Travel control method and travel control device

By generating a smoother speed profile based on past travel data and setting speed limits, the method addresses the issue of poor ride comfort in automatic driving, ensuring a more comfortable ride by constraining acceleration and jerk.

JP2024170093APending Publication Date: 2024-12-06NISSAN MOTOR CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023087060
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Existing vehicle speed control systems generate speed profiles that are not smooth, leading to increased acceleration and jerk, resulting in poor ride comfort during automatic driving.

Method used

A method that generates a smoother speed profile by comparing the vehicle's own speed with its past travel trajectory and speed profile, setting upper and lower limits, and controlling the vehicle to follow a second speed profile within a defined speed setting area that satisfies acceleration and jerk constraints.

Benefits of technology

This approach ensures a smoother speed profile that aligns with the occupant's intention, providing a more comfortable ride by constraining acceleration and jerk within preset limits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024170093000001_ABST
    Figure 2024170093000001_ABST
Patent Text Reader

Abstract

To generate a smoother speed profile, while taking an advantage of the speed profiler on the basis of a travel track on which a vehicle has traveled in the past and the speed profile of the vehicle on the travel track.SOLUTION: A travel control method includes: generating a first speed profile that is a profile of target speed at a position along a target travel track, on the basis of a travel track on which a vehicle has traveled in the past and a speed profile of the vehicle on the travel track (S3); setting an upper limit profile and a lower limit profile that are profiles of upper limit speed and lower limit speed on the target travel track, on the basis of the first speed profile (S4); and generating a second speed profile that is a profile of target speed on the target travel track so that the profile is set in a speed setting region sandwiched between the upper limit profile and the lower limit profile and a constraint condition for at least one of acceleration and jerk of the vehicle is satisfied (S5).SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a cruise control method and a cruise control device. [Background technology]

[0002] Patent Document 1 below proposes a vehicle driving control device that learns the vehicle speed during past manual driving and sets the driving speed during automatic driving based on the driving speed when driving manually. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-022353 A Summary of the Invention [Problem to be solved by the invention]

[0004] By setting a speed profile of the target vehicle speed for the vehicle using a learning model that has learned the speeds at which the vehicle has been manually driven in the past, the vehicle can be made to travel at a speed close to that intended by the occupant. However, a speed profile generated using a learning model is not necessarily a smooth profile, and there is a risk that acceleration and jerk will increase, resulting in a poor ride. The present invention aims to generate a smoother speed profile while taking advantage of the advantages of a speed profile generated based on the driving trajectory of a vehicle's past travels and the vehicle's speed profile on the driving trajectory. [Means for solving the problem]

[0005] In a driving control method according to one embodiment of the present invention, a host vehicle speed is detected, a target driving trajectory for the host vehicle is set, a first speed profile is generated which is a profile of the target speed at a position along the target driving trajectory based on a driving trajectory when the vehicle has traveled in the past and a speed profile of the vehicle on the driving trajectory, an upper limit profile is set which is a profile of the upper limit speed at a position along the target driving trajectory based on the first speed profile, a lower limit profile is set which is a profile of the lower limit speed at a position along the target driving trajectory, a second speed profile is generated which is a profile of the target speed at a position along the target driving trajectory so as to be set within a speed setting region which is an area sandwiched between the upper limit profile and the lower limit profile and to satisfy predetermined constraint conditions for at least one of the vehicle acceleration and jerk, and the host vehicle is controlled to travel at a vehicle speed that follows the second speed profile along the target driving trajectory. Effect of the Invention

[0006] According to the present invention, it is possible to generate a smoother speed profile while taking advantage of the advantages of a speed profile generated based on the driving trajectory of the vehicle when it was driven in the past and the speed profile of the vehicle on the driving trajectory. [Brief description of the drawings]

[0007] [Figure 1] 1 is a schematic configuration diagram of an example of a driving control device according to an embodiment; [Diagram 2] FIG. 2 is a block diagram illustrating an example of a functional configuration of a controller according to the first embodiment. [Diagram 3] FIG. 2A is a graph showing a schematic example of a first speed profile, and FIG. 2B is a schematic diagram showing an example of a speed setting region and a second speed profile. [Figure 4] 4 is a flowchart of an example of a driving control method according to the first embodiment. [Diagram 5] FIG. 11 is a block diagram illustrating an example of a functional configuration of a controller according to a second embodiment. [Figure 6] FIG. 2 is a schematic diagram illustrating an example of learning data of a learning model. [Figure 7] FIG. 4 is a schematic diagram of an example of a first velocity profile. [Figure 8] 10A and 10B are schematic diagrams illustrating an example of a method for setting a speed setting region width. [Figure 9] FIG. 11 is a schematic diagram illustrating an example of a method for setting a speed setting region. [Figure 10] FIG. 11 is a schematic diagram illustrating an example of a method for setting a speed setting region. [Figure 11] FIG. 11 is a schematic diagram illustrating an example of a method for setting a speed setting region. [Figure 12] 10 is a flowchart of an example of a driving control method according to a second embodiment. [Figure 13] 13(a) and 13(b) are schematic diagrams illustrating an example of a driving control method according to a third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that each drawing is a schematic view and may differ from the actual one. In addition, the embodiment of the present invention shown below is an example of an apparatus and a method for embodying the technical idea of ​​the present invention, and the technical idea of ​​the present invention does not specify the structure, arrangement, etc. of the components as described below. The technical idea of ​​the present invention can be modified in various ways within the technical scope defined by the claims described in the claims.

[0009] (First embodiment) (composition) FIG. 1 is a schematic configuration diagram of an example of a cruise control device according to an embodiment. The host vehicle 1 is equipped with a cruise control device 10 that controls the traveling of the host vehicle 1. The cruise control by the cruise control device 10 includes automatic control that sets a target traveling trajectory based on the shape of the lane on which the host vehicle 1 travels, and controls the acceleration, deceleration, and steering of the host vehicle 1 so that the host vehicle 1 travels along the target traveling trajectory. For example, the cruise control by the cruise control device 10 may be autonomous driving control that automatically drives the host vehicle 1 without the involvement of a driver, based on the traveling environment around the host vehicle 1.

[0010] The driving control device 10 includes an external sensor 11, a vehicle sensor 12, a positioning device 13, a map database (map DB) 14, a navigation device 15, an actuator 17, and a controller 18. The external sensor 11 includes a plurality of different types of object detection sensors mounted on the vehicle 1, such as a laser radar, a millimeter wave radar, a camera, and a LIDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging) that detect objects around the vehicle 1.

[0011] The vehicle sensor 12 is mounted on the host vehicle 1 and detects various information (vehicle signals) obtained from the host vehicle 1. The vehicle sensor 12 includes, for example, a vehicle speed sensor that detects the vehicle speed of the host vehicle 1, a wheel speed sensor that detects the rotational speed of the tires of the host vehicle 1, an acceleration sensor that detects the lateral acceleration Gy and longitudinal acceleration Gx of the host vehicle 1, a steering angle sensor that detects the steering angle of the steering wheel, a turning angle sensor that detects the turning angle of the steered wheels, a gyro sensor that detects the angular velocity of the host vehicle 1, a yaw rate sensor that detects the yaw rate, an accelerator sensor that detects the accelerator opening of the host vehicle, and a brake sensor that detects the amount of brake operation by the driver.

[0012] The positioning device 13 includes a Global Navigation System (GNSS) receiver and receives radio waves from multiple navigation satellites to measure the current position of the vehicle 1. The GNSS receiver may be, for example, a Global Positioning System (GPS) receiver. The positioning device 13 may be, for example, an inertial navigation system. The map database 14 stores road map data. For example, the map database 14 may store high-precision map data (hereinafter simply referred to as "high-precision map") suitable as map information for autonomous driving. The map database 14 may also store map data for navigation (hereinafter simply referred to as "navigation map").

[0013] The navigation device 15 recognizes the current position of the vehicle 1 using the positioning device 13, and obtains map information for the current position from the map database 14. The navigation device 15 sets a target route to the destination input by the occupant, and provides route guidance to the occupant along this target route. The navigation device 15 also outputs information on the set target route to the controller 18. When executing autonomous driving control, the controller 18 automatically drives the vehicle 1 so that it travels along the target route set by the navigation device 15.

[0014] The actuator 17 operates the steering wheel, accelerator opening and braking device of the host vehicle in response to control signals from the controller 18 to generate vehicle behavior of the host vehicle. The actuator 17 includes a steering actuator, an accelerator opening actuator and a brake control actuator. The steering actuator controls the steering direction and steering amount of the host vehicle. The accelerator opening actuator controls the accelerator opening of the host vehicle. The brake control actuator controls the braking operation of the braking device of the host vehicle.

[0015] The controller 18 is an electronic control unit that controls the running of the host vehicle 1. The controller 18 includes a processor 18a and peripheral components such as a storage device 18b. The processor 18a may be, for example, a CPU or an MPU. The storage device 18b may include a semiconductor storage device, a magnetic storage device, an optical storage device, etc. The storage device 18b may include memories such as a register, a cache memory, and a ROM and a RAM used as a main storage device.

[0016] The functions of the controller 18 described below are realized, for example, by the processor 18a executing a computer program stored in the storage device 18b. The controller 18 may be formed of dedicated hardware for executing each information processing described below. For example, the controller 18 may include a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the controller 18 may include a PLD such as an FPGA.

[0017] 2 is a block diagram showing an example of a functional configuration of the controller 18 according to the first embodiment. The controller 18 includes a target running trajectory setting unit 30, a first speed profile generating unit 31, a speed setting region setting unit 32, a second speed profile generating unit 33, and a vehicle control unit 34. The target driving trajectory setting unit 30 sets a target driving trajectory, which is a target value of a trajectory along which the host vehicle 1 should travel in the driving lane ahead of the host vehicle 1. The target driving trajectory setting unit 30 outputs the set target driving trajectory to the first speed profile generating unit 31 and the vehicle control unit 34.

[0018] For example, the target driving trajectory setting unit 30 may detect the shape of the lane ahead of the vehicle 1 based on images captured by the camera of the external sensor 11 or distance measurement data from a distance measuring device such as a laser radar, millimeter wave radar, or LIDAR. For example, the target driving trajectory setting unit 30 may set the target driving trajectory by inputting the detected lane shape ahead of the vehicle 1 into a learning model that has learned the lane shapes and driving trajectories of lanes on which the vehicle has been manually driven in the past.

[0019] The first speed profile generation unit 31 generates a first speed profile, which is a profile representing each target speed at a position along the target driving trajectory, based on the driving trajectory when the vehicle traveled in the past and the speed profile of the vehicle on the driving trajectory. 3(a), the dashed line Vt indicates the speed profile of the vehicle when it traveled in the past. The speed profile is a time series of the vehicle speed with respect to the travel position (travel distance) or travel time of the vehicle. Moreover, the circular plots Va0 to Va11 are a first speed profile indicating the target speeds at the positions P0 to P11 along the target travel trajectory.

[0020] In this specification, the embodiments are described using a time series of the vehicle speed with respect to the travel position as the speed profile, but a time series of the vehicle speed with respect to the travel time may also be used as the speed profile. For example, the first speed profile generating unit 31 may have a learning model 31a that has learned the travel path, vehicle speed, lateral acceleration and longitudinal acceleration of the vehicle, the detection distance of the lane shape ahead of the vehicle, and the road gradient ahead of the vehicle, and the speed profile of the vehicle on the travel path when the vehicle traveled in the past. For example, the first speed profile generating unit 31 may have a learning model 31a that has learned when the vehicle traveled in the past under manual driving. The learning data of the learning model 31a (driving trajectory, vehicle speed, lateral acceleration, longitudinal acceleration, lane shape detection distance, road gradient, speed profile) may be data obtained when the host vehicle 1 is driven manually, or may be data obtained when a vehicle other than the host vehicle 1 is driven manually.

[0021] For example, the learning model 31a may be a multi-layered neural network including at least an input layer and an output layer. For example, when the target driving trajectory set by the target driving trajectory setting unit 30, the vehicle speed, lateral acceleration Gy, and vertical acceleration Gx of the vehicle 1 detected by the vehicle sensor 12, the calculation result of the detection distance of the lane shape, and information on the road gradient are input to the input layer, the learning model 31a outputs the learned speed history as first speed profiles Va0 to Va11 from the output layer. In the following description, the first speed profiles Va0 to Va11 may be collectively referred to as "first speed profile Va".

[0022] For example, the input layer receives the X coordinates (coordinates in the lane direction) and Y coordinates (coordinates in the lane width direction) of 30 passing points at approximately equal intervals on the target driving trajectory in a 70 m section of the driving lane ahead of the vehicle 1, the vehicle speed, the lateral acceleration Gy, and the longitudinal acceleration Gx, the calculation results of the detection distance of the lane shape, and information on the road gradient. For example, the first speed profile generating unit 31 may calculate the detection distance of the lane shape based on the detection result of the lane boundary line by the external sensor 11. Furthermore, for example, the first speed profile generating unit 31 may calculate the detection distance of the lane shape based on the curvature of the front of the traveling lane of the host vehicle 1 stored in the map database 14. The first speed profile generating unit 31 may obtain information on the road gradient ahead of the host vehicle 1. For example, the first speed profile generating unit 31 may obtain the information on the road gradient from the map database 14. The output layer outputs the target speed at each of 30 passing points at approximately equal intervals on the target driving trajectory in a predetermined section (eg, 70 m) ahead of the host vehicle 1 as a first speed profile Va.

[0023] When generating the first speed profile Va using such a learning model 31a, a problem may arise in that the speed profile is not smooth, particularly when traveling a route that has not been traveled before, or when the route has been traveled before but the input at the time of learning is significantly different from the input during travel. In addition, the past manual driving data (driving trajectory, vehicle speed, lateral acceleration, vertical acceleration, lane shape detection distance, road gradient, speed profile) to be learned by the learning model 31a may be driving data of the vehicle 1 for each specified section (e.g., 70 m) that includes driving in which the speed change or acceleration is equal to or greater than a specified value.

[0024] 3(a), the horizontal axis indicates the traveling position of the host vehicle 1 along the target traveling trajectory, the vertical axis indicates the target speed, and the circle plots indicate the target speed at positions P0 to P11 along the target traveling trajectory. Note that position P0 is the current position of the host vehicle 1, and the target speed at position P0 is restricted to the current host vehicle speed Va0 detected by the vehicle speed sensor.

[0025] Also, for example, the first speed profile generating unit 31 may generate a speed profile along which the vehicle has traveled in the past as the first speed profile Va. The speed profile along which the vehicle has traveled in the past may be, for example, a speed profile along which the vehicle has traveled in the case of being driven manually, or may be a speed profile along which the vehicle has traveled with driving assistance that assists in speed control and acceleration / deceleration control of the vehicle.

[0026] With reference to Fig. 2, the speed setting region setting unit 32 sets an upper limit profile PU, which is a profile of an upper limit speed, and a lower limit profile PL, which is a profile of a lower limit speed, at positions P0 to P11 along the target traveling trajectory, based on the first speed profile Va set by the first speed profile generating unit 31. The dashed lines PU and PL in FIG. 3(b) represent the upper and lower limit profiles, respectively.

[0027] The speed setting region setting unit 32 sets the region between the upper limit profile PU and the lower limit profile PL as the speed setting region Rt. The hatched region Rv in Fig. 3(b) represents the speed setting region between the upper limit profile PU and the lower limit profile PL. The upper limit profile PU forms the upper boundary of the speed setting region Rv, and the lower limit profile PL forms the lower boundary of the speed setting region Rv. That is, the speed setting region setting unit 32 defines the boundary of the speed setting region Rv by the upper limit profile PU and the lower limit profile PL.

[0028] For example, the speed setting region setting unit 32 may alternately allocate the target speeds Va0-Va11 on the first speed profile to the upper limit profile PU and the lower limit profile PL to set a sequence of points of the target speeds forming the upper limit profile PU and the lower limit profile PL. Also, for example, the speed setting region setting unit 32 may allocate, among the target speeds Va0-Va11 on the first speed profile, a target speed higher than an actual speed profile Vt when the vehicle traveled in the past to the upper limit profile PU, and allocate a target speed lower than the speed profile Vt to the lower limit profile PL to set a sequence of points forming the upper limit profile PU and the lower limit profile PL.

[0029] The speed setting region setting unit 32 may generate the upper limit profile PU based on the sequence of points assigned to the upper limit profile PU, and may generate the lower limit profile PL based on the sequence of points assigned to the lower limit profile PL. For example, the upper limit profile PU may be generated by connecting the sequence of points assigned to the upper limit profile PU with a straight line, and the lower limit profile PL may be generated by connecting the sequence of points assigned to the lower limit profile PL with a straight line. Alternatively, the upper limit profile PU may be generated by forming an approximation curve or an approximation line based on the sequence of points assigned to the upper limit profile PU, and the lower limit profile PL may be generated by forming an approximation curve or an approximation line based on the sequence of points assigned to the lower limit profile PL.

[0030] Please refer to Fig. 2. The second speed profile generating unit 33 sets, within the speed setting region Rv set by the speed setting region setting unit 32, a second speed profile which is a profile of the target speed at positions along the target travel trajectory. At this time, the second speed profile generating unit 33 generates the second speed profile so as to satisfy a preset constraint condition for at least one of the acceleration and the jerk of the host vehicle 1. The solid line Vb in Fig. 3(b) represents the second speed profile set within the speed setting region Rv. The vehicle control unit 34 generates a control signal for the actuator 17 so that the vehicle 1 travels at a vehicle speed that conforms to the second speed profile Vb along the target travel trajectory generated by the target travel trajectory setting unit 30, and outputs the generated control signal to the actuator 17.

[0031] In this way, by setting the second speed profile Vb within the speed setting region Rv that is set based on the first speed profile Va, the advantages of the first speed profile Va generated by the learning model 31a that has learned the traveling speed when the vehicle was manually driven in the past can be utilized for the second speed profile Vb. For example, a vehicle speed profile close to the intention of the occupant can be generated. Moreover, by generating the second velocity profile Vb so that at least one of the acceleration and the jerk of the host vehicle 1 satisfies a preset constraint condition, a smooth second velocity profile Vb can be generated.

[0032] (operation) FIG. 4 is a flowchart of an example of the driving control method according to the first embodiment. In step S1, the vehicle speed sensor of the vehicle sensor 12 detects the current host vehicle speed Va0 of the host vehicle 1. In step S2, the target driving trajectory setting unit 30 sets a target driving trajectory for the driving lane ahead of the host vehicle 1. In step S3, the first speed profile generating unit 31 generates a first speed profile Va by inputting the target driving trajectory set by the target driving trajectory setting unit 30 and the current vehicle speed Va0 to the learning model 31a.

[0033] In step S4, the speed setting region setting unit 32 sets a speed setting region Rv based on the first speed profile Va. In step S5, the second speed profile generating unit 33 generates a second speed profile Vb that is set within the speed setting region Rv and satisfies a preset constraint condition for at least one of the acceleration and jerk of the host vehicle 1. In step S6, the vehicle control unit 34 controls the host vehicle 1 so that the host vehicle 1 travels along the target travel trajectory at a vehicle speed that conforms to the second speed profile Vb, after which the process ends.

[0034] Second embodiment 5 is a block diagram of an example of the functional configuration of the controller 18 of the second embodiment. The controller 18 of the second embodiment has a configuration similar to that of the controller 18 of the first embodiment, and the same or similar components are given the same reference numerals and redundant explanations are omitted. The controller 18 of the second embodiment includes an allowable upper limit speed setting unit 35.

[0035] As described above, the learning model 31a is a learning model that learns the driving trajectory when the vehicle was driven manually in the past and the speed profile of the vehicle on the driving trajectory. The learning model 31a may be configured by, for example, a neural network, a random forest, a support vector machine, or the like.

[0036] 6(a) is a schematic diagram for explaining an example of learning data of the learning model 31a. For example, when the vehicle was driven manually in the past, position data of positions p0 to p11 on a travel trajectory of a predetermined length L along which the vehicle actually traveled is acquired. For example, the positions p0 and p11 may be the start point and end point of the travel trajectory of the predetermined length L, and the positions p0 to p11 may be positions at equal intervals on the travel trajectory. The acquired position data of the positions p0 to p11 is trained by the learning model 31a as learning data of the travel trajectory.

[0037] The number of position data on the travel locus of the predetermined length L is not limited to 12, and may be more or less than 12. On the other hand, as learning data of the speed profile Vt of the vehicle on the travel locus, the learning model 31a may learn the vehicle speeds Vt0 to Vt11 of the vehicle at the positions p0 to p11 on the travel locus, respectively.

[0038] The target driving trajectory setting unit 30 sets a target driving trajectory of the host vehicle 1 in the driving lane ahead of the host vehicle 1. The target driving trajectory setting unit 30 outputs the set target driving trajectory to the first speed profile generating unit 31 and the allowable upper limit speed setting unit 35.

[0039] The first speed profile generating unit 31 inputs the target driving trajectory set by the target driving trajectory setting unit 30 and the current vehicle speed Va0 detected by the vehicle speed sensor of the vehicle sensor 12 to a learning model 31a. For example, the first speed profile generating unit 31 may input position data of positions P0 to P11 on a target driving trajectory of a predetermined length L starting from the current position P0 of the vehicle 1 to the learning model 31a as data of the target driving trajectory. The learning model 31a generates a first speed profile in which the target speed at the current position P0 is the current vehicle speed Va0, and the target speeds at the positions P1 to P11 on the target travel path are Va1 to Va11, respectively.

[0040] 7, circular plots Va0 to Va11 represent the first velocity profile Va. The first velocity profile generating unit 31 outputs the first velocity profile Va to the velocity setting range setting unit 32. The allowable upper speed setting unit 35 sets an allowable upper speed at each of the positions P0 to P11 on the target driving trajectory based on the target driving trajectory set by the target driving trajectory setting unit 30. For example, the allowable upper speed setting unit 35 may calculate the curvature of the target driving trajectory at each of the positions P0 to P11, and set the speed at which the lateral acceleration generated in the host vehicle 1 at each of the positions P0 to P11 becomes a predetermined upper limit value as the allowable upper speed.

[0041] The speed setting region setting unit 32 of the second embodiment includes a region width setting unit 32a and a region boundary setting unit 32b. The region width setting unit 32a sets the speed setting region width W, which is the width of the speed setting region Rv, based on the magnitude of the time series fluctuation of the first speed profile Va. For example, the region width setting unit 32a may set the speed setting region width W based on the smoothness of the first speed profile Va. For example, the speed setting region width W may be larger when the first speed profile Va is not smooth, compared to the speed setting region width W when the first speed profile Va is smoother.

[0042] For example, the region width setting unit 32a may select a plurality of points from among the points Va0 to Va11 on the first speed profile Va, and generate an approximation line of these plurality of points. Then, the speed setting region width W may be set based on the distance from the points on the first speed profile Va to the approximation line. For example, the speed setting region width W may be set based on a statistical value (maximum value, average value, median value, etc.) of the distance from the points on the first speed profile Va to the approximation line.

[0043] FIG. 8 is a schematic diagram for explaining an example of a method for setting the speed setting region width W based on an approximation line of a plurality of points on the first speed profile Va. In FIG. For example, the region width setting unit 32a sets a plurality of groups each including three adjacent points among the points Va0 to Va11 on the first speed profile Va. In the following description, each of the points Va0 to Va11 on the first speed profile Va may be referred to as a "profile point."

[0044] In the example of FIG. 8, a group consisting of profile points Va0, Va1, and Va2, a group consisting of profile points Va1, Va2, and Va3, a group consisting of profile points Va2, Va3, and Va4, a group consisting of profile points Va3, Va4, and Va5, a group consisting of profile points Va4, Va5, and Va6, a group consisting of profile points Va5, Va6, and Va7, a group consisting of profile points Va6, Va7, and Va8, a group consisting of profile points Va7, Va8, and Va9, a group consisting of profile points Va8, Va9, and Va10, and a group consisting of profile points Va9, Va10, and Va11 are set.

[0045] The area width setting unit 32a calculates a straight line connecting the first point and the third point at both ends of three adjacent profile points, and calculates the distance from a second point sandwiched between the first point and the third point to the straight line connecting the first point and the third point. 8, for a group consisting of profile points Va0, Va1, and Va2, a straight line La1 is calculated connecting the first point Va0 and the third point Va2, and a distance D1 is calculated from the second point Va1 to the straight line La1. For a group consisting of profile points Va1, Va2, and Va3, a straight line La2 is calculated connecting the first point Va1 and the third point Va3, and a distance D2 is calculated from the second point Va2 to the straight line La2. Thereafter, distances D3 to D10 are calculated similarly for the remaining groups. The region width setting unit 32a sets the speed setting region width W based on the statistical values ​​(maximum value, average value, median value, etc.) of the distances D1 to D10 calculated for each group of multiple profile points.

[0046] The region boundary setting unit 32b sets an upper limit profile PU that forms the upper boundary line of the speed setting region Rv and a lower limit profile PL that forms the lower boundary line of the speed setting region Rv based on the speed setting region width W set by the region width setting unit 32a and the first speed profile Va. FIG. 9 is a schematic diagram for explaining an example of a method for setting boundary points that form the upper limit profile PU and the lower limit profile PL.

[0047] First, the region boundary setting unit 32b sets each profile point Va1 to Va11 (circle plot) on the first speed profile Va as a first boundary point, which is either one of the boundary points that define the upper and lower limits of the speed setting region Rv (i.e., the boundary point that forms the upper limit profile PU and the boundary point that forms the lower limit profile PL). However, the profile point Va0 at the current position P0 of the host vehicle 1 is set as a constraint point (boundary condition) of the second speed profile Vb at the current position P0.

[0048] Next, the region boundary setting unit 32b sets a group of at least three profile points (circle plots) on the first velocity profile Va, and generates an approximation line (dashed line) of at least three profile points included in the group. The region boundary setting unit 32b sets a point (square plot) obtained by moving each of the at least three profile points by the speed setting region width W in each direction toward the approximation line from these profile points as a second boundary point, which is the other of the boundary points that define the upper and lower limits of the speed setting region Rv.

[0049] 9, for a group of three profile points Va0, Va1, and Va2, an approximation line Lb1 between the profile points Va0, Va1, and Va2 is calculated. For example, the region boundary setting unit 32b may calculate the approximation line Lb1 based on the least squares method. The region boundary setting unit 32b sets a point Vb1 (square plot) obtained by moving the profile point Va1 by the speed setting region width W in the direction from the profile point Va1 toward the approximation line Lb1 as the second boundary point. Moreover, the region boundary setting unit 32b sets a point Vb2 obtained by moving the profile point Va2 by the speed setting region width W in the direction from the profile point Va2 toward the approximation line Lb1 as a second boundary point.

[0050] Similarly, for a group of three profile points Va3, Va4, and Va5, an approximation straight line Lb2 of the profile points Va3, Va4, and Va5 is calculated. The region boundary setting unit 32b sets a point Vb3 obtained by moving the profile point Va3 by the speed setting region width W in a direction from the profile point Va3 toward the approximation line Lb2 as the second boundary point. The region boundary setting unit 32b sets a point Vb4 obtained by moving the profile point Va4 by the speed setting region width W in a direction from the profile point Va4 toward the approximation line Lb2 as the second boundary point. The region boundary setting unit 32b sets a point Vb5 obtained by moving the profile point Va5 by the speed setting region width W in a direction from the profile point Va5 toward the approximation line Lb2 as the second boundary point.

[0051] Similarly, for a group of three profile points Va6, Va7, and Va8, an approximation line Lb3 of the profile points Va6, Va7, and Va8 is calculated. The region boundary setting unit 32b sets a point Vb6 obtained by moving the profile point Va6 by the speed setting region width W in a direction from the profile point Va6 toward the approximation line Lb3 as the second boundary point. The region boundary setting unit 32b sets a point Vb7 obtained by moving the profile point Va7 by the speed setting region width W in a direction from the profile point Va7 toward the approximation line Lb3 as the second boundary point. The region boundary setting unit 32b sets a point Vb8 obtained by moving the profile point Va8 by the speed setting region width W in a direction from the profile point Va8 toward the approximation line Lb3 as the second boundary point.

[0052] Similarly, for a group of three profile points Va9, Va10, and Va11, an approximation line Lb4 of the profile points Va9, Va10, and Va11 is calculated. The region boundary setting unit 32b sets a point Vb9 obtained by moving the profile point Va9 by the speed setting region width W in a direction from the profile point Va9 toward the approximation line Lb4 as the second boundary point. The region boundary setting unit 32b sets a point Vb10 obtained by moving the profile point Va10 by the speed setting region width W in a direction from the profile point Va10 toward the approximation line Lb4 as the second boundary point. The region boundary setting unit 32b sets a point Vb11 obtained by moving the profile point Va11 by the speed setting region width W in a direction from the profile point Va11 toward the approximation line Lb4 as the second boundary point.

[0053] The area boundary setting unit 32b sets the larger of the first boundary point and a second boundary point set by moving the first boundary point as an upper boundary point, and sets the smaller of the first boundary point as a lower boundary point. The region boundary setting unit 32b sets an upper limit profile PU by connecting upper limit boundary points, and sets a lower limit profile PL by connecting lower limit boundary points, thereby setting a speed setting region Rv as shown in FIG.

[0054] In addition, the profile points Va1 to Va11 on the first speed profile Va, or the points Vb1 to Vb11 obtained by moving the profile points Va1 to Va11 by the speed setting region width W as described above, may exceed the allowable upper limit speed set by the target running trajectory setting unit 30. 11 shows an example in which the profile point Va4 or a point Vb9 obtained by moving the profile point Va9 exceeds the allowable upper limit speed VaU set by the target driving trajectory setting unit 30. In such a case, the area boundary setting unit 32b may set the allowable upper limit speed VaU at position P4 as a first boundary point Vc4 at position P4, and may set the allowable upper limit speed VaU at position P9 as a second boundary point Vc9 at position P9.

[0055] 5, the second speed profile generating unit 33 generates a second speed profile Vb within the speed setting region Rv set by the speed setting region setting unit 32. For example, the second speed profile generation unit 33 may generate a second speed profile Vb in which at least one of the acceleration and jerk of the vehicle 1 satisfies a predetermined constraint condition, or in which both of the acceleration and jerk of the vehicle 1 satisfy predetermined constraint conditions.

[0056] The constraint condition regarding the acceleration may be, for example, that an evaluation function including the acceleration of the host vehicle 1 as a variable is a minimum value, or may be a value within a predetermined allowable range. Similarly, the constraint condition regarding the jerk may be, for example, that an evaluation function including the jerk of the host vehicle 1 as a variable is a minimum value, or may be a value within a predetermined allowable range. The second speed profile generating unit 33 may generate the second speed profile Vb that satisfies the constraint conditions, for example, by an optimization calculation method. For example, the second speed profile generating unit 33 may generate the second speed profile Vb by an optimization calculation method so that an evaluation function including the acceleration and jerk of the host vehicle 1 as variables is minimized. Furthermore, for example, the second speed profile generating unit 33 may generate the second speed profile Vb that satisfies the constraint conditions by using a learning model such as a neural network, a random forest, or a support vector machine.

[0057] FIG. 12 is a flowchart of an example of a driving control method according to the second embodiment. In step S11, the vehicle sensor 12 detects the host vehicle speed Va0 of the host vehicle 1. In step S12, the target driving trajectory setting unit 30 sets a target driving trajectory for the driving lane ahead of the host vehicle 1. In step S13, the first speed profile generating unit 31 generates the first speed profile Va by inputting the target driving trajectory and the host vehicle speed Va0 to the learning model 31a.

[0058] In step S14, the region width setting section 32a of the speed setting region setting unit 32 sets a speed setting region width W. In step S15, the region boundary setting unit 32b sets boundary points of the speed setting region Rv based on the first speed profile Va and the speed setting region width W, thereby setting the speed setting region Rv. In step S16, the second speed profile generating unit 33 generates the second speed profile Vb. In step S17, the vehicle control unit 34 controls the host vehicle 1 so that the host vehicle 1 travels along the target travel trajectory at a vehicle speed that conforms to the second speed profile Vb, after which the process ends.

[0059] Third embodiment The controller 18 of the third embodiment generates a second speed profile Vb within a speed setting region Rv in a section where the first speed profile Va generated by the first speed profile generating unit 31 is not smooth, and generates the second speed profile Vb so as to pass through points on the first speed profile Va in a section where the first speed profile Va is smooth. The controller 18 of the third embodiment has a similar configuration to the controller 18 of the first and second embodiments, and the same or similar components are given the same reference symbols and overlapping descriptions are omitted.

[0060] 13(a), the speed setting region setting unit 32 generates an approximation line (dashed line) Lc of a plurality of profile points on the first speed profile Va. A first section is set in which the distance D from the profile points on the first speed profile Va to the approximation line is equal to or greater than a threshold, and a second section is set in which the distance D is less than the threshold. In the first section, the first velocity profile Va has a relatively non-smooth shape, and in the second section, the first velocity profile Va has a relatively smooth shape.

[0061] 13A, a group of three profile points on the first velocity profile Va is set, and an approximation line Lc of the three profile points included in the group is generated. For example, a group consisting of profile points Va0, Va1, and Va2, a group consisting of profile points Va3, Va4, and Va5, a group consisting of profile points Va5, Va6, and Va7, a group consisting of profile points Va7, Va8, and Va9, and a group consisting of profile points Va9, Va10, and Va11 are set.

[0062] The speed setting region setting unit 32 calculates a distance D from a profile point on the first target driving trajectory to the approximation line Lc, and sets first sections Sa1, Sa2, and Sa3 where the distance D is equal to or greater than a threshold, and second sections Sb1 and Sb2 where the distance D is less than the threshold. The second speed profile generating unit 33 generates the second speed profile Vb so as to travel within the speed setting region Rv in the first sections Sa1, Sa2, and Sa3, and generates the second speed profile Vb so as to pass through points on the first speed profile Va in the second sections Sb1 and Sb2. Note that the speed setting region setting unit 32 may omit setting the speed setting region Rv in the second sections Sb1 and Sb2.

[0063] (Effects of the embodiment)

[0064] (1) The vehicle sensor 12 detects the host vehicle speed, which is the vehicle speed of the host vehicle 1. The controller 18 sets a target travel trajectory for the host vehicle 1, generates a first speed profile Va, which is a profile of the target speed at a position along the target travel trajectory, based on a travel trajectory when the vehicle traveled in the past and a speed profile of the vehicle on the travel trajectory, sets an upper limit profile PU, which is a profile of the upper limit speed, and a lower limit profile PL, which is a profile of the lower limit speed, at a position along the target travel trajectory, based on the first speed profile Va, generates a second speed profile Vb, which is a profile of the target speed at a position along the target travel trajectory, set within a speed setting region Rv, which is a region sandwiched between the upper limit profile PU and the lower limit profile PL, and satisfies a constraint condition previously set for at least one of the acceleration and jerk of the host vehicle 1, and controls the host vehicle 1 to travel at a vehicle speed according to the second speed profile Vb along the target travel trajectory. For example, a first speed profile Va, which is a profile of the target speed at a position along the target driving trajectory, may be generated by inputting the target driving trajectory and the vehicle speed into a learning model 31a that has learned the driving trajectory and the vehicle speed profile on the driving trajectory when the vehicle was driven manually in the past.

[0065] In this way, by setting the second speed profile Vb within the speed setting region Rv that is set based on the first speed profile Va, the advantages of the first speed profile Va generated by the learning model 31a that has learned the traveling speed when the vehicle was manually driven in the past can be utilized for the second speed profile Vb. For example, a vehicle speed profile close to the intention of the occupant can be generated. Moreover, by generating the second velocity profile Vb so that at least one of the acceleration and the jerk of the host vehicle 1 satisfies a preset constraint condition, a smooth second velocity profile Vb can be generated.

[0066] (2) The controller 18 may generate the second speed profile Vb so that an evaluation function including at least one of the acceleration and the jerk of the host vehicle 1 as a variable as a constraint condition becomes minimum or is less than a threshold value. This makes it possible to generate the second speed profile Vb, which is smooth and provides a comfortable ride.

[0067] (3) The controller 18 may set the speed setting region width W, which is the width of the speed setting region Rv, based on the shape of the first speed profile Va. For example, the controller 18 may generate an approximation line of a plurality of points on the first speed profile Va, and set the speed setting region width W based on the distance from the points on the first speed profile Va to the approximation line.

[0068] For example, the controller 18 may set multiple groups including three adjacent points on the first speed profile Va, calculate the distance from a second point, which is between the first and third points among the three adjacent points, to a straight line connecting the first and third points for each group, and set the speed setting region width W based on the maximum distance from the second point to the straight line connecting the first and third points. This makes it possible to set the width of the speed setting region Rv wider for sections where the first speed profile Va is less smooth, thereby increasing the degree of freedom of the passing points of the second speed profile Vb and generating a smooth second speed profile Vb.

[0069] (4) The controller 18 may generate an approximation line of at least three points on the first speed profile Va, and may set the points obtained by moving each of the at least three points by the speed setting region width W in each direction from these points toward the approximation line as boundary points of the speed setting region Rv. For example, the controller 18 may set a point on the first speed profile Va as a first boundary point, which is either one of the upper and lower limit boundary points of the speed setting region Rv, and may set points obtained by moving each of at least three points by the speed setting region width W in each direction toward the approximation line from these points as a second boundary point, which is the other of the upper and lower limit boundary points of the speed setting region Rv. This makes it possible to set the speed setting region Rv having a shape that has characteristics roughly similar to the shape of the first speed profile Va. Also, the speed setting region width W of the speed setting region Rv can be adjusted according to the smoothness of the first speed profile Va.

[0070] (5) When the vehicle speed at the boundary point exceeds the permissible upper limit speed, the controller 18 may correct the vehicle speed to the permissible upper limit speed. Furthermore, when the vehicle speed at the first boundary point or the second boundary point exceeds the permissible upper limit speed, the controller 18 may correct it to the permissible upper limit speed. This makes it possible to prevent the generation of the second speed profile Vb that exceeds the allowable upper limit speed.

[0071] (6) The controller 18 may generate an approximation line of multiple points on the first speed profile Va, set a first section in which the distance from the points on the first speed profile Va to the approximation line is equal to or greater than a threshold, and a second section in which the distance is less than the threshold, generate a second speed profile Vb within the speed setting region Rv in the first section, and generate a second speed profile Vb that passes through the points on the first speed profile Va in the second section. As a result, in a section where the first speed profile Va is smooth, a speed profile closer to the first speed profile Va is generated as the second speed profile Vb, so that the host vehicle 1 can travel according to a target speed that more closely matches the intention of the occupant. Also, in a section where the first speed profile Va is smooth, calculation of the speed setting region Rv can be omitted, so that the calculation load of the controller 18 can be reduced.

[0072] (7) The learning model 31a may be a neural network that has learned a driving trajectory when the vehicle was driven manually in the past, a speed profile of the vehicle on the driving trajectory, and the lateral and longitudinal accelerations of the vehicle. The controller 18 may generate the first speed profile Va by inputting the target driving trajectory, the host vehicle speed, and the lateral and longitudinal accelerations of the host vehicle 1 to the neural network. This allows a speed profile to be generated by predicting the target speed intended by the occupant.

[0073] (12) The learning model 31a may be a neural network that has learned a driving trajectory when the vehicle was driven manually in the past, a speed profile of the vehicle on the driving trajectory, and a detection distance of the lane shape ahead of the vehicle. The controller 18 may generate the first speed profile Va by inputting the target driving trajectory, the host vehicle speed, and the detection distance of the lane shape ahead of the host vehicle 1 to the neural network. This makes it possible to generate an optimal speed profile according to the detection distance of the lane shape.

[0074] (13) The learning model 31a may be a neural network that has learned a driving trajectory when the vehicle was manually driven in the past, a speed profile of the vehicle on the driving trajectory, and a road gradient ahead of the vehicle. The controller 18 may generate the first speed profile Va by inputting the target driving trajectory, the host vehicle speed, and the road gradient ahead of the host vehicle 1 to the neural network. This allows the generation of an optimal speed profile according to the road gradient. [Explanation of symbols]

[0075] 1... host vehicle, 10... cruise control device, 11... external sensor, 12... vehicle sensor, 13... positioning device, 14... map database, 15... navigation device, 17... actuator, 18... controller, 18a... processor, 18b... storage device, 30... target travel trajectory setting unit, 31... first speed profile generation unit, 31a... learning model, 32... speed setting region setting unit, 32a... region width setting unit, 32b... region boundary setting unit, 33... second speed profile generation unit, 34... vehicle control unit, 35... allowable upper limit speed setting unit

Claims

1. Detecting a vehicle speed, which is a speed of the vehicle; A target travel trajectory of the host vehicle is set; generating a first speed profile which is a profile of a target speed at a position along the target travel path based on a travel path of the vehicle in the past and a speed profile of the vehicle on the travel path; Based on the first speed profile, an upper limit profile which is a profile of an upper limit speed and a lower limit profile which is a profile of a lower limit speed at a position along the target travel path are set; generating a second speed profile, which is a profile of a target speed at a position along the target travel trajectory, set within a speed setting region that is a region between the upper limit profile and the lower limit profile and so as to satisfy a preset constraint condition for at least one of the acceleration and jerk of the host vehicle; controlling the host vehicle so as to travel along the target travel trajectory at a vehicle speed that conforms to the second speed profile; A driving control method comprising:

2. The cruise control method according to claim 1, characterized in that the second speed profile is generated so that an evaluation function including at least one of an acceleration and a jerk of the host vehicle as a variable as the constraint condition is minimized or is less than a threshold value.

3. 2. The cruise control method according to claim 1, further comprising the step of: setting a speed setting region width, which is a width of the speed setting region, based on a shape of the first speed profile.

4. generating an approximation line of a plurality of points on the first velocity profile; setting the speed setting region width based on a distance from a point on the first speed profile to the approximation straight line; 4. The method of claim 3, wherein the vehicle speed is controlled by the vehicle speed sensor.

5. Setting a plurality of groups each including three adjacent points on the first velocity profile; calculating, for each group, a distance from a second point between the first point and the third point among the three adjacent points to a straight line connecting the first point and the third point; setting the speed setting region width based on the maximum value of the distance from the second point to a straight line connecting the first point and the third point; 5. The method of claim 4, wherein the vehicle speed is controlled by the vehicle speed sensor.

6. generating an approximation line of at least three points on the first velocity profile; a point obtained by moving each of the at least three points in a direction toward the approximation line by the speed setting region width from each of the at least three points is set as a boundary point of the speed setting region; 4. The method of claim 3, wherein the vehicle speed is controlled by the vehicle speed sensor.

7. A point on the first speed profile is set as a first boundary point, which is either one of an upper limit boundary point and a lower limit boundary point of the speed setting region; a second boundary point, which is the other of the upper and lower boundary points of the speed setting region, is set by moving each of the at least three points in a direction toward the approximation line by the speed setting region width from each of the at least three points; 7. The method of claim 6, wherein the vehicle speed is controlled by the vehicle speed sensor.

8. 7. The cruise control method according to claim 6, wherein when the vehicle speed at the boundary point exceeds an allowable upper limit speed, the vehicle speed is corrected to the allowable upper limit speed.

9. 8. The cruise control method according to claim 7, wherein when the vehicle speed at the first boundary point or the second boundary point exceeds an allowable upper limit speed, the vehicle speed is corrected to the allowable upper limit speed.

10. generating an approximation line of a plurality of points on the first velocity profile; a first section in which a distance from a point on the first speed profile to the approximation line is equal to or greater than a threshold, and a second section in which the distance is less than the threshold; The second speed profile is generated within the speed setting region in the first section; generating a second velocity profile that passes through points on the first velocity profile in the second section; 2. The method of claim 1, wherein the vehicle speed is controlled by the vehicle speed sensor.

11. The driving control method according to claim 1, characterized in that the first speed profile is generated by inputting the target driving trajectory and the vehicle speed into a learning model that learns a driving trajectory when the vehicle has driven in the past and a speed profile of the vehicle on the driving trajectory.

12. A sensor for detecting a host vehicle speed, which is a vehicle speed of the host vehicle; a controller that sets a target travel trajectory for the host vehicle, generates a first speed profile which is a profile of a target speed at a position along the target travel trajectory based on a travel trajectory when the vehicle has traveled in the past and a speed profile of the vehicle on the travel trajectory, sets an upper limit profile which is a profile of an upper limit speed and a lower limit profile which is a profile of a lower limit speed at a position along the target travel trajectory based on the first speed profile, generates a second speed profile which is a profile of the target speed at a position along the target travel trajectory, the second speed profile being set within a speed setting region which is a region sandwiched between the upper limit profile and the lower limit profile and satisfying a preset constraint condition for at least one of the acceleration and jerk of the host vehicle, and controls the host vehicle to travel at a vehicle speed in accordance with the second speed profile along the target travel trajectory; A driving control device comprising:

Citation Information

Patent Citations

  • Vehicle travel control device, vehicle travel control system, and vehicle travel control method

    JP2018022353A