Trajectory generation device and trajectory generation method

Abstract

The technique disclosed in the description of the present application is a technique for suppressing excessive constraints in trajectory setting of a moving body. This trajectory generation device pertaining to the technique disclosed in the description of the present application is provided with: 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. Furthermore, the constraint conditions include those that are set on the basis of the probability of a state of the moving body that should satisfy predetermined conditions.

Description

Trajectory generation device and trajectory generation method

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

[0002] A method for generating a trajectory of a moving object by taking into account the probability of an event that may occur in the future has been proposed. For example, Patent Document 1 discloses a method for calculating an optimal trajectory of a vehicle by probabilistically calculating the future behavior of an obstacle.

[0003] Japanese Patent Application Laid-Open No. 2020-15489

[0004] If the constraints imposed when setting a trajectory include events with a low probability of occurring, the opportunities for the vehicle (moving body) to perform the desired action will be reduced, which may reduce the moving body's freedom of action and reduce the comfort of the occupants.

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

[0006] A trajectory generation device, which is a first aspect of the technology disclosed in the present specification, includes a constraint condition setting unit for setting constraint conditions that a moving body passing through a trajectory must satisfy, and a trajectory generation unit for generating the trajectory that the moving body will pass through so as to satisfy the constraint conditions, and includes a device in which the constraint conditions are set based on the probability of a state of the moving body that should satisfy a predetermined condition.

[0007] According to at least the first aspect of the technology disclosed in the present specification, a trajectory is set to satisfy constraints based on the probability of the state of the moving body, thereby making it possible to suppress excessive constraints when setting the trajectory of the moving body.

[0008] Furthermore, objects, features, aspects, and advantages associated with the technology disclosed herein will become more apparent from the detailed description and accompanying drawings set forth below.

[0009] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control system including a trajectory generation device according to an embodiment. FIG. 2 is a diagram conceptually illustrating a modified configuration of a vehicle control system including a trajectory generation device according to an embodiment. FIG. 3 is a diagram conceptually illustrating a modified configuration of a vehicle control system including a trajectory generation device according to an embodiment. FIG. 4 is a diagram conceptually illustrating an example of the hardware configuration of a host vehicle equipped with a vehicle control system according to an embodiment. FIG. 5 is a flowchart showing an example of a procedure for driving control of a host vehicle according to an embodiment. FIG. 6 is a flowchart showing an example of a procedure for generating a target trajectory. FIG. 7 is a diagram conceptually illustrating an example of the range of a no-entry area expressed by equation (9). FIG. 8 is a diagram showing an example of the relationship between the probability to be satisfied and time. FIG. 9 is a diagram showing an example of the probability distribution of a no-entry area in the near future. FIG. 10 is a diagram showing an example of the probability distribution of a no-entry area in the distant future. FIG. 11 is a diagram showing an example of the probability distribution of a modified no-entry area in the distant future. FIG. 12 is a diagram showing an example of the relationship between the probability to be satisfied and the distance from the current position. FIG. 13 is a diagram showing an example of the relationship between the probability to be satisfied and the type of action. FIG. 14 is a diagram showing a no-entry area when an obstacle position is at an expected value, and a no-entry area when the obstacle position is at a position with variation. FIG. 15 is a diagram showing a deformed no-entry area.

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

[0011] The drawings are schematic, and for the sake of convenience, components may be omitted or simplified as appropriate. The relative sizes and positions of components shown in different drawings are not necessarily accurately depicted and may be changed as appropriate. Hatching may also be used in drawings such as plan views that are not cross-sectional views to facilitate understanding of the embodiments.

[0012] In the following description, the same components are denoted by the same reference numerals, and their names and functions are also the same. Therefore, detailed descriptions of them may be omitted to avoid duplication.

[0013] Furthermore, in the description given in this specification, when a certain component is described as "comprising," "including," or "having," unless otherwise specified, this is not an exclusive expression that excludes the presence of other components.

[0014] Furthermore, in the description of this specification, even if ordinal numbers such as "first" or "second" are used, these terms are used for convenience to make it easier to understand the contents of the embodiments, and the contents of the embodiments are not limited to the order that may result from these ordinal numbers.

[0015] <Embodiment> A trajectory generation device and a trajectory generation method according to this embodiment will be described below.

[0016] <Configuration of Trajectory Generation Device> FIG. 1 is a diagram conceptually showing an example of the configuration of a vehicle control system including a trajectory generation device according to this embodiment.

[0017] As shown in 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 body, such as a vehicle, a robot, or a drone, must satisfy when traveling along the trajectory, and a trajectory generation unit 114 that generates a trajectory along which the moving body will travel. In this embodiment, a vehicle is assumed as the moving body.

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

[0021] The information acquisition unit 200 acquires information used when the trajectory generation device 110 generates a trajectory, and outputs the information 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 roads.

[0022] The controller unit 300 controls the operation of the vehicle based on control signals input from the vehicle control unit 120. The controller unit 300 includes a powertrain controller 310 that controls a powertrain unit described below, a brake controller 320 that controls a brake unit described below, and an EPS (Electric Power Steering) controller 330 that steers the front wheels independently of the operation of the steering wheel 2 by the driver.

[0023] FIG. 2 is a diagram conceptually showing a modified example of the configuration of a vehicle control system including a trajectory generation device according to this 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-restricted area setting unit 112 that sets an entry-restricted area.

[0027] As shown in FIG. 2, a no-entry area setting unit 112 may be additionally provided in the trajectory generation device 110A.

[0028] FIG. 3 is a diagram conceptually showing a modified example of the configuration of a vehicle control system including a trajectory generation device according to this 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, a no-entry area setting unit 112, and an obstacle movement prediction unit 111 that predicts the movement of an obstacle.

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

[0033] As shown in FIG. 3, a trajectory generation device 110B may additionally include a no-entry area setting unit 112 and an obstacle movement prediction unit 111.

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

[0035] 4, the vehicle 1 includes, as a drive system, a steering wheel 2, a steering shaft 3, a steering unit 4, an EPS motor 5, a powertrain unit 6, and a brake unit 7. The powertrain unit 6 is, for example, a gasoline-fueled engine.

[0036] The host vehicle 1 also includes a sensor system including a forward 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 powertrain controller 310, and a brake controller 320.

[0038] A steering wheel 2, which is installed so that a driver can drive the vehicle, is connected to a steering shaft 3. A steering unit 4 is connected to the steering shaft 3.

[0039] The steering unit 4 rotatably supports the two front tires as steering wheels, and is supported on the vehicle body frame so that it can be steered. Therefore, 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 to the left and right. By operating the steering wheel 2, the driver can control the lateral movement of the vehicle when moving forward and backward.

[0040] The steering shaft 3 can also be rotated by the EPS motor 5. The EPS controller 330 controls the current flowing through the EPS motor 5, thereby enabling the front wheels to be steered independently of the driver's operation of the steering wheel 2.

[0041] The vehicle control device 100 is, for example, an integrated circuit such as a microprocessor also known as an ADAS-ECU (Advanced Driving Assistance Systems-Electronic Control Unit), 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] The vehicle control device 100 is connected to a forward camera 11, a radar sensor 12, a GNSS sensor 13, a V2X receiver 15, a yaw rate sensor 16 that detects the yaw rate, a speed sensor 17 that detects the speed of the vehicle, an acceleration sensor 18 that detects the acceleration of the vehicle, a steering angle sensor 20 that detects the steering angle, a steering torque sensor 21 that detects the steering torque, an EPS controller 330, a powertrain controller 310, and a brake controller 320.

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

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

[0045] The front camera 11 is installed in a position where it can detect the lane markings ahead of the vehicle as an image, and detects the environment ahead of the host vehicle 1, such as lane information and the location of obstacles, based on the image information. Note that in the vehicle control system 500 according to this embodiment, only a camera that detects the environment ahead of the host vehicle 1 is shown, but other cameras that detect the environment behind and to the sides of the host vehicle 1 may also be provided. The front camera 11 can also be used to estimate the condition of the road surface on which the host vehicle 1 is traveling.

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

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

[0048] The V2X receiver 15 has a function of acquiring and outputting information through wireless communication between other vehicles, including surrounding vehicles, and roadside devices and the host vehicle 1. The acquired information includes surrounding vehicle information such as the position and speed of the 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 powertrain controller 310 controls the acceleration of the host vehicle 1 by controlling the powertrain unit 6 so as to realize the target acceleration 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 about the host vehicle 1. The vehicle information includes state quantities of the host vehicle that indicate the state of the host vehicle 1. The host vehicle information acquisition unit 210 includes, for example, the GNSS sensor 13, the yaw rate sensor 16, the speed sensor 17, the acceleration sensor 18, the steering angle sensor 20, and the steering torque sensor 21.

[0053] The obstacle information acquisition unit 220 acquires obstacle information including position information of surrounding vehicles present around the host vehicle 1. The obstacle information acquisition unit 220 is, for example, the forward 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 about the road on which the host vehicle 1 is traveling. The road information acquisition unit 230 is, for example, the front camera 11 and the V2X receiver 15.

[0055] Although the vehicle 1 equipped with the vehicle control system 500 according to this embodiment is shown as a vehicle using only an engine as a driving force source, the vehicle may also be a vehicle using only an electric motor as a driving force source, or a vehicle using both an engine and an electric motor as driving force sources.

[0056] In this embodiment, the trajectory generation unit 114 generates a trajectory for the moving object by solving an optimization problem. However, the trajectory generation unit 114 may generate a trajectory by other methods, such as a method of generating a trajectory using the center of a road or a route that another vehicle has taken as a target position, or a method of randomly generating multiple candidate routes and selecting one from them using some kind of evaluation index.

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

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

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

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

[0061]

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

[0063] Here, the above optimization problem is a constrained optimization problem to which the constraints described below are imposed.

[0064] 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]

[0067] Here, x(k) is the vehicle state quantity at the prediction point k (k=0,...,N), u(k) is the control input at the prediction point k (k=0,...,N), h is a vector value function related to the evaluation item, h Ｎ is a vector-valued function for the evaluation item at the end (prediction point N), and r(k) is the reference value at prediction point k (k=0,...,N). Ｎ is a weight matrix, which is a diagonal matrix having weights for each evaluation item in the diagonal elements, and can be changed as appropriate as a parameter.

[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]

[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. Furthermore, jt is the target longitudinal jerk, and ωt is the target steering angular velocity. Note that the vehicle state quantity x includes a variable related to position, and as long as 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 may be set in any manner. Furthermore, the position variable is not limited to being defined in an orthogonal coordinate system, and may be defined, for example, in a path coordinate system.

[0071] In addition, when the vehicle control device 100 performs only steering control, the vehicle state quantity x includes a variable related to position, and the vehicle state quantity x and the control input u may be set in any way as long as the variable related to steering is included in either the vehicle state quantity x or the control input u.

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

[0073]

[0074] Here, M is the vehicle mass, I is the yaw moment of inertia of the vehicle, lf and lr are the distances from the front and rear wheel axles to the center of gravity of the vehicle, Tax and Tδ are time constants when the tracking ability of the longitudinal acceleration and steering angle to the target value is expressed in a first-order lag system, and 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]

[0076] It should be noted that the vehicle model f may be a vehicle model other than the two-wheel model.

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

[0078] 5, obstacle information is acquired by the obstacle information acquisition unit 220. The obstacle information is information including the positions of obstacles including surrounding vehicles, and in this embodiment, if an obstacle is located to the left front of the host vehicle, the positions of the right front end PFR, right rear end PRR, and left rear end PRL of the obstacle in the host vehicle coordinate system are acquired, and if an obstacle is located to the right front of the host vehicle, the positions of the left front end PFL, left rear end PRL, and right rear end PRR of the obstacle in the host vehicle coordinate system are acquired.

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

[0080] Next, in step ST120 of Fig. 5, road information is acquired by road information acquisition unit 230. The road information is information including the boundaries of the road on which the vehicle is traveling and the adjacent roads (hereinafter referred to as the current lane, left lane, and right lane). In this embodiment, coefficients are acquired when the left and right lane markings of the current lane, left lane, and right lane are expressed by a third-order polynomial. That is, for the left lane marking (which is also the right lane marking) on ​​the current lane, the values ​​of cel0 to cel3 in the following equation are acquired.

[0081]

[0082] For the right dividing line of the own lane (which is also the left dividing line of the right lane), the values ​​of cer0 to cer3 are obtained using the following equations.

[0083]

[0084] For the left lane marking on the left, the values ​​c110 to c113 of the following equations are obtained.

[0085]

[0086] For the right lane marking on the right side, the values ​​of crr0 to crr3 are obtained as follows:

[0087]

[0088] In this case, the center of the own lane, the center of the left lane, and the center of the right lane are expressed by equations (205), (206), and (207), respectively.

[0089]

[0090] Here, the coefficients are expressed by equations (208), (209), and (210).

[0091]

[0092] The information on the lane markings is not limited to a third-order polynomial, and may be expressed by any function.

[0093] 5, vehicle information is acquired by the host vehicle information acquisition unit 210. The vehicle information includes the steering angle, yaw rate, speed, acceleration, etc. of the host vehicle, and in this embodiment, 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) predicts the movement of the obstacle. In the movement prediction, the central position X of the obstacle at each prediction point k (k = 0, ..., N) is calculated. ｏ (k), Y ｏ (k), vehicle direction θ ｏ (k), vehicle speed V ｏ In this embodiment, the motion of the obstacle is approximated by uniform linear motion, and the center position X of the obstacle at the predicted point k (k=0, . . . , N) is calculated. ｏ (k), Y ｏ (k), vehicle direction θ ｏ (k), vehicle speed V ｏ (k) is predicted as follows:

[0095]

[0096] However, X ｏ (0), Y ｏ (0), θ ｏ (0), V ｏ (0) is the center position of the obstacle, the vehicle direction, and the vehicle speed at the current time acquired by the obstacle information acquisition unit 220. If there are multiple obstacles, the above prediction is made for each obstacle. Note that instead of uniform linear motion, it is also possible to make a prediction that the obstacle moves at a uniform speed along the driving lane. Alternatively, a driver model may be used to make the prediction.

[0097] On the other hand, the obstacle movement prediction unit 111 (FIG. 3) may predict the future behavior of the obstacle and display it probabilistically. By displaying the behavior of the obstacle probabilistically, the obstacle movement prediction unit 111 can predict the behavior of the obstacle including the variability of the obstacle behavior. Note that the obstacle movement prediction unit 111 may display only a part of the state quantities of the obstacle probabilistically. Methods for expressing the behavior of the obstacle probabilistically include a probability distribution according to a Gaussian distribution, a probability distribution according to a uniform distribution, and a probability distribution up to predetermined upper and lower limit values.

[0098] Next, in step ST220 of Fig. 5, the no-entry area setting unit 112 (Figs. 2 and 3) sets a no-entry area ζ. The no-entry area ζ may be outside a lane on a road, based on a wall, an obstacle, or the like.

[0099] In this embodiment, the central position X of the obstacle at each prediction point k (k=0, . . . , N) is ｏ (0), Y ｏ An elliptical no-entry area is set at (0). The equation of the ellipse ζ(X, Y) = 0 is expressed as follows:

[0100]

[0101] l ａ , l ｂ are the lengths of the major and minor axes of the ellipse set for the obstacle, and may be changed for each prediction point k. ｏ (k), Y ｏ (k). The no-entry area set for an obstacle does not have to be elliptical, and any shape of no-entry area may be set. If there are multiple obstacles, a no-entry area is set for each obstacle.

[0102] The no-entry area ζ may be one in which the behavior of the obstacles forming the area is shown probabilistically, or the position or size of the area may change with time. ｔ is expressed, for example, as equation (1) below.

[0103] Considering safety, it is more important to reduce false positives (mistakenly determining that a lane change is possible when it is not) than false negatives (mistakenly determining that a lane change is possible when it is not). Therefore, if you want to reduce false positives in determining whether a lane change is possible, you can expand the no-entry area only when making a decision. This makes it more difficult for the vehicle to reach the target lane at the time of decision, so if there is not enough time to change lanes, it can be determined that a lane change is not possible, improving safety.

[0104] 5, the trajectory generation unit 114 generates a target trajectory ξ by solving the optimization problem of equation (101). The target trajectory ξ is series data including the target position of the host vehicle, and in this embodiment, it is series data of the vehicle state quantity x of equation (104).

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

[0106] Next, in step ST240 of Fig. 5, the trajectory generation unit 114 determines whether or not to change lanes based on the target lane-change trajectory ξLC. In this embodiment, this determination is made when the target behavior changes to a lane change, that is, when the lane change starts. However, the determination may also be made while the lane change is still in progress.

[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 this embodiment, the target lane-keeping trajectory ξLK output at this time is generated based on the target lane-keeping trajectory ξLK last output by the trajectory generation unit 114. Note that a target lane-keeping trajectory ξLK obtained by changing the target behavior to lane keeping and resolving the optimization problem may also be output. Furthermore, if it is determined that a lane change is not possible and there is sufficient calculation time, the target lane-changing trajectory ξLC may be recalculated by changing the reference value or weight of the optimization problem.

[0109] If the desired behavior is lane keeping, no judgment is made and the desired lane keeping trajectory ξLK generated by the trajectory generating unit 114 is output as is.

[0110] Next, in step ST250 of Fig. 5, the vehicle control unit 120 calculates target values ​​for steering control and vehicle speed control so that the vehicle follows the target trajectory ξ. In this 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 this embodiment, the target trajectory ξ is calculated based on the target steering angle δt at each prediction point k (k = 0, ..., N). ｔ Optimal value of (k) and target vertical acceleration ax ｔ Since the optimum value of (k) is included, the target steering angle δ ｔ Optimal value of (k) and target vertical acceleration ax ｔ The target steering angle δ is calculated by interpolating the optimal values ​​of (k) in the time direction. ｔ and the target longitudinal acceleration axt are calculated.

[0111] 5, the actuators are controlled based on the control variables by the powertrain controller 310, the brake controller 320, and the EPS controller 330. In this embodiment, the EPS motor 5 is controlled so that the steering angle δ follows the target steering angle δt, and the powertrain unit 6 and the brake unit 7 are controlled so that the longitudinal acceleration ax follows the target longitudinal acceleration axt.

[0112] <Procedure for Generating a Target Trajectory> Fig. 6 is a flowchart showing an example of a procedure for generating a target trajectory. This process is performed in step ST230 of Fig. 5.

[0113] First, in step ST231 of Fig. 6, the trajectory generation unit 114 calculates a group of reference points. Here, the group of reference points is calculated from the current time 0 to the time interval T ｓ Forecast period T ｈ Reference position X into the future ｒ , Y ｒ , reference orbital orientation ψ ｒ , reference vehicle speed V ｒ Hereafter, the reference position X ｒ (k), Y ｒThe sequence data of (k) (k=0, . . . , N) is called a reference trajectory χr.

[0114] Reference position X at each time ｒ (k), Y ｒ (k), reference orbital orientation 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 lane speed limit Vl and the preceding vehicle speed Vp. For example, V ｒ (k) = Vl. ｒ (k) does not have to be a constant value within the horizon.

[0116] Next, when the target behavior is to keep the vehicle in the lane, the reference position X ｒ (k), Y ｒ (k), reference orbital orientation ψ ｒ (k) is determined based on the X position, Y position and track direction of the lane center. ｒ (k), Y ｒ (k) and the reference vehicle speed V ｒ (k) is matched to the reference position X ｒ (k), Y ｒ (k) and the reference vehicle speed V ｒ In other words, the reference position X is set to satisfy the following two equations: ｒ (k), Y ｒ (k) is determined.

[0117]

[0118] Equation (301) is the reference position X ｒ (k), Y ｒ (k) is a function Y=l that represents the center of the vehicle lane ｅ (X) (equation (205))), the condition for being on the adjacent reference position X ｒ (k-1), Y ｒ (k-1) and X ｒ (k), Y ｒ This is the condition for the interval between (k) to be equal to the movement amount of the host vehicle during the time interval Ts.

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

[0120] When the target behavior is a lane change, for example, a function Y = l that expresses a reference trajectory for lane change (reference lane change trajectory χrLC) by connecting the center of the current lane to the center of the target lane so as to be continuous and smooth is obtained. ＬＣ (X) is generated.

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

[0122]

[0123] The reference position X determined by these ｒ (k), Y ｒ Reference lane change trajectory Y = l at (k) ＬＣ By calculating the orientation of (X), the reference orbital orientation ψ ｒ (k) can also be determined. Note that when connecting, the connections are made so that a reference lane change trajectory χrLC can be generated that will complete the lane change within the target required time tLC, for example, so that the lateral movement of the host vehicle to the target lane is completed within a distance d that the host vehicle moves longitudinally during the target required time tLC. The distance d may be calculated by integrating the reference vehicle speed Vr, or by multiplying the current vehicle speed V0 by the target required time tLC. Furthermore, if the traveling lane is curved, the connections may be made in a route coordinate system.

[0124] In addition, if it is not necessary to specify the target required time tLC for lane change and the prediction period Th is sufficiently long, the reference lane change trajectory χrLC is not generated, and the reference position X is simply calculated using the following equation instead of equation (301): ｒ (k), Y ｒ (k) may be determined.

[0125]

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

[0127] The reference position X calculated as above ｒ (k), Y ｒ (k), reference orbital orientation ψ ｒ (k), reference vehicle speed V ｒ (k) (k=0, . . . , N) is a set of reference points.

[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, a probability p ｔ The constraints may include a probability constraint that does not include probability (a constraint that is not a probability constraint) at the same time as the probability constraint.

[0129] The probability constraint is the probability p of the vehicle state satisfying a predetermined condition at a future time. ｔ The probability p of the vehicle state to satisfy a predetermined condition over the entire time series is set based on ｔ It should be noted that even if the probability constraint is set based on the probability of not satisfying a predetermined condition, it is essentially the same as the above.

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

[0131] An example of a probability constraint is "the probability p that the vehicle is located outside the no-entry area ζ" ｔ is within a threshold value,” or “the probability p ｔ is within the threshold value."

[0132] If 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," the acceleration of the host vehicle at time t is a ｔ The lower limit of acceleration is a ｍｉｎ The upper limit of acceleration is a ｍａｘ Let P[A] be the probability that event A occurs, and let p be the probability that the condition should be met. ｔ Then, the probability constraint is expressed as follows:

[0133]

[0134] The probability constraint based on the state quantity of the host vehicle may be set based on at least one of the upper and lower limits of the state quantity of the host vehicle (steering angle, steering angular velocity, lateral acceleration, lateral deviation from the center of the trajectory, etc.) Even when the host vehicle travels according to the generated trajectory, an error from the trajectory may occur due to external disturbances (wind, road resistance, slope), modeling errors, etc., so the future state quantity of the host vehicle will vary and change probabilistically.

[0135] If the probability constraint is "at each time, the probability that the vehicle is located outside the no-entry area ζ is greater than a threshold value," the position of the vehicle at time t is defined as (x ｔ , y ｔ ), and the predicted position of the obstacle (vehicle) is (X obs ｔ , Yobs ｔ ) and the predicted position of the obstacle (vehicle) (X obs ｔ , Yobs ｔ ) is defined as the no-entry area ζ ｔ Let P[A] be the probability that event A occurs, and let p be the probability that the condition should be met at time t. ｔ Then, the probability constraint is expressed as follows:

[0136]

[0137] FIG. 7 shows the no-entry area ζ shown in equation (9). ｔ 7 is a diagram conceptually illustrating an example of a no-entry area ζ corresponding to a predicted position of an obstacle. ｔ is shown, and the position of the vehicle (x ｔ , y ｔ ) is a prohibited area ζ ｔ Located outside.

[0138] In this embodiment, the no-entry area ζ (no-entry area ζ ｔ ) and the center of gravity position X of the vehicle at each prediction point k (k=0, . . . , N) ｇ (k), Y ｇ The probability that (k) does not enter (in other words, the probability that the host vehicle is located outside the no-entry zone) is set as a constraint (the above formula (9)). Methods for expressing the position of the center of gravity of the host vehicle probabilistically include a probability distribution according to a Gaussian distribution centered on each prediction point k, a probability distribution according to a uniform distribution, and a probability distribution up to predetermined upper and lower limit values.

[0139] In this embodiment, the constraint conditions are set based on the no-entry area, but the constraint conditions may be set without using the no-entry area (FIG. 1). One example is the probability constraint based on the state quantity of the host vehicle, as explained using equation (8).

[0140] Next, in step ST233 of FIG. 6, the trajectory generation unit 114 sets the evaluation function J (equation (103)). In this embodiment, the vehicle uses the reference point group (reference position X ｒ (k), Y ｒ (k), reference orbital orientation ψ ｒ (k), reference vehicle speed V ｒ The vector value functions h and hN for the evaluation items are set as follows so that a target trajectory ξ for following (k) (k=0, ..., N) can be generated and the control input at that time is small.

[0141]

[0142] eｗ (k) is the reference position X at the prediction point k (k=0, . . . , N) ｒ (k), Y ｒ (k) is the lateral deviation relative to the reference position X at the prediction point k (k=0, . . . , N) ｒ (k), Y ｒ (k) and reference orbital orientation ψ ｒ Using (k), it is expressed as equation (309).

[0143]

[0144] Furthermore, the reference values ​​r(k) and r(N) are set as follows:

[0145]

[0146] Here, V ｒ (k) is the reference vehicle speed. This allows the trajectory generation unit 114 to generate a target trajectory that allows the host vehicle to follow the reference point group with a small control input. Note that in order to improve the tracking ability to the reference point group and the ride comfort, trajectory orientation, yaw rate, longitudinal acceleration, lateral acceleration, etc. may be added to the evaluation items. Furthermore, the evaluation function may be changed depending on 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) to obtain the optimal control input u ＊ Calculate the optimal control input u ＊ For the calculation of , known means are used, such as ACADO (Automatic Control and Dynamic Optimization) developed by K. U. Leuven University, and AutoGen, an automatic code generation tool that solves optimization problems based on the C / GMRES method. When ACADO or AutoGen is used, the time series (optimal control input) u of the optimized control input at each prediction point k (k=0, ..., N-1) is calculated. ＊ That is, the output of step ST234 is equation (312).

[0148]

[0149] Here, jｘｔ ＊ (k), ω ｔ ＊ (k) (k=0,...,N-1) is the optimal value of the target pitch jerk and the target steering angular velocity. Note that the solution may be a value that makes the evaluation function fall below a predetermined threshold value, or if the evaluation function does not fall below the threshold value within a predetermined number of iterations, a value that minimizes the evaluation function within the predetermined number of iterations may be the solution.

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

[0151]

[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 the optimum value of the center of gravity position, the optimum value of the vehicle body orientation, the optimum value of the sideslip angle, the optimum value of the yaw rate, the optimum value of the vehicle speed, the optimum value of the longitudinal acceleration, the optimum value of the target longitudinal acceleration, the optimum value of the steering angle, and the optimum value of the target steering angle, respectively.

[0153] Next, in step ST236 of FIG. 6, the trajectory generating unit 114 generates a target trajectory ξ. The target trajectory ξ is calculated by the optimal state quantity x ＊ and the optimal control input u ＊ When the trajectory generation unit 114 determines whether or not to change lanes based on the information on the position of the target trajectory ξ, the target trajectory ξ includes the optimal center-of-gravity position Xｇ ＊ , Y ｇ ＊ If the trajectory generation unit 114 further determines whether or not a lane change is possible based on the steering behavior, the target trajectory ξ further includes an optimal steering angle δ ＊ and the optimal target steering angle speed ω ｔ ＊ In this embodiment, the optimal state quantity x ＊ is the target trajectory ξ. Therefore, the output of step ST236 is given by equation (314).

[0154]

[0155] The target trajectory ξ when the target behavior is lane keeping is called a target lane keeping trajectory ξLK, and the target trajectory ξ when the target behavior is lane changing is called a target lane changing trajectory ξLC.

[0156] As explained in step ST231, when the target behavior is different, at least the reference trajectory χr is different. However, in addition to this, the item or value of the constraint may be changed in step ST232, or the item or value of the evaluation function may be changed in step ST233.

[0157] <Probability p ｔ How to set the probability p that should satisfy the conditions in the probability constraint ｔ The following are examples of how to set this:

[0158] First, a setting based on time can be considered. When a probability constraint is set so that a predetermined condition is satisfied at each time, the probability p ｔ The magnitude of may vary based on future time, for example, the further in the future the time, the less likely the condition should be met.

[0159] FIG. 8 shows the probability p ｔ 8 is a diagram showing an example of the relationship between the probability p ｔ As shown in the example in FIG. 8, the probability p ｔcan be set low.

[0160] 9 is a diagram showing an example of the probability distribution of no-entry areas in the near future. In Fig. 9, the vertical axis represents probability density, and the horizontal axis represents position. The hatched area in Fig. 9 corresponds to the no-entry area.

[0161] In contrast, Fig. 10 is a diagram showing an example of the probability distribution of no-entry areas in the distant future. In Fig. 10, the vertical axis indicates probability density, and the horizontal axis indicates position. The range indicated by diagonal lines in Fig. 10 corresponds to the no-entry areas, and the probability density is lower and the position range is wider than in Fig. 9. In other words, the variance of the no-entry areas is larger. Therefore, the probability p that should be satisfied under the same conditions as in Fig. 9 is ｔ If the above equation is set, the probability constraint is imposed even in a no-entry area where the probability density is sufficiently low, and the range in which the probability constraint is satisfied (the white area in FIG. 10) becomes excessively narrow.

[0162] On the other hand, Fig. 11 is a diagram showing an example of the probability distribution of a changed no-entry area in the distant future. In Fig. 11, the vertical axis indicates probability density, and the horizontal axis indicates position. The hatched area in Fig. 11 corresponds to the changed no-entry area, and the spread of the probability density is the same as in Fig. 10, but since the range has been changed so that the no-entry area does not include areas with low probability density, the position range is about the same as in Fig. 9. This change is made by changing the probability p ｔ This corresponds to setting a low value. This prevents the variation in the no-entry zone from becoming excessively large, and prevents the range that satisfies the probability constraint (the white area in FIG. 11 ) from becoming excessively narrow. As a result, the chances of the host vehicle being able to perform the target action increase.

[0163] Next, a setting based on distance may 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 shows the probability p ｔ12 is a diagram showing an example of the relationship between the probability p ｔ , and the horizontal axis represents the distance from the current position. As shown in the example in FIG. 12, as the distance of the position on the track from the current position of the vehicle increases, the probability p ｔ can be set low.

[0165] As the distance from the current position increases, the variation in the probability density at the position on the orbit increases. Therefore, the probability p ｔ By setting ρ low, it is possible to prevent the range in which the probability constraint is satisfied from being excessively narrowed by events with low probability density, thereby increasing the chances of the host vehicle being able to execute the target action.

[0166] Next, the setting based on the type of behavior can be considered. The probability p ｔ may be set based on at least one of the type of action that the host vehicle is currently taking and the type of action that the host vehicle is scheduled to take in the future.

[0167] Here, in the case of a vehicle, the types of actions include maintaining the current state, lane following, lane change, turning right or left, stopping, obstacle avoidance, parking, etc. Furthermore, the actions currently being performed by the vehicle and the actions that will be performed in 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 in which approaching an obstacle is undesirable, the probability of approaching the obstacle can be changed, thereby improving comfort during driving.

[0169] Furthermore, when the current behavior of the vehicle differs from the behavior it plans to perform in the future, the probability p ｔ For example, if the current behavior type is lane keeping and the next behavior type is lane changing, the probability p ｔ can be set high.

[0170] FIG. 13 shows the probability p ｔ13 is a diagram showing an example of the relationship between the probability p ｔ As shown in the example in FIG. 13, the probability p ｔ is set low, but if the type of target behavior (the behavior planned to be performed in the future) is different from the type of behavior currently being performed, the probability p ｔ is set high.

[0171] According to the above, when the type of behavior is different, the constraints become stricter, and since the change in type of behavior is made under such strict constraints, the probability of success (the probability of achieving safe driving) is increased, thereby improving the comfort of driving.

[0172] From the above, the trajectory generation unit 114 can determine that the next behavior type is executable when a trajectory that satisfies the constraint conditions is obtained, whereas it can determine that the next behavior type is not executable when a trajectory that satisfies the constraint conditions is not obtained.

[0173] Next, a setting based on the degree of necessity can be considered. ｔ may be set based on the degree of necessity of the behavior type. For example, the higher the degree of necessity of the behavior type, the higher the probability p ｔ may be set lower. Here, the degree of necessity can be calculated based on, for example, the relationship between the road structure and the behavior type of the host vehicle. For example, when traveling on a merging road, the degree of necessity of a lane change is increased as the host vehicle approaches the end of the merging road. Also, when there is a branching road on the track and the host vehicle is traveling on a lane that is not a branching lane, the degree of necessity of a lane change is increased as the host vehicle approaches the branching point. Also, if the host vehicle wants to turn right at an intersection, but the required time is not significantly different if the host vehicle also turns right at the next intersection, the degree of necessity of a right turn is decreased.

[0174] <Modification of Probability Constraints> The conditional expressions of the probability constraints may be modified. Specifically, they may be converted into equivalent expressions, approximate expressions, or stricter conditional expressions.

[0175] For example, the probability constraint corresponding to "at each time, the probability that the acceleration of the host vehicle is within a predetermined range is greater than a threshold value" is assumed to be as follows:

[0176]

[0177] On the other hand, if the condition can be transformed into a speed condition, the speed of the vehicle is V ｔ The lower limit of the speed is V Ｐ，ｍｉｎ The upper limit of the speed is V Ｐ，ｍａｘ can be transformed as follows:

[0178]

[0179] Furthermore, the probability constraint corresponding to "the probability that the vehicle is located outside the no-entry area at each time is greater than a threshold value" is assumed to be expressed as follows:

[0180]

[0181] On the other hand, taking into consideration the variation in the predicted position of the obstacle, the conditions can be rewritten as a transformed no-entry area, which is an area that the host vehicle should not enter in order to satisfy the above formula. This transformed no-entry area is called ζ Ｐ，ｔ Then the probability constraint can be expressed in a probability-free form as follows:

[0182]

[0183] Specifically, it is transformed as follows: First, the no-entry area ζ of the obstacle is ｔ Let be inside the ellipse shown below.

[0184]

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

[0186] FIG. 14 shows the expected value (μ Ｘｏｂｓｔ , μ Ｙｏｂｓｔ ) the no-entry area ζ ｔ and the position when there is variation (X1 obs ｔ , Y1obs ｔ ) the no-entry area ζ1 ｔ As shown in FIG. 14, the no-entry area ζ ｔ and prohibited area ζ1 ｔ The range varies depending on the location of the obstacle. ｔ Determine the size of d ｘ and d ｙ is treated deterministically.

[0187] In this case, the equation can be transformed as follows: First, the obstacle position is determined with probability p ｔ This region is determined by the expected value (μ Ｘｏｂｓｔ , μ Ｙｏｂｓｔ ) = (0, 0), standard deviation (σ Ｘｏｂｓｔ , σ Ｙｏｂｓｔ If ) = (1, 1), it will be inside a circle of radius r centered at the origin, which is calculated by the following formula. Ｘｏｂｓｔ , μ Ｙｏｂｓｔ ), standard deviation (σ Ｘｏｂｓｔ , σ Ｙｏｂｓｔ ), then (μ Ｘｏｂｓｔ , μ Ｙｏｂｓｔ ) in the x direction. Ｘｏｂｓｔ times, σ in the y direction Ｙｏｂｓｔ It will be inside the doubled ellipse.

[0188] The formula f(x, y) for the two-dimensional standard Gaussian distribution is written as follows:

[0189]

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

[0191]

[0192] If the standard deviation is (1, 1), then the probability p ｔ The range that exists is P(r) = p ｔSolving this, we get the following:

[0193]

[0194] Therefore, the predicted obstacle position (Xobs ｔ , Yobs ｔ ) is expected to be (μ Ｘｏｂｓｔ , μ Ｙｏｂｓｔ ), with a standard deviation of (σ Ｘｏｂｓｔ , σ Ｙｏｂｓｔ ) is obtained as a Gaussian distribution, the obstacle position is ｔ The range that exists is inside the ellipse expressed by the following formula.

[0195]

[0196] The no-entry area for an obstacle is expressed by equation (1), and the obstacle position (X obs ｔ , Yobs ｔ When the object 1 moves within the ellipse expressed by equation (6), the range of the area that the no-entry area can take can be approximately expressed as the inside of the following ellipse:

[0197]

[0198] Therefore, if the position of the vehicle is within the no-entry area ζ ｔ The probability that it exists outside of p ｔ The transformed no-entry area ζ is an area into which the position of the host vehicle must not enter because it is larger than Ｐ，ｔ is inside the ellipse expressed by equation (7).

[0199] FIG. 15 shows the deformation forbidden area ζ Ｐ，ｔ As shown in FIG. 15, the post-deformation no-entry area ζ Ｐ，ｔ is the prohibited area ζ ｔ Its scope extends beyond the

[0200] By transforming the conditional equations (equational transformation or approximation transformation) as described above, the probability constraint equations become computer-friendly, expressed in terms that do not include probability, while maintaining the effect of imposing probability constraints by probabilistically viewing the moving body (subject vehicle). This reduces the computational load and improves the computation speed.

[0201] In this embodiment, a case has been shown in which a target trajectory ξ is generated based on acquired vehicle information, and vehicle control is performed after determining whether or not a lane change is possible based on the target trajectory ξ. However, the vehicle state quantities may be estimated in advance using known techniques such as a low-pass filter, an observer, a Kalman filter, or a particle filter, and the target action that the vehicle should take and the target lane in which the vehicle should travel may be decided based on obstacle information, road information, and vehicle information (vehicle state quantities).

[0202] The above decision-making can use known techniques such as finite state machines, ontologies, decision trees, reinforcement learning, and Markov decision processes. In this embodiment, a finite state machine is used for decision-making, and when autonomous driving starts, the target behavior is to maintain the lane, and the need for a lane change is determined based on the destination and the current lane the vehicle is traveling in, and the target behavior can be a lane change. Alternatively, the need for overtaking of the vehicle can be determined based on movement prediction information, and the target behavior can be a lane change if overtaking is necessary. Note that when the target behavior is a lane change, it is also determined whether to change lanes to the right or left. This determination can be made based on, for example, the position of the overtaking lane.

[0203] For example, if the target action is to maintain the lane, the target lane is the own lane. If the target action is to change lanes to the right, the target lane is the right lane. However, the moment the own vehicle crosses a dividing line to move into the right lane during a lane change, the target lane becomes the right lane as seen from the original lane, i.e., the own lane after crossing the dividing line. The same applies to a lane change to the left.

[0204] <Regarding the Effects Produced by the Embodiments Described Above> Next, examples of the effects produced by the embodiments described above will be described. Note that in the following description, the effects will be described based on the specific configurations exemplified in the embodiments described above, but these may be replaced with other specific configurations exemplified in the present specification to the extent that similar effects are produced. In other words, for convenience, only one of the associated specific configurations may be described as a representative below, but the representatively described specific configuration may be replaced with another associated specific configuration.

[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 (host vehicle 1) passing through a trajectory must satisfy, and a trajectory generation unit 114 for generating a trajectory along which the host vehicle 1 will pass so as to satisfy the constraint conditions. The constraint conditions are set based on the probability of a state of the host vehicle 1 that must satisfy a predetermined condition.

[0206] With this configuration, a trajectory is set to satisfy constraints based on the probability of the state of the moving body (vehicle). As the moving body is perceived as having a probabilistic range, it becomes easier to satisfy the constraints, and it becomes possible to set a trajectory that does not impose excessive constraints on unlikely events, thereby increasing the opportunities for the vehicle to perform the desired action.

[0207] Furthermore, even if other configurations shown as examples in this specification are appropriately added to the above configuration, that is, even if other configurations in this specification that were not mentioned as the above configuration are appropriately added, the same effect can be achieved.

[0208] Furthermore, according to the embodiment described above, the trajectory generation device generates a no-entry area ζ (or no-entry area ζ ｔThe vehicle control system includes a no-entry area setting unit 112 for setting a no-entry area. The constraint condition is set based on the probability that the vehicle 1 is outside the no-entry area. With this configuration, whether or not the constraint condition is satisfied is determined based on the probability that the vehicle 1 is located outside the no-entry area. This makes it possible to set a trajectory that does not impose excessive constraints on unlikely events, thereby increasing the opportunities for the vehicle to perform the desired action.

[0209] Furthermore, according to the embodiment described above, the trajectory generation device includes an obstacle movement prediction unit 111 for probabilistically predicting the state of an obstacle. Then, the no-entry area setting unit 112 sets the no-entry area ζ based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit 111. ｔ According to this configuration, the no-entry area is set based on the probabilistically indicated positions of obstacles, and as a result, the no-entry area is captured probabilistically, making it possible to set a trajectory that is not excessively restricted by unlikely events, thereby increasing the opportunities for the host vehicle to perform the intended action.

[0210] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 transforms a term indicating the probability of the state of the vehicle 1 in a conditional expression indicating a constraint condition into a term that does not include a probability. With this configuration, the calculation load is reduced and the calculation speed is improved. Furthermore, a trajectory can be generated using a conventional deterministic calculation method.

[0211] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the host vehicle 1 under 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. This configuration makes it possible to prevent the range that satisfies the probability constraint from becoming excessively narrow. As a result, excessive guarantees are not made in the distant future, and the opportunities for the host vehicle to execute the target action are increased.

[0212] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets a lower probability of the state of the host vehicle 1 under the constraint conditions 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 increases. This configuration makes it possible to prevent the range that satisfies the probability constraint from becoming excessively narrow. As a result, excessive guarantees are not made in the distant future, and the opportunities for the host vehicle to execute the target action increase.

[0213] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets, in the constraint conditions, the probability of the state of the host vehicle 1 at a position on the trajectory generated by the trajectory generation unit 114, based on the distance between the position on the trajectory and the current position of the host vehicle 1. With this configuration, there is no excessive guarantee for events with low probability in the distance, and therefore the chances of the host vehicle being able to execute the target action increase.

[0214] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets a lower probability of the state of the vehicle 1 at the position on the trajectory as the distance between the position on the trajectory and the current position of the vehicle 1 increases. With this configuration, there is no excessive guarantee for events with low probability in the distance, and the chances of the vehicle being able to execute the target action increase.

[0215] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the vehicle 1 under the constraint condition based on at least one of the current action type of the vehicle 1 and the next action type of the vehicle 1. With this configuration, for example, when approaching an obstacle is an undesirable action, the probability of approaching the obstacle can be changed, thereby improving comfort.

[0216] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets the probability of the state of the vehicle 1 under the constraint conditions higher when the current action type of the vehicle 1 and the next action type to be performed by the vehicle 1 are different than when they are the same. With this configuration, the constraint conditions become stricter when the action types are different, and since the change in action type is made under such strict constraint conditions, the probability of success (probability of realizing safe driving) is increased, thereby improving driving comfort.

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

[0218] Furthermore, according to the embodiment described above, the constraint condition setting unit 113 sets the degree of necessity of the behavior type based on the relationship between the trajectory structure at the position on the trajectory generated by the trajectory generation unit 114 and the behavior type of the vehicle 1. With this configuration, it is possible to prioritize the realization of behaviors with a high degree of necessity.

[0219] Furthermore, according to the embodiment described above, when the trajectory generation unit 114 obtains a trajectory that satisfies the constraint conditions, it determines that the next action type to be performed by the vehicle 1 is feasible. Furthermore, when the trajectory generation unit 114 does not obtain a trajectory that satisfies the constraint conditions, it determines that the next action type to be performed by the vehicle 1 is not feasible. With this configuration, it is possible to determine the feasibility of the next action type to be performed based on whether or not a trajectory that satisfies the constraint conditions has been obtained.

[0220] According to the embodiment described above, in the trajectory generation method, constraint conditions that must be satisfied by the host vehicle 1 traveling along the trajectory are set. Then, a trajectory that the host vehicle 1 travels along is generated so as to satisfy the constraint conditions. Then, the constraint conditions are set based on the probability of the state of the host vehicle 1 that should satisfy the predetermined conditions.

[0221] With this configuration, a trajectory is set to satisfy constraints based on the probability of the state of the moving body (vehicle). As the moving body is perceived as having a probabilistic range, it becomes easier to satisfy the constraints, and it becomes possible to set a trajectory that does not impose excessive constraints on unlikely events, thereby increasing the opportunities for the vehicle to perform the desired action.

[0222] Unless otherwise specified, the order in which the processes are performed can be changed.

[0223] Furthermore, even if other configurations shown as examples in this specification are appropriately added to the above configuration, that is, even if other configurations in this specification that were not mentioned as the above configuration are appropriately added, the same effect can be achieved.

[0224] <Regarding Modifications of the Embodiments Described Above> In the embodiments described above, the dimensions, shapes, relative positional relationships, and implementation conditions of each component may be described, but these are merely examples in all aspects and are not limiting.

[0225] Thus, numerous variations and equivalents not shown are contemplated within the scope of the technology disclosed herein, including, for example, the modification, addition, or omission of at least one component.

[0226] Furthermore, unless a contradiction arises, when it is stated in the above-described embodiments that "one" component is provided, "one or more" of that component may be provided.

[0227] Furthermore, each component in the embodiments described above is a conceptual unit, and the scope of the technology disclosed in this specification includes cases where one component is made up of multiple structures, cases where one component corresponds to a part of a structure, and even cases where multiple components are provided in one structure.

[0228] Furthermore, each of the components in the embodiments described above includes structures having other structures or shapes as long as they perform the same function.

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

[0230] Various aspects of the present disclosure are summarized below as appendices.

[0231] (Supplementary Note 1) A trajectory generation device comprising: a constraint condition setting unit for setting constraint conditions that a moving body passing through a trajectory must satisfy; and a trajectory generation unit for generating the trajectory that the moving body will pass through so as to satisfy the constraint conditions, wherein the constraint conditions are set based on the probability of a state of the moving body that should satisfy a predetermined condition.

[0232] (Supplementary Note 2) The trajectory generation device according to Supplementary Note 1, further comprising a no-entry area setting unit for setting a no-entry area, which is an area where the moving object is prohibited from entering, and the constraint condition is set based on a probability that the moving object is outside the no-entry area.

[0233] (Supplementary Note 3) The trajectory generation device according to Supplementary Note 2, further comprising an obstacle movement prediction unit for probabilistically predicting a state of an obstacle, wherein the no-entry area setting unit sets the no-entry area based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit.

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

[0235] (Supplementary Note 5) The trajectory generation device according to any one of Supplementary Notes 1 to 4, wherein the constraint condition setting unit sets a probability of a state of the moving object under the constraint condition based on a time difference between a current time and a time when the moving object passes through the trajectory generated by the trajectory generation unit.

[0236] (Supplementary Note 6) The trajectory generation device according to Supplementary Note 5, wherein the constraint condition setting unit sets a lower probability of the state of the moving body under the constraint condition 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 increases.

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

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

[0239] (Supplementary Note 9) The trajectory generation device according to any one of Supplementary Notes 1 to 8, wherein the constraint condition setting unit sets the probability of the state of the moving object under the constraint condition based on at least one of a current action type of the moving object and a next action type to be performed by the moving object.

[0240] (Supplementary Note 10) The trajectory generation device according to Supplementary Note 9, wherein the constraint condition setting unit sets the probability of the state of the moving body under the constraint condition to be higher when the current action type of the moving body and the next action type to be performed by the moving body are different than when the two are the same.

[0241] (Supplementary Note 11) The trajectory generation device according to Supplementary Note 9 or 10, wherein the constraint condition setting unit sets a probability of a state of the moving object under the constraint condition based on a degree of necessity of the action type.

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

[0243] (Supplementary Note 13) A trajectory generation device according to any one of Supplementary Notes 1 to 12, wherein the trajectory generation unit determines that the next action type to be performed by the moving object is executable when the trajectory that satisfies the constraint condition is obtained, and determines that the next action type to be performed by the moving object is not executable when the trajectory that satisfies the constraint condition is not obtained.

[0244] (Supplementary Note 14) A trajectory generation method, comprising: setting constraint conditions to be satisfied by a moving body passing through a trajectory; generating the trajectory along which the moving body passes so as to satisfy the constraint conditions; and setting the constraint conditions based on the probability of a state of the moving body that should satisfy a predetermined condition.

[0245] 1 Vehicle, 2 Steering wheel, 3 Steering shaft, 4 Steering unit, 5 EPS motor, 6 Power train unit, 7 Brake unit, 11 Forward 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 No entry area setting unit, 113 Constraint condition setting unit, 114 Trajectory generation unit, 120 Vehicle control unit, 200 Information acquisition unit, 210 Vehicle information acquisition unit, 220 Obstacle information acquisition unit, 230 Road information acquisition unit, 300 Controller unit, 310 Powertrain controller, 320 brake controller, 330 EPS controller, 500 vehicle control system, 500A vehicle control system, 500B vehicle control system.

Claims

1. A trajectory generation device comprising: a constraint condition setting unit for setting constraint conditions that a moving body passing through a trajectory must satisfy; and a trajectory generation unit for generating the trajectory that the moving body will pass through so as to satisfy the constraint conditions, wherein the constraint conditions are set based on the probability of the moving body's state satisfying predetermined conditions.

2. A trajectory generation device according to claim 1, further comprising a no-entry area setting unit for setting a no-entry area, which is an area where the moving object is prohibited from entering, and wherein the constraint condition is set based on the probability that the moving object will be outside the no-entry area.

3. A trajectory generation device as claimed in claim 2, further comprising an obstacle movement prediction unit for probabilistically predicting the state of an obstacle, wherein the no-entry area setting unit sets the no-entry area based on the state of the obstacle probabilistically predicted by the obstacle movement prediction unit.

4. A trajectory generation device according to any one of claims 1 to 3, wherein the constraint condition setting unit transforms a term indicating the probability of the state of the moving body in a conditional expression indicating the constraint condition into a term that does not include probability.

5. A trajectory generation device according to any one of claims 1 to 4, wherein the constraint condition setting unit sets the probability of the state of the moving object under the constraint condition based on the time difference between the current time and the time when the moving object passes through the trajectory generated by the trajectory generation unit.

6. A trajectory generation device according to claim 5, wherein the constraint condition setting unit sets the probability of the state of the moving body under the constraint conditions to be lower the greater the time difference between the current time and the time when the moving body passes through the trajectory generated by the trajectory generation unit.

7. A trajectory generation device according to any one of claims 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 under the constraint condition based on the distance between the position on the trajectory and the current position of the moving body.

8. A trajectory generation device according to claim 7, wherein the constraint condition setting unit sets a lower probability of the state of the moving body at the position on the trajectory as the distance between the position on the trajectory and the current position of the moving body increases.

9. A trajectory generation device according to any one of claims 1 to 8, wherein the constraint condition setting unit sets the probability of the state of the moving object under the constraint condition based on at least one of the current action type of the moving object and the action type that the moving object will next perform.

10. A trajectory generation device as described in claim 9, wherein the constraint condition setting unit sets the probability of the state of the moving body under the constraint conditions to be higher when the current action type of the moving body and the next action type to be performed by the moving body are different than when they are the same.

11. A trajectory generation device according to claim 9 or 10, wherein the constraint condition setting unit sets the probability of the state of the moving object under the constraint condition based on the degree of necessity of the action type.

12. A trajectory generation device according to claim 11, wherein the constraint condition setting unit sets the degree of necessity of the behavior type based on the relationship between the trajectory structure at a position on the trajectory generated by the trajectory generation unit and the behavior type of the moving object.

13. A trajectory generation device according to any one of claims 1 to 12, wherein the trajectory generation unit determines that the next type of action to be taken by the moving object is executable when the trajectory that satisfies the constraint conditions is obtained, and determines that the next type of action to be taken by the moving object is not executable when the trajectory that satisfies the constraint conditions is not obtained.

14. A trajectory generation method, comprising: setting constraint conditions that must be satisfied by a moving body passing through a trajectory; generating the trajectory that the moving body will pass through so as to satisfy the constraint conditions; and setting the constraint conditions based on the probability of the moving body's state satisfying predetermined conditions.

Images