Control device, control method thereof, vehicle, and program

Abstract

To make it possible to suppress a deterioration in accuracy in risk calculation even when traveling on a movement route having a road shape including a curved shape.SOLUTION: A control device according to the present embodiment includes: target recognition means for recognizing a state of a target outside a movable body; traveling lane recognition means for recognizing a traveling lane on a movement route on which the movable body travels; generation means for generating information on a virtual traveling lane which is a straight traveling lane, on the basis of information on the recognized traveling lane and the recognized state of the target; setting means for setting, on the virtual traveling lane, a search area for calculating a risk, as an index value indicating a degree to which the movable body should avoid entry; and calculation means for calculating the risk in the set search area. In a case where the traveling lane has a road shape including a curved shape, the generation means converts each position of the traveling lane so that a curved part of the traveling lane becomes a straight traveling lane along a traveling direction, and generates information on the virtual traveling lane.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a control device, a control method thereof, a vehicle, and a program. [Background technology]

[0002] Conventionally, as a technology for generating an appropriate travel trajectory according to the travel environment when a moving body such as a vehicle travels, there is known a technology for setting a target potential area when the travel path is curved, in which a target potential area set for a straight road is changed based on the radius of curvature of the curved road (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-46161 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology disclosed in Patent Document 1 uses highly accurate curvature of curved roads that is included in advance in map information. However, there are cases where map information does not include the curvature of each curve of a road, or where a mobile object travels while recognizing the surrounding environment without using comprehensive map information. The calculation accuracy of the process of calculating the curvature of a road may decrease depending on the behavior of the vehicle. For this reason, when estimating the curvature of a road and using the estimated curvature to determine the risk (an index value indicating the degree to which a vehicle should avoid entering a curve) according to the curve or to issue a warning based on the risk, the process may become complicated and the accuracy of the risk determination and warning may decrease.

[0005] The present invention has been made in consideration of the above-mentioned problems, and its purpose is to realize a technology that can suppress a decrease in accuracy in risk calculation even when traveling on a travel route with a road shape that includes a curved shape. [Means for solving the problem]

[0006] According to the present invention, a target recognition means for recognizing the state of a target outside the moving body; a lane recognition means for recognizing a lane on a travel route along which the moving body travels; a generating means for generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and the state of the recognized target; a setting means for setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the moving body should avoid entering the virtual driving lane; a calculation means for calculating the risk in the set search area, A control device is provided in which, when the road shape of the driving lane includes a curved shape, the generation means converts each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel, thereby generating information about the virtual driving lane. [Effects of the Invention]

[0007] According to the present invention, even when traveling on a travel route whose road shape includes a curved shape, it is possible to suppress a decrease in accuracy in risk calculation. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a vehicle as an example of a moving body according to an embodiment; [Figure 2] FIG. 1 is a block diagram illustrating an example of a functional configuration of a control device according to an embodiment. [Figure 3] FIG. 1 is a diagram illustrating an overview of risk calculation according to an embodiment. [Figure 4] 1 is a flowchart showing a series of operations of a driving assistance process according to an embodiment; [Figure 5] FIG. 1 is a diagram illustrating an example of a process for determining a road shape including a curved shape according to an embodiment. [Figure 6]FIG. 10 is a diagram illustrating an example of a process for determining a relationship with a lane boundary according to an embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of a process for estimating the curvature of a curve according to an embodiment. [Figure 8] FIG. 10 is a diagram illustrating an example of a process for converting the position of a target according to an embodiment. [Figure 9] FIG. 1 is a diagram illustrating an example of a risk to a target according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention as claimed, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Furthermore, the same reference numerals are used for the same or similar components, and redundant explanations will be omitted.

[0010] <Vehicle configuration example> FIG. 1 is a block diagram of a vehicle 1 as an example of a moving body according to the present invention. In FIG. 1, the vehicle 1 is shown in outline in plan view and side view. As an example, the vehicle 1 is a four-wheeled passenger car, but it may also be a two-wheeled vehicle or other types of vehicle. Furthermore, the moving body according to the present invention is not limited to a vehicle, and may include various moving bodies such as an autonomously moving robot.

[0011] The vehicle 1 includes a vehicle control device (hereinafter simply referred to as the control device 2) that controls the vehicle 1. The control device 2 includes multiple ECUs (Electronic Control Units) 20 to 29 that are communicatively connected via an in-vehicle network. Each ECU includes a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), a memory such as a semiconductor memory, an interface with external devices, etc. The memory stores programs executed by the processor and data used by the processor for processing, etc. Each ECU may include multiple processors, memories, interfaces, etc. For example, the ECU 20 includes a processor 20a and a memory 20b. The processor 20a executes instructions included in a program stored in the memory 20b, thereby performing processing by the ECU 20. Alternatively, the ECU 20 may include a dedicated integrated circuit such as an ASIC (Application Specific Integrated Circuit) for performing processing by the ECU 20. The same applies to the other ECUs.

[0012] The functions and the like that are handled by each of the ECUs 20 to 29 will be described below. The number of ECUs and the functions that they are responsible for can be designed as appropriate, and they can be subdivided or integrated more than in this embodiment. For example, one ECU (e.g., ECU 22) may also have the functions of other ECUs.

[0013] The ECU 20 executes control related to manual driving and automatic driving of the vehicle 1. In automatic driving, at least one of steering and acceleration / deceleration of the vehicle 1 is automatically controlled. Note that the automatic driving by the ECU 20 may include automatic driving that does not require driving operation by the driver (also called automatic driving) and automatic driving that assists driving operation by the driver (also called driving assistance). The control of driving by the ECU 20 may include, for example, control to automatically stop or steer the vehicle to avoid a collision in place of driving by the driver.

[0014] The ECU 21 controls the electric power steering device 3. The electric power steering device 3 includes a mechanism for steering the front wheels in response to a driver's driving operation (steering operation) on the steering wheel 31. The electric power steering device 3 also includes a motor that generates driving force to assist the steering operation and automatically steer the front wheels, a sensor that detects the steering angle, etc. When the driving state of the vehicle 1 is autonomous driving, the ECU 21 automatically controls the electric power steering device 3 in response to instructions from the ECU 20, and controls the traveling direction of the vehicle 1.

[0015] The ECUs 22 and 23 control the detection units that detect the vehicle's surroundings and process information on the detection results. The vehicle 1 includes, for example, one standard camera 40 and four fisheye cameras 41 to 44 as detection units that detect the vehicle's surroundings. The standard camera 40 and the fisheye cameras 42 and 44 are connected to the ECU 22. The fisheye cameras 41 and 43 are connected to the ECU 23. By analyzing images captured by the standard camera 40 and the fisheye cameras 41 to 44, the ECUs 22 and 23 can recognize the status of targets, such as their type, position, and speed, as well as lane boundaries on the travel path, lane boundaries (white lines), and dividing lines (broken lines, etc.) between lanes. Note that the type, number, and mounting positions of the cameras in the vehicle 1 are not limited to the example in this embodiment and may be other configurations. Furthermore, the vehicle 1 may include a lidar (light detection and ranging) or millimeter-wave radar as a detection unit for detecting targets around the vehicle 1 and measuring the distance to the targets.

[0016] The standard camera 40 is attached to the center of the front of the vehicle 1 and captures the surroundings in front of the vehicle 1. The fisheye camera 41 is attached to the center of the front of the vehicle 1 and captures the surroundings in front of the vehicle 1. In FIG. 1, the standard camera 40 and the fisheye camera 41 are shown aligned horizontally. However, the arrangement of the standard camera 40 and the fisheye camera 41 is not limited to this; for example, they may be aligned vertically. Furthermore, at least one of the standard camera 40 and the fisheye camera 41 may be attached to the front of the roof of the vehicle 1 (for example, on the inside of the front windshield). The fisheye camera 42 is attached to the center of the right side of the vehicle 1 and captures the surroundings to the right of the vehicle 1. The fisheye camera 43 is attached to the center of the rear of the vehicle 1 and captures the surroundings behind the vehicle 1. The fisheye camera 44 is attached to the center of the left side of the vehicle 1 and captures the surroundings to the left of the vehicle 1.

[0017] The ECU 22 controls the standard camera 40 and the fisheye cameras 42 and 44 and processes information on the detection results. The ECU 23 controls the fisheye cameras 41 and 43 and processes information on the detection results. By dividing the detection unit that detects the vehicle's surroundings into two systems, the reliability of the detection results can be improved. In addition, the ECU 22 can detect the driver's head direction and line of sight using an image of the driver captured by a fisheye camera (not shown) installed inside the vehicle cabin.

[0018] The ECU 24 controls the gyro sensor 5, the GPS sensor 24b, and the communication device 24c, and processes information on the detection results or communication results. The gyro sensor 5 detects the rotational motion of the vehicle 1. The path of the vehicle 1 can be determined based on the detection results of the gyro sensor 5, the wheel speed, etc. The GPS sensor 24b detects the current position of the vehicle 1. The communication device 24c acquires map information and traffic information through wireless communication with a server that provides this information. The ECU 24 can access a database 24a of map information stored in memory, and performs tasks such as searching for a route from the current location to a destination. The ECU 24, the map database 24a, and the GPS sensor 24b constitute a so-called navigation device.

[0019] The ECU 25 includes a communication device 25a for vehicle-to-vehicle communication. The communication device 25a performs, for example, wireless communication with other vehicles in the vicinity, and exchanges information between the vehicles.

[0020] The ECU 26 controls the power plant 6. The power plant 6 is a mechanism that outputs driving force to rotate the drive wheels of the vehicle 1, and includes, for example, an engine and a transmission. The ECU 26 controls the output of the engine in response to a driving operation (accelerator operation or acceleration operation) by the driver detected by an operation detection sensor 7a provided on the accelerator pedal 7A, for example, and switches the gear position of the transmission based on information such as the vehicle speed detected by a vehicle speed sensor 7c.

[0021] The ECU 27 controls lighting devices (headlights, taillights, etc.) including turn signals 8. In the example of Fig. 1, the turn signals 8 are provided at the front, door mirrors, and rear of the vehicle 1.

[0022] The ECU 28 controls the input / output device 9. The input / output device 9 outputs information to a passenger (e.g., the driver) and receives information input from the driver. The audio output device 91 notifies the driver of information by audio, for example, including a predetermined sound or speech. The content of the notification is output when, for example, the ECU 22 performs a driving assistance process described below, determines whether to issue a notification, and transmits the determined content to the ECU 28. The driving assistance process will be described later. The display device 92 notifies the driver of information by displaying an image. The display device 92 is disposed, for example, on the surface of the driver's seat and constitutes an instrument panel or the like. Note that, although audio and display are exemplified here, information may be notified by vibration or light. Information may also be notified by a combination of audio, display, vibration, and light. The input device 93 is a group of switches disposed in a position operable by the driver to issue instructions to the vehicle 1, but may also include an audio input device.

[0023] The ECU 29 controls the braking device 10 and the parking brake (not shown). The braking device 10 is, for example, a disk brake device, which is provided on each wheel of the vehicle 1 and decelerates or stops the vehicle 1 by applying resistance to the rotation of the wheels. The ECU 29 controls the operation of the braking device 10 in response to a driving operation (braking operation) of the driver detected by an operation detection sensor 7b provided on the brake pedal 7B, for example. When the driving state of the vehicle 1 is in autonomous driving, the ECU 29 automatically controls the braking device 10 in response to an instruction from the ECU 20 and controls the deceleration and stop of the vehicle 1. The braking device 10 and the parking brake can also operate to maintain the stopped state of the vehicle 1. Further, when the transmission of the power plant 6 includes a parking lock mechanism, this can also operate to maintain the stopped state of the vehicle 1.

[0024] <Functional configuration example realized in the ECU22> Next, referring to FIG. 2, a functional configuration example realized in the ECU 22 will be described. Although some or all of the functions described below as being realized in the ECU 22 may be realized in other ECUs (for example, the ECU 20). The functional configuration example shown in FIG. 2 shows an example of a functional configuration realized by the ECU 22 executing a program stored in an internal memory. Further, the functional configuration example shown in FIG. 2 focuses on the configuration related to the driving support process described later. Therefore, the functions realized in the ECU 22 are not limited to those shown in FIG. 2 and may include other functions.

[0025] The object recognition unit 201 recognizes the state of an object in the external environment of the vehicle 1 based on at least one of the image obtained from the detection unit and sensor information such as a lidar. The object includes, for example, a moving object around the vehicle 1 (surrounding vehicles, pedestrians, passengers on bicycles, etc.) or a fallen object. The state of the object includes, for example, the type of the object, the position of the object, the speed of the object, the movement trajectory of the object, etc. The position of the object may be a relative position from the vehicle 1. The object recognition unit 201 can recognize the state of an object in the external environment using, for example, one or more neural networks, but other learning models may also be used.

[0026] The driving lane recognition unit 202 recognizes the driving lanes on the travel route on which the vehicle 1 is traveling, based on at least one of images obtained from the detection unit and sensor information such as LIDAR. The information on the recognized driving lanes includes, for example, information on lane boundaries, lane markings, and lane areas on the travel route. The information on lane boundaries and lane markings may be provided, for example, as position information of a discrete point cloud at predetermined distances (for example, every meter). The driving lane recognition unit 202 can recognize the driving lanes on the travel route using, for example, one or more neural networks, but other learning models may also be used. Note that the functions of the target object recognition unit 201 and the driving lane recognition unit 202 may be implemented by a single neural network or learning model.

[0027] The driving lane recognition unit 202 further uses information on the road boundary of the driving lane to determine whether the driving lane has a predetermined road shape that includes a curved shape. The determination of whether the road shape is a predetermined road shape will be described later.

[0028] Fig. 3 shows an overview of the driving assistance processing according to this embodiment. In the example shown in Fig. 3, a vehicle 301 (i.e., vehicle 1), which is the vehicle itself, is traveling in a driving lane 302 on a travel route, and a vehicle 303 is stopped on the driving lane 302. The driving lane 302 shown in Fig. 3 is a driving lane having a road shape that includes a curved shape. Note that in the example shown in Fig. 3, the curvature of the driving lane 302 is exaggerated for the sake of explanation, but as will be described later, the driving assistance processing according to this embodiment is mainly executed when the vehicle is traveling in a driving lane with a gentle curvature having a curvature radius of 100R or more.

[0029] When the vehicle 301 is traveling in the driving lane 302, the target recognition unit 201 recognizes the state of the target, including the position, speed, and movement trajectory of the vehicle 303. In addition, the driving lane recognition unit 202 recognizes the road boundaries, division lines, and lane areas of the driving lane 302.

[0030] The virtual driving lane generation unit 203 generates information on a virtual driving lane, which is a straight driving lane, based on information on the driving lane recognized by the target recognition unit 201 and the state of the target recognized by the driving lane recognition unit 202.

[0031] In the example shown in FIG. 3 , the virtual driving lane generation unit 203 generates information about the virtual driving lane by converting each position of the driving lane 302 so that the curved portion of the driving lane 302 becomes a straight driving lane (i.e., driving lane 304) along the traveling direction. As described above, the driving lane 302 curves with a gentle curvature, for example, a curvature radius of 100R or more, so it is possible to perform processing that approximates the information about the driving lane 302 to a straight driving lane. The virtual driving lane generation unit 203 generates the straight line that constitutes the virtual driving lane 304, for example, by drawing a straight line in the traveling direction from the average position of a cloud of points within a predetermined range of a road boundary that exists on the left (or right) side of the vehicle 301. The conversion of each position of the driving lane 302 may be processing that moves (maps) each position in a direction perpendicular to the traveling direction. However, when each position in the driving lane 302 is moved in a direction perpendicular to the traveling direction, the distance on the virtual driving lane 304 may become shorter than the actual distance on the driving lane 302. Therefore, instead of simply moving each position in a direction perpendicular to the traveling direction, the position of the target may be offset on the virtual driving lane 304 so that the target position moves away from the position of the vehicle 301 in the traveling direction of the vehicle 301. This allows the positional relationship between the vehicle 301 and the target in the driving lane 302 to be reflected on the virtual driving lane 304 with greater accuracy through simple calculations. By generating a virtual driving lane that is a straight driving lane in this way, it is not necessary to perform processing specific to a curved road that matches the curvature when calculating risks and notifying the driver, as will be described later. In other words, the processing for calculating risks and notifying the driver can be simplified and sped up. Furthermore, because conversion using the estimated curvature is not performed, a decrease in processing accuracy can be suppressed.

[0032] The risk calculation unit 204 calculates risk, which is an index value indicating the degree to which the vehicle should avoid entering the area. The risk for a specific target becomes more negative (the degree to which entry should be avoided increases) the closer the target is to the recognized target, and decreases as the distance from the target increases, eventually reaching zero. The risk calculation unit 204 sets a search area on a virtual driving lane for calculating the risk. The search area includes, for example, a first observation point set in the direction of travel of the vehicle 301 and one or more second observation points (two in the example described below) to the left and right of the first observation point as viewed from the vehicle 301. These observation points are grouped together, and the risk is calculated at each observation point in the search area. The lowest risk among the calculated risks is then found, thereby obtaining a driving trajectory with the lowest risk. Note that the illustrated example shows a case in which one observation point is set at a predetermined position from the vehicle 301 in the direction of travel. However, multiple observation points can be set in the direction of travel, and multiple observation points can be set to the left and right of each observation point. In this way, it is possible to grasp the risk that exists in a specific direction or position on the driving lane. In the following explanation, calculating the risk at each observation point in the search area is also simply referred to as calculating the risk in the search area.

[0033] The risk calculation unit 204 sets a risk potential for the virtual driving lane. The setting of the risk potential may be realized using known technology. The risk potential may be a combination of the risk potential set for the driving lane and the risk potential caused by the presence of a target, or it may be possible to use only the risk potential caused by the presence of a target.

[0034] FIG. 9 schematically shows an example of a risk potential caused by the presence of a target (e.g., vehicle 303). The vertical axis indicates the level of risk, and the horizontal axis indicates the left-right position of vehicle 303. In area 902 close to vehicle 303, the risk potential indicates the highest value of the risks set for vehicle 303. Furthermore, in areas 901 and 902, the risk decreases the further away from the center of vehicle 303. Similar risk potentials may be set in front of and behind vehicle 303. The risk potential set for a target is also referred to as target potential. If the search area in which risk is calculated is within area 901 to 903, the presence of vehicle 303 increases the risk. On the other hand, if the search area does not overlap with area 901 to 903, the presence of vehicle 303 does not increase the risk.

[0035] The risk potential set for a driving lane is set so that, for example, the risk value is lowest in the center of the driving lane and becomes higher the further away from the center (the closer to the lane boundary). Such a risk potential is also called an induced potential. When using such a risk potential, the risk is lowest near the center of the driving lane within the search area. Furthermore, the risk is higher near the lane boundary within the search area.

[0036] Referring again to FIG. 3, an observation point 310 in the search area is set at a predetermined distance from vehicle 301. When vehicle 301 moves forward in a virtual driving lane, observation point 310 on the left side of the search area will be located within the range of risk potential 306 of vehicle 305 (i.e., vehicle 303). In this case, risk calculation unit 204 calculates the risk in the search area by combining the risks of risk potential 306. In this way, the risk calculated in the search area becomes a risk value that includes the influence of targets. Note that when multiple targets exist, the risk potentials of the targets are combined. When two targets are close to observation point 310 on the left side of the search area and the risk potentials of each target are not zero at the position of observation point 310, the risk potentials of each target are combined. In other words, risk calculation unit 204 calculates the risk in the search area based on the combined risk potential. In this way, it is possible to determine the vehicle's actions, such as autonomous driving and alerting the driver, based on the risk calculated in the search area.

[0037] The driving control unit 205 determines the behavior of the vehicle based on the risk calculated in the search area. For example, the driving control unit 205 determines a driving route for the vehicle 301 so that the vehicle travels through the position of the observation point for which the lowest risk is calculated. Furthermore, the driving control unit 205 controls at least one of the speed and steering of the vehicle 301 so that the vehicle 301 travels automatically along the determined driving route. Of course, the driving control unit 205 can perform various controls necessary for the vehicle 301 to travel automatically along the determined driving route, in addition to the speed and steering. The automatic driving may include automatic driving of the vehicle 301 that does not require driving operation by the driver, or automatic driving that assists driving operation by the driver.

[0038] The notification unit 206 notifies the driver based on the risk calculated in the search area. When the risk in the search area (at any observation point) exceeds a predetermined value, the notification unit 206 notifies the driver with a predetermined warning sound or a voice in natural language (including an expression describing the recognized target). For example, when the notification unit 206 issues a voice notification, the voice notification includes at least one of the presence or absence, position, direction, distance, and time until collision with the target with which there is a possibility of collision. The notification unit 206 may display the content of the notification on the display device 92. For example, the notification unit 206 includes at least one of the presence or absence, position, direction, distance, and time until collision with the target with which there is a possibility of collision on the display device 92. The notification unit 206 may notify the driver when the distance from the vehicle 301 to the target is less than a predetermined distance or when the arrival time to the target is less than a predetermined time.

[0039] The risk may correspond to the possibility of collision between the vehicle 301 and another target (vehicle 303). In this case, the traveling control unit 205 or the notification unit 206 determines the behavior of the moving object based on the possibility of collision between the vehicle 301 and another target (vehicle 303).

[0040] Next, a series of operations of the driving assistance process in the vehicle will be described with reference to Fig. 4. This process is realized, for example, by the processor 20a of the ECU 22 of the control device 2 executing a program in the memory 20b.

[0041] In S401, the target object recognition unit 201 recognizes the state of a target object in the external world of the vehicle 1 based on at least one of an image obtained from the detection unit and sensor information such as a LIDAR. In addition, the driving lane recognition unit 202 recognizes the driving lane on the travel route on which the vehicle 1 is traveling based on at least one of an image obtained from the detection unit and sensor information such as a LIDAR.

[0042] Next, through the processes of S402 to S405, the driving lane recognition unit 202 determines whether the driving lane has a predetermined road shape that includes a curved shape. First, in S402, the driving lane recognition unit 202 determines whether the driving lane is curved.

[0043] FIG. 5 schematically shows an example in which a driving lane is curved. The example shown in FIG. 5 shows an example in which a lane boundary exists in the traveling direction of vehicle 301 (because the driving lane includes a curved road). In this example, the lane boundary exists at position 502 that is more than distance 501 (for example, 20 meters) away from vehicle 301. If a lane boundary exists in the traveling direction, driving lane recognition unit 202 determines that the driving lane is curved. If driving lane recognition unit 202 determines that the driving lane is curved, the process proceeds to S403; otherwise, the process returns to S401.

[0044] In S403, the driving lane recognition unit 202 determines whether the positional relationship between the lane boundary and the vehicle is in a specific state. FIG. 6 schematically shows an example in which the relationship with the lane boundary is in a specific state. In the example shown in FIG. 6, the lane boundary is present at a distance 501 or less from the vehicle. This state may be a state in which the vehicle is deviating from the road, for example, by making a right or left turn or entering a parking lot. Therefore, in this embodiment, if this specific state is present, the driving assistance process is terminated. If the lane boundary is present at a distance 501 or less from the vehicle, the driving lane recognition unit 202 determines that this is a specific state and terminates the process; otherwise, the process proceeds to S404.

[0045] In S404, the driving lane recognition unit 202 estimates the curvature of the lane boundary of the driving lane by fitting the lane boundary of the driving lane to a circular arc. FIG. 7 schematically shows the fitting of the lane boundary to a circular arc. In this example, the lane boundary of the driving lane 302 is given as position information 701 of a discrete point cloud at predetermined distances (for example, every meter). The driving lane recognition unit 202 estimates the parameters of the arc that best match the point cloud position information 701, for example, by the least squares method. The curvature of the arc can be obtained by estimating the parameters of the arc.

[0046] In S405, the driving lane recognition unit 202 determines whether the estimated curvature is equal to or less than a predetermined value, and if the curvature is equal to or less than the predetermined value, the process proceeds to S406, otherwise the process ends. If the curvature of the road boundary is large, risk calculation using a virtual driving lane may not be appropriate, so the driving lane recognition unit 202 does not continue the driving assistance process.

[0047] In S406, the virtual driving lane generation unit 203 converts the information on the driving lane recognized by the target recognition unit 201 and the state of the target recognized by the driving lane recognition unit 202 into a virtual driving lane, which is a straight driving lane.

[0048] FIG. 8 shows an example of generating virtual driving lane information based on driving lane information and the position of a target (vehicle 303). The virtual driving lane generation unit 203 maps the positions of the road boundaries of the driving lane 302 and the positions of targets to the road boundaries of the driving lane 304, for example, using the method described above with reference to FIG. 3. In this embodiment, when converting the positions of targets onto the virtual driving lane, the positions of the recognized targets are offset using geometric calculations such as trigonometric functions. For example, a right triangle including a side connecting the intersection of the position of the vehicle 301 and the road boundary ((0, y) in the host vehicle coordinate system) with the position where the vehicle 303 was located may be formed, and the position of the vehicle 305 may be offset to a position forming a triangle similar to the right triangle. In this way, simple and high-speed calculations can be realized, and the offsetting of the target position allows the position of the target on the virtual driving lane to be determined with higher accuracy.

[0049] In S407, the risk calculation unit 204 sets a search area on the virtual driving lane for calculating risk, as described above, and calculates the risk including the influence of targets in the search area on the virtual driving lane. As described above, in order to set the risk potential on the virtual driving lane, the risk calculation unit 204 calculates the risk using, for example, a risk value of the risk potential in the search area on the virtual driving lane.

[0050] In S408, if the calculated risk is equal to or greater than a predetermined value, the risk calculation unit 204 advances the process to S409, and if not, ends the process without issuing a notification.

[0051] In S409, the notification unit 206 notifies the driver in response to, for example, an instruction from the risk calculation unit 204. As described above, the notification unit 206 notifies the driver with a predetermined warning sound or a voice using a natural language (including an expression expressing the recognized target). After finishing the notification, the notification unit 206 then ends the series of operations of the driving assistance process.

[0052] In the series of operations of the driving assistance process described above, an example has been described in which a notification is given when the calculated risk is equal to or greater than a predetermined value, but either one of the two may be performed by the driving control unit 205. Also, both the notification by the notification unit 206 and the automatic driving by the driving control unit 205 may be performed.

[0053] As described above, in the above-described embodiment, the vehicle 1 generates information about a virtual driving lane, which is a straight driving lane, based on information about the recognized driving lane and the state of the recognized target. In this case, when the driving lane has a predetermined road shape that includes a curved shape, the vehicle 1 converts each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel, thereby generating information about the virtual driving lane. Furthermore, the vehicle 1 sets a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which a moving object should avoid entering the virtual driving lane, and calculates the risk in the set search area. This eliminates the need for processing specific to a curved road that matches the curvature when calculating the risk and notifying the driver, thereby simplifying and speeding up the processing for calculating the risk and notifying the driver. Furthermore, it is possible to suppress a decrease in processing accuracy. In other words, it is possible to suppress a decrease in accuracy in risk calculation even when traveling on a travel route with a road shape that includes a curved shape.

[0054] <Summary of the embodiment> (Item 1) A target recognition means (e.g., 201) for recognizing the state of a target outside the moving body (e.g., 1); a lane recognition means (e.g., 202) for recognizing a lane on the travel route along which the moving body travels; A generating means (e.g., 203) for generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and the state of the recognized target; A setting means (e.g., 204) for setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the moving body should avoid entering the virtual driving lane; a calculation means (e.g., 204) for calculating the risk in the set search area, The control device (e.g., 22) is characterized in that, when the road shape of the driving lane includes a curved shape, the generation means converts each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel, thereby generating information about the virtual driving lane.

[0055] According to this embodiment, even when traveling on a travel route with a road shape that includes a curved shape, it is possible to suppress a decrease in accuracy in risk calculation.

[0056] (Item 2) The target recognition means recognizes the position of a target, 2. The control device according to item 1, wherein the generating means generates information about the virtual driving lane by converting the position of the recognized target onto the virtual driving lane.

[0057] According to this embodiment, even when traveling on a travel route with a road shape that includes a curved shape, it is possible to suppress a decrease in accuracy in calculating the risk to a target.

[0058] (Item 3) 2. The control device according to item 1, wherein the generating means does not generate the virtual driving lane information when the curvature of the road boundary of the driving lane is greater than a predetermined value (for example, S405).

[0059] According to this embodiment, if it is not suitable to generate a virtual driving lane that is a straight driving lane, the generation of the virtual driving lane can be refrained from.

[0060] (Item 4) 2. The control device according to item 1, further comprising a decision means (e.g., 205, 206) for deciding the behavior of the moving object based on the calculated risk.

[0061] According to this embodiment, vehicle control according to risk can be realized.

[0062] (Item 5) the risk corresponds to a possibility of a collision between the moving object and the recognized target in the search area; 5. The control device according to item 4, wherein the determining means determines the behavior of the moving body based on the possibility of a collision between the moving body and the recognized target.

[0063] According to this embodiment, it is possible to suppress a decrease in accuracy in calculating the possibility of collision with a target.

[0064] (Item 6) 5. The control device according to item 4, wherein the behavior of the moving body includes a notification to a driver of the moving body.

[0065] According to this embodiment, when traveling on a travel route that includes curves, it is possible to suppress a decrease in accuracy of risk-based notifications.

[0066] (Item 7) 5. The control device according to item 4, wherein the behavior of the moving body includes automatic driving of the moving body that does not require driving operation by the driver, or automatic driving to assist driving operation by the driver.

[0067] According to this embodiment, when traveling on a travel route that includes curves, it is possible to suppress a decrease in accuracy of automated traveling due to risk.

[0068] (Item 8) The control device described in item 7, characterized in that when the moving body is driven automatically without requiring driving operation by a driver, the determination means determines a driving route of the moving body based on the calculated risk, and controls at least one of the speed and steering of the moving body according to the driving route.

[0069] According to this embodiment, various controls relating to the automatic driving of a mobile object can be performed according to a driving route based on the calculated risk.

[0070] (Item 9) The method further includes a determination means for determining whether the road shape of the driving lane includes a curved shape using information on the road boundary of the driving lane (e.g., S402), 2. The control device according to item 1, wherein the generating means does not generate information about the virtual driving lane if the road shape of the driving lane does not include a curved shape.

[0071] According to this embodiment, risk calculation using virtual driving lanes can be applied to appropriate curved roads.

[0072] (Item 10) The control device according to item 9, wherein the determining means determines whether the road shape of the driving lane includes a curved shape based on the curvature of the road boundary of the driving lane (e.g., S405).

[0073] According to this embodiment, the curvature of the curved road can be taken into consideration when determining whether the curved road is appropriate.

[0074] (Item 11) The control device described in item 10 is characterized in that the determination means determines that the road shape of the driving lane includes a curved shape when the curvature of the road boundary of the driving lane is within a predetermined range of curvature (e.g., S405).

[0075] According to this embodiment, it is possible to prevent risk calculation using a virtual driving lane from being applied to a curved road with a large curvature.

[0076] (Item 12) Item 11. The control device according to item 10, wherein the determining means estimates the curvature of the lane boundary of the driving lane by fitting the lane boundary of the driving lane to a circular arc (for example, S404).

[0077] According to this embodiment, the curvature of the lane boundary can be dynamically acquired.

[0078] (Item 13) 3. The control device according to item 2, wherein when converting the position of the recognized target onto the virtual driving lane, the generation means offsets the position of the recognized target on the virtual driving lane so that the position of the recognized target moves away from the position of the moving body in the traveling direction of the moving body.

[0079] According to this embodiment, when traveling on a travel route that includes curves, the positional relationship between the vehicle 301 and the target in the travel lane 302 can be reflected more accurately on the virtual travel lane 304 with simple calculations.

[0080] (Item 14) Item 14. The control device according to item 13, wherein the generation means offsets the position of the recognized target by using a geometric operation when converting the position of the recognized target onto the virtual driving lane.

[0081] According to this embodiment, when traveling along a travel route that includes curves, it is possible to realize simpler and faster calculations.

[0082] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0083] 1...vehicle, 2...control device, 21-29...ECU

Claims

1. a target recognition means for recognizing the state of a target outside the moving body; a lane recognition means for recognizing a lane on a travel route along which the moving body travels; a generating means for generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and the state of the recognized target; a setting means for setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the moving body should avoid entering the virtual driving lane; a calculation means for calculating the risk in the set search area, The control device is characterized in that, when the road shape of the driving lane includes a curved shape, the generation means converts each position of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel, thereby generating information about the virtual driving lane.

2. The target recognition means recognizes the position of a target, 2. The control device according to claim 1, wherein the generating means generates the information on the virtual driving lane by converting the position of the recognized target object onto the virtual driving lane.

3. 2. The control device according to claim 1, wherein the generating means does not generate the virtual driving lane information when a curvature of a road boundary of the driving lane is greater than a predetermined value.

4. 2. The control device according to claim 1, further comprising a decision unit that decides the behavior of the mobile unit based on the calculated risk.

5. the risk corresponds to a possibility of a collision between the moving object and the recognized target in the search area; 5. The control device according to claim 4, wherein the determining means determines the behavior of the moving body based on a possibility of collision between the moving body and the recognized target.

6. The control device according to claim 4 , wherein the behavior of the mobile object includes a notification to a driver of the mobile object.

7. 5. The control device according to claim 4, wherein the behavior of the mobile body includes automatic driving of the mobile body that does not require driving operation by a driver, or automatic driving to assist driving operation by the driver.

8. The control device according to claim 7, characterized in that, when the moving body is driven automatically without requiring driving operation by a driver, the determination means determines a driving route of the moving body based on the calculated risk, and controls at least one of the speed and steering of the moving body in accordance with the driving route.

9. The vehicle further includes a determination means for determining whether the road shape of the driving lane includes a curved shape using information on the road boundary of the driving lane, 2. The control device according to claim 1, wherein the generating means does not generate the virtual driving lane information when the road shape of the driving lane does not include a curved shape.

10. 10. The control device according to claim 9, wherein the determining means determines whether the road shape of the driving lane includes a curved shape based on a curvature of a road boundary of the driving lane.

11. 11. The control device according to claim 10, wherein the determining means determines that the road shape of the driving lane includes a curved shape when a curvature of a road boundary of the driving lane is within a predetermined range of curvature.

12. 11. The control device according to claim 10, wherein the determining means estimates the curvature of the lane boundary by fitting the lane boundary to a circular arc.

13. 3. The control device according to claim 2, wherein, when converting the position of the recognized target onto the virtual driving lane, the generation means offsets the position of the recognized target on the virtual driving lane so that the position of the recognized target moves away from the position of the moving body in the traveling direction of the moving body.

14. 14. The control device according to claim 13, wherein the generation means offsets the position of the recognized target object by using a geometric calculation when converting the position of the recognized target object onto the virtual driving lane.

15. a target recognition means for recognizing the state of a target outside the vehicle; a lane recognition means for recognizing a lane on a travel route on which the vehicle is traveling; a generating means for generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and the state of the recognized target; a setting means for setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the vehicle should avoid entering the virtual driving lane; a calculation means for calculating the risk in the set search area; a determination means for determining an action of the vehicle, including automatic driving of the vehicle that does not require driving operation by a driver, or automatic driving to assist driving operation by the driver, based on a risk calculated in the set search area; The generating means generates the virtual driving lane information by converting the positions of the driving lane so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel when the driving lane has a road shape that includes a curved shape.

16. a target recognition step of recognizing a state of a target outside the moving body; a travel lane recognition step of recognizing a travel lane on a travel route along which the moving body travels; a generating step of generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and a state of the recognized target; a setting step of setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the moving body should avoid entering the virtual driving lane; a calculation step of calculating the risk in the set search area, A control method for a control device, characterized in that in the generation step, when the driving lane has a road shape that includes a curved shape, each position of the driving lane is converted so that the curved portion of the driving lane becomes a straight driving lane that follows the direction of travel, thereby generating information about the virtual driving lane.

17. A program for causing a computer to function as each means of a control device, the control device comprising: a target recognition means for recognizing the state of a target outside the moving body; a lane recognition means for recognizing a lane on a travel route along which the moving body travels; a generating means for generating information on a virtual driving lane, which is a straight driving lane, based on information on the recognized driving lane and the state of the recognized target; a setting means for setting a search area on the virtual driving lane for calculating a risk, which is an index value indicating the degree to which the moving body should avoid entering the virtual driving lane; a calculation means for calculating the risk in the set search area, The generating means generates information about the virtual driving lane by converting the positions of the driving lane when the road shape includes a curved shape so that the curved portion of the driving lane becomes a straight driving lane along the direction of travel.

Images