Orbit generation device and orbit generation method

Abstract

The technology disclosed in this specification is a technology for suppressing excessive constraints in the trajectory setting of a moving body. A trajectory generation device related to the technology disclosed in this specification includes a constraint condition setting unit for setting constraint conditions that a moving body passing through a trajectory should satisfy, and a trajectory generation unit for generating a trajectory through which the moving body passes so as to satisfy the constraint conditions. And the constraint conditions include those set based on the probability of the state of the moving body that should satisfy predetermined conditions.

Description

Technical Field

[0001] The technology disclosed in this specification relates to a trajectory generation technology for a moving body.

Background Art

[0002] A method of generating a trajectory of a moving body in consideration of the probability of an event that may occur in the future has been proposed. For example, Patent Document 1 discloses a method of probabilistically calculating the future behavior of an obstacle and calculating an optimal trajectory of the host vehicle.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When the constraint conditions imposed during trajectory setting include an event with a low probability of occurrence, the opportunity for the host vehicle (moving body) to perform the target behavior decreases, impairing the freedom of movement of the moving body and the comfort of the passengers.

[0005] The technology disclosed in this specification has been made in view of the problems described above, and is a technology for suppressing excessive constraints in the trajectory setting of a moving body.

Means for Solving the Problems

[0006] A trajectory generation device according to a first aspect of the technology disclosed in this specification includes a constraint condition setting unit for setting constraint conditions that a moving body passing through a trajectory should satisfy, and a trajectory generation unit for generating the trajectory through which the moving body passes so as to satisfy the constraint conditions, where the constraint conditions include those set based on the probability of the state of the moving body satisfying predetermined conditions. The constraint condition setting unit sets the probability of the state of the moving body in the constraint condition based on the time difference between the current time and the time when the moving body passes through the trajectory generated by the trajectory generation unit 。

Advantages of the Invention

[0007] According to at least the first aspect of the technology disclosed in the present specification, since the trajectory is set so as to satisfy the constraint conditions based on the probability of the state of the moving body, excessive constraints can be suppressed in setting the trajectory of the moving body.

[0008] In addition, the objects, features, aspects, and advantages related to the technology disclosed in the present specification will become clearer by the following detailed description and the accompanying drawings.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments will be described with reference to the accompanying drawings. In the following embodiments, detailed features and the like are also shown for the purpose of explaining the technology, but these are examples, and not all of them are necessarily essential features for the embodiments to be practicable.

[0011] The drawings are schematically shown, and for the convenience of explanation, omissions of components or simplifications of components are made in the drawings as appropriate. Also, the mutual relationships of the sizes and positions of the components shown in different drawings are not necessarily accurately described and can be changed as appropriate. Also, in drawings such as a plan view that is not a cross-sectional view, hatching may be added to facilitate understanding of the content of the embodiments.

[0012] Also, in the descriptions shown below, the same reference numerals are attached to and illustrated for similar components, and their names and functions are also considered the same. Therefore, detailed descriptions thereof may be omitted to avoid duplication.

[0013] Also, in the descriptions described in the present specification, when a component is described as "comprising", "including", or "having", etc., it is not an exclusive expression excluding the existence of other components unless otherwise specified.

[0014] In addition, in the description described in the present specification, even if ordinal numbers such as "first" or "second" are used, these terms are used for convenience in order to facilitate understanding of the content of the embodiment, and the content of the embodiment is not limited to the order that may be caused by these ordinal numbers.

[0015] <Embodiment> Hereinafter, a trajectory generation device and a trajectory generation method according to the present embodiment will be described.

[0016] <Regarding the configuration of the trajectory generation device> FIG. 1 conceptually shows an example of the configuration of a vehicle control system including a trajectory generation device according to the present embodiment.

[0017] As shown in the example of FIG. 1, the vehicle control system 500 includes a vehicle control device 100, an information acquisition unit 200, and a controller unit 300.

[0018] The vehicle control device 100 includes a trajectory generation device 110 and a vehicle control unit 120.

[0019] The trajectory generation device 110 includes a constraint condition setting unit 113 that sets constraint conditions that a moving object such as a vehicle, a robot, or a drone passing through the trajectory should satisfy, and a trajectory generation unit 114 that generates a trajectory through which the moving object passes. In the present embodiment, a vehicle is assumed as the moving object.

[0020] The vehicle control unit 120 controls the operation of the vehicle so as to pass through the trajectory generated by the trajectory generation device 110. Specifically, the vehicle control unit 120 outputs a control signal to the controller unit 300 for controlling the vehicle.

[0021] The information acquisition unit 200 acquires information used when the trajectory generation device 110 generates a trajectory and outputs it to the trajectory generation device 110. The information acquisition unit 200 includes a host vehicle information acquisition unit 210 that acquires information about the host vehicle, an obstacle information acquisition unit 220 that acquires information about obstacles, and a road information acquisition unit 230 that acquires information about the road.

[0022] Based on the control signal input from the vehicle control unit 120, the controller unit 300 controls the operation of the vehicle. The controller unit 300 includes a power train controller 310 that controls a power train unit described later, a brake controller 320 that controls a brake unit described later, and an EPS (Electric Power Steering) controller 330 that steers the front wheels independently of the operation of the driver's steering wheel 2.

[0023] FIG. 2 is a diagram conceptually showing a modification of the configuration of a vehicle control system including a trajectory generation device according to the present embodiment.

[0024] As shown in the example of FIG. 2, the vehicle control system 500A includes a vehicle control device 100A, an information acquisition unit 200, and a controller unit 300.

[0025] The vehicle control device 100A includes a trajectory generation device 110A and a vehicle control unit 120.

[0026] The trajectory generation device 110A includes a constraint condition setting unit 113, a trajectory generation unit 114, and an entry prohibition area setting unit 112 that sets an entry prohibition area.

[0027] As shown in FIG. 2, in the trajectory generation device 110A, the entry prohibition area setting unit 112 may be additionally provided.

[0028] FIG. 3 is a diagram conceptually showing a modification of the configuration of a vehicle control system including a trajectory generation device according to the present embodiment.

[0029] As shown in the example of FIG. 3, the vehicle control system 500B includes a vehicle control device 100B, an information acquisition unit 200, and a controller unit 300.

[0030] The vehicle control device 100B includes a trajectory generation device 110B and a vehicle control unit 120.

[0031] The trajectory generation device 110B includes a constraint condition setting unit 113, a trajectory generation unit 114, an entry prohibited area setting unit 112, and an obstacle movement prediction unit 111 that predicts the movement of obstacles.

[0032] The obstacle movement prediction unit 111 predicts the state quantity of an obstacle at a future time. The state quantity of the obstacle includes at least position information, and in addition, direction, speed, acceleration, yaw rate, etc. are included. Information on the type of behavior such as turning right or left or lane change may be included.

[0033] As shown in FIG. 3, in the trajectory generation device 110B, the entry prohibited area setting unit 112 and the obstacle movement prediction unit 111 may be additionally provided.

[0034] FIG. 4 is a diagram showing an example of the hardware configuration of a host vehicle equipped with the vehicle control system 500 according to the present embodiment.

[0035] As shown by the example in FIG. 4, the host vehicle 1 includes, as a drive system, a steering wheel 2, a steering shaft 3, a steering unit 4, an EPS motor 5, a power train unit 6, and a brake unit 7. The power train unit 6 is, for example, an engine that uses gasoline as fuel.

[0036] In addition, the host vehicle 1 includes, as a sensor system, a front camera 11, a radar sensor 12, a GNSS (Global Navigation Satellite System) sensor 13, a yaw rate sensor 16, a speed sensor 17, an acceleration sensor 18, a steering angle sensor 20, and a steering torque sensor 21.

[0037] Furthermore, the host vehicle 1 includes a V2X (Vehicle to Everything) receiver 15, a vehicle control device 100, an EPS controller 330, a power train controller 310, and a brake controller 320.

[0038] The steering wheel 2 installed for a driver to drive a vehicle is coupled to a steering shaft 3. A steering unit 4 is connected to the steering shaft 3.

[0039] The steering unit 4 rotatably supports two tires of the front wheels as steering wheels and is pivotally supported by the vehicle body frame. Therefore, the torque generated by the driver's operation of the steering wheel 2 rotates the steering shaft 3, and the steering unit 4 steers the front wheels in the left - right direction. By the driver operating the steering wheel 2, the lateral movement of the vehicle during forward and reverse driving can be controlled.

[0040] Note that the steering shaft 3 can also be rotated by an EPS motor 5. The EPS controller 330 can steer the front wheels independently of the driver's operation of the steering wheel 2 by controlling the current flowing through the EPS motor 5.

[0041] The vehicle control device 100 is an integrated circuit such as a microprocessor, also called an ADAS - ECU (Advanced Driving Assistance Systems - Electronic Control Unit) for example, and includes an A / D (Analog / Digital) conversion circuit, a D / A (Digital / Analog) conversion circuit, a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

[0042] Connected to the vehicle control device 100 are a front camera 11, a radar sensor 12, a GNSS sensor 13, a V2X receiver 15, a yaw rate sensor 16 for detecting the yaw rate, a speed sensor 17 for detecting the speed of the host vehicle, an acceleration sensor 18 for detecting the acceleration of the host vehicle, a steering angle sensor 20 for detecting the steering angle, a steering torque sensor 21 for detecting the steering torque, an EPS controller 330, a power train controller 310, and a brake controller 320.

[0043] The vehicle control device 100 processes the information input from various connected sensors according to the program stored in the ROM, transmits the target driving force to the power train controller 310, and transmits the target braking force to the brake controller 320.

[0044] The vehicle control device 100 has a function of calculating an optimal driving route for the destination set by the driver and stores the road information on the driving route. The road information is map node data representing the road alignment and can be obtained from the road information acquisition unit 230. Each map node data incorporates information such as latitude, longitude, altitude, lane width, cant angle, and inclination angle indicating the absolute position at each node.

[0045] The front camera 11 is installed at a position where the lane lines in front of the vehicle can be detected as an image, and detects the front environment of the host vehicle 1 such as lane information and the position of obstacles based on the image information. In the vehicle control system 500 according to the present embodiment, only the camera for detecting the front environment of the host vehicle 1 is shown, but another camera for detecting the rear environment and the side environment of the host vehicle 1 may be provided. Further, the front camera 11 can also be used to estimate the state of the road surface on which the host vehicle 1 travels.

[0046] The radar sensor 12 irradiates a target object with radar and detects its reflected wave, thereby outputting the relative distance and relative speed between the host vehicle 1 and surrounding vehicles. As the radar sensor 12, well-known ranging sensors such as millimeter wave radar, LiDAR (Light Detection and Ranging), laser rangefinder, and ultrasonic radar can be used.

[0047] The GNSS sensor 13 receives radio waves from positioning satellites with an antenna (not shown here) mounted on the host vehicle, and outputs the absolute position and absolute orientation of the host vehicle by performing positioning calculations.

[0048] The V2X receiver 15 has a function of acquiring and outputting information through wireless communication between the host vehicle 1 and other vehicles including surrounding vehicles and roadside units. The information to be acquired includes surrounding vehicle information such as the position and speed of surrounding vehicles relative to the host vehicle 1 and road information such as the friction coefficient of the road surface.

[0049] The EPS controller 330 controls the traveling direction of the host vehicle 1 by controlling the EPS motor 5 so as to realize the target steering angle transmitted from the vehicle control device 100.

[0050] The power train controller 310 controls the acceleration of the host vehicle 1 by controlling the power train unit 6 so as to realize the target accelerating force transmitted from the vehicle control device 100.

[0051] The brake controller 320 controls the deceleration of the host vehicle 1 by controlling the brake unit 7 so as to realize the target braking force transmitted from the vehicle control device 100.

[0052] The host vehicle information acquisition unit 210 acquires vehicle information which is information of the host vehicle 1. The vehicle information includes state quantities of the host vehicle representing the state of the host vehicle 1. The host vehicle information acquisition unit 210 is, for example, the GNSS sensor 13, the yaw rate sensor 16, the speed sensor 17, the acceleration sensor 18, the steering angle sensor 20, the steering torque sensor 21, and the like.

[0053] The obstacle information acquisition unit 220 acquires obstacle information including the position information of surrounding vehicles existing around the host vehicle 1. The obstacle information acquisition unit 220 is, for example, the front camera 11, the radar sensor 12, the V2X receiver 15, and the like.

[0054] The road information acquisition unit 230 acquires road information which is information of the road on which the host vehicle 1 travels. The road information acquisition unit 230 is, for example, the front camera 11, the V2X receiver 15, and the like.

[0055] Note that, as the host vehicle 1 equipped with the vehicle control system 500 according to the present embodiment, a vehicle having only an engine as a driving force source has been shown, but a vehicle having only an electric motor as a driving force source or a vehicle having both an engine and an electric motor as driving force sources may be used.

[0056] In the present embodiment, the trajectory generation unit 114 generates a trajectory through which the moving body passes by solving an optimization problem. However, the trajectory generation unit 114 may generate a trajectory by other methods. For example, a method of generating a trajectory using the center of a road or a path through which another vehicle has passed as a target position, or a method of randomly generating a plurality of candidate paths and selecting one of them using some evaluation index.

[0057] <Setting of Optimization Problem> The trajectory generation unit 114 uses a vehicle model f that mathematically represents the motion of the vehicle to predict the vehicle state quantity x from the current time 0 to the future prediction period Th at time intervals Ts, and solves an optimization problem for obtaining a series of data of the control input u that minimizes the evaluation function J representing the desired operation of the host vehicle under the constraint conditions.

[0058] Then, based on the optimized control input u obtained from the optimization problem and the vehicle model f, a series of data of the optimized vehicle state quantity x from the current time 0 to the future prediction period Th at time intervals Ts is predicted.

[0059] Then, based on the series of data of the optimized control input u and the series of data of the vehicle state quantity x, a trajectory ξ which is a series of data including the position of the host vehicle is generated. In the following description, the time from the current time to the prediction period Th may be abbreviated as a horizon.

[0060] <Formulation of Optimization Problem> As described above, in the present embodiment, a constrained optimization problem is solved at regular intervals. The optimization problem is formulated as follows.

[0061]

Equation

[0062] Here, J is the evaluation function, x is the vehicle state quantity, u is the control input, f is the vector-valued function related to the dynamic vehicle model, and x0 is the initial value (the current vehicle state quantity).

[0063] Here, the above optimization problem is a constrained optimization problem subject to the following constraints to be described later.

[0064] Note that in this embodiment, the above optimization problem is treated as a minimization problem, but it can also be treated as a maximization problem by inverting the sign of the evaluation function.

[0065] In this embodiment, the following equation is used for the evaluation function J.

[0066]

Equation

[0067] Here, x(k) is the vehicle state quantity at the prediction point k (k = 0, ···, N), and u(k) is the control input at the prediction point k (k = 0, ···, N). h is the vector-valued function related to the evaluation item, and h N is the vector-valued function related to the evaluation item at the end (prediction point N), and r(k) is the reference value at the prediction point k (k = 0, ···, N). W, W N are weight matrices, which are diagonal matrices having the weights for the respective evaluation items as diagonal components and can be appropriately changed as parameters.

[0068] <Vehicle Model> In this embodiment, the vehicle state quantity x and the control input u used in the trajectory generation unit 114 are set as follows.

[0069]

Equation

[0070] Here, β is the sideslip angle, γ is the yaw rate, ax is the longitudinal acceleration, δ is the steering angle, axt is the target longitudinal acceleration, and δt is the target steering angle. Also, jt is the target longitudinal jerk, and ωt is the target steering angular velocity. Note that the vehicle state quantity x includes variables related to the position. If variables related to steering and vehicle speed are included in either the vehicle state quantity x or the control input u, the vehicle state quantity x and the control input u can be set in any way. Also, the variable of the position is not limited to the orthogonal coordinate system and may be defined, for example, in the path coordinate system.

[0071] Note that when the vehicle control device 100 performs only steering control, if the vehicle state quantity x includes variables related to the position and variables related to steering are included in either the vehicle state quantity x or the control input u, the vehicle state quantity x and the control input u can be set in any way.

[0072] The vehicle model f uses the following two-wheel model.

[0073]

Equation

[0074] Here, M is the vehicle mass, and I is the yaw moment of inertia of the vehicle. lf and lr are the distances from the axles of the front and rear wheels to the vehicle center of gravity. Tax and Tδ are the time constants when the followability with respect to the target values of the longitudinal acceleration and the steering angle is expressed by a first-order lag system. Yf and Yr are the cornering forces of the front and rear wheels and are expressed by Equations (107) and (108) using the cornering stiffnesses Cf and Cr of the front and rear wheels.

[0075]

Equation

[0076] Note that a vehicle model other than the two-wheel model may be used for the vehicle model f.

[0077] <Operation of the Vehicle Control Device> FIG. 5 is a flowchart showing an example of the procedure of the driving control of the host vehicle according to the present embodiment.

[0078] In step ST110 of FIG. 5, the obstacle information acquisition unit 220 acquires obstacle information. The obstacle information is information including the positions of obstacles including surrounding vehicles. In the present embodiment, when an obstacle exists in the left front of the host vehicle, the positions of the right front end PFR, the right rear end PRR, and the left rear end PRL of the obstacle in the host vehicle coordinate system are acquired. When an obstacle exists in the right front of the host vehicle, the positions of the left front end PFL, the left rear end PRL, and the right rear end PRR of the obstacle in the host vehicle coordinate system are acquired.

[0079] Furthermore, based on those position information, the obstacle information acquisition unit 220 estimates the position of the left front end PFL or the right front end PFR of the obstacle, the position Xo, Yo of the center PC, the vehicle body orientation θo, the vehicle speed Vo, the length lo, and the width wo.

[0080] Next, in step ST120 of FIG. 5, the road information acquisition unit 230 acquires road information. The road information is information including the boundary portions of the road on which the host vehicle travels and the roads adjacent thereto (hereinafter referred to as the host lane, the left lane, and the right lane). In the present embodiment, the coefficients when the left and right dividing lines of the host lane, the left lane, and the right lane are expressed by a cubic polynomial are acquired. That is, for the left dividing line of the host lane (which is also the right dividing line of the left lane), the values of cel0 to cel3 in the following formula are acquired.

[0081]

Equation

[0082] For the right dividing line of the host lane (which is also the left dividing line of the right lane), the values of cer0 to cer3 in the following formula are acquired.

[0083]

Equation

[0084] For the left dividing line of the left lane, the values of cll0 to cll3 in the following formula are acquired.

[0085]

Number

[0086] For the right dividing line of the right lane, the values of crr0 to crr3 in the following formula are obtained.

[0087]

Number

[0088] At this time, the center of the own lane, the center of the left lane, and the center of the right lane are respectively expressed by formula (205), formula (206), and formula (207).

[0089]

Number

[0090] Here, each coefficient is represented by formula (208), formula (209), and formula (210).

[0091]

Number

[0092] Note that the information of the dividing line is not limited to a cubic polynomial and may be expressed by any function.

[0093] In step ST130 of FIG. 5, vehicle information is acquired by the own vehicle information acquisition unit 210. The vehicle information is information such as the steering angle, yaw rate, speed, and acceleration of the own vehicle. In this embodiment, it is assumed that the steering angle δ, yaw rate γ, speed V, and longitudinal acceleration ax are acquired.

[0094] Next, in step ST210 of FIG. 5, the obstacle movement prediction unit 111 (FIG. 3) performs obstacle movement prediction. In the movement prediction, the center position X o (k), Yo (k), vehicle body orientation θ o (k), vehicle speed V o (k) is predicted. In the present embodiment, the movement of the obstacle is approximated as a uniform linear motion, and the center position X of the obstacle at the prediction point k (k = 0, ···, N) o (k), Y o (k), vehicle body orientation θ o (k), vehicle speed V o (k) is predicted as follows.

[0095] [Number]

[0096] However, X o (0), Y o (0), θ o (0), V o (0) are the center position, vehicle body orientation, and vehicle speed of the obstacle at the current time acquired by the obstacle information acquisition unit 220. When there are a plurality of obstacles, the above prediction is performed for each obstacle. Note that, instead of the uniform linear motion, a prediction such as the obstacle moving at a constant speed along the driving lane may be performed. Alternatively, the prediction may be performed using a driver model.

[0097] On the other hand, the future behavior of the obstacle may be predicted probabilistically by the obstacle movement prediction unit 111 (FIG. 3). By probabilistically showing the behavior of the obstacle, the obstacle movement prediction unit 111 can predict the behavior including the variation in the behavior of the obstacle. Note that the obstacle movement prediction unit 111 may probabilistically show only a part of the state quantities of the obstacle. As an expression method for probabilistically showing the behavior of the obstacle, there are a probability distribution following a Gaussian distribution, a probability distribution following a uniform distribution, a probability distribution up to a predetermined upper limit value and lower limit value, and the like.

[0098] Next, in step ST220 of FIG. 5, the entry prohibited area ζ is set by the entry prohibited area setting unit 112 (FIGS. 2 and 3). As the entry prohibited area ζ, those based on outside the vehicle lane of the road, a wall, an obstacle, etc. are assumed.

[0099] In this embodiment, an elliptical prohibited entry area is set for the center position X o (0) and Y o (0) of the obstacle at each prediction point k (k = 0, ···, N). The equation of the ellipse ζ(X, Y) = 0 is expressed by the following formula.

[0100] [Equation]

[0101] l a and l b are the lengths of the major axis and minor axis of the ellipse set for the obstacle respectively, and may be changed for each prediction point k. Also, the center of the ellipse does not necessarily coincide with the center position X o (k) and Y o (k) of the obstacle. Also, the prohibited entry area set for the obstacle does not necessarily have to be elliptical, and a prohibited entry area with an arbitrary shape may be set. When there are multiple obstacles, a prohibited entry area is set for each obstacle.

[0102] The prohibited entry area ζ may be such that the behavior of the obstacle forming the area is probabilistically shown, or the position or size of the area may change over time. In that case, the prohibited entry area ζ t is shown, for example, as in Equation (1) described later.

[0103] Considering safety, it is important to reduce the false positive (misjudging as impossible when lane change is possible) rather than the false negative (misjudging as possible when lane change is impossible) in the determination of whether lane change is possible. Therefore, when it is desired to reduce the false positive in the determination of whether lane change is possible, the prohibited entry area may be enlarged only at the time of determination. As a result, it becomes difficult for the host vehicle to reach the target lane at the time of determination, so when it is not possible to change lanes with a margin, it can be determined that lane change is impossible, and safety is improved.

[0104] Next, in step ST230 of FIG. 5, the trajectory generation unit 114 solves the optimization problem of equation (101) to generate a target trajectory ξ. The target trajectory ξ is a series of data including the target position of the host vehicle, and in the present embodiment, it is a series of data of the vehicle state quantity x of equation (104).

[0105] When the target action is lane keeping, the trajectory generation unit 114 generates a target trajectory ξ (target lane keeping trajectory ξLK) for lane keeping, and when the target action is lane change, the trajectory generation unit 114 generates a target trajectory ξ (target lane change trajectory ξLC) for lane change.

[0106] Next, in step ST240 of FIG. 5, the trajectory generation unit 114 determines whether a lane change is possible based on the target lane change trajectory ξLC. In the present embodiment, this determination is made at the timing when the target action changes to a lane change, that is, at the start of the lane change. However, the determination may also be made during the lane change.

[0107] If it is determined that a lane change is possible, the target lane change trajectory ξLC is output to the vehicle control unit 120. On the other hand, if it is determined that a lane change is not possible, the target lane keeping trajectory ξLK is output to the vehicle control unit 120.

[0108] In the present embodiment, the target lane keeping trajectory ξLK output at this time is generated based on the target lane keeping trajectory ξLK that the trajectory generation unit 114 output last. In addition, it is also possible to output the target lane keeping trajectory ξLK obtained by changing the target action to lane keeping and solving the optimization problem again. Further, if there is time for calculation when it is determined that a lane change is not possible, the reference value or weight of the optimization problem may be changed to recalculate the target lane change trajectory ξLC.

[0109] When the target action is lane keeping, the target lane keeping trajectory ξLK generated by the trajectory generation unit 114 is output as it is without making a determination.

[0110] Next, in step ST250 of FIG. 5, the vehicle control unit 120 calculates target values for performing steering control and vehicle speed control so that the host vehicle follows the target trajectory ξ. In the present embodiment, a target steering angle δt, which is a target value related to steering, and a target longitudinal acceleration axt, which is a target value related to vehicle speed, are calculated. In the present embodiment, since the target trajectory ξ includes the optimal values of the target steering angle δ t (k) and the target longitudinal acceleration ax t (k) at each prediction point k (k = 0, ···, N), according to the control period of each actuator, the optimal values of the target steering angle δ t (k) and the target longitudinal acceleration ax t (k) are interpolated in the time direction to calculate the target steering angle δ t and the target longitudinal acceleration axt, respectively.

[0111] Next, in step ST260 of FIG. 5, the power train controller 310, the brake controller 320, and the EPS controller 330 control the actuator based on the control amount. In the present embodiment, the EPS motor 5 is controlled so that the steering angle δ follows the target steering angle δt, and the power train unit 6 and the brake unit 7 are controlled so that the longitudinal acceleration ax follows the target longitudinal acceleration axt.

[0112] <Generation Procedure of Target Trajectory> FIG. 6 is a flowchart showing an example of the generation procedure of the target trajectory. This process is performed within step ST230 of FIG. 5.

[0113] First, in step ST231 of FIG. 6, the trajectory generation unit 114 calculates a reference point group. Here, the reference point group is a series of data of the reference position X s from the current time 0 to the prediction period T h in the future at a time interval T r , Y r , the reference trajectory azimuth ψ r , and the reference vehicle speed V r . Hereinafter, the series data of the reference positions X r (k), Y r (k) (k = 0, ···, N) is referred to as the reference trajectory χr.

[0114] Reference position X at each time r (k), Y r (k), reference trajectory azimuth ψ r (k), reference vehicle speed V r (k) (k = 0, ···, N) is determined as follows.

[0115] First, the reference vehicle speed V r (k) is determined based on the speed limit Vl of the driving lane and the vehicle speed Vp of the preceding vehicle. For example, V r (k) = Vl. Note that V r (k) does not necessarily have to be a constant value within the horizon.

[0116] Next, when the target behavior is lane keeping, the reference positions X r (k), Y r (k), and the reference trajectory azimuth ψ r (k) are determined based on the X position, Y position, and trajectory azimuth at the center of the lane. At the same time, the reference positions X r (k), Y r (k) and the reference vehicle speed V r (k) are made consistent, and conditions are set for the relationship between the reference positions X r (k), Y r (k) and the reference vehicle speed V r (k). That is, the reference positions X r (k), Y r (k) are determined so as to satisfy the following two equations.

[0117]

Equation

[0118] Equation (301) is the condition for the reference positions X r (k), Y r (k) to exist on the function Y = l e (X) (Equation (205)) representing the center of the own lane. Equation (302) is for the adjacent reference positions X r (k - 1), Y r (k - 1) and X r (k), Y r(k) is a condition for the distance between them to be equal to the amount of movement of the host vehicle at the time interval Ts.

[0119] The reference position X determined by these r (k), Y r The center of the host vehicle lane Y = l at (k) e By calculating the azimuth of (X), the reference trajectory azimuth ψ r (k) can also be determined. Hereinafter, the reference trajectory for lane keeping is referred to as the reference lane keeping trajectory χrLK.

[0120] When the target behavior is a lane change, for example, by connecting continuously and smoothly from the center of the current lane to the center of the target lane, a function Y = l representing the reference trajectory for lane change (reference lane change trajectory χrLC) LC (X) is generated.

[0121] This reference lane change trajectory χrLC is a trajectory generated without the constraint condition of not entering the prohibited entry area, and can be said to be a lane change trajectory when there are no obstacles. For the connection, a known method such as a spline curve or a fifth-order function is used. Then, instead of Equation (301), the following equation is used to determine the reference position X r (k), Y r (k).

[0122] [Number]

[0123] The reference position X determined by these r (k), Y r The azimuth of the reference lane change trajectory Y = l at (k) LC (X) is calculated to obtain the reference trajectory azimuth ψ r(k) can also be determined. When connecting, a reference lane change trajectory χrLC can be generated such that the lane change is completed within the target required time tLC for lane change. For example, when connecting, the lateral movement to the target lane is completed within the distance d that the host vehicle moves in the longitudinal direction during the target required time tLC. For calculating the distance d, it may be calculated by integrating the reference vehicle speed Vr, or may be calculated by the product of the current vehicle speed V0 and the target required time tLC. Also, when the driving lane is a curve, connection may be made in the path coordinate system.

[0124] Further, when it is not necessary to specify the target required time tLC for lane change and the prediction period Th is sufficiently long, without generating the reference lane change trajectory χrLC, simply using the following formula instead of formula (301), the reference position X r (k), Y r (k) may be determined.

[0125] [Number]

[0126] Here, Y = l o (X) is a function representing the center of the target lane. From formulas (205), (206), and (207), when the target lane is the host lane, the left lane, and the right lane respectively, l o = le, ll, lr.

[0127] The reference positions X r (k), Y r (k), the reference trajectory azimuth ψ r (k), the reference vehicle speed V r (k) (k = 0, ···, N) are used as a reference point group.

[0128] Next, in step ST232 of FIG. 6, the constraint condition setting unit 113 sets constraint conditions. The constraint conditions include, at least in part, the probability p of the vehicle state satisfying a predetermined condition tProbability constraints including elements based on [certain conditions] are included. Note that the constraint conditions may include non-probability constraints (constraint conditions that are not probability constraints) simultaneously with the probability constraints.

[0129] The probability constraint is the probability p of the state of the vehicle that should satisfy the conditions predetermined at a future time t set based on, or the probability p of the state of the vehicle that should satisfy the conditions predetermined over the entire time series t set based on. Note that even if the probability constraint is set based on the probability that the predetermined conditions are not satisfied, it is substantially synonymous with the above.

[0130] The probability constraint may describe the probability of the state of the vehicle that should satisfy the predetermined conditions as it is as a constraint, or may describe as a constraint a replacement of the probability with an equivalent formula or an approximate formula.

[0131] Examples of probability constraints include, for example, "the probability p that the host vehicle is located outside the prohibited entry area ζ t is within a threshold value", or "the probability p that the state quantity of the host vehicle is within a predetermined range t is within a threshold value", etc.

[0132] When the probability constraint is "at each time, the probability that the acceleration of the host vehicle is within a predetermined range is greater than a threshold value", let the acceleration of the host vehicle at time t be a t and the lower limit value of the acceleration be a min and the upper limit value of the acceleration be a max and the probability of the occurrence of event A be P[A], and the probability that should satisfy the conditions be p t then the probability constraint is shown as follows.

[0133]

Equation

[0134] As the probabilistic constraint based on the state quantity of the host vehicle, those set based on at least one of the upper and lower limits of the state quantity of the host vehicle (such as steering angle, steering angular velocity, lateral acceleration, lateral deviation from the track center, etc.) can be considered. Even when the host vehicle travels according to the generated track, an error from the track may occur due to disturbances (wind, road surface resistance, slopes), modeling errors, etc., so the future state quantity of the host vehicle varies and changes probabilistically.

[0135] When the probabilistic constraint is "at each time, the probability that the host vehicle is located outside the entry prohibited region ζ is greater than the threshold value", the position of the host vehicle at time t is (x t , y t ), the predicted position of the obstacle (vehicle) is (Xobs t , Yobs t ), the entry prohibited region corresponding to the predicted position (Xobs t , Yobs t ) of the obstacle (vehicle) is the entry prohibited region ζ t , the probability of the occurrence of event A is P[A], and the probability p t that should satisfy the condition at time t, then the probabilistic constraint is shown as follows.

[0136]

Equation

[0137] FIG. 7 is a diagram conceptually showing an example of the range of the entry prohibited region ζ t shown by Equation (9). In FIG. 7, the entry prohibited region ζ t corresponding to the predicted position of the obstacle is shown, and at a future time, the position (x t , y t ) of the host vehicle is located outside the entry prohibited region ζ t .

[0138] In the present embodiment, the center of gravity positions X t of the host vehicle at each predicted point k (k = 0, ···, N) in the entry prohibited region ζ (entry prohibited region ζ g ) set in step ST220, Y gSet the probability that (k) does not enter (in other words, the probability that the host vehicle is located outside the prohibited entry area) as a constraint condition (the above formula (9)). As an expression method for probabilistically indicating the center-of-gravity position of the host vehicle, there are a probability distribution following a Gaussian distribution centered on each prediction point k, a probability distribution following a uniform distribution, a probability distribution up to a predetermined upper limit value and a lower limit value, and the like.

[0139] In the present embodiment, the constraint condition is set based on the prohibited entry area, but the constraint condition may be set regardless of the prohibited entry area (FIG. 1). As an example, there is the probability constraint based on the state quantity of the host vehicle described using formula (8).

[0140] Next, in step ST233 of FIG. 6, the trajectory generation unit 114 sets the evaluation function J (formula (103)). In the present embodiment, in order to generate the target trajectory ξ that follows the reference point group (reference position X r (k), Y r (k), reference trajectory azimuth ψ r (k), reference vehicle speed V r (k) (k = 0, ···, N)) calculated by the host vehicle in step ST231, and to minimize the control input at that time, the vector value functions h and hN regarding the evaluation items are set as follows.

[0141]

Equation

[0142] e w (k) is the lateral deviation with respect to the reference position X r (k), Y r (k) at the prediction point k (k = 0, ···, N), and is shown as in formula (309) using the reference position X r (k), Y r (k) and the reference trajectory azimuth ψ r (k) at the prediction point k (k = 0, ···, N).

[0143]

Equation

[0144] Also, the reference values r(k) and r(N) are set as follows.

[0145] [Number]

[0146] Here, V r (k) is the reference vehicle speed. As a result, the trajectory generation unit 114 can generate a target trajectory such that the host vehicle follows the reference point group with a small control input. Note that, in order to improve the followability and ride comfort with respect to the reference point group, items such as the trajectory azimuth, yaw rate, longitudinal acceleration, and lateral acceleration may be added to the evaluation items. Also, the evaluation function may be changed according to the target behavior.

[0147] Next, in step ST234 of FIG. 6, the trajectory generation unit 114 solves the constrained optimization problem equation (101) using the evaluation function equation (103) and the constraint condition equation (9), thereby calculating the optimal control input u * . For the calculation of the optimal control input u * , known means are used, such as AutoGen, which is an automatic code generation tool developed by K.U. Leuven University and solves optimization problems based on the C / GMRES method and ACADO (Automatic Control And Dynamic Optimization). When ACADO or AutoGen is used, a time series (optimal control input) u * of the optimized control input at each prediction point k (k = 0, ···, N - 1) is output. That is, the output of step ST234 becomes equation (312).

[0148] [Number]

[0149] Here, j xt * (k), ω t *(k) (k = 0, ···, N - 1) are the optimal values of the target vertical jump and the target rudder angular velocity. Regarding the solution, a value for which the evaluation function is below a predetermined threshold may be used as the solution. If the threshold is not exceeded within a predetermined number of iterations, a value that minimizes the evaluation function within the number of iterations may also be used as the solution.

[0150] Next, in step ST235 of FIG. 6, the trajectory generation unit 114 calculates the optimal state quantity x * . In the calculation of the optimal state quantity x * , using the optimal control input u * and the vehicle model f, a time series of optimized vehicle state quantities (optimal state quantity) x * at each prediction point k (k = 0, ···, N) is calculated. Therefore, the output of step ST235 becomes Equation (313).

[0151]

Equation

[0152] Here, X g * (k), Y g * (k), θ * (k), β * (k), γ * (k), V * (k), a x * (k), a xt * (k), δ * (k), δ t * (k) are, respectively, the optimal value of the center of gravity position, the optimal value of the vehicle body orientation, the optimal value of the sideslip angle, the optimal value of the yaw rate, the optimal value of the vehicle speed, the optimal value of the longitudinal acceleration, the optimal value of the target longitudinal acceleration, the optimal value of the rudder angle, and the optimal value of the target rudder angle.

[0153] Next, in step ST236 of FIG. 6, the trajectory generation unit 114 generates the target trajectory ξ. The target trajectory ξ is the optimal state quantity x * and the optimal control input u *It is generated based on [this]. When the trajectory generation unit 114 determines whether lane change is possible based on the information of the position of the target trajectory ξ, the target trajectory ξ only needs to include the optimal center of gravity position X g * , Y g * is sufficient. When the trajectory generation unit 114 further determines whether lane change is possible based on the steering behavior, the target trajectory ξ further needs to include the optimal steering angle δ * and the optimal target steering angular velocity ω t * which are variables related to steering. In this embodiment, the optimal state quantity x * is used as the target trajectory ξ. Therefore, the output of step ST236 is given by Equation (314).

[0154] [Number]

[0155] Note that the target trajectory ξ when the target behavior is lane keeping is called the target lane keeping trajectory ξLK, and the target trajectory ξ when the target behavior is lane change is called the target lane change trajectory ξLC.

[0156] As described in step ST231, when the target behavior is different, at least the reference trajectory χr is different. However, in addition, the items or values of the constraints may be changed in step ST232, or the items or values of the evaluation function may be changed in step ST233.

[0157] [Probability p t Setting method] As a method for setting the probability p t that should satisfy the conditions in the probabilistic constraint, for example, the following can be considered.

[0158] First, setting based on time is considered. When setting the probabilistic constraint so as to satisfy the conditions determined in advance at each time, the magnitude of the probability p t that should satisfy the conditions may be changed based on future time. For example, the probability of satisfying the conditions can be made lower as the time is in the more distant future.

[0159] FIG. 8 is a diagram showing an example of the relationship between the probability p to be satisfied t and time. In FIG. 8, the vertical axis represents the probability p to be satisfied t and the horizontal axis represents time. As shown in the example of FIG. 8, as the future becomes farther from the current time, the probability p to be satisfied t can be set lower.

[0160] Further, FIG. 9 is a diagram showing an example of the probability distribution of the prohibited entry area in the near future. In FIG. 9, the vertical axis represents the probability density and the horizontal axis represents the position. The range indicated by the hatching in FIG. 9 corresponds to the prohibited entry area.

[0161] On the other hand, FIG. 10 is a diagram showing an example of the probability distribution of the prohibited entry area in the distant future. In FIG. 10, the vertical axis represents the probability density and the horizontal axis represents the position. The range indicated by the hatching in FIG. 10 corresponds to the prohibited entry area, and the probability density is lower and the position range is wider than in the case of FIG. 9. That is, the variation of the prohibited entry area has increased. Therefore, when the probability p to be satisfied is set under the same conditions as in FIG. 9, probability constraints are imposed including the prohibited entry area where the probability density is sufficiently low, and the range that satisfies the probability constraints (the blank area in FIG. 10) becomes excessively narrow. t

[0162] On the other hand, FIG. 11 is a diagram showing an example of the probability distribution of the changed prohibited entry area in the distant future. In FIG. 11, the vertical axis represents the probability density and the horizontal axis represents the position. The range indicated by the hatching in FIG. 11 corresponds to the changed prohibited entry area. The spread of the probability density is the same as in the case of FIG. 10, but the range is changed so that the range where the probability density is low is not included in the prohibited entry area, so the position range is about the same as in the case of FIG. 9. This change means that in the distant future, the probability p to be satisfied t ​This corresponds to setting it low. As a result, it is possible to prevent the variation in the prohibited entry area from becoming excessively large and suppress the probability constraint satisfaction range (the blank area in FIG. 11) from becoming excessively narrow. Consequently, the opportunity to execute the target behavior of the host vehicle increases.

[0163] Next, a setting based on distance can be considered. The probability of the state of the host vehicle at a position on the trajectory generated by the trajectory generation unit 114 may be set based on the distance between the position on the trajectory and the current position of the host vehicle.

[0164] FIG. 12 is a diagram showing an example of the relationship between the probability p t to be satisfied and the distance from the current position. In FIG. 12, the vertical axis represents the probability p t to be satisfied, and the horizontal axis represents the distance from the current position. As shown by the example in FIG. 12, as the distance of the position on the trajectory from the current position of the vehicle increases, the probability p t to be satisfied can be set lower.

[0165] Since the variation in the probability density at the position on the trajectory increases as the distance from the current position increases, by setting the probability p t to be satisfied lower, it is possible to suppress the probability constraint satisfaction range from becoming excessively narrow due to events with low probability density. As a result, the opportunity to execute the target behavior of the host vehicle increases.

[0166] Next, a setting based on the type of behavior can be considered. The probability p t to satisfy the conditions may be set based on at least one of the type of behavior that the host vehicle is currently performing and the type of behavior that it is planned to perform in the future.

[0167] Here, the type of behavior includes, in the case of a vehicle, maintaining the current state, following the lane, changing lanes, turning right or left, stopping, avoiding obstacles, parking, etc. Also, the current behavior of the host vehicle and the behavior planned for the future can be determined by a finite state machine, ontology, decision tree, reinforcement learning, Markov decision process, etc.

[0168] According to the above, for example, in the case of an action where approaching an obstacle is not desirable, the probability of approaching the obstacle can be changed, so the comfort during driving is improved.

[0169] Furthermore, when the action that the host vehicle is currently performing is different from the action that it is planned to perform in the future, considering that the fluctuation becomes larger as the action changes, the probability p t to be satisfied may be set higher. For example, when the current action type is lane following and the action type to be performed next is lane change, the probability p t to be satisfied can be set higher.

[0170] FIG. 13 is a diagram showing an example of the relationship between the probability p t to be satisfied and the action type. In FIG. 13, the vertical axis represents the probability p t to be satisfied, and the horizontal axis represents the time. As shown in the example of FIG. 13, as it approaches the distant future, the probability p t to be satisfied is set low, but when the type of the target action (the action planned to be performed in the future) is different from the type of the action currently being performed, the probability p t to be satisfied is set higher than in the same case.

[0171] According to the above, when the action types are different, the constraint conditions become stricter. Since the change of the action type is made under such strict constraint conditions, the probability of success (the probability of realizing safe driving) can be increased, so the comfort of driving is improved.

[0172] Note that according to the above, when a trajectory that satisfies the constraint conditions is obtained, the trajectory generation unit 114 can determine that the action type to be performed next is executable. On the other hand, when a trajectory that satisfies the constraint conditions is not obtained, it can be determined that the action type to be performed next is not executable.

[0173] Next, setting based on the degree of necessity can be considered. The probability p tmay be set based on the required degree of the action type. For example, the higher the required degree of the action type, the lower the probability p t may be set. Here, the required degree can be calculated based on, for example, the relationship between the road structure and the action type of the own vehicle. For example, when driving on a merging road, the required degree of lane change increases as approaching the end of the merge. Also, when there is a branch on the track and the own vehicle is driving in a lane that is not the branch lane, the required degree of lane change increases as approaching the branch point. Further, when wanting to turn right at an intersection but there is little difference in the required time even if turning right at the next intersection, the required degree of right turn is decreased.

[0174] <Modification of Probability Constraint> The conditional expression of the probability constraint may be modified. Specifically, conversion to an equivalent expression, conversion to an approximate expression, conversion to a more stringent conditional expression, etc. are conceivable.

[0175] For example, assume that the probability constraint corresponding to "at each time, the probability that the acceleration of the own vehicle is within a predetermined range is greater than a threshold" is as shown below.

[0176]

Equation

[0177] On the other hand, if the condition can be transformed into a condition of speed, let the speed of the own vehicle be V t and the lower limit value of the speed be V P,min and the upper limit value of the speed be V P,max then it can be transformed as follows.

[0178]

Equation

[0179] Also, assume that the probability constraint corresponding to "at each time, the probability that the own vehicle is located outside the entry prohibited area is greater than a threshold" is as shown below.

[0180]

Number

[0181] On the other hand, considering the variation in the predicted position of the obstacle, it can be rewritten as the condition of the deformed prohibited entry area, which is the area where the host vehicle should not enter, in order to satisfy the above equation. This deformed prohibited entry area is denoted as ζ P,t Then, the probability constraint is expressed in a form that does not include probability as follows.

[0182]

Number

[0183] Specifically, it is deformed as follows. First, the prohibited entry area ζ t of the obstacle is set to be inside the ellipse shown below.

[0184]

Number

[0185] By probabilistically capturing the obstacle, variation occurs in the predicted position (Xobs t , Yobs t ) of the obstacle, and the expected value of the obstacle position is (μ Xobst , μ Yobst ), and it is assumed to be obtained as a Gaussian distribution with a standard deviation of (σ Xobst , σ Yobst ).

[0186] Figure 14 shows the prohibited entry area ζ Xobst when the obstacle position is at the expected value (μ Yobst ), and the prohibited entry area ζ1 t when at the position (X1obs t , Y1obs t ) with variation. As shown in Figure 14, the prohibited entry area ζ t and the prohibited entry area ζ1 t ​t That is, a deviation occurs in the range according to the variation in the obstacle position. In this case, the size of the entry prohibited area ζ t d that determines x and d y are treated deterministically.

[0187] As a formula transformation in this case, first, the area where the obstacle position exists with probability p t is obtained. This area is inside a circle with radius r centered at the origin, which is obtained by the following formula when the expected value (μ Xobst , μ Yobst ) = (0, 0) and the standard deviation (σ Xobst , σ Yobst ) = (1, 1). When the expected value (μ Xobst , μ Yobst ) and the standard deviation (σ Xobst , σ Yobst ) are given, it is inside an ellipse that is σ Xobst times in the x - direction and σ Yobst times in the y - direction centered at (μ Xobst , μ Yobst ).

[0188] The formula f(x, y) of the two - dimensional standard Gaussian distribution is described as follows.

[0189]

Equation

[0190] On the other hand, as a general property of the Gaussian distribution, the cumulative distribution function P(r) is shown as follows.

[0191]

Equation

[0192] When the standard deviation is (1, 1), the range where it exists with probability p t is obtained by solving P(r) = p t and is as follows.

[0193] [Number]

[0194] Therefore, when the expected value of the obstacle prediction position (Xobs t , Yobs t ) is (μ Xobst , μ Yobst ) and the standard deviation is (σ Xobst , σ Yobst ), and it is obtained as a Gaussian distribution, the range where the obstacle position exists with probability p t is inside the ellipse represented by the following formula.

[0195] [Number]

[0196] When the entry prohibited area for the obstacle is represented by Equation (1) and the obstacle position (Xobs t , Yobs t ) which is the center of it moves inside the ellipse represented by Equation (6), the range of the area that the entry prohibited area can take can be approximately expressed as inside the following ellipse.

[0197] [Number]

[0198] Therefore, since the probability that the position of the host vehicle exists outside the entry prohibited area ζ t of the obstacle is greater than p t , the deformed entry prohibited area ζ P,t which is the area where the position of the host vehicle must not enter is inside the ellipse represented by Equation (7).

[0199] Figure 15 is a diagram showing the deformed entry prohibited area ζ P,t . As shown in Figure 15, the deformed entry prohibited area ζ P,t extends its range to the outside of the entry prohibited area ζ t .

[0200] By transforming the conditional expression (equality transformation or approximate transformation) as described above, the expression of the probabilistic constraint becomes an expression that is easy to handle by a computer and is represented by terms without probability while maintaining the effect of probabilistically capturing the moving body (own vehicle) and imposing a probabilistic constraint. Therefore, the computational load is reduced and the computational speed is improved.

[0201] In the present embodiment, although a case has been shown where the target trajectory ξ is generated based on the acquired vehicle information, and vehicle control is performed after determining whether lane change is possible based on the target trajectory ξ, the vehicle state quantity may be estimated in advance using known techniques such as a low-pass filter, an observer, a Kalman filter, and a particle filter, and the target action to be taken by the host vehicle and the target lane on which the host vehicle should travel may be determined based on obstacle information, road information, and vehicle information (vehicle state quantity).

[0202] For the above decision-making, known techniques such as a finite state machine, ontology, decision tree, reinforcement learning, and Markov decision process can be used. In the present embodiment, it is assumed that a finite state machine is used for decision-making. At the start of automatic driving, the target action is lane keeping, and it is determined whether lane change is necessary based on the destination and the current driving lane of the host vehicle, and the target action can be set to lane change. In addition, it may be determined whether overtaking of the host vehicle is necessary from the movement prediction information, and when overtaking is necessary, the target action may be set to lane change. When the target action is lane change, it is assumed that it is also determined whether it is a right lane change or a left lane change. This determination can be made based on, for example, the position of the overtaking lane.

[0203] The target lane is, for example, the own lane when the target action is lane keeping. When the target action is a right lane change, the right lane is the target lane. However, when the host vehicle crosses the lane line and moves into the right lane during lane change, the target lane becomes the right lane as seen from the original lane, that is, the own lane after crossing. The same applies to a left lane change.

[0204] <Regarding the effects resulting from the embodiments described above> Next, examples of the effects produced by the embodiments described above are shown. In the following description, the effects are described based on the specific configurations exemplified in the embodiments described above. However, within the range where the same effects are produced, they may be replaced with other specific configurations exemplified in the present specification. That is, hereinafter, for the sake of convenience, only one of the corresponding specific configurations may be representatively described, but the representatively described specific configuration may be replaced with other corresponding specific configurations.

[0205] According to the embodiment described above, the trajectory generation device includes a constraint condition setting unit 113 for setting constraint conditions that a moving body (own vehicle 1) passing through a trajectory should satisfy, and a trajectory generation unit 114 for generating a trajectory through which the own vehicle 1 passes so as to satisfy the constraint conditions. And the constraint conditions are set based on the probability of the state of the own vehicle 1 that should satisfy predetermined conditions.

[0206] According to such a configuration, since the trajectory is set so as to satisfy the constraint conditions based on the probability of the state of the moving body (vehicle), the moving body can be probabilistically captured with a spread, so it becomes easier to satisfy the constraint conditions, and it is possible to set a trajectory that is not overly constrained by rare events, and the own vehicle can increase the opportunity to perform the target behavior.

[0207] Note that even when other configurations exemplified in the present specification are appropriately added to the above configuration, that is, even when other configurations in the present specification not mentioned as the above configuration are appropriately added, the same effects can be produced.

[0208] Also, according to the embodiment described above, the trajectory generation device is a prohibited entry area ζ (or prohibited entry area ζ where entry of the own vehicle 1 is prohibited) tIt includes an entry prohibited area setting unit 112 for setting ). And the constraint condition is set based on the probability that the host vehicle 1 exists outside the entry prohibited area. According to such a configuration, in order to determine whether the constraint condition is satisfied based on the probability that the host vehicle is located outside the entry prohibited area, it is possible to set a trajectory without imposing excessive constraints on unlikely events, and the opportunity for the host vehicle to perform the target action can be increased.

[0209] Also, according to the above-described embodiment, the trajectory generation device includes an obstacle movement prediction unit 111 for probabilistically predicting the state of an obstacle. And the entry prohibited area setting unit 112 sets the entry prohibited area ζ t based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit 111. According to such a configuration, as a result of setting the entry prohibited area based on the probabilistically indicated position of the obstacle, the entry prohibited area can be probabilistically grasped, so that it is possible to set a trajectory without imposing excessive constraints on unlikely events, and the opportunity for the host vehicle to perform the target action can be increased.

[0210] Also, according to the above-described embodiment, the constraint condition setting unit 113 transforms the term indicating the probability of the state of the host vehicle 1 in the conditional expression indicating the constraint condition into a term not including probability. According to such a configuration, the calculation load is reduced and the calculation speed is improved. Also, a trajectory can be generated by a conventional deterministic calculation method.

[0211] Also, according to the above-described embodiment, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 in the constraint condition based on the time difference between the current time and the time when the host vehicle 1 passes through the trajectory generated by the trajectory generation unit 114. According to such a configuration, it is possible to suppress the range that satisfies the probabilistic constraint from becoming excessively narrow. As a result, since excessive guarantee is not required in the future, the opportunity for the host vehicle to execute the target action increases.

[0212] Also, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 in the constraint condition to be lower as the time difference between the current time and the time when the host vehicle 1 passes through the trajectory generated by the trajectory generation unit 114 is larger. According to such a configuration, it is possible to suppress the range that satisfies the probability constraint from becoming excessively narrow. As a result, since it will not be excessively guaranteed in the distant future, the opportunity to execute the target behavior of the host vehicle increases.

[0213] Also, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 at the position on the trajectory generated by the trajectory generation unit 114 in the constraint condition based on the distance between the position on the trajectory and the current position of the host vehicle 1. According to such a configuration, since an event with a low probability in the distance is not excessively guaranteed, the opportunity to execute the target behavior of the host vehicle increases.

[0214] Also, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 at the position on the trajectory to be lower as the distance between the position on the trajectory and the current position of the host vehicle 1 is larger. According to such a configuration, since an event with a low probability in the distance is not excessively guaranteed, the opportunity to execute the target behavior of the host vehicle increases.

[0215] Also, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 in the constraint condition based on at least one of the current action type of the host vehicle 1 and the action type that the host vehicle 1 will perform next. According to such a configuration, for example, in an action where approaching an obstacle is not desirable, the probability of approaching the obstacle can be changed, so the comfort is improved.

[0216] Further, according to the embodiment described above, when the current action type of the host vehicle 1 and the action type that the host vehicle 1 will perform next are the same, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 in the constraint condition to be higher when they are different than when they are the same. According to such a configuration, when the action types are different, the constraint conditions become stricter. Since the change of the action type is made under such strict constraint conditions, the probability of success (the probability of realizing safe driving) can be increased, and thus the comfort of driving is improved.

[0217] Further, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 in the constraint condition based on the degree of necessity of the action type. According to such a configuration, an action with a high degree of necessity can be executed even if the probability of success is low.

[0218] Further, according to the embodiment described above, the constraint condition setting unit 113 sets the degree of necessity of the action type based on the relationship between the track structure at the position on the track generated by the track generation unit 114 and the action type of the host vehicle 1. According to such a configuration, an action with a high degree of necessity can be preferentially realized.

[0219] Further, according to the embodiment described above, when the track generation unit 114 obtains a track that satisfies the constraint condition, it determines that the action type that the host vehicle 1 will perform next is executable. When the track generation unit 114 fails to obtain a track that satisfies the constraint condition, it determines that the action type that the host vehicle 1 will perform next is unexecutable. According to such a configuration, based on whether a track that satisfies the constraint condition is obtained, the feasibility of the next action type can be determined.

[0220] According to the embodiment described above, in the track generation method, the constraint conditions that the host vehicle 1 passing through the track should satisfy are set. Then, a track that the host vehicle 1 passes through so as to satisfy the constraint conditions is generated. The constraint conditions are set based on the probability of the state of the host vehicle 1 that should satisfy the predetermined conditions.

[0221] According to such a configuration, since the trajectory is set so as to satisfy the constraint conditions based on the probability of the state of the moving body (vehicle), the moving body can be probabilistically captured with a spread, making it easier to satisfy the constraint conditions and enabling trajectory setting that does not overly constrain unlikely events, and increasing the opportunity for the host vehicle to perform the target action.

[0222] Note that when there are no special restrictions, the order in which each process is performed can be changed.

[0223] Also, when other configurations exemplified in the present specification are appropriately added to the above configuration, that is, even when other configurations in the present specification that are not mentioned as the above configuration are appropriately added, the same effects can be achieved.

[0224] <Regarding the modifications of the embodiments described above> In the embodiments described above, the dimensions, shapes, relative arrangement relationships, or implementation conditions of each component may be described, but these are all examples in all aspects and are not limiting.

[0225] Therefore, countless modifications and equivalents that are not exemplified are assumed to be within the scope of the technology disclosed in the present specification. For example, it is assumed to include cases where at least one component is modified, added, or omitted.

[0226] Also, as long as there is no contradiction, when it is described in the embodiments described above that "one" component is provided, the component may be provided with "one or more".

[0227] Furthermore, each component in the embodiments described above is a conceptual unit, and within the scope of the technology disclosed in the present specification, it is assumed to include cases where one component consists of a plurality of structures, cases where one component corresponds to a part of a certain structure, and further cases where a plurality of components are provided in one structure.

[0228] In addition, each component in the above-described embodiments shall include structures having other structures or shapes as long as they exhibit the same functions.

[0229] Also, the descriptions in the present specification are for all purposes related to the present technology and none of them are admitted to be prior art.

[0230] Hereinafter, aspects of the present disclosure will be collectively described as appendices.

[0231] (Appendix 1) A constraint condition setting unit for setting constraint conditions to be satisfied by a moving body passing through an orbit, and an orbit generation unit for generating the orbit through which the moving body passes so as to satisfy the constraint conditions. The constraint conditions include those set based on the probability of the state of the moving body satisfying predetermined conditions. Orbit generation device.

[0232] (Appendix 2) The orbit generation device according to Appendix 1, further comprising an entry prohibited area setting unit for setting an entry prohibited area which is an area where entry of the moving body is prohibited, wherein the constraint conditions are set based on the probability that the moving body exists outside the entry prohibited area. Orbit generation device.

[0233] (Appendix 3) The orbit generation device according to Appendix 2, further comprising an obstacle movement prediction unit for probabilistically predicting the state of an obstacle, wherein the entry prohibited area setting unit sets the entry prohibited area based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit. Orbit generation device.

[0234] (Appendix 4) The trajectory generation device according to any one of Appendices 1 to 3, wherein the constraint condition setting unit transforms a term indicating the probability of the state of the moving body in the conditional expression indicating the constraint condition into a term not including probability, Trajectory generation device.

[0235] (Appendix 5) The trajectory generation device according to any one of Appendices 1 to 4, wherein the constraint condition setting unit sets the probability of the state of the moving body in the constraint condition based on the time difference between the current time and the time when the moving body passes through the trajectory generated by the trajectory generation unit, Trajectory generation device.

[0236] (Appendix 6) The trajectory generation device according to Appendix 5, wherein the constraint condition setting unit sets the probability of the state of the moving body in the constraint condition to be lower as the time difference between the current time and the time when the moving body passes through the trajectory generated by the trajectory generation unit is larger, Trajectory generation device.

[0237] (Appendix 7) The trajectory generation device according to any one of Appendices 1 to 6, wherein the constraint condition setting unit sets the probability of the state of the moving body at a position on the trajectory generated by the trajectory generation unit in the constraint condition based on the distance between the position on the trajectory and the current position of the moving body, Trajectory generation device.

[0238] (Appendix 8) The trajectory generation device according to Appendix 7, wherein the constraint condition setting unit sets the probability of the state of the moving body at the position on the trajectory to be lower as the distance between the position on the trajectory and the current position of the moving body is larger, Trajectory generation device.

[0239] (Appendix 9) The trajectory generation device according to any one of Appendices 1 to 8, wherein the constraint condition setting unit sets the probability of the state of the moving body in the constraint condition based on at least one of the current action type of the moving body and the action type that the moving body will perform next. Trajectory generation device.

[0240] (Appendix 10) The trajectory generation device according to Appendix 9, wherein the constraint condition setting unit sets the probability of the state of the moving body in the constraint condition to be higher when the current action type of the moving body and the action type that the moving body will perform next are different than when they are the same. Trajectory generation device.

[0241] (Appendix 11) The trajectory generation device according to Appendix 9 or 10, wherein the constraint condition setting unit sets the probability of the state of the moving body in the constraint condition based on the degree of necessity of the action type. Trajectory generation device.

[0242] (Appendix 12) The trajectory generation device according to Appendix 11, wherein the constraint condition setting unit sets the degree of necessity of the action type based on the relationship between the trajectory structure at the position on the trajectory generated by the trajectory generation unit and the action type of the moving body. Trajectory generation device.

[0243] (Appendix 13) The trajectory generation device according to any one of Appendices 1 to 12, wherein the trajectory generation unit when obtaining the trajectory that satisfies the constraint condition, determines that the action type that the moving body will perform next is executable, and when not obtaining the trajectory that satisfies the constraint condition, determines that the action type that the moving body will perform next is not executable. Trajectory generation device.

[0244] (Appendix 14) Set the constraint conditions that the moving object passing through the trajectory should satisfy, Generate the trajectory through which the moving object passes so as to satisfy the constraint conditions, The constraint conditions include those set based on the probability of the state of the moving object that should satisfy predetermined conditions. Trajectory generation method.

Explanation of symbols

[0245] 1 Own vehicle, 2 Steering wheel, 3 Steering shaft, 4 Steering unit, 5 EPS motor, 6 Power train unit, 7 Brake unit, 11 Front camera, 12 Radar sensor, 13 GNSS sensor, 15 V2X receiver, 16 Yaw rate sensor, 17 Speed sensor, 18 Acceleration sensor, 20 Steering angle sensor, 21 Steering torque sensor, 100 Vehicle control device, 100A Vehicle control device, 100B Vehicle control device, 110 Trajectory generation device, 110A Trajectory generation device, 110B Trajectory generation device, 111 Obstacle movement prediction unit, 112 Prohibited entry area setting unit, 113 Constraint condition setting unit, 114 Trajectory generation unit, 120 Vehicle control unit, 200 Information acquisition unit, 210 Own vehicle information acquisition unit, 220 Obstacle information acquisition unit, 230 Road information acquisition unit, 300 Controller unit, 310 Power train controller, 320 Brake controller, 330 EPS controller, 500 Vehicle control system, 500A Vehicle control system, 500B Vehicle control system.

Claims

1. A constraint setting unit for setting constraint conditions that a moving object following a trajectory must satisfy, The system includes a trajectory generating unit for generating the trajectory through which the moving body passes so as to satisfy the aforementioned constraints, The aforementioned constraints include those set based on the probability of the moving body being in a state that satisfies predetermined conditions, The probability of the state of the aforementioned moving object is variable. Trajectory generator.

2. A constraint setting unit for setting constraint conditions that a moving object passing through a track must satisfy, The system includes a trajectory generating unit for generating the trajectory through which the moving body passes so as to satisfy the aforementioned constraints, The aforementioned constraints include those set based on the probability of the moving body being in a state that satisfies predetermined conditions, The constraint setting unit transforms the term in the conditional expression representing the constraint, which indicates the probability of the state of the moving body, into a term that does not include probability. Trajectory generator.

3. The orbital generation apparatus according to claim 1 or 2, The system further includes an entry restriction area setting unit for setting an entry restriction area, which is an area where the aforementioned moving object is prohibited from entering. The aforementioned constraints are set based on the probability that the moving body is outside the no-entry area. Trajectory generator.

4. The orbital generation device according to claim 3, It further includes an obstacle movement prediction unit for probabilistically predicting the state of obstacles, The entry restriction area setting unit sets the entry restriction area based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit. Trajectory generator.

5. The orbital generation device according to claim 2, The constraint setting unit transforms the term in the conditional expression representing the constraint, which indicates the probability of the state of the moving body, into a term that does not include probability. Trajectory generator.

6. The orbital generation apparatus according to claim 1 or 2, The constraint setting unit sets the probability of the state of the moving body under the constraint conditions based on the time difference between the current time and the time at which the moving body passes through the trajectory generated by the trajectory generation unit. Trajectory generator.

7. The orbital generation device according to claim 6, The constraint setting unit sets a lower probability for the state of the moving object in the constraint conditions as the time difference between the current time and the time at which the moving object travels along the trajectory generated by the trajectory generation unit is larger. Trajectory generator.

8. The orbital generation apparatus according to claim 1 or 2, The constraint setting unit sets the probability of the state of the moving body at the position on the trajectory generated by the trajectory generation unit based on the distance between the position on the trajectory and the current position of the moving body. Trajectory generator.

9. The orbital generation device according to claim 8, The constraint setting unit sets the probability of the state of the moving body at the position on the trajectory to be lower the greater the distance between the position on the trajectory and the current position of the moving body. Trajectory generator.

10. The orbital generation apparatus according to claim 1 or 2, The constraint setting unit sets the probability of the state of the moving body under the constraints based on at least one of the current type of action of the moving body and the next type of action the moving body will perform. Trajectory generator.

11. The orbital generation device according to claim 10, The constraint setting unit sets the probability of the state of the moving body in the constraint conditions higher when the current type of action of the moving body and the next type of action of the moving body are different, than when they are the same. Trajectory generator.

12. The orbital generation device according to claim 10, The constraint setting unit sets the probability of the state of the moving body under the constraints based on the degree of necessity of the type of action. Trajectory generator.

13. The orbital generation apparatus according to claim 12, The constraint setting unit sets the degree of necessity of the action type based on the relationship between the trajectory structure at the position on the trajectory generated by the trajectory generation unit and the action type of the moving body. Trajectory generator.

14. The orbital generation apparatus according to claim 1 or 2, The orbital generation unit, When the trajectory that satisfies the aforementioned constraints is obtained, it is determined that the next type of action that the moving body is to perform is possible, If the trajectory that satisfies the aforementioned constraints cannot be obtained, the moving object determines that the next type of action it is to perform is impossible. Trajectory generator.

15. Set constraints that a moving object following a trajectory must satisfy, The trajectory through which the moving body passes is generated so as to satisfy the aforementioned constraints, The aforementioned constraints include those set based on the probability of the moving body being in a state that satisfies predetermined conditions, The probability of the state of the aforementioned moving object is variable. Trajectory generation method.

16. Set constraints that a moving object following a trajectory must satisfy, The trajectory through which the moving body passes is generated so as to satisfy the aforementioned constraints, The aforementioned constraints include those set based on the probability of the moving body being in a state that satisfies predetermined conditions, The term in the conditional expression representing the constraints that indicates the probability of the state of the moving body is transformed into a term that does not include probability. Trajectory generation method.

Images