by machine learning using past data may be used. The slope and shape of the boundary line may be changed based on the characteristics of the merging lane and the own vehicle lane (e.g., the speed difference between the merging lane and the own vehicle lane, the length of the merging lane). The slope and shape of the boundary line may be changed based on the distance from the merging vehicle to the end of the merging lane.

[0053] The merging position prediction unit 52 predicts that the merging vehicle will merge in front of the own vehicle if the detected value Xrdet of the relative position and the detected value Vrdet of the relative speed of the merging vehicle are located on the increasing side of the relative position Xr and the relative speed Vr with respect to the boundary line, and predicts that the merging vehicle will merge behind the own vehicle if the detected value Xrdet of the relative position and the detected value Vrdet of the relative speed of the merging vehicle are located on the decreasing side of the relative position Xr and the relative speed Vr with respect to the boundary line.

[0054] The merging position prediction unit 52 sets a boundary line in a two-dimensional coordinate system having axes of the relative position Xr and relative speed Vr of the merging vehicle relative to the host vehicle in the longitudinal direction X of the vehicle, and predicts whether the merging vehicle will cut in front of or behind the host vehicle based on the relative positional relationship of the detected value Xrdet of the relative position of the merging vehicle and the detected value Vrdet of the relative speed of the merging vehicle relative to the boundary line.

[0055] The merging position prediction unit 52 sets a curve as the boundary line such that when the relative speed Vr of the merging vehicle is positive, the relative position Xr of the merging vehicle is the value obtained by multiplying the square of the relative speed Vr of the merging vehicle by the negative value of the weighting coefficient W, and when the relative speed Vr of the merging vehicle is negative, the value obtained by multiplying the square of the relative speed Vr of the merging vehicle by the positive value of the weighting coefficient W is the relative position Xr of the merging vehicle. Here, the weighting coefficient W itself is set to a positive value. The weighting coefficient W is set by adaptation. sgn(Vr) is a sign function that outputs 1 when Vr is positive and -1 when Vr is negative.

number

[0056] The merging position prediction unit 52 predicts that the merging vehicle will cut in front of the own vehicle if the detected value Xrdet of the relative position and the detected value Vrdet of the relative speed of the merging vehicle are located on the increasing side of the relative position Xr and the relative speed Vr with respect to the boundary line, and predicts that the merging vehicle will cut in behind the own vehicle if the detected value Xrdet of the relative position and the detected value Vrdet of the relative speed of the merging vehicle are located on the decreasing side of the relative position Xr and the relative speed Vr with respect to the boundary line.

[0057] The merging position predicting unit 52 predicts the merging position D based on the distance between the detected value Xrdet of the relative position of the merging vehicle and the detected value Vrdet of the relative speed of the merging vehicle relative to the boundary line.

[0058] 10 and the following equation, the merging position prediction unit 52 calculates the distance from the boundary line to the direction of the relative position Xr of the merging vehicle, which is the detected value Xrdet of the relative position of the merging vehicle and the detected value Vrdet of the relative speed of the merging vehicle, as the merging position D. The merging position D is the relative position or inter-vehicle distance between the host vehicle and the merging vehicle when merging is complete.

number

[0059] If the merging position D at the time of merging completion is positive, the merging vehicle is predicted to merge in front of the host vehicle. If the merging position D at the time of merging completion is negative, the merging vehicle is predicted to merge behind the host vehicle.

[0060] Alternatively, the merging position of a merging vehicle may be predicted using a machine learning model such as a neural network. The machine learning model learns in advance through machine learning the relationship between previously acquired input data and output data. The past input data for learning includes at least one or both of feature quantities of the position and speed of the merging vehicle, such as the relative position and relative speed of the merging vehicle with respect to the host vehicle, the distance from the merging vehicle to the end of the merging lane, and the relative positions of vehicles in front of and behind the host vehicle. The past output data for learning includes at least the merging position of the merging vehicle in front of or behind the host vehicle.

[0061] It should be noted that various other known methods may be used to predict the merging position of a merging vehicle.

[0062] 1-1-4. Reliability calculation unit 53 The reliability calculation unit 53 calculates the reliability C of the merging position predicted by the merging position prediction unit 52 based on the movement information of the vehicle itself, the movement information of the merging vehicle, the lane information of the vehicle itself (target lane), and the lane information of the merging lane.

[0063] <Multiple reliability calculation processes> In this embodiment, the reliability calculation unit 53 executes a plurality of reliability calculation processes to calculate a plurality of reliability degrees, and integrates the calculated plurality of reliability degrees to calculate a final single reliability degree C.

[0064] In this embodiment, the reliability calculation unit 53 executes a first reliability calculation process to calculate a first reliability C1, a second reliability calculation process to calculate a second reliability C2, and a third reliability calculation process to calculate a third reliability C3, and integrates the calculated first reliability C1, second reliability C2, and third reliability C3 to calculate a final single reliability C.

[0065] For example, as shown in the following equation, the reliability calculation unit 53 calculates one reliability C by multiplying the first reliability C1, the second reliability C2, and the third reliability C3 together.

number

[0066] Each reliability C has a value between 0 and 1, with C=1 being the highest reliability C (100%) and C=0 being the lowest reliability C (0%).

[0067] The reliability calculation unit 53 may use a set function in which the relationship between the first reliability C1, the second reliability C2, the third reliability C3 and the final reliability C is preset, and calculate one final reliability C based on the current first reliability C1, the current second reliability C2, and the current third reliability C3. Map data or a mathematical formula is used as the set function.

[0068] Alternatively, the reliability calculation unit 53 may execute any one of the first reliability calculation process, the second reliability calculation process, and the third reliability calculation process. Then, the reliability calculation unit 53 may calculate the reliability calculated by the one executed reliability calculation process as the final reliability C. Alternatively, the reliability calculation unit 53 may execute any two of the first reliability calculation process, the second reliability calculation process, and the third reliability calculation process. Then, the reliability calculation unit 53 may integrate the two reliabilities calculated by the two executed reliability calculation processes to calculate the final reliability C. Alternatively, a reliability calculation process different from the first to third reliability calculation processes may be executed, and the calculated reliabilities may be further integrated.

[0069] <Calculation of first reliability C1 based on merging distance> The reliability calculation unit 53 executes a first reliability calculation process to calculate a first reliability C1 of the merging position based on a merging distance until the merging vehicle reaches the merging point between the merging lane and the own lane. The reliability calculation unit 53 decreases the first reliability C1 as the merging distance increases.

[0070] As the merging distance when predicting the merging position becomes longer, the merging position may fluctuate more due to changes in the speed and acceleration of the merging vehicle until it reaches the merging point, and the accuracy of the merging position predicted based on the current movement information of the merging vehicle may deteriorate. Therefore, by decreasing the first reliability C1 as the merging distance becomes longer, it is possible to calculate the reliability taking the merging distance into consideration.

[0071] In this embodiment, the reliability calculation unit 53 calculates a merging arrival time t* that is the time it takes for a merging vehicle to reach the merging point based on the merging arrival distance and the movement information of the merging vehicle, calculates a first reliability C1 based on the merging arrival time t*, and decreases the first reliability C1 as the merging arrival time t* becomes longer.

[0072] The merging position D at the time of merging completion is a function of the speed, acceleration, and time of the merging vehicle, and as the merging arrival time t* becomes longer, there is a possibility that the merging position D at the time of merging completion will fluctuate more due to changes in the speed and acceleration of the merging vehicle. With the above configuration, the merging arrival time t* is calculated based on the merging arrival distance and the movement information of the merging vehicle, and the first reliability C1 is reduced as the merging arrival time t* becomes longer, thereby making it possible to accurately calculate the first reliability C1.

[0073] The principle will be explained using mathematical formulas. Using the current relative position Xr0, relative speed Vr0, and relative acceleration ar0 between the host vehicle and the merging vehicle, and the merging arrival time t* from the present time until the merging vehicle reaches the merging point, the merging position D at the time of merging completion when the merging vehicle reaches the merging point can be expressed by the following formula.

number

[0074] In this case, the current relative acceleration ar0 cannot be observed, and if there is variation depending on the merging vehicle, ar0 is t* 2 , the uncertainty of the merging position D when the merging vehicle reaches the merging point is proportional to t* 2In addition, even if the current relative acceleration ar0 can be observed, it may change before reaching the junction point, and if this occurs, the uncertainty of the junction position D is t* 2 It is thought to be proportional to

[0075] Therefore, as shown in the following equation, the reliability calculation unit 53 calculates the first reliability C1 in inverse proportion to the square of the junction arrival time t*, where Wp1 is an adjustment coefficient that adjusts the magnitude of the first reliability C1 and is a positive value.

number

[0076] When the current relative acceleration ar0 has been acquired, the reliability calculation unit 53 may change the adjustment coefficient Wp1 of the first reliability C1 based on the current relative acceleration ar0. For example, the reliability calculation unit 53 increases the adjustment coefficient Wp1 of the first reliability C1 as the absolute value of the current relative acceleration ar0 increases. When the absolute value of the current relative acceleration ar0 is large, the merging vehicle has already accelerated or decelerated in order to merge, and there is a high possibility that merging will occur in this state. Therefore, the adjustment coefficient Wp1 is increased, and the first reliability C1 is raised.

[0077] The reliability calculation unit 53 calculates the merging arrival time t* based on the merging arrival distance and the movement information of the merging vehicle. For example, the reliability calculation unit 53 calculates the merging arrival time t* by dividing the merging arrival distance by the current speed of the merging vehicle. Note that the acceleration of the current merging vehicle may also be taken into consideration.

[0078] When the current lane and the merging lane are parallel, the merging arrival time t* may be calculated using a corrected merging arrival distance obtained by subtracting an offset distance from the actual merging arrival distance, taking into account the fact that the merging will occur before the merging point. The offset distance may be set according to the length of the tapered portion of the merging lane near the merging point. The offset distance may be set based on the type of vehicle of the merging vehicle. The offset distance is increased as the merging vehicle becomes larger. The offset distance may be set based on the current lateral speed of the merging vehicle or the expected lateral speed.

[0079] Alternatively, when the merging vehicle has started to move laterally, the reliability calculation unit 53 may calculate the merge arrival time t* based on the current lateral position and lateral speed of the merging vehicle. For example, the reliability calculation unit 53 may calculate the merge arrival time t* by dividing the lateral distance of the current merging vehicle from the center position of the own lane by the lateral speed of the current merging vehicle.

[0080] Furthermore, the reliability calculation unit 53 may use a preset function in which the relationship between the merging distance or merging time t* and the first reliability C1 is set, and calculate the first reliability C1 based on the current merging distance or merging time t*. The set function may use map data or a mathematical formula.

[0081] <Calculation of second reliability C2 based on relative velocity Vr> The reliability calculation unit 53 executes a second reliability calculation process to calculate a second reliability C2 based on the relative speed Vr between the host vehicle and the merging vehicle. The reliability calculation unit 53 decreases the second reliability C2 as the absolute value of the relative speed Vr increases.

[0082] As the absolute value of the current relative speed Vr increases, the relative position at the time when the merging vehicle starts accelerating or decelerating to merge may fluctuate more, and the accuracy of the merging position predicted based on the relative position may deteriorate. Therefore, by decreasing the second reliability C2 as the absolute value of the current relative speed Vr increases, it is possible to calculate the reliability taking the relative speed into consideration.

[0083] The principle will be explained using mathematical formulas. Using the current relative position Xr0 and relative speed Vr0 between the host vehicle and the merging vehicle before the merging vehicle starts accelerating or decelerating, and the acceleration / deceleration start time ts from the present until the merging vehicle starts accelerating or decelerating, the relative position Xrs at the time the merging vehicle starts accelerating or decelerating to merge can be expressed by the following formula:

number

[0084] In this case, if the acceleration / deceleration start time ts at which a merging vehicle begins accelerating or decelerating varies depending on the merging vehicle, the acceleration / deceleration start time ts is proportional to the current relative speed Vr0, and therefore the uncertainty of the relative position Xrs at the time the merging vehicle starts accelerating or decelerating is proportional to the current relative speed Vr0. The relative position Xrs at the time the merging vehicle starts accelerating or decelerating corresponds to the relative position Xr at the time the merging vehicle begins operating to merge, and is related to the prediction of the merging position based on the relative position Xr. Therefore, the uncertainty of the merging position is considered to be proportional to the current relative speed Vr0.

[0085] Therefore, as shown in the following equation, the reliability calculation unit 53 calculates the second reliability C2 in inverse proportion to the absolute value of the relative speed Vr: where Wp2 is an adjustment coefficient that adjusts the magnitude of the second reliability C2 and is a positive value.

number

[0086] When the current relative acceleration ar0 has been acquired, the reliability calculation unit 53 may change the adjustment coefficient Wp2 of the second reliability C2 based on the current relative acceleration ar0. For example, the reliability calculation unit 53 increases the adjustment coefficient Wp2 of the second reliability C2 as the absolute value of the current relative acceleration ar0 increases. When the absolute value of the current relative acceleration ar0 is large, the merging vehicle has already accelerated or decelerated in order to merge, and there is a high possibility that merging will occur in this state. Therefore, the adjustment coefficient Wp2 is increased, and the second reliability C2 is raised.

[0087] Alternatively, the reliability calculation unit 53 may use a set function in which the relationship between the absolute value of the relative speed Vr and the second reliability C2 is set in advance, and calculate the second reliability C2 based on the absolute value of the current relative speed Vr. The set function may use map data or a mathematical formula.

[0088] <Calculation of third reliability C3 based on the presence or absence of a preceding vehicle or a following vehicle for each vehicle> The reliability calculation unit 53 executes a third reliability calculation process to calculate a third reliability C3 based on whether or not there is a vehicle preceding the merging vehicle in the merging lane, whether or not there is a vehicle preceding the host vehicle in the host lane, and whether or not there is a vehicle following the host vehicle in the host lane.

[0089] The merging position of the merging vehicle may change depending on whether or not there is a vehicle preceding or following each vehicle, and the accuracy of the merging position of the merging vehicle predicted based on the movement information of the host vehicle and the movement information of the merging vehicle changes. Therefore, by changing the third reliability C3 depending on whether or not there is a vehicle preceding or following each vehicle, it is possible to calculate a reliability that takes into account the presence or absence of a vehicle preceding or following each vehicle. Note that the presence or absence of a vehicle following the merging vehicle in the merging lane may also be taken into account.

[0090] The reliability calculation unit 53 calculates the third reliability C3 based on the presence or absence of a vehicle preceding the current merging vehicle, the presence or absence of a vehicle preceding the host vehicle, and the presence or absence of a vehicle following the host vehicle, using a setting function in which the relationship between the presence or absence of a vehicle preceding the merging vehicle, the presence or absence of a vehicle preceding the host vehicle, and the presence or absence of a vehicle following the host vehicle is preset. The setting function sets the third reliability C3 for each combination of the presence or absence of a vehicle preceding the merging vehicle, the presence or absence of a vehicle preceding the host vehicle, and the presence or absence of a vehicle following the host vehicle. Table data such as that shown in FIG. 11 is used for such a setting function.

[0091] 11, when there is a vehicle preceding the merging vehicle, a vehicle preceding the host vehicle, and a vehicle following the host vehicle, the third reliability C3 is lowest. On the other hand, when there is no vehicle preceding the merging vehicle, no vehicle preceding the host vehicle, and no vehicle following the host vehicle, the third reliability C3 is highest. As the total number of vehicles preceding or following each vehicle increases, the third reliability C3 decreases.

[0092] Alternatively, a different setting function may be used depending on whether the merging vehicle's merging position is in front of or behind the host vehicle. Basically, the third reliability C3 decreases as the total number of preceding or following vehicles of each vehicle increases. However, when the merging vehicle's merging position is in front of the host vehicle, the setting function shown in FIG. 12 is used, and even if the total number of preceding or following vehicles is the same, the third reliability C3 when there is a vehicle preceding the host vehicle is set lower than the third reliability C3 when there is no vehicle preceding the host vehicle, and the third reliability C3 when there is a vehicle preceding the merging vehicle is set lower than the third reliability C3 when there is no vehicle preceding the merging vehicle.

[0093] When the merging position of the merging vehicle is behind the vehicle, the setting function shown in Figure 13 is used, and even if the total number of preceding or following vehicles is the same, the third reliability C3 when there is a following vehicle behind the vehicle is set lower than the third reliability C3 when there is no following vehicle, and the third reliability C3 when there is no vehicle ahead of the merging vehicle is set lower than the third reliability C3 when there is a vehicle ahead of the merging vehicle.

[0094] Furthermore, when there is a vehicle preceding the merging vehicle, the reliability calculation unit 53 determines whether to change the display to indicate that there is no vehicle preceding the merging vehicle based on one or both of the inter-vehicle distance and the relative speed between the merging vehicle and the preceding vehicle, when there is a vehicle preceding the host vehicle, determines whether to change the display to indicate that there is no vehicle preceding the host vehicle based on one or both of the inter-vehicle distance and the relative speed between the host vehicle and the preceding vehicle, and when there is a vehicle following the host vehicle, determines whether to change the display to indicate that there is no vehicle following the host vehicle based on one or both of the inter-vehicle distance and the relative speed between the host vehicle and the following vehicle.The reliability calculation unit 53 then similarly calculates a third reliability C3 based on the presence or absence of a vehicle preceding the merging vehicle after the determination, the presence or absence of a vehicle preceding the host vehicle after the determination, and the presence or absence of a vehicle following the host vehicle after the determination.

[0095] For example, the reliability calculation unit 53 changes the obtained result if there is no preceding or following vehicle for which the inter-vehicle distance between each vehicle and the preceding or following vehicle is equal to or greater than a threshold. Alternatively, the reliability calculation unit 53 changes the obtained result to indicate that there is no preceding or following vehicle if the inter-vehicle distance between each vehicle and the preceding or following vehicle is equal to or greater than a threshold and the relative speed between each vehicle and the preceding or following vehicle is equal to or greater than a threshold in the direction in which the inter-vehicle distance increases. Alternatively, the reliability calculation unit 53 calculates the inter-vehicle time by dividing the inter-vehicle distance between each vehicle and the preceding or following vehicle by the relative speed, and changes the obtained result if there is no preceding or following vehicle for which the inter-vehicle time is equal to or greater than the threshold.

[0096] 1-1-5. Merge probability calculation unit 54 Based on the merging position D and the reliability C, the merging probability calculation unit 54 calculates the merging probability Pf of a vehicle merging ahead of the host vehicle and the merging probability Pr of a vehicle merging behind the host vehicle.

[0097] According to this configuration, the probability Pf of merging ahead and the probability Pr of merging behind can be calculated based on the merging position D and the reliability C, and the accuracy of the predicted result of the merging position D can be evaluated.

[0098] 14 , when the merging position D of the merging vehicle is ahead of the host vehicle (in this example, when the merging position D is a positive value), the merging probability calculation unit 54 increases the merging probability Pf ahead and decreases the merging probability Pr behind as the absolute value of the merging position D, which is the relative position or inter-vehicle distance between the host vehicle and the merging vehicle, increases, and increases the increase amount of the merging probability Pf ahead and decreases the merging probability Pr behind as the reliability C increases. On the other hand, when the merging position D of the merging vehicle is behind the host vehicle (in this example, when the merging position D is a negative value), the merging probability calculation unit 54 decreases the merging probability Pf ahead and increases the merging probability Pr behind as the absolute value of the merging position D, which is the relative position or inter-vehicle distance between the host vehicle and the merging vehicle, increases, and increases the decrease amount of the merging probability Pf ahead and increases the increase amount of the merging probability Pr behind as the reliability C increases.

[0099] In this embodiment, the meeting probability calculation unit 54 uses a preset function that defines the relationship between the meeting position D and reliability C and the meeting probability Pf to the front and the meeting probability Pr to the rear, and calculates the meeting probability Pf to the front and the meeting probability Pr to the rear based on the current meeting position D and reliability C.

[0100] For example, the following equation is used as the setting function. The calculation result using the following equation is shown in FIG. 14. Other equations or map data may be used in addition to equation (8). Note that to convert each meeting probability to a percentage, the calculated value of equation (8) is multiplied by 100.

number

[0101] <Adjustment of each adjustment coefficient Wp> As described above, the reliability calculation unit 53 calculates each reliability C using each adjustment coefficient Wp that adjusts the magnitude of each reliability C.

[0102] The reliability calculation unit 53 changes each adjustment coefficient Wp so that the probability of meeting to the front side Pf and the probability of meeting to the rear side Pr calculated by the meeting probability calculation unit 54 approach the actual probability of meeting to the front side Pf and the probability of meeting to the rear side Pr collected.

[0103] According to this configuration, by adjusting each adjustment coefficient Wp using collected past data, the calculated probability of merging ahead Pf and probability of merging behind Pr can be made closer to the actual probability of merging ahead Pf and probability of merging behind Pr, thereby improving prediction accuracy.

[0104] The actual merging probabilities Pf and Pr to the front and rear may be data from an actual vehicle, or may be data generated by a simulator.

[0105] For example, the reliability calculation unit 53 adjusts each adjustment coefficient Wp using the gradient descent method. The following cross-entropy function is used as the error function. Here, q is the target output, and when merging from the front, q=1, and when merging from the rear, q=0. Pf is the probability Pf of merging to the front.

number

[0106] Using the following formula, each adjustment coefficient Wp is updated so that E becomes smaller. This calculation is repeated multiple times.

number

[0107] 1-1-5. Vehicle control unit 55 The vehicle control unit 55 controls the traveling of the host vehicle. The vehicle control unit 55 controls at least the traveling of the host vehicle so that traveling at the time of merging is smooth based on the merging probability Pf to the front and the merging probability Pr to the rear.

[0108] For example, the vehicle control unit 55 controls at least the speed of the host vehicle so as to ensure a sufficient inter-vehicle distance between the host vehicle and the merging vehicle when merging is complete, based on the merging probability Pf ahead and the merging probability Pr behind. Specifically, if the merging probability Pf ahead is greater than 50% (0.5 in this example) and the merging probability Pr behind is less than 50% (0.5), the vehicle control unit 55 determines that the merging vehicle will merge ahead of the host vehicle, and performs forward inter-vehicle distance control, which controls the speed of the host vehicle so as to ensure a sufficient inter-vehicle distance between the host vehicle and the merging vehicle when the host vehicle is positioned behind the merging vehicle. On the other hand, if the probability of merging ahead Pf is less than 50% (0.5) and the probability of merging behind Pr is greater than 50% (0.5), the vehicle control unit 55 determines that the merging vehicle will merge behind the host vehicle, and performs rear inter-vehicle distance control to control the speed of the host vehicle so as to ensure a sufficient inter-vehicle distance between the host vehicle and the merging vehicle while the host vehicle is positioned ahead of the merging vehicle. At this time, the merging position D predicted by the merging position prediction unit 52 or the current relative position Xr may be used as the inter-vehicle distance.

[0109] The vehicle control unit 55 sets the target speed to a value that is increased or decreased from the current speed of the host vehicle or the target speed so that the inter-vehicle distance can be maintained, and changes one or both of the output of the power machine 8 and the braking force of the brakes so that the speed of the host vehicle follows the target speed. Furthermore, the vehicle control unit 55 may change lanes of the host vehicle to an adjacent lane based on the merging probability Pf ahead and the merging probability Pr behind.

[0110] The vehicle control unit 55 may generate guidance information to prompt the driver of the vehicle to drive in accordance with the driving control of the vehicle, and notify the driver of the guidance information. The guidance information includes information to prompt the driver to decelerate, accelerate, or change lanes to facilitate smooth driving when merging. The guidance information is output from the human interface device 37, such as a speaker or a display screen.

[0111] Furthermore, in addition to the driving of the own vehicle, the driving of merging vehicles may also be supported, or the driving of surrounding vehicles may also be supported.

[0112] In this embodiment, the vehicle control unit 55 changes the set values ​​used when controlling the vehicle based on the merging probability Pf ahead and the merging probability Pr behind.

[0113] According to this configuration, the set values ​​can be changed depending on whether the merging probabilities Pf and Pr are high or low, thereby changing the behavior of the vehicle control. Therefore, it is possible to realize appropriate vehicle control behavior according to the level of each merging probability. For example, when both merging probabilities Pf and Pr are close to 50% (0.5) and the prediction accuracy of a merging to the front or rear is low, the vehicle control unit 55 has little need to perform vehicle control such as aggressive acceleration / deceleration in preparation for a merging. On the other hand, when one merging probability is close to 100% (1.0) and the prediction accuracy of a merging to the front or rear is high, the vehicle control unit 55 has a high need to perform vehicle control such as aggressive acceleration / deceleration in preparation for a merging.

[0114] In this embodiment, the vehicle control unit 55 changes one or both of the maximum allowable acceleration / deceleration and maximum acceleration / deceleration jerk as set values ​​based on the probability of merging ahead Pf and the probability of merging behind Pr. With this configuration, the degree of acceleration / deceleration of the vehicle control can be appropriately changed depending on the level of the probability of merging ahead or behind.

[0115] For example, the vehicle control unit 55 increases one or both of the maximum acceleration / deceleration and the maximum acceleration / deceleration jerk as the probability of one of the merging directions approaches 100% from 50%. With this configuration, as the prediction accuracy of a merging direction to the front or rear increases, more aggressive acceleration / deceleration can be performed in preparation for the merging direction, thereby improving safety during merging. On the other hand, when the prediction accuracy of a merging direction to the front or rear is low, aggressive acceleration / deceleration that is not necessary can be suppressed, thereby preventing the occupants from feeling uncomfortable.

[0116] For example, when the probability of merging to the front Pf is greater than 50% (0.5 in this example) and the probability of merging to the rear Pf is less than 50% (0.5), the vehicle control unit 55 adjusts the allowable maximum deceleration [m / s 2] and the maximum allowable deceleration jerk [m / s 3 ] is increased. As a result, as the probability Pf of merging ahead increases, the host vehicle is decelerated more aggressively, thereby ensuring a sufficient inter-vehicle distance from the merging vehicle merging ahead of the host vehicle. As shown in FIG. 15, the deceleration may be increased in stages or continuously. Here, the deceleration is the absolute value of the negative acceleration, and the deceleration jerk is the absolute value of the negative jerk.

[0117] Furthermore, when the probability of merging at the rear Pr is greater than 50% (0.5 in this example) and the probability of merging at the front Pf is less than 50% (0.5), the vehicle control unit 55 adjusts the allowable maximum acceleration [m / s 2 ] and the maximum allowable acceleration jerk [m / s 3 ] is increased. As a result, as the probability Pr of merging behind the host vehicle increases, the host vehicle is accelerated more aggressively, thereby ensuring a sufficient inter-vehicle distance from the merging vehicle merging behind the host vehicle. As shown in FIG. 16, the acceleration jerk may be increased stepwise or continuously. Here, the acceleration jerk is a positive acceleration, and the acceleration jerk is a positive jerk.

[0118] 1-1-6. Flowchart 17 is a flowchart illustrating the processing of the merging prediction device 1 and the vehicle control device 50 according to this embodiment. The processing of FIG. 17 is executed, for example, at every predetermined calculation cycle.

[0119] In step S01, as described above, the information acquisition unit 51 acquires movement information of the subject vehicle (target vehicle), movement information of a merging vehicle traveling in a merging lane that merges into the subject vehicle's lane (target lane) in which the subject vehicle is traveling, lane information of the subject vehicle's lane, and lane information of the merging lane.

[0120] In step S02, as described above, the merging position prediction unit 52 predicts the merging position of a merging vehicle in front of or behind the vehicle based on the movement information of the vehicle itself, the movement information of the merging vehicle, the lane information of the vehicle itself, and the lane information of the merging lane.

[0121] In step S03, as described above, the reliability calculation unit 53 calculates the reliability C of the merging position predicted by the merging position prediction unit 52 based on the movement information of the host vehicle, the movement information of the merging vehicle, the lane information of the host lane (target lane), and the lane information of the merging lane. In this embodiment, the reliability calculation unit 53 executes a first reliability calculation process to calculate a first reliability C1 based on the merging distance, a second reliability calculation process to calculate a second reliability C2 based on the relative speed Vr, and a third reliability calculation process to calculate a third reliability C3 based on the presence or absence of a preceding vehicle or a following vehicle of each vehicle, and integrates the calculated first reliability C1, second reliability C2, and third reliability C3 to calculate a final single reliability C.

[0122] In step S04, as described above, the merging probability calculation unit 54 calculates the merging probability Pf of a vehicle merging in front of the vehicle and the merging probability Pr of a vehicle merging behind the vehicle based on the merging position D and the reliability C.

[0123] In step S05, as described above, the vehicle control unit 55 controls the traveling of the host vehicle. In this embodiment, the vehicle control unit 55 controls the traveling of the host vehicle based on the merging probability Pf ahead and the merging probability Pr behind. The vehicle control unit 55 also changes the setting values ​​used when controlling the vehicle based on the merging probability Pf ahead and the merging probability Pr behind.

[0124] <Other embodiments> In the above-described first embodiment, the merging prediction device 1 is provided in a target vehicle (own vehicle). However, the merging prediction device 1 may be provided in a management server, each of a plurality of vehicles managed by the management server may be set as a target vehicle, and the merging prediction device 1 may perform processing for each target vehicle to predict the merging probability Pf to the front and the merging probability Pr to the rear, and the prediction results may be transmitted to a vehicle control unit 55 provided in each target vehicle.

[0125] Summary of Aspects of the Disclosure Various aspects of the present disclosure are summarized below as appendices. (Appendix 1) an information acquisition unit that acquires movement information of a target vehicle, movement information of a merging vehicle traveling in a merging lane that merges into a target lane in which the target vehicle is traveling, lane information of the target lane, and lane information of the merging lane; a merging position prediction unit that predicts a merging position of the merging vehicle ahead of or behind the target vehicle based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a reliability calculation unit that calculates the reliability of the merging position based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a merging probability calculation unit that calculates the merging probability of the merging vehicle in front of the target vehicle and the merging probability of the merging vehicle in rear of the target vehicle based on the merging position and the reliability.

[0126] (Appendix 2) the information acquisition unit acquires a merging reach distance until the merging vehicle reaches a merging point between the merging lane and the target lane, 2. The merging prediction device according to claim 1, wherein the reliability calculation unit calculates the reliability based on the merging distance, and decreases the reliability as the merging distance becomes longer.

[0127] (Appendix 3) The merging prediction device according to claim 2, wherein the reliability calculation unit calculates a merging arrival time required for the merging vehicle to reach a merging point between the merging lane and the target lane based on the merging arrival distance and movement information of the merging vehicle, calculates the reliability based on the merging arrival time, and decreases the reliability as the merging arrival time becomes longer.

[0128] (Appendix 4) 4. The merging prediction device according to claim 3, wherein the reliability calculation unit changes the reliability in inverse proportion to a square of the merging arrival time.

[0129] (Appendix 5) the information acquisition unit acquires a relative speed between the target vehicle and the merging vehicle; 5. The merging prediction device according to claim 1, wherein the reliability calculation unit calculates the reliability based on the relative speed, and decreases the reliability as the absolute value of the relative speed increases.

[0130] (Appendix 6) 6. The merging prediction device according to claim 5, wherein the reliability calculation unit changes the reliability in inverse proportion to an absolute value of the relative speed.

[0131] (Appendix 7) the information acquisition unit acquires whether or not there is a vehicle preceding the merging vehicle in the merging lane, whether or not there is a vehicle preceding the target vehicle in the target lane, and whether or not there is a vehicle following the target vehicle in the target lane; 7. The merging prediction device according to claim 1, wherein the reliability calculation unit calculates the reliability based on whether or not there is a vehicle preceding the merging vehicle, whether or not there is a vehicle preceding the target vehicle, and whether or not there is a vehicle following the target vehicle.

[0132] (Appendix 8) the information acquisition unit acquires one or both of an inter-vehicle distance and a relative speed between the merging vehicle and the preceding vehicle of the merging vehicle, one or both of an inter-vehicle distance and a relative speed between the target vehicle and the preceding vehicle of the target vehicle, and one or both of an inter-vehicle distance and a relative speed between the target vehicle and the following vehicle of the target vehicle, the reliability calculation unit, when there is a vehicle preceding the merging vehicle, determines whether or not to change the state to indicate that there is no vehicle preceding the merging vehicle, based on one or both of the inter-vehicle distance and the relative speed between the merging vehicle and the preceding vehicle; when there is a vehicle preceding the target vehicle, determines whether or not to change the state to indicate that there is no vehicle preceding the target vehicle, based on one or both of the inter-vehicle distance and the relative speed between the target vehicle and the preceding vehicle; when there is a vehicle following the target vehicle, determines whether or not to change the state to indicate that there is no vehicle following the target vehicle, based on one or both of the inter-vehicle distance and the relative speed between the target vehicle and the following vehicle; 8. The merging prediction device according to claim 7, wherein the reliability is calculated based on whether or not there is a vehicle preceding the merging vehicle after the determination, whether or not there is a vehicle preceding the target vehicle after the determination, and whether or not there is a vehicle following the target vehicle after the determination.

[0133] (Appendix 9) a first reliability calculation process in which the reliability calculation unit calculates a first reliability based on a merging distance until the merging vehicle reaches a merging point between the merging lane and the target lane; a second reliability calculation process for calculating a second reliability based on a relative speed between the target vehicle and the merging vehicle; and a third reliability calculation process for calculating a third reliability based on whether or not there is a vehicle preceding the merging vehicle, whether or not there is a vehicle preceding the target vehicle, and whether or not there is a vehicle following the target vehicle; Do two or more of the following: A confluence prediction device according to claim 1, which integrates two or more of the calculated first reliability, second reliability, and third reliability to calculate a final single reliability.

[0134] (Appendix 10) The merging prediction device according to any one of appendices 1 to 9, wherein the merging probability calculation unit uses a set function in which a relationship between the merging position and the reliability and the probability of merging to the front and the probability of merging to the rear is set in advance, and calculates the probability of merging to the front and the probability of merging to the rear based on the current merging position and the reliability.

[0135] (Appendix 11) the reliability calculation unit calculates the reliability using an adjustment coefficient that adjusts the magnitude of the reliability; 11. The confluence prediction device according to claim 1, wherein the adjustment coefficient is changed so that the confluence probability to the front side and the confluence probability to the rear side calculated by the confluence probability calculation unit approach the actual confluence probability to the front side and the confluence probability to the rear side that have been collected.

[0136] (Appendix 12) A confluence prediction device according to any one of Supplementary Notes 1 to 11; a vehicle control unit that controls the running of the target vehicle, The vehicle control unit is a vehicle control device that controls the traveling of the target vehicle based on the probability of merging ahead and the probability of merging behind.

[0137] (Appendix 13) 13. The vehicle control device according to claim 12, wherein the vehicle control unit changes a setting value used when performing vehicle control based on a probability of merging ahead and a probability of merging behind.

[0138] (Appendix 14) The vehicle control device according to claim 13, wherein the vehicle control unit changes one or both of the maximum allowable acceleration / deceleration and the maximum acceleration / deceleration jerk as the setting values ​​based on the probability of merging ahead and the probability of merging behind.

[0139] Although exemplary embodiments are described in this disclosure, the various features, aspects, and functions described in the embodiments are not limited to specific embodiments, but may be applied to the embodiments alone or in various combinations. Therefore, countless variations not illustrated are anticipated within the scope of the technology disclosed in this disclosure specification. For example, variations in, addition to, or omission of at least one component are included. [Explanation of symbols]

[0140] 1: merging prediction device, 50: vehicle control device, 51: information acquisition unit, 52: merging position prediction unit, 53: reliability calculation unit, 54: merging probability calculation unit, 55: vehicle control unit, C: reliability, C1: first reliability, C2: second reliability, C3: third reliability, D: merging position, Pf: probability of merging to the front, Pr: probability of merging to the rear, Vr: relative speed, Wp: adjustment coefficient, Xr: relative position

Claims

1. an information acquisition unit that acquires movement information of a target vehicle, movement information of a merging vehicle traveling in a merging lane that merges into a target lane in which the target vehicle is traveling, lane information of the target lane, and lane information of the merging lane; a merging position prediction unit that predicts a merging position of the merging vehicle ahead of or behind the target vehicle based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a reliability calculation unit that calculates the reliability of the merging position based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a merging probability calculation unit that calculates the merging probability of the merging vehicle in front of the target vehicle and the merging probability of the merging vehicle in rear of the target vehicle based on the merging position and the reliability.

2. the information acquisition unit acquires a merging reach distance until the merging vehicle reaches a merging point between the merging lane and the target lane, The merging prediction device according to claim 1 , wherein the reliability calculation unit calculates the reliability based on the merging distance, and decreases the reliability as the merging distance increases.

3. 3. The merging prediction device according to claim 2, wherein the reliability calculation unit calculates a merging arrival time required for the merging vehicle to reach a merging point between the merging lane and the target lane based on the merging arrival distance and movement information of the merging vehicle, calculates the reliability based on the merging arrival time, and decreases the reliability as the merging arrival time becomes longer.

4. The merging prediction device according to claim 3 , wherein the reliability calculation unit changes the reliability in inverse proportion to a square of the merging arrival time.

5. the information acquisition unit acquires a relative speed between the target vehicle and the merging vehicle; The merging prediction device according to claim 1 , wherein the reliability calculation unit calculates the reliability based on the relative speed, and decreases the reliability as the absolute value of the relative speed increases.

6. The merging prediction device according to claim 5 , wherein the reliability calculation unit changes the reliability in inverse proportion to the absolute value of the relative speed.

7. the information acquisition unit acquires whether or not there is a vehicle preceding the merging vehicle in the merging lane, whether or not there is a vehicle preceding the target vehicle in the target lane, and whether or not there is a vehicle following the target vehicle in the target lane; 5. The merging prediction device according to claim 1, wherein the reliability calculation unit calculates the reliability based on whether or not there is a vehicle preceding the merging vehicle, whether or not there is a vehicle preceding the target vehicle, and whether or not there is a vehicle following the target vehicle.

8. the information acquisition unit acquires one or both of an inter-vehicle distance and a relative speed between the merging vehicle and the preceding vehicle of the merging vehicle, one or both of an inter-vehicle distance and a relative speed between the target vehicle and the preceding vehicle of the target vehicle, and one or both of an inter-vehicle distance and a relative speed between the target vehicle and the following vehicle of the target vehicle, the reliability calculation unit, when there is a vehicle preceding the merging vehicle, determines whether or not to change the state to indicate that there is no vehicle preceding the merging vehicle, based on one or both of the inter-vehicle distance and the relative speed between the merging vehicle and the preceding vehicle; when there is a vehicle preceding the target vehicle, determines whether or not to change the state to indicate that there is no vehicle preceding the target vehicle, based on one or both of the inter-vehicle distance and the relative speed between the target vehicle and the preceding vehicle; when there is a vehicle following the target vehicle, determines whether or not to change the state to indicate that there is no vehicle following the target vehicle, based on one or both of the inter-vehicle distance and the relative speed between the target vehicle and the following vehicle; The merging prediction device according to claim 7, wherein the reliability is calculated based on whether or not there is a vehicle preceding the merging vehicle after the determination, whether or not there is a vehicle preceding the target vehicle after the determination, and whether or not there is a vehicle following the target vehicle after the determination.

9. a first reliability calculation process in which the reliability calculation unit calculates a first reliability based on a merging distance until the merging vehicle reaches a merging point between the merging lane and the target lane; a second reliability calculation process for calculating a second reliability based on a relative speed between the target vehicle and the merging vehicle; and a third reliability calculation process for calculating a third reliability based on whether or not there is a vehicle preceding the merging vehicle, whether or not there is a vehicle preceding the target vehicle, and whether or not there is a vehicle following the target vehicle; Execute two or more of the following: The confluence prediction device according to claim 1 , wherein two or more of the calculated first reliability, the second reliability, and the third reliability are integrated to calculate a final single reliability.

10. 5. The merging prediction device according to claim 1, wherein the merging probability calculation unit uses a preset function in which a relationship between the merging position and the reliability and the probability of merging to the front and the probability of merging to the rear is set, and calculates the probability of merging to the front and the probability of merging to the rear based on the current merging position and the reliability.

11. the reliability calculation unit calculates the reliability using an adjustment coefficient that adjusts the magnitude of the reliability; 5. The confluence prediction device according to claim 1, wherein the adjustment coefficient is changed so that the confluence probability to the front side and the confluence probability to the rear side calculated by the confluence probability calculation unit approach the actual confluence probability to the front side and the confluence probability to the rear side collected.

12. The confluence prediction device according to any one of claims 1 to 4, a vehicle control unit that controls the running of the target vehicle, The vehicle control unit is a vehicle control device that controls the traveling of the target vehicle based on the probability of merging ahead and the probability of merging behind.

13. The vehicle control device according to claim 12 , wherein the vehicle control unit changes a set value used when controlling the vehicle based on a probability of merging ahead and a probability of merging behind.

14. 14. The vehicle control device according to claim 13, wherein the vehicle control unit changes one or both of the maximum acceleration / deceleration and the maximum acceleration / deceleration jerk as the set values ​​based on the probability of merging ahead and the probability of merging behind.

15. an information acquisition step of acquiring movement information of a target vehicle, movement information of a merging vehicle traveling in a merging lane that merges into a target lane in which the target vehicle is traveling, lane information of the target lane, and lane information of the merging lane; a merging position prediction step of predicting a merging position of the merging vehicle ahead of or behind the target vehicle based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a reliability calculation step of calculating a reliability of the merging position based on movement information of the target vehicle, movement information of the merging vehicle, lane information of the target lane, and lane information of the merging lane; a merging probability calculation step of calculating the merging probability of the merging vehicle in front of the target vehicle and the merging probability of the merging vehicle in rear of the target vehicle based on the merging position and the reliability.

Images