JP2018095149A - Locus evaluation device, locus evaluation method and locus evaluation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a locus evaluation device, a locus evaluation method and a locus evaluation program capable of evaluating a locus more properly.SOLUTION: A locus evaluation device comprises: a generation part for generating a future locus where a vehicle travels; a prediction part for predicting a future position of an object in the surrounding of the vehicle; and an evaluation part for performing evaluation based on a relative position relationship with the future position of the object predicted by the prediction part in a first direction along a longitudinal direction of a road, and a relative position relationship in a second direction along a width direction of a road, for each of plural points on the locus generated by the generation part where passage timings of a vehicle are different from each other, and evaluating the locus based on the evaluation result for every point.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a trajectory evaluation apparatus, a trajectory evaluation method, and a trajectory evaluation program.

  Conventionally, the surrounding environment of the host vehicle is recognized, the current risk level is set for each target of the recognized surrounding environment, and the current risk level is set according to at least one of the relative speed and relative acceleration between each target and the host vehicle. Correct and add the risk level of each corrected target, predict the temporal change of the position of each target, predict the temporal change of the added risk level, and based on the predicted temporal change of the risk level In addition, for each position of the host vehicle at each time, the minimum point of the risk is calculated from the risk in the current vehicle width direction at that position, and the turning control amount of the host vehicle is calculated based on at least each minimum point Then, an invention of a vehicle driving support device that generates an avoidance route for the host vehicle based on a turn control amount and determines a final avoidance route is disclosed (see Patent Document 1).

Japanese Patent No. 4970156

  In the above conventional technology, the minimum point of the risk is calculated from the risk in the width direction of the vehicle exclusively for each position of the vehicle at each time, and the turning control amount of the vehicle is calculated based on the minimum point. Yes. For this reason, the calculation accuracy of the risk level may not be sufficient.

  The present invention has been made in view of such circumstances, and an object thereof is to provide a trajectory evaluation apparatus, a trajectory evaluation method, and a trajectory evaluation program that can evaluate a trajectory more appropriately. .

  The invention described in claim 1 includes a generation unit (123A, 125A) that generates a future trajectory on which the vehicle travels, a prediction unit (123B, 125B) that predicts a future position of an object around the vehicle, and the generation. A plurality of points (coordinates) on the trajectory generated by the unit, each of a plurality of points having different passing timings of the vehicle, and a future position of the object predicted by the prediction unit Evaluation is performed based on the relative positional relationship in the first direction along the longitudinal direction and the relative positional relationship in the second direction along the width direction of the road, and the trajectory is determined based on the evaluation result for each point. It is a trajectory evaluation apparatus provided with the evaluation part (123C, 125C) to evaluate.

  According to a second aspect of the present invention, in the first aspect of the invention, the evaluation unit further includes, for each of the plurality of points, further based on a degree of variation regarding the second direction of the plurality of points on the trajectory. An evaluation is performed.

  According to a third aspect of the present invention, in the first aspect of the invention, the evaluation unit further evaluates each of the plurality of points on the track based on the degree of turning of the vehicle.

  The invention according to claim 4 is the invention according to any one of claims 1 to 3, wherein the evaluation unit further evaluates each of the plurality of points on the track based on conditions relating to the lane. Is what you do.

  The invention according to claim 5 is the invention according to claim 4, wherein the condition relating to the lane is a condition relating to a deviation from a preset recommended lane.

  The invention according to claim 6 is the invention according to any one of claims 1 to 5, wherein the evaluation unit has at least a relative positional relationship with respect to the first direction, the speed of the vehicle, or the object. The evaluation is performed using a threshold value that varies based on the speed.

  According to a seventh aspect of the present invention, in the sixth aspect of the present invention, the evaluation unit is configured to at least relate to the object existing ahead of the vehicle with respect to the relative positional relationship with respect to the first direction. The evaluation is performed using a threshold value that varies based on the speed of the vehicle, and the object existing behind the vehicle is evaluated using a threshold value that varies based on the speed of the object.

  The invention according to claim 8 is the invention according to any one of claims 1 to 7, further comprising a determination unit that determines the type of the object, wherein the evaluation unit is determined by the determination unit. The evaluation criteria are made different based on the type of the object.

  The invention according to claim 9 is the invention according to any one of claims 1 to 8, wherein the generation unit generates a plurality of the trajectories, and the evaluation unit includes a plurality of generations generated by the generation unit. Each of the trajectories is evaluated, and a trajectory with a good evaluation result is selected.

  According to a tenth aspect of the invention, in the ninth aspect of the invention, the generation unit repeatedly generates the trajectory until a trajectory with a good evaluation result is selected by the evaluation unit.

  According to an eleventh aspect of the present invention, there is provided a generation unit that generates a future trajectory on which a vehicle travels, and a plurality of points on the track generated by the generation unit, and a plurality of points having different passing timings of the vehicle. Each of the track evaluation apparatuses includes an evaluation unit that performs evaluation based on a degree of change of a point related to a direction along the width direction of the road, and evaluates the track based on an evaluation result for each point.

  In the invention according to claim 12, the computer generates a future trajectory on which the vehicle travels, predicts a future position of an object around the vehicle, and is a plurality of points on the trajectory, and passes through the vehicle For each of the plurality of points having different timings, a relative positional relationship with respect to the predicted future position of the object in the first direction along the longitudinal direction of the road and a second position along the width direction of the road This is a trajectory evaluation method in which an evaluation is performed based on a relative positional relationship with respect to a direction, and the trajectory is evaluated based on an evaluation result for each point.

  The invention according to claim 13 causes a computer to generate a future trajectory on which the vehicle travels, predicts future positions of objects around the vehicle, and includes a plurality of points on the trajectory that pass through the vehicle. For each of the plurality of points having different timings, a relative positional relationship with respect to the predicted future position of the object in the first direction along the longitudinal direction of the road and a second position along the width direction of the road A trajectory evaluation program for performing an evaluation based on a relative positional relationship with respect to a direction and for evaluating the trajectory based on an evaluation result for each point.

  According to the first to fifth and ninth to thirteenth inventions, the trajectory can be evaluated more appropriately.

  According to the sixth and seventh aspects of the invention, the track can be evaluated more appropriately based on the speed at which the vehicle and the object approach each other.

  According to the eighth aspect of the present invention, it is possible to travel with a margin with respect to an object that particularly requires attention to approach.

It is a lineblock diagram of vehicles system 1 using a track evaluation device concerning a 1st embodiment. It is a figure which shows a mode that the relative position and attitude | position of the own vehicle M with respect to the driving lane L1 are recognized by the own vehicle position recognition part 122. FIG. It is a figure which shows a mode that a target track is produced | generated based on a recommended lane. It is a figure for demonstrating an example of the target track | orbit production | generation method. It is a figure for demonstrating an example of the target track | orbit production | generation method. It is a figure for _{demonstrating} space _| interval _Sie and _Wie . It is a diagram for explaining penalty function _{P 2 (S i, W i} ). It is a figure for demonstrating the other example of the target track | orbit production | generation method. It is a flowchart which shows an example of the flow of the process performed by the action plan production | generation part 123. FIG. It is a flowchart which shows the other example of the flow of the process performed by the action plan production | generation part 123. FIG. It is a block diagram of the vehicle system 2 using the track | orbit evaluation apparatus which concerns on 2nd Embodiment.

  Hereinafter, embodiments of a trajectory evaluation apparatus, a trajectory evaluation method, and a trajectory evaluation program according to the present invention will be described with reference to the drawings.

<First Embodiment>
[overall structure]
In the first embodiment, the trajectory evaluation apparatus is described as being applied to an autonomous driving vehicle. FIG. 1 is a configuration diagram of a vehicle system 1 that uses the trajectory evaluation apparatus according to the first embodiment. The vehicle on which the vehicle system 1 is mounted is, for example, a vehicle such as a two-wheel, three-wheel, or four-wheel vehicle, and a drive source thereof is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. The electric motor operates using electric power generated by a generator connected to the internal combustion engine or electric discharge power of a secondary battery or a fuel cell.

  The vehicle system 1 includes, for example, a camera 10, a radar device 12, a finder 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a navigation device 50, and an MPU (Micro-Processing). Unit) 60, a vehicle sensor 70, a driving operator 80, an automatic driving control unit 100, a travel driving force output device 200, a brake device 210, and a steering device 220. These devices and devices are connected to each other by a multiple communication line such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, or the like. The configuration illustrated in FIG. 1 is merely an example, and a part of the configuration may be omitted, or another configuration may be added.

  The camera 10 is a digital camera using a solid-state image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). One or a plurality of cameras 10 are attached to any part of a vehicle (hereinafter referred to as the host vehicle M) on which the vehicle system 1 is mounted. When imaging the front, the camera 10 is attached to the upper part of the front windshield, the rear surface of the rearview mirror, or the like. For example, the camera 10 periodically and repeatedly images the periphery of the host vehicle M. The camera 10 may be a stereo camera.

  The radar device 12 radiates a radio wave such as a millimeter wave around the host vehicle M and detects a radio wave (reflected wave) reflected by the object to detect at least the position (distance and direction) of the object. One or a plurality of radar devices 12 are attached to arbitrary locations of the host vehicle M. The radar apparatus 12 may detect the position and speed of an object by FM-CW (Frequency Modulated Continuous Wave) method.

  The finder 14 is LIDAR (Light Detection and Ranging or Laser Imaging Detection and Ranging) that measures the scattered light with respect to the irradiation light and detects the distance to the target. One or a plurality of the finders 14 are attached to arbitrary locations of the host vehicle M.

  The object recognition device 16 performs sensor fusion processing on the detection results of some or all of the camera 10, the radar device 12, and the finder 14, and recognizes the position, type, speed, and the like of the object. The object recognition device 16 outputs the recognition result to the automatic driving control unit 100.

  The communication device 20 communicates with other vehicles existing around the host vehicle M using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), or wirelessly. It communicates with various server apparatuses via a base station.

  The HMI 30 presents various information to the occupant of the host vehicle M and accepts an input operation by the occupant. The HMI 30 includes various display devices, speakers, buzzers, touch panels, switches, keys, and the like.

  The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The first map information 54 is stored in a storage device such as an HDD (Hard Disk Drive) or a flash memory. Holding. The GNSS receiver specifies the position of the host vehicle M based on the signal received from the GNSS satellite. The position of the host vehicle M may be specified or supplemented by an INS (Inertial Navigation System) using the output of the vehicle sensor 70. The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, and the like. The navigation HMI 52 may be partly or wholly shared with the HMI 30 described above. The route determination unit 53, for example, determines the route from the position of the host vehicle M specified by the GNSS receiver 51 (or any input position) to the destination input by the occupant using the navigation HMI 52. This is determined with reference to one map information 54. The first map information 54 is information in which a road shape is expressed by, for example, a link indicating a road and nodes connected by the link. The first map information 54 may include road curvature and POI (Point Of Interest) information. The route determined by the route determination unit 53 is output to the MPU 60. Further, the navigation device 50 may perform route guidance using the navigation HMI 52 based on the route determined by the route determination unit 53. In addition, the navigation apparatus 50 may be implement | achieved by the function of terminal devices, such as a smart phone and a tablet terminal which a user holds, for example. Further, the navigation device 50 may acquire the route returned from the navigation server by transmitting the current position and the destination to the navigation server via the communication device 20.

  For example, the MPU 60 functions as the recommended lane determining unit 61 and holds the second map information 62 in a storage device such as an HDD or a flash memory. The recommended lane determining unit 61 divides the route provided from the navigation device 50 into a plurality of blocks (for example, every 100 [m] with respect to the vehicle traveling direction), and refers to the second map information 62 for each block. Determine the recommended lane. The recommended lane determining unit 61 performs determination such as what number of lanes from the left to travel. The recommended lane determining unit 61 determines a recommended lane so that the host vehicle M can travel on a reasonable route for proceeding to the branch destination when there is a branch point or a merge point in the route.

  The second map information 62 is map information with higher accuracy than the first map information 54. The second map information 62 includes, for example, information on the center of the lane or information on the boundary of the lane. The second map information 62 may include road information, traffic regulation information, address information (address / postal code), facility information, telephone number information, and the like. Road information includes information indicating the type of road such as expressway, toll road, national road, prefectural road, road lane number, width of each lane, road gradient, road position (longitude, latitude, height). Information including 3D coordinates), curvature of lane curves, lane merging and branch point positions, signs provided on roads, and the like. The second map information 62 may be updated at any time by accessing another device using the communication device 20.

  The vehicle sensor 70 includes a vehicle speed sensor that detects the speed of the host vehicle M, an acceleration sensor that detects acceleration, a yaw rate sensor that detects an angular velocity around the vertical axis, a direction sensor that detects the direction of the host vehicle M, and the like.

  The driving operation element 80 includes, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, and other operation elements. A sensor that detects the amount of operation or the presence or absence of an operation is attached to the driving operator 80, and the detection result is the automatic driving control unit 100, or the traveling driving force output device 200, the brake device 210, and the steering device. 220 is output to one or both of 220.

  The automatic operation control unit 100 includes, for example, a first control unit 120 and a second control unit 140. The first control unit 120 and the second control unit 140 are realized by a processor (CPU) or the like executing a program (software). In addition, some or all of the functional units of the first control unit 120 and the second control unit 140 described below are LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), and FPGA (Field-Programmable Gate Array). ) Or the like, or may be realized by cooperation of software and hardware.

  The 1st control part 120 is provided with the external world recognition part 121, the own vehicle position recognition part 122, and the action plan production | generation part 130, for example. The external world recognition unit 121 includes an object type determination unit 121A. The action plan generation unit 123 includes a trajectory generation unit 123A, a future position prediction unit 123B, and an evaluation unit 123C. A combination of the object type determination unit 121A, the trajectory generation unit 123A, the future position prediction unit 123B, and the evaluation unit 123C is an example of a trajectory evaluation device.

  Based on information input from the camera 10, the radar device 12, and the finder 14 via the object recognition device 16, the external environment recognition unit 121 is in a position of an object around the host vehicle M, and is in a state such as speed and acceleration. Recognize The position of the object may be represented by a representative point such as the center of gravity or corner of the object, or may be represented by a represented area. The “state” of the object may include acceleration or jerk of both objects or “behavioral state” (for example, whether or not the lane is changed or whether or not).

  The object type determination unit 121A of the external recognition unit 121 determines the type of object (large vehicle, ordinary vehicle, truck, two-wheeled vehicle, pedestrian, guardrail, utility pole, parked vehicle, etc.). The object type determination unit 121A determines the type of the object based on, for example, the size and shape of the object imaged by the camera 10, the reception intensity in the radar device 12, and other information.

  The own vehicle position recognition unit 122 recognizes, for example, the lane (traveling lane) in which the own vehicle M is traveling, and the relative position and posture of the own vehicle M with respect to the traveling lane. The own vehicle position recognition unit 122, for example, includes a road marking line pattern (for example, an arrangement of solid lines and broken lines) obtained from the second map information 62 and an area around the own vehicle M recognized from an image captured by the camera 10. The traveling lane is recognized by comparing the road marking line pattern. In this recognition, the position of the host vehicle M acquired from the navigation device 50 and the processing result by INS may be taken into account.

  And the own vehicle position recognition part 122 recognizes the position and attitude | position of the own vehicle M with respect to a travel lane, for example. FIG. 2 is a diagram illustrating a state in which the vehicle position recognition unit 122 recognizes the relative position and posture of the vehicle M with respect to the travel lane L1. The own vehicle position recognizing unit 122 makes, for example, a line connecting the deviation OS of the reference point (for example, the center of gravity) of the own vehicle M from the travel lane center CL and the travel lane center CL in the traveling direction of the own vehicle M. The angle θ is recognized as the relative position and posture of the host vehicle M with respect to the traveling lane L1. Instead, the host vehicle position recognition unit 122 recognizes the position of the reference point of the host vehicle M with respect to any side end of the host lane L1 as the relative position of the host vehicle M with respect to the traveling lane. Also good. The relative position of the host vehicle M recognized by the host vehicle position recognition unit 122 is provided to the recommended lane determination unit 61 and the action plan generation unit 123.

  The action plan generation unit 123 determines events that are sequentially executed in the automatic driving so that the recommended lane determination unit 61 determines the recommended lane and travels along the recommended lane, and can cope with the surrounding situation of the host vehicle M. Events include, for example, a constant speed traveling event that travels in the same lane at a constant speed, a following traveling event that follows the preceding vehicle, an overtaking event that overtakes the preceding vehicle, an avoidance event that avoids obstacles, a lane change event, There are a merge event, a branch event, an emergency stop event, a handover event for ending automatic driving and switching to manual driving. Further, during execution of these events, actions for avoidance may be planned based on the surrounding situation of the host vehicle M (the presence of surrounding vehicles and pedestrians, lane narrowing due to road construction, etc.).

  The action plan generation unit 123 generates a target track on which the host vehicle M will travel in the future by the functions of the track generation unit 123A, the future position prediction unit 123B, and the evaluation unit 123C. Details of each functional unit will be described later. The target trajectory includes, for example, a velocity element. For example, the target trajectory is generated as a set of target points (orbit points) that should be set at a plurality of future reference times for each predetermined sampling time (for example, about 0 comma [sec]) and reach these reference times. The For this reason, when the space | interval of a track point is wide, it has shown running in the area between the track points at high speed.

  FIG. 3 is a diagram illustrating a state in which a target track is generated based on the recommended lane. As shown in the figure, the recommended lane is set so as to be convenient for traveling along the route to the destination. The action plan generation unit 123 activates a lane change event, a branch event, a merge event, or the like when a predetermined distance before the recommended lane switching point (may be determined according to the type of event) is reached. If it becomes necessary to avoid an obstacle during the execution of each event, an avoidance trajectory is generated as shown in the figure.

  The second control unit 140 includes a travel control unit 141. The travel control unit 141 controls the travel driving force output device 200, the brake device 210, and the steering device 220 so that the host vehicle M passes the target track generated by the action plan generation unit 123 at a scheduled time. To do.

  The traveling driving force output device 200 outputs a traveling driving force (torque) for traveling of the vehicle to driving wheels. The travel driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, and the like, and an ECU that controls these. The ECU controls the above-described configuration in accordance with information input from the travel control unit 141 or information input from the driving operator 80.

  The brake device 210 includes, for example, a brake caliper, a cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the cylinder, and a brake ECU. The brake ECU controls the electric motor in accordance with the information input from the travel control unit 141 or the information input from the driving operation element 80 so that the brake torque corresponding to the braking operation is output to each wheel. The brake device 210 may include, as a backup, a mechanism that transmits the hydraulic pressure generated by operating the brake pedal included in the driving operation element 80 to the cylinder via the master cylinder. The brake device 210 is not limited to the configuration described above, and may be an electronically controlled hydraulic brake device that controls the actuator according to information input from the travel control unit 141 and transmits the hydraulic pressure of the master cylinder to the cylinder. Good.

  The steering device 220 includes, for example, a steering ECU and an electric motor. For example, the electric motor changes the direction of the steered wheels by applying a force to a rack and pinion mechanism. The steering ECU drives the electric motor according to the information input from the travel control unit 141 or the information input from the driving operator 80, and changes the direction of the steered wheels.

[Orbit determination based on orbit evaluation]
Hereinafter, an example of the target trajectory generation method by the action plan generation unit 123 will be described. The technique described below is executed when some of the various events described above are activated.

  FIG. 4 is a diagram for explaining an example of the target trajectory generation method. First, the trajectory generating unit 123A of the action plan generating unit 123 first selects a road surface area in the target lane in the target section in a direction along the longitudinal direction of the road (traveling direction) S and a direction along the road width direction (lateral direction). ) Assuming a coordinate system with W as an axis, a grid obtained by virtually dividing a road surface region in two directions with a constant width is set. The partition width of the grid may be set to be equal in the traveling direction and the horizontal direction, or may be set to be different. The target lane includes, for example, a lane Lp in which the host vehicle M is traveling and a recommended lane Lr determined by the MPU 60 as described above. The target lane is not particularly limited and may be set arbitrarily. Further, FIG. 4 shows a straight road for the sake of simplification of explanation, but the same processing can be performed for a curve through some conversion processing.

  The trajectory generation unit 123A sets, as a target trajectory candidate, a trajectory that is specified by selecting horizontal coordinates for each grid with respect to the traveling direction with respect to a grid that is virtually set as illustrated. In the figure, a hatched portion corresponds to one target trajectory candidate. In the figure, the horizontal direction is expressed so as to have coordinates in increments of one grid, but the coordinates included in the target trajectory candidate may have coordinates after the decimal point in the horizontal direction. This target trajectory candidate is a path through which a representative point (such as the center of gravity as described above) of the host vehicle M passes. For example, the trajectory generating unit 123A generates all combinations that can be generated under a predetermined constraint as target trajectory candidates.

Hereinafter, it is assumed that the number of grids (the number of coordinates) related to the traveling direction S in the target section is N, and one target trajectory candidate includes N coordinates. Each coordinate is represented by (S _i , W _i ) (i = 1, 2,..., N). When a grid is selected every predetermined number r, one target trajectory candidate includes N / r grids.

For example, the trajectory generation unit 123A selects one discretized gradient (input), thereby determining the next coordinate (S _{i + 1} , W _{i + 1} ) based on a certain coordinate (S _i , W _i ). To do. FIG. 5 is a diagram for explaining an example of the target trajectory generation method. As shown in the figure, the trajectory generating unit 123A sets an upper limit for the inclination with respect to the traveling direction S with respect to a certain coordinate (S _i , W _i ), and sets a finite number of angles within a predetermined angle within the range up to the upper limit. Then, the coordinates at the tip extended with the angle are determined as options for the next coordinates (S _{i + 1} , W _{i + 1} ) (an example of “predetermined constraints”). In the figure, five angles of θ, 2θ, 0, −θ, and −2θ are illustrated as a finite number of angles. In this way, all combinations of a series of coordinates that are obtained in a ripple manner from the coordinates (S ₁ , W ₁ ) that are the starting points correspond to the target trajectory candidates. The trajectory generation unit 123A of the action plan generation unit 123 may select a grid every predetermined number with respect to the traveling direction S.

  The future position prediction unit 123B predicts the future position of the object recognized by the external recognition unit 121. The future position prediction unit 123B predicts the future position of the object, for example, assuming that the object moves at a constant speed. Instead of this, the future position predicting unit 123B may predict the future position of the object on the assumption that the object performs a uniform acceleration motion or a uniform jerk motion. Further, the future position predicting unit 123B predicts the future position of the object with respect to the future timing every time the host vehicle M moves by one grid in the traveling direction S in the target trajectory candidate, for example. Although the time required for the host vehicle M to move by one grid in the traveling direction S in the target track candidate depends on the future speed change of the host vehicle M, the future position prediction unit 123B may, for example, The future timing is determined as an arbitrary motion that can be predicted, such as a uniform motion, a uniform acceleration motion, a uniform jerk motion, or a motion based on a predicted motion model calculated from a probability statistical model.

  The evaluation unit 123C evaluates the target trajectory candidate generated by the trajectory generation unit 123A for each coordinate based on the relative positional relationship with the object and the like based on the evaluation result for each coordinate (for example, addition). Evaluate trajectory candidates.

  Formula (1) is a formula which shows an example of the evaluation method for every coordinate. The evaluation value Ji represented in this way indicates that the smaller the value, the better the evaluation in the grid.

C1 is a positive constant. W _ref is a position in the horizontal direction that should be the target, for example, a position corresponding to the center line of the recommended lane Lr. In each grid, as the lateral position deviates from Wref, (W _i −W _ref ) ² increases, and thus the value of J _i increases.

C2 is a positive constant. The term multiplied by C2 indicates the amount of variation in the horizontal direction between the grids on the target trajectory candidates adjacent to each other in the traveling direction. Therefore, the value of J _i increases as the vehicle M suddenly turns. Note that this term may be a term that increases as the angular velocity or steering angle (degree of turning) generated by traveling on the target trajectory candidate increases.

P ₁ (S _i , W _i ) is a penalty function related to deviation from the target lane. P ₁ (S _i , W _i ) is expressed by, for example, the formula (2). In the formula, | W _i −Wb | indicates a deviation amount from any side end portion of the target lane. Instead of | W _i −Wb |, a positive constant that is sufficiently large (the possibility that the target trajectory candidate is selected becomes very low when this is added) may be used as an element of the equation.

P ₂ (S _i , W _i ) is a penalty function related to the approach to the object. When there are a plurality of objects around the host vehicle M, P ₂ (S _i , W _i ) may be set for each of the objects. P ₂ (S _i , W _i ) is expressed by, for example, the formula (3). _Sie is an interval in the traveling direction between the _host vehicle M and the object, _Wie is an interval in the lateral direction between the _host vehicle M and the object, and _Smin and _Wmin are threshold _values . C3 is a positive constant that is sufficiently large (adding this makes it very unlikely that the target trajectory candidate will be selected). Note that, instead of C3, a value that becomes larger as the object is closer may be used as an element of the equation.

FIG. 6 is a diagram for explaining the intervals _Sie and _Wie . In the illustrated example, the object is assumed to be another vehicle m. As shown in the upper diagram of FIG. 6, when the object is present in front of the host vehicle M, the interval _Sie is, for example, the interval from the representative point R of the host vehicle M to the rear end mr of the other vehicle m. is there. Further, as shown in the lower diagram of FIG. 6, the interval _Sie is, for example, an interval from the representative point R of the host vehicle M to the front end mf of the other vehicle m when the object is present behind the host vehicle. . The interval _Wie is, for example, an interval in the horizontal direction between the representative point of the _host vehicle M and the representative point of the object. When the object is the other vehicle m, the representative point of the object is, for example, a point through which the center line in the vehicle width direction passes. Such a definition is merely an example, and may be arbitrarily defined as long as similar properties are maintained.

FIG. 7 is a diagram for explaining the penalty function P ₂ (S _i , W _i ). As shown in FIG. 7A, when _Sie ≧ _Smin and _Wie ≧ _Wmin are established, it is assumed that the other vehicle m is traveling in a lane different from the own vehicle M, for example. Since the distance is also sufficiently maintained, the penalty function P ₂ (S _i , W _i ) is zero.

As shown in FIG. 7B, when _Sie ≧ _Smin and _Wie < _Wmin are established, it is estimated that the other vehicle m is traveling in the same lane as the own vehicle M. Since the distance is sufficiently maintained, the penalty function P ₂ (S _i , W _i ) is zero.

As shown in FIG. 7C, when _Sie < _Smin and _Wie ≧ _Wmin are satisfied, the inter-vehicle distance is not sufficient, but the other vehicle m is traveling on a lane different from the own vehicle M. Therefore, even if the host vehicle M accelerates as it is, it can be safely overtaken. Therefore, the penalty function P ₂ (S _i , W _i ) is zero.

As shown in FIG. 7D, when _Sie < _Smin and _Wie < _Wmin are established, it is assumed that the other vehicle m is traveling in the same lane as the own vehicle M, and Since the inter-vehicle distance is not sufficiently maintained, the penalty function P ₂ (S _i , W _i ) has a large value C3.

Here, the threshold value W _min is a constant value, for example, but the threshold value S _min may be a variable value corresponding to the speed as shown in the equation (4). In the equation, v _x is the speed of the host vehicle M when the host vehicle M exists behind the other vehicle m, and the speed of the host vehicle M when the host vehicle M exists ahead of the other vehicle m. It is. The value th may be a fixed value or may be set to a different value depending on the event being executed. For example, it may be set small for a lane change event and large for a follow-up driving event. Also, the threshold value W _min may be a variable value corresponding to the speed in the lateral direction of the host vehicle M, similarly to the threshold value S _min .

S _min = v _x × th (4)

Further, the threshold value S _min and / or W _min in the penalty function P ₂ (S _i , W _i ) may be corrected based on the type of the object determined by the object type determination unit 121A. For example, for objects that should be avoided in particular (pedestrians, motorcycles, large vehicles, etc.), one or more correction factors may be multiplied by the threshold values S _min and / or W _min . As a result, it is possible to travel with a margin, especially for an object that should be avoided from approaching.

  When there is a lane narrowing due to a cone placed on the road in front of the host vehicle M, the cone may be regarded as an object or the target lane may be narrowed.

When the evaluation value for each coordinate is obtained by Expression (1), the evaluation unit 123C obtains the evaluation value J for the target trajectory candidate based on Expression (5). In the equation, W _N −W _ref is the difference between the horizontal position of the grid at the end point of the target trajectory candidate and the horizontal position W _ref to be targeted.

  Finally, for example, the evaluation unit 123C selects a target trajectory candidate having the smallest evaluation value J (high evaluation) and determines it as a target trajectory. As a result, the trajectory can be evaluated more appropriately.

The method described above is an example in which the horizontal position W _ref to be targeted is determined as one. The present invention is not limited to this, and a plurality of lateral positions W _ref to be targeted may be set in an overtaking event or an obstacle avoidance event. FIG. 8 is a diagram for explaining another example of the target trajectory generation method. As shown in the figure, when there is another vehicle m that travels in front of the host vehicle M at a low speed and can travel in either of the left and right lanes, the action plan generation unit 123 determines the lateral position W to be targeted. _ref is set for each of the left and right lanes (W _ref (1), W _ref (2) in the figure), and the evaluation value J is calculated for each, and the smaller (higher evaluation) evaluation value J is obtained. A target trajectory traveling in the lane may be selected. By such processing, it is possible to change the lane to a side where a more appropriate track can be generated.

  Hereinafter, the flow of the process of the action plan production | generation part 123 is demonstrated using a flowchart. FIG. 9 is a flowchart illustrating an example of the flow of processing executed by the action plan generation unit 123.

  First, the trajectory generation unit 123A generates a plurality of target trajectory candidates (step S100). Next, the future position prediction unit 123B predicts the future position of an object around the host vehicle M (step S102).

  Next, the evaluation unit 123C selects one target trajectory candidate (step S104), and performs evaluation for each coordinate (step S106). Then, evaluation for each coordinate is integrated to evaluate a target trajectory candidate (step S108).

  Next, the evaluation unit 123C determines whether or not all the target trajectory candidates generated in step S100 have been selected in step S104 (step S110). If it is determined that all the target trajectory candidates have not been selected, the process returns to step S104. On the other hand, when it is determined that all the target trajectory candidates have been selected, the evaluation unit 123C selects the target trajectory candidate having the smallest evaluation value as the target trajectory (step S112).

  In the flowchart of FIG. 9, among the plurality of target trajectory candidates, the one with the smallest evaluation value is selected, but instead, a process as described below may be performed. FIG. 10 is a flowchart illustrating another example of the flow of processing executed by the action plan generation unit 123.

  First, the future position prediction unit 123B predicts the future position of an object around the host vehicle M (step S200).

  Next, the trajectory generation unit 123A generates a target trajectory candidate (step S202). Next, the evaluation unit 123C performs evaluation for each coordinate (step S204), integrates the evaluation for each coordinate, and evaluates a target trajectory candidate (step S206).

  Next, the evaluation unit 123C determines whether or not the evaluation value of the target trajectory is equal to or less than the reference value (step S208). If the evaluation value of the target trajectory exceeds the reference value, the process returns to step S202, and the trajectory generation unit 123A generates another target trajectory candidate. On the other hand, if the evaluation value of the target trajectory is equal to or less than the reference value, the target trajectory candidate is determined as the target trajectory (step S210).

  According to the vehicle system 1 (trajectory evaluation apparatus) of the first embodiment described above, the future position of the object predicted by the future position prediction unit 123B for each of the grids on the track generated by the track generation unit 123A. Between the relative position relationship for the first direction (S) along the longitudinal direction of the road and the relative position relationship for the second direction (W) along the width direction of the road, By evaluating the trajectory based on the evaluation result for each coordinate, the trajectory can be evaluated more appropriately.

Second Embodiment
In the second embodiment, the trajectory evaluation device is described as being applied to a driving support device that performs driving support such as a change in an automobile line. FIG. 11 is a configuration diagram of the vehicle system 2 using the trajectory evaluation apparatus according to the second embodiment. In FIG. 11, components having the same functions as those in FIG. Therefore, a repetitive description thereof will be omitted.

  The vehicle system 2 automatically changes lanes based on an operation performed on an ALC (Auto Lane Change) switch 40. For example, the ALC switch 40 also serves as a direction indicator. The driving support unit 100A includes a lane change control unit 125 instead of the action plan generation unit 123 in the first embodiment. When the ALC switch 40 is operated, the lane change control unit 125 is in a predetermined condition (for example, the speed of the host vehicle M is within a specified range, and the distance from the surrounding vehicle is maintained at a reference value or more). If the condition is satisfied, the lane is automatically changed.

  When the lane change is automatically performed, the track generation unit 125A, the future position prediction unit 125B, and the evaluation unit 125C determine the target track. These functions are the same as the functions of the trajectory generation unit 123A, the future position prediction unit 123B, and the evaluation unit 123C in the first embodiment.

  According to the vehicle system 2 (trajectory evaluation apparatus) of the second embodiment described above, the trajectory can be more appropriately evaluated as in the first embodiment.

  As mentioned above, although the form for implementing this invention was demonstrated using embodiment, this invention is not limited to such embodiment at all, In the range which does not deviate from the summary of this invention, various deformation | transformation and substitution Can be added.

100 automatic driving control unit 100A driving support unit 120 first control unit 121 external world recognition unit 121A object type determination unit 122 own vehicle position recognition unit 123 behavior plan generation unit 123A track generation unit 123B future position prediction unit 123C evaluation unit 125 lane change control Unit 125A track generation unit 125B future position prediction unit 125C evaluation unit 140 second control unit 141 travel control unit

Claims (13)

A generator for generating a future track on which the vehicle travels;
A prediction unit for predicting future positions of objects around the vehicle;
The length of the road between the plurality of points on the track generated by the generation unit and the future position of the object predicted by the prediction unit for each of the plurality of points having different timings of passing the vehicle An evaluation is performed based on the relative positional relationship regarding the first direction along the direction and the relative positional relationship regarding the second direction along the width direction of the road, and the trajectory is evaluated based on the evaluation result for each point. An evaluation section to
A trajectory evaluation apparatus comprising: The evaluation unit evaluates each of the plurality of points based on a degree of variation related to the second direction of the plurality of points on the trajectory.
The trajectory evaluation apparatus according to claim 1. The evaluation unit further evaluates each of the plurality of points on the track based on the turning degree of the vehicle;
The trajectory evaluation apparatus according to claim 1. The evaluation unit further evaluates each of the plurality of points on the track based on conditions regarding the lane.
The trajectory evaluation apparatus according to any one of claims 1 to 3. The condition relating to the lane is a condition relating to a deviation from a preset recommended lane,
The trajectory evaluation apparatus according to claim 4. The evaluation unit evaluates at least the relative positional relationship in the first direction using a threshold that varies based on the speed of the vehicle or the speed of the object.
The trajectory evaluation apparatus according to any one of claims 1 to 5. The evaluation unit evaluates at least the relative positional relationship with respect to the first direction using a threshold that varies based on the speed of the vehicle with respect to the object that is present ahead of the vehicle. The object existing behind the vehicle is evaluated using a threshold that varies based on the speed of the object.
The trajectory evaluation apparatus according to claim 6. A discrimination unit for discriminating the type of the object;
The evaluation unit varies evaluation criteria based on the type of the object determined by the determination unit.
The trajectory evaluation apparatus according to any one of claims 1 to 7. The generation unit generates a plurality of the trajectories,
The evaluation unit performs an evaluation for each of the plurality of trajectories generated by the generation unit, and selects a trajectory from which a good evaluation result is obtained.
The trajectory evaluation apparatus according to any one of claims 1 to 8. The generation unit repeatedly generates the trajectory until a trajectory with a good evaluation result is selected by the evaluation unit.
The trajectory evaluation apparatus according to claim 9. A generator for generating a future track on which the vehicle travels;
For each of a plurality of points on the track generated by the generation unit and having different timings for passing the vehicle, an evaluation is performed based on the degree of variation of the point with respect to the direction along the width direction of the road. , An evaluation unit that evaluates the trajectory based on an evaluation result for each point,
A trajectory evaluation apparatus comprising: Computer
Generate a future track on which the vehicle will travel,
Predicting future positions of objects around the vehicle,
A first direction along the longitudinal direction of the road between each of a plurality of points on the track and a plurality of points having different passing timings of the vehicle with the predicted future position of the object Based on the relative positional relationship and the relative positional relationship in the second direction along the width direction of the road,
Evaluating the trajectory based on the evaluation results for each point,
Orbit evaluation method. On the computer,
Generate a future trajectory for the vehicle to travel,
Predicting future positions of objects around the vehicle,
A first direction along the longitudinal direction of the road between each of a plurality of points on the track and a plurality of points having different passing timings of the vehicle with the predicted future position of the object Evaluation is performed based on the relative positional relationship and the relative positional relationship in the second direction along the width direction of the road,
The trajectory is evaluated based on the evaluation result for each point,
Orbit evaluation program.

Images