Object recognition device, mobile body, and object recognition method

Abstract

To provide an object identification device, a moving body, and an object identification method capable of accurately identifying objects.SOLUTION: The object identification device includes: an area determination circuit that determines whether that object detected based on detection waves transmitted and received by sensors mounted on a moving body is located within a given region in front of the moving body; and an identification circuit that is configured so as to, when the area determination circuit determines that the object is located within the predetermined area, identify whether the object is an object to be controlled depending on the curvature of the reflecting surface of the object estimated based on the detected wave.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an object identification device, a moving body, and an object identification method.

Background Art

[0002] Conventionally, an object identification device capable of detecting an object based on the round-trip of a detection wave between a moving body such as a vehicle and the object is known. For example, Patent Document 1 discloses a configuration capable of correcting the reflection intensity of a detection wave according to the height of an object and the distance from the vehicle to the object, and identifying the type of the object based on the corrected reflection intensity.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in the object identification device, in order to detect an object based on the round-trip of a detection wave, an object disposed outside the travel path, such as on the side of the moving body, is also detected. Even for such an object, depending on its type, there is a possibility of colliding with the moving body. Therefore, in the object identification device, such an object may also be regarded as a control target.

[0005] However, when the above object is set as a control target, a small object smaller than a predetermined value, such as a pole, which has almost no possibility of colliding with the moving body, may also be identified. Such identification may cause malfunction of other devices operating based on the identification, and the user may feel annoyed.

[0006] An object of the present disclosure is to provide an object identification device, a moving body, and an object identification method capable of accurately identifying an object.

Means for Solving the Problem

[0007] The object identification device according to the present disclosure includes a region determination circuit that determines whether an object detected based on a detection wave transmitted and received by a sensor mounted on a moving body is located within a predetermined region in front of the moving body, and, when it is determined by the region determination circuit that the object is located within the predetermined region, Based on the difference between the first coordinates of the first reflection point on the object of the detection wave received by the moving body at the first position at the first time and the second coordinates of the second reflection point on the object of the detection wave received by the moving body at the second position at the second time after the first time an identification circuit that identifies whether the object is a control target. and, when the difference between the first coordinates and the second coordinates is equal to or less than a predetermined value, identify that the object is a non-control target

[0008] The moving body according to the present disclosure includes the above object identification device, and an object detection unit that has a sensor for transmitting and receiving the detection wave and detects the object based on the detection wave.

[0009] The object identification method according to the present disclosure is an object identification method, which determines whether an object detected based on a detection wave transmitted and received by a sensor mounted on a moving body is located within a predetermined region in front of the moving body, and, when it is determined that the object is located within the predetermined region, Based on the difference between the first coordinates of the first reflection point on the object of the detection wave received by the moving body at the first position at the first time and the second coordinates of the second reflection point on the object of the detection wave received by the moving body at the second position at the second time after the first time, identifies whether the object is a control target. and when the difference between the first coordinates and the second coordinates is equal to or less than a predetermined value, identify that the object is a non-control target

[0010] According to the present disclosure, an object can be accurately identified.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Mode for Carrying Out the Invention

[0012] (Embodiment) Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing a configuration example of a vehicle 1 to which a vehicle control unit 100 according to an embodiment of the present disclosure is applied.

[0013] As shown in FIG. 1, the vehicle 1 is a moving body having a function of identifying whether an object existing around the traveling route may collide with the vehicle 1. The vehicle 1 includes an acceleration unit 10, a braking unit 20, a vehicle speed information acquisition unit 30, an object detection unit 40, and a vehicle control unit 100.

[0014] The acceleration unit 10 is an acceleration device that accelerates and decelerates the vehicle 1 in response to an acceleration request from the vehicle control unit 100.

[0015] The braking unit 20 is a braking device that brakes the vehicle 1 in response to a braking request from the vehicle control unit 100.

[0016] The vehicle speed information acquisition unit 30 acquires information regarding the speed of the vehicle 1. Specifically, the vehicle speed information acquisition unit 30 acquires information on the vehicle speed and acceleration of the vehicle 1 from the acceleration unit 10 and the like, and also acquires information such as braking information from the braking unit 20 and the like. In addition, the vehicle speed information acquisition unit 30 acquires information such as the steering angle from an operation unit such as a steering wheel (not shown).

[0017] The object detection unit 40 is, for example, an in-vehicle sensor such as a sonar or a radar. It transmits detection waves such as ultrasonic waves and millimeter waves (electromagnetic waves), and receives the detection waves reflected by an object to detect an object existing around the traveling route of the vehicle 1. The object detection unit 40 is provided at the front end or the rear end of the vehicle 1.

[0018] FIG. 2 is a diagram showing an example of the arrangement of the object detection unit 40 in the vehicle 1. In the following description, a rectangular coordinate system (X, Y, Z) is used. The same rectangular coordinate system (X, Y, Z) is also shown in the figures described later. For example, the X direction indicates the left-right direction of the vehicle 1, the Y direction indicates the front-rear direction (traveling direction) of the vehicle 1, and the Z direction indicates the up-down direction (height direction) of the vehicle 1.

[0019] For example, as shown in FIG. 2, the object detection unit 40 has a total of four transmission / reception sensors 41, one at each of the two ends in the X direction and two at the center in the X direction, at the + side end of the vehicle 1 in the Y direction.

[0020] The transmitting and receiving sensor 41 is a sensor capable of transmitting and receiving detection waves. In the case of, for example, a sonar, the transmitting and receiving sensor 41 generates and transmits ultrasonic waves (detection waves) of the same frequency by applying a voltage of a predetermined frequency to a piezoelectric element.

[0021] Also, after the detection wave transmitted from any one of the four transmitting and receiving sensors 41 hits the object 2 and is reflected, the transmitting and receiving sensor 41 receives the detection wave. In the case of, for example, a sonar, the transmitting and receiving sensor 41 converts the sound pressure of the detection wave into a voltage by the piezoelectric element, and rectifies the converted voltage to convert the received detection wave into a sound wave reception intensity (reflection intensity).

[0022] By measuring the flight time when the detection wave travels back and forth from any one of the four transmitting and receiving sensors 41 to any one of the four transmitting and receiving sensors 41 via the object 2, it becomes possible to calculate the distance between the vehicle 1 and the object 2. Also, by calculating the distance between the vehicle 1 and the object 2, it becomes possible to calculate the coordinates of the position where the detection wave is reflected by the object 2 based on the principle of triangulation.

[0023] Also, since a total of four transmitting and receiving sensors 41 are provided, the detection wave transmitted from the transmitting and receiving sensor 41 can be received by each of the four transmitting and receiving sensors 41. Therefore, when the detection wave transmitted from at least one transmitting and receiving sensor 41 is received by two transmitting and receiving sensors 41, each of the detection waves received by the two transmitting and receiving sensors 41 returns to each transmitting and receiving sensor 41 through different paths D1 and D2.

[0024] In the paths D1 and D2, since the detection wave is reflected at different positions P1 and P2 on the object 2, when the detection wave can be received by two transmitting and receiving sensors 41, it becomes possible to calculate two coordinates at the positions P1 and P2 of the object 2. Note that the object 2 in FIG. 2 is a wall having a plane parallel to the X direction.

[0025] Returning to FIG. 1, the vehicle control unit 100 is, for example, an ECU (Electronic Control Unit) or the like, and includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and input / output circuits (not shown). Based on a preset program, the vehicle control unit 100 identifies whether an object existing around the traveling route is a control target object (for example, an object that may cause a collision), and performs predetermined driving control.

[0026] The vehicle control unit 100 includes an identification unit 110, a shape determination unit 120, a modification unit 130, a region determination unit 140, and a control unit 150. The identification unit 110 and the region determination unit 140 correspond to the "object identification device" of the present disclosure. The identification unit 110 corresponds to the "identification circuit" of the present disclosure, and the region determination unit 140 corresponds to the "region determination circuit" of the present disclosure.

[0027] When an object 2 is located in the front region of the vehicle 1, the identification unit 110 identifies whether the object is a control target object based on the comparison result between the reflection intensity of the detection wave and the identification threshold value when the detection wave transmitted from the vehicle 1 toward the object is reflected by the object and received by the vehicle 1. The front region is, for example, the + side region in the Y direction of the vehicle 1, and is the region on the vehicle 1 side of the first control target determination line L1 described later.

[0028] Specifically, when the reflection intensity based on the detection wave received by any of the transmission / reception wave sensors 41 is equal to or greater than the identification threshold value, the identification unit 110 identifies the object as a control target object, and when the reflection intensity is less than the identification threshold value, the identification unit 110 identifies the object as a non-control target object that is not a control target object.

[0029] The identification threshold value is a threshold value that serves as a criterion for identifying whether an object is a control target object of the vehicle 1 by being compared with the reflection intensity based on the detection wave received by the transmission / reception wave sensor 41. In the identification unit 110, when the reflection intensity of the object 2 located in the front region is equal to or greater than the identification threshold value, the object 2 is identified as a control target object.

[0030] In addition, since the detected wave rapidly attenuates in the air, the attenuation amount increases as the distance between the vehicle 1 and the object increases. Therefore, the reflection intensity based on the detected wave received by the transmission / reception wave sensor 41 also decreases as the distance between the vehicle 1 and the object increases, as shown in, for example, FIG. 3. Generally, the discrimination threshold is set to decrease as the distance between the vehicle 1 and the object increases, in accordance with the reflection intensity.

[0031] However, an object below, such as a curb, does not have the same tendency of change in reflection intensity with respect to distance as shown in FIG. 3, for example, due to the relationship between the incident angle and the reflection angle of the detected wave. For example, as shown in FIG. 4, when there is an object 2A below whose distance from the vehicle 1 is closer than that of the object 2B below, the object 2A is in a position where it is difficult for the detected wave transmitted from the transmission / reception wave sensor 41 to hit, so the reflection intensity is small for the object 2A existing at a close position.

[0032] On the other hand, the object 2B below that is relatively far from the vehicle 1 is easy for the detected wave to hit, and the detected wave reflected by the object 2B is also easy to enter the transmission / reception wave sensor 41, so the reflection intensity increases. Specifically, as shown in FIG. 5, the tendency of change in reflection intensity with respect to distance is such that the reflection intensity gradually increases as the distance increases from the position at a distance T1, and after the reflection intensity reaches the maximum value at the distance T2, the reflection intensity decreases.

[0033] Therefore, if a discrimination threshold that decreases as the distance increases, as shown in FIG. 3, is set, the reflection intensity related to the object below will exceed the discrimination threshold. The object below is located on the road surface and has a height at which it can avoid a collision with the main body of the vehicle 1, so it cannot be an obstacle (non-control target object). There is a possibility that such an object below may be identified as a control target object due to the emphasized reflection intensity. Note that FIG. 4 shows an example of an object (object below) located at the rear of the vehicle 1, but the same applies to the case of an object located at the front of the vehicle 1.

[0034] Therefore, in the present embodiment, as shown by the dashed line in FIG. 5, the discrimination threshold is set so that the reflection intensity related to the object below does not exceed the discrimination threshold. Specifically, the discrimination threshold is set to increase step by step from the position at a distance T1 from the vehicle 1 to the distance T2 at which the reflection intensity reaches the maximum value, and then decrease as the distance from the vehicle 1 increases.

[0035] Thereby, it is possible to suppress identifying an object below such as a curb as a control target (obstacle).

[0036] The shape determination unit 120 determines the shape of the object based on two coordinates of the object calculated by detecting the detection waves that have propagated through different paths. Specifically, the shape determination unit 120 determines whether the object is a columnar object based on the two coordinates. A columnar object is, for example, a cylindrical object such as a pole provided at the edge of a road.

[0037] Specifically, the shape determination unit 120 calculates, based on the principle of triangulation, the coordinates indicating the position where the detection wave is reflected on the object from the distance between the vehicle 1 and the object calculated by the round-trip of the detection wave.

[0038] The shape determination unit 120 calculates two coordinates based on the detection waves received by at least two transceiver sensors 41. Then, the shape determination unit 120 determines whether the object is a columnar object according to the coordinate difference between the two coordinates. Specifically, when the coordinate difference is greater than or equal to the shape determination threshold, the shape determination unit 120 determines that the object is not a columnar object, and when the coordinate difference is less than the shape determination threshold, the shape determination unit 120 determines that the object is a columnar object.

[0039] The shape determination threshold is a threshold corresponding to a value where the two coordinates are closely spaced, being thinner than a pedestrian or a vehicle like a columnar object, and is appropriately set according to the thickness of the columnar object and the like.

[0040] As shown in Fig. 6, since the columnar object 2C has a circumferential surface, detection waves are reflected from two different points P3 and P4 with adjacent coordinate positions along different paths D3 and D4 respectively towards each of the two transmission / reception wave sensors 41.

[0041] On the other hand, non-columnar objects other than the columnar object 2C (for example, an object 2 such as a wall having a plane extending in the X direction shown in Fig. 2) reflect detection waves from two different points P1 and P2 with separated coordinate positions along different paths D1 and D2 respectively towards each of the two transmission / reception wave sensors 41.

[0042] Thus, since there is a clear difference between the columnar object and the non-columnar object in the coordinate difference between the two coordinates, it is possible to determine whether the object is a columnar object or not based on the shape determination threshold. Also, although the reflection intensity is likely to vary in value under the influence of disturbances (wind, rain, heat, etc.), the coordinate difference is less affected by disturbances, so it is possible to accurately determine whether the object is a columnar object or not.

[0043] Also, the coordinate difference is indicated by the distance of at least the X-direction component among the X-direction component and the Y-direction component of the two coordinates. Note that the distance of the Y-direction component may also be considered in addition to the X-direction component for the coordinate difference.

[0044] Also, since the calculated coordinate difference may be different depending on the distance between the vehicle 1 and the object, in this case, for example, as shown in Fig. 7, different shape determination thresholds may be set for each distance between the vehicle 1 and the object. In the example shown in Fig. 7, the shape determination threshold is set to increase as the distance between the vehicle 1 and the object increases.

[0045] When the detected wave is reflected at two points of an object and received by the vehicle 1, the changing unit 130 changes the discrimination sensitivity of the discrimination unit 110 that discriminates whether the object is a control target according to the positions of the two points. Specifically, the changing unit 130 changes the discrimination threshold according to the coordinate difference between the two coordinates. For example, the changing unit 130 changes the discrimination threshold according to whether the object is a columnar object or not based on the determination result of the shape determination unit 120, thereby changing the above discrimination sensitivity.

[0046] In the present embodiment, as shown in FIG. 8, when the object is a non-columnar object, the discrimination threshold is set to a first threshold corresponding to a lower object such as a curb. The first threshold is the discrimination threshold shown in FIG. 5 above. For example, the discrimination threshold is set according to the reflection intensity of the detected wave with respect to the non-control target when the coordinate difference (distance between two points) of the two coordinates is equal to or greater than the shape determination threshold.

[0047] Since the columnar object is erected on the road surface and has a certain height, unlike a lower object, the reflection intensity does not increase as the distance increases. Therefore, the reflection intensity based on the detected wave related to the columnar object decreases as the distance between the vehicle 1 and the columnar object increases.

[0048] When the distance between the vehicle 1 and the columnar object is separated to a certain extent, the reflection intensity related to the columnar object falls below the first threshold, so the discrimination unit 110 discriminates the columnar object as a non-control target that is not a control target.

[0049] Therefore, when the object is a columnar object, the changing unit 130 changes the discrimination threshold to a second threshold corresponding to the reflection intensity related to the columnar object. The second threshold changes so as to decrease as the distance between the vehicle 1 and the columnar object increases, similarly to the reflection intensity related to the columnar object.

[0050] By doing so, the discrimination unit 110 can surely discriminate that the columnar object is a control target.

[0051] Further, the changing unit 130 may determine whether to perform control to change the identification threshold according to the distance between the vehicle 1 and the object. As the distance between the vehicle 1 and the object increases, the error in the calculated coordinates of the object becomes larger, which tends to affect the determination accuracy of the columnar object.

[0052] Therefore, when the distance between the vehicle 1 and the object is equal to or less than a predetermined distance, the changing unit 130 performs control to change the above-mentioned identification threshold. The predetermined distance is, for example, a distance at which a certain degree of calculation accuracy of the coordinates of the object is ensured, and is appropriately set according to the reflection intensity based on the detection wave of the object detection unit 40 or the like.

[0053] By doing so, it is possible to identify the columnar object as a control target within a range where the determination accuracy of the columnar object is ensured.

[0054] The area determination unit 140 determines whether the object 2 detected based on the detection wave capable of transmitting and receiving waves from the vehicle 1 is located within a predetermined area in front of the vehicle 1. As shown in FIG. 9, the predetermined area is an area on the side of the vehicle 1 and is an area between the first control target determination line L1 and the second control target determination line L2.

[0055] The first control target determination line L1 is a line passing through a position at a predetermined width away from the side surface of the vehicle 1. The predetermined width is, for example, the X-direction distance between the edge of the road and the side surface of the vehicle 1 when the vehicle 1 is traveling in the center of the road, and can be appropriately set in consideration of safety and the like.

[0056] The second control target determination line L2 is a line passing through a position farther from the vehicle 1 than the first control target determination line L1. The second control target determination line L2 is, for example, a line passing through a position where, when the object 2 is located between the first control target determination line L1 and the second control target determination line L2, the possibility of collision between the object 2 and the vehicle 1 increases when the vehicle 1 moves in the traveling direction (Y direction) and approaches the object 2, and can be appropriately set in consideration of safety and the like.

[0057] Note that although the first control target determination line L1 and the second control target determination line L2 are shown on the - side in the X direction of the vehicle 1 in FIG. 9 and the like, they may also be set on the + side in the X direction of the vehicle 1.

[0058] The region determination unit 140 compares the identification threshold value set by the change unit 130 with the reflection intensity based on the detected object 2, and when the reflection intensity is equal to or greater than the identification threshold value, based on the coordinates indicating the position of the object 2, it determines whether the object 2 is located within a predetermined region.

[0059] When the region determination unit 140 determines that the coordinates of the object 2 are outside the predetermined region, for example, on the vehicle 1 side (the above-mentioned front region) rather than in the range sandwiched between the first control target determination line L1 and the second control target determination line L2, the identification unit 110 identifies that the object is a control target.

[0060] Note that when the region determination unit 140 determines that the coordinates of the object 2 are outside the predetermined region and are located in the region on the side opposite to the vehicle 1 with respect to the second control target determination line L2, the identification unit 110 identifies that the object is a non-control target.

[0061] Further, when the region determination unit 140 determines that the coordinates of the object are located within the predetermined region, the identification unit 110 determines whether the object is a control target according to the curvature of the reflection surface of the object 2 estimated based on the detection wave.

[0062] Specifically, when the region determination unit 140 determines that the coordinates of the object 2 are located within the predetermined region, the identification unit 110 determines whether the object is a control target based on the time-series change of the coordinates of the object 2. More specifically, the identification unit 110 determines whether the object is a control target based on the difference between the first coordinate and the second coordinate.

[0063] The first coordinate is the coordinate indicating the first reflection point of the object 2 of the detection wave received by the vehicle 1 at the first position. The second coordinate is the coordinate indicating the second reflection point of the object 2 of the detection wave received by the vehicle 1 at the second position.

[0064] Note that the difference between the first coordinate and the second coordinate, for example, the difference between two coordinates, may be represented by a distance in the X - Y plane, for example.

[0065] The first position is, for example, at time t1, the position of the vehicle 1 when the detection wave is received by the transmission - reception wave sensor 41b. The second position is, for example, at time t2 after time t1, the position of the vehicle 1 when the detection wave is received by the transmission - reception wave sensor 41a.

[0066] Note that in the following description, the position of the vehicle 1 shown in FIG. 9 is taken as the first position, and the position of the vehicle 1 shown in FIG. 10 is taken as the second position. In FIGS. 9 and 10, the second position is located on the + side in the Y direction with respect to the first position.

[0067] At the first position and the second position, since the transmission positions of the detection waves of the transmission - reception wave sensor 41 (41a, 41b) are different, the paths of the detection waves that reciprocate between the vehicle 1 and the object 2 are different. For example, in FIG. 9, the detection wave transmitted by the second transmission - reception wave sensor 41b from the - side in the X direction is received by the transmission - reception wave sensor 41a located at the end on the - side in the X direction via the first reflection point P5. Also, in FIG. 10, the detection wave transmitted from the transmission - reception wave sensor 41a located at the end on the - side in the X direction is received by the second transmission - reception wave sensor 41b from the - side in the X direction via the second reflection point P6. Note that in FIG. 9 etc., the third transmission - reception wave sensor from the - side in the X direction is denoted by reference numeral 41c, and the transmission - reception wave sensor located at the end on the + side in the X direction is denoted by reference numeral 41d.

[0068] Due to the relationship between the incident angle and the reflection angle of the detection wave, a difference occurs between the first coordinate related to the first reflection point P5 and the second coordinate related to the second reflection point P6.

[0069] FIG. 11 shows the result of obtaining the coordinates of a columnar object arranged on the side of the road on which the vehicle 1 travels while moving the vehicle 1 and calculating the difference between two coordinates for each distance of the vehicle 1.

[0070] In Fig. 11, the vertical axis indicates the difference between two coordinates, and the horizontal axis indicates the distance in the Y direction. The difference between the two coordinates is the difference between the first detected coordinate and the coordinate detected at the position corresponding to each distance. The distance in the Y direction is the distance from the position where the coordinate was first detected to the vehicle end. Although the vehicle 1 shows an example where the transmitting and receiving sensor 41 for transmitting waves is different at the first position in Fig. 9 and the second position in Fig. 10, it may transmit waves from the same transmitting and receiving sensor 41.

[0071] In Fig. 11, the symbol L3 indicates the change in the difference of the coordinates of a columnar object with a larger diameter than L4 and L5, and the symbol L4 indicates the change in the difference of the coordinates of a columnar object with a smaller diameter than L3 and L5. Also, the symbol L5 indicates the change in the difference of the coordinates of a columnar object having a diameter between the diameters of L3 and L4.

[0072] As shown in Fig. 11, the smaller the diameter of the columnar object, the smaller the difference between the first coordinate and the second coordinate.

[0073] This indicates that the greater the curvature of the reflecting surface of the object 2 (the smaller the diameter), the smaller the time-series change of the coordinates. Therefore, the discrimination unit 110 compares the difference between the first coordinate and the second coordinate with a predetermined value, and based on the comparison result, determines whether the object 2 is a control target object.

[0074] The predetermined value is, for example, a value corresponding to the difference between the first coordinate and the second coordinate when the object is a columnar object (pole), and is a value appropriately set according to the curvature of the type of object to be a control target object.

[0075] For example, when the difference between the first coordinate and the second coordinate is greater than the predetermined value, the discrimination unit 110 discriminates that the curvature of the reflecting surface of the object 2 is smaller than the predetermined value and is a large columnar object. In this case, the discrimination unit 110 discriminates that the object 2 is a control target object. Note that large columnar objects include, for example, utility poles, and may also be objects having a reflecting surface with a small curvature in part.

[0076] For example, as shown in FIG. 12, when the object 2 is larger compared to FIGS. 9 and 10, the vehicle 1 receives the detection wave via the first reflection point P7 and the second reflection point P8 having a large coordinate difference compared to the first reflection point P5 in FIG. 9 and the second reflection point P6 in FIG. 10. Specifically, the vehicle 1 transmits the detection wave from the transmission / reception sensor 41a at the first position (the position of the two-dot chain line), and receives the detection wave at the transmission / reception sensor 41b via the first reflection point P7. Also, the vehicle 1 transmits the detection wave from the transmission / reception sensor 41b at the second position (the position of the solid line), and receives the detection wave at the transmission / reception sensor 41a via the second reflection point P8 having a coordinate difference of a predetermined value or more from the first reflection point P7. In FIG. 12, an example is shown where the transmission / reception sensor 41 for transmission is different at the first position and the second position for the vehicle 1, but transmission may be performed from the same transmission / reception sensor.

[0077] When a large object is located within a predetermined region, considering the possibility of collision with the vehicle 1, the object is considered as a control target. In the present embodiment, as described above, since the difference in the coordinates of the reflection points can be clearly determined at the first position and the second position, such an object can be accurately identified as a control target.

[0078] When the difference between the first coordinate and the second coordinate is equal to or less than a predetermined value, the identification unit 110 identifies that the object 2 is an object having a large curvature of the reflection surface and a small diameter. In this case, the identification unit 110 identifies the object 2 as a non-control target.

[0079] The predetermined region is a region close to the vehicle 1, but since the amount of protrusion of the vehicle 1 forward is small, there may be a case where a small object such as a pole, which has a low possibility of collision even when the vehicle 1 approaches, exists within the predetermined region. If such a small object is also regarded as a control target, it will lead to operating other devices such as the braking device for the small object. Also, such malfunction of other devices will be troublesome for the user.

[0080] In this embodiment, when the identification unit 110 determines that the object is a small object with a large curvature of the reflecting surface and a low possibility of collision, the identification unit 110 identifies the small object as a non-control target object. For example, as shown in FIGS. 9 and 10, when the object 2 is small, the difference in coordinates between the first reflection point P5 and the second reflection point P6 becomes small.

[0081] As a result, based on the difference in coordinates between the first reflection point P5 and the second reflection point P6, it can be identified that the object 2 is a small object. In this embodiment, since the identification unit 110 can identify the object 2 as a non-control target object, it is possible to prevent the malfunction of other devices.

[0082] Further, after the region determination unit 140 determines that the object is located within a predetermined region, the identification unit 110 may determine whether the object 2 is a control target object based on the time-series change of the coordinates of the object at three or more times.

[0083] For example, as shown in FIGS. 9 and 10, in the case of determination based on the time-series change of two times, such as the difference between the coordinates at time t1 and the coordinates at time t2, depending on the moving speed of the vehicle 1 and the transmission / reception wave situation of the detection waves of each transmission / reception wave sensor 41, the two coordinates may be close to each other.

[0084] Therefore, in addition to the difference in coordinates at times t1 and t2, as shown in FIG. 13, the coordinates of the reflection point P9 are acquired at the position at time t3 (t3>t2), and the difference in coordinates at times t2 and t3 is calculated. Then, when it is determined that the differences between the two sets of coordinates are both equal to or less than a predetermined value (determined to be a non-control target object), the identification unit 110 identifies the object as a non-control target object.

[0085] In this way, by using the information on the differences between the two sets of coordinates for identification control, the identification accuracy in the object identification device can be improved.

[0086] Here, the information on the difference between two sets of coordinates is used, but it is also possible to use the information on the difference between three or more sets of coordinates. Among the differences between three or more sets of coordinates, when the number of times the difference between coordinates is determined to be equal to or less than a predetermined value (the number of times determined to be a non-control object) is equal to or more than a predetermined number of times, the identification unit 110 identifies the object as a non-control object.

[0087] The predetermined number of times can be arbitrarily set, such as at least two times.

[0088] By doing so, the identification accuracy by the identification unit 110 can be further improved.

[0089] Based on the movement of the control object identified by the identification unit 110 and the relative speed of the control object based on the movement of the vehicle 1 (information on the vehicle speed), the control unit 150 predicts the possibility of collision between the vehicle 1 and the control object. As a method for predicting the possibility of collision, for example, a known technique can be applied.

[0090] Then, the control unit 150 outputs an acceleration request to the acceleration unit 10 or a braking request to the braking unit 20 according to the possibility of collision and the state of the acceleration of the vehicle 1.

[0091] As a result, appropriate driving control can be performed, such as controlling the braking operation for the accurately identified control object.

[0092] An operation example of the identification control in the vehicle control unit 100 configured as described above will be described. FIGS. 14 and 15 are flowcharts showing operation examples of the identification control in the vehicle control unit 100. The processes in FIGS. 14 and 15 are appropriately executed, for example, when the vehicle 1 is running. Also, in this flowchart, it is assumed that a detection wave has been transmitted from the transmission / reception wave sensor 41.

[0093] As shown in FIG. 14, the vehicle control unit 100 determines whether or not detection waves are received by the two transmission / reception sensors 41 (step S101). As a result of the determination, if the detection waves are not received by the two transmission / reception sensors 41 (step S101, NO), the process of step S101 is repeated.

[0094] On the other hand, if the detection waves are received by the two transmission / reception sensors 41 (step S101, YES), the vehicle control unit 100 acquires information on the distance between the vehicle 1 and the object and the reflection intensity of the detection waves (step S102).

[0095] Next, the vehicle control unit 100 determines whether or not the distance between the vehicle 1 and the object is within a predetermined distance (step S103). As a result of the determination, if the distance is greater than the predetermined distance (step S103, NO), the process transitions to step S105.

[0096] On the other hand, if the distance is within the predetermined distance (step S103, YES), the vehicle control unit 100 determines whether or not the coordinate difference between the two coordinates is less than the shape determination threshold (step S104).

[0097] As a result of the determination, if the coordinate difference is greater than or equal to the shape determination threshold (step S104, NO), the vehicle control unit 100 sets the discrimination threshold to the first threshold related to non-columnar objects (step S105). On the other hand, if the coordinate difference is less than the shape determination threshold (step S104, YES), the vehicle control unit 100 sets the discrimination threshold to the second threshold related to columnar objects (step S106).

[0098] As shown in FIG. 15, after step S105 or step S106, the vehicle control unit 100 determines whether or not the reflection intensity is greater than or equal to the discrimination threshold (step S107). As a result of the determination, if the reflection intensity is less than the discrimination threshold (step S107, NO), the process transitions to step S111.

[0099] On the other hand, when the reflection intensity is equal to or greater than the discrimination threshold value (step S107, YES), the vehicle control unit 100 determines whether the coordinates are within a predetermined area (step S108).

[0100] As a result of the determination, when the coordinates are not within the predetermined area (step S108, NO), the process proceeds to step S112. Note that the case where the coordinates are not within the predetermined area in step S108 means that the coordinates are located within the front area of vehicle 1. Regarding the determination process for distinguishing between the area on the side opposite to vehicle 1 and the front area with respect to the second control target determination line L2, additional determination may be performed before and after step S108.

[0101] On the other hand, when the coordinates are within the predetermined area (step S108, YES), the vehicle control unit 100 determines whether the difference between two coordinates obtained at different positions is greater than a predetermined value (step S109).

[0102] As a result of the determination, when the difference is equal to or less than the predetermined value (step S109, NO), the vehicle control unit 100 determines whether the number of times the difference is equal to or less than the predetermined value is less than a predetermined number of times (step S110). As a result of the determination, when the number of times is less than the predetermined number of times (step S110, YES), the process proceeds to step S112. Here, the predetermined number of times is a preset number of 2 or more.

[0103] On the other hand, when the number of times is equal to or more than the predetermined number of times (step S110, NO), the vehicle control unit 100 identifies that the object is a non-control target object (step S111).

[0104] Returning to the determination in step S109, when the difference is greater than the predetermined value (step S109, YES), the vehicle control unit 100 identifies that the object is a control target object (step S112). After step S111 or step S112, this control ends.

[0105] Note that after step S112, the vehicle control unit 100 performs predetermined driving control on vehicle 1.

[0106] According to the present embodiment configured as described above, it is determined whether the object 2 is a control target according to the curvature of the reflecting surface of the object 2. Specifically, it is determined whether the object 2 is a control target based on the temporal change in the coordinates of the object 2, for example, the difference between the first coordinate corresponding to the first position and the second coordinate corresponding to the second position.

[0107] Thereby, the size of the object 2 can be identified. As a result, it is possible to accurately identify whether the object 2 is a control target.

[0108] Further, when the difference between the two coordinates is equal to or less than a predetermined value, it can be determined that the object 2 is a small object such as a pole, so that an object with almost no possibility of colliding with the vehicle 1 can be identified as a non-control target. In the present embodiment, the object can be accurately identified.

[0109] In addition, since the object 2 is identified based on the temporal change at three or more times in the coordinates of the object 2, the identification accuracy of the object 2 can be improved as compared with the configuration in which the object 2 is identified based on the temporal change at two times.

[0110] Further, when the number of times the object 2 is determined to be a non-control target is equal to or more than a predetermined number of times, the object 2 is identified as a non-control target, so that the identification accuracy of the object 2 can be further improved.

[0111] In addition, since the predetermined area is a lateral area that is a predetermined width away from the side surface of the vehicle 1, the object to be identified according to the curvature of the reflecting surface can be specified as an object in the lateral area of the vehicle 1. As a result, apart from the object located in the front area, it is possible to identify whether the object on the side of the vehicle 1 is a control target, so that it is easy to accurately identify the object 2.

[0112] In addition, since the identification threshold is changed according to whether the object is a columnar object, the columnar object can be accurately identified as a control target.

[0113] Further, since the identification threshold (first threshold) is set according to the reflection intensity of the non-controlled object for the non-controlled object, when the object is a non-controlled object, it is possible to surely suppress identifying the object as a controlled object.

[0114] In addition, in the present embodiment, it is possible to suppress misidentifying an object due to the fact that the tendency of change in the reflection intensity is not the same depending on the shape of the object. As a result, in the present embodiment, the object can be stably identified.

[0115] Also, since it is determined whether the object is a columnar object based on the coordinate difference between two coordinates, it is possible to suppress misjudging the shape of the object due to the influence of disturbance. As a result, in the present embodiment, the shape of the object can be accurately determined.

[0116] Also, since it is determined whether to change the identification sensitivity according to the distance between the vehicle 1 and the object, the columnar object can be identified as a controlled object within a range where the determination accuracy of the columnar object is ensured. As a result, it is possible to accurately determine that the object is a columnar object.

[0117] In the above embodiment, it has been determined whether the object 2 is a controlled object based on the time-series change of the coordinates of the object 2, but the present disclosure is not limited to this. For example, by acquiring information on the degree of bending of the reflection surface of the object 2 from an external device, it may be determined whether the object 2 is a controlled object.

[0118] Also, in the above embodiment, when the number of times the object 2 is determined to be a non-controlled object is equal to or more than a predetermined number of times, the object 2 is identified as a non-controlled object, but the present disclosure is not limited to this. For example, if it is determined even once that the object 2 is a controlled object, the object 2 may be identified as a controlled object.

[0119] In the above-described embodiment, the identification unit 110 identifies whether the object 2 is a control target based on the time-series change in the coordinates of the object 2 at two times. However, the present disclosure is not limited to this. As shown in FIG. 6, based on the difference between two coordinates of the reflection surface of the object 2 detected by different detection wave paths at one time, it may be identified whether the object 2 is a control target.

[0120] In addition, when the difference between two coordinates of the reflection surface of the object 2 detected at one time is greater than a predetermined value, the identification unit 110 may assume that the object 2 is a large columnar object with a small curvature of the reflection surface of the object 2, and identify the object 2 as a control target.

[0121] On the other hand, when the difference between two coordinates of the reflection surface of the object 2 detected at one time is less than or equal to the predetermined value, the identification unit 110 assumes that the object 2 is an object with a large curvature of the reflection surface of the object 2 and a small diameter, and identifies the object 2 as a non-control target.

[0122] In the above-described embodiment, when the object 2 within the predetermined region is determined to be a small object with a large curvature, the identification unit 110 identifies the object 2 as a non-control target. However, the present disclosure is not limited to this. For example, the region determination unit 140 may shift the second control target determination line L2 toward the vehicle 1 side to narrow the predetermined region.

[0123] By doing so, since the object 2 deviates from the predetermined region, after narrowing the predetermined region, the object 2 can be removed from the identification target by the identification unit 110.

[0124] In the above-described embodiment, the shape determination unit 120 and the change unit 130 are provided. However, the present disclosure is not limited to this, and the shape determination unit 120 and the change unit 130 may not be provided.

[0125] Further, in the above embodiment, the discrimination sensitivity is set as the discrimination threshold value and the discrimination threshold value is changed. However, the present disclosure is not limited to this. For example, the discrimination sensitivity may be set as the reflection intensity, and instead of changing the discrimination threshold value, the reflection intensity may be changed. When the discrimination sensitivity is the reflection intensity, the reflection intensity is changed by changing the output pressure (such as sound pressure) of the detection wave or the amplification degree of the detection wave.

[0126] Specifically, when the object is a columnar object, the change unit 130 changes the reflection intensity so that the output pressure of the detection wave or the amplification degree of the detection wave is increased and the reflection intensity exceeds the discrimination threshold value (first threshold value).

[0127] Even in this way, the object can be stably discriminated.

[0128] Further, in the above embodiment, a columnar object such as a pole is exemplified as the columnar object. However, the present disclosure is not limited to this. As long as the object is a shape capable of reflecting the detection wave transmitted from the transmission / reception wave sensor 41 at two points of the object toward the two transmission / reception wave sensors 41 (for example, a columnar object having a plurality of reflection parts such as H-shaped steel), any columnar object may be used.

[0129] Further, the object to be the target of whether it is a control target may include a vehicle. For example, although the corner of the vehicle body has a curved surface, the curvature of this curved surface is smaller than the curvature of the curved surface of a small pole.

[0130] Therefore, when the difference between the first coordinate and the second coordinate, which are the coordinates of the reflection point where the detection wave is reflected by the reflection surface that is the curved surface of the vehicle body, is larger than a predetermined value, the vehicle can be discriminated as a control target by distinguishing it from a small pole.

[0131] Further, in the above embodiment, the object detection unit 40 has a configuration having four sensors. However, the present disclosure is not limited to this. As long as it has at least one sensor capable of transmitting a detection wave and two sensors capable of receiving a detection wave, the object detection unit 40 may have any number of sensors. For example, as shown in FIG. 16, the object detection unit 40 has six transmission / reception wave sensors.

[0132] Six sensors are arranged such that two are at the center in the X direction, one at each of both ends in the X direction, and one on each of both side surfaces of the vehicle 1. In the case where the object detection unit 40 has six sensors, it becomes possible to increase the variations in the combinations of the reciprocating paths of the detection waves as compared with the configuration shown in FIG. 2.

[0133] Further, in the above embodiment, when the detection wave is reflected at two points of the object and received by the vehicle 1, the discrimination sensitivity was changed. However, the present disclosure is not limited to this, and even when the detection wave is reflected at three or more points of the object and received by the vehicle 1, the discrimination sensitivity may be changed. Also, in this case, it is sufficient that it is provided so as to be receivable by three or more transmitting / receiving sensors.

[0134] Further, in the above embodiment, discrimination control was performed when the detection wave was received by two transmitting / receiving sensors. However, the present disclosure is not limited to this, and when the detection wave is received by one transmitting / receiving sensor, the discrimination threshold value may be set to the first threshold value related to a non-columnar object to identify the object.

[0135] Further, in the above embodiment, the object identification device (identification unit, shape determination unit, and change unit) was incorporated into the vehicle control unit. However, the present disclosure is not limited to this, and it may not be incorporated into the vehicle control unit.

[0136] In addition, each of the above embodiments is merely an example of a specific implementation when implementing the present disclosure, and the technical scope of the present disclosure should not be construed in a limited manner by these. That is, the present disclosure can be implemented in various forms without departing from the gist or its main features.

[0137] Note that in the object detection device of the above-described embodiment and modification example, the notation “··· unit” used for each component can be replaced with other notations such as “··· circuitry”, “··· assembly”, “··· device”, “··· unit”, or “··· module” as described above.

[0138] Also, in the object detection apparatus of the above-described embodiments and modified examples, the CPU 11 executes a program installed in the ROM 13, for example, to perform object detection processing.

[0139] However, the program executed by the object detection apparatus may be provided by being recorded on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), etc. in a file in an installable format or an executable format. Alternatively, the program may be downloaded via a network and executed on a computer.

[0140] Also, at least a part of the functions of the object detection apparatus may be realized by a dedicated hardware circuit that does not have a CPU.

[0141] As described above, the object detection apparatus of the above-described embodiments and modified examples can be realized by software, hardware, or software in cooperation with hardware. Also, the object detection apparatus of the above-described embodiments and modified examples may be realized by a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium, or may be realized by an arbitrary combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium. Note that a program product is a computer-readable medium on which a computer program is recorded.

[0142] In addition, each functional block of the object detection device according to the above-described embodiments and modifications is realized, in part or in whole, as an LSI which is an integrated circuit, and each process of the object detection device according to the above-described embodiments and modifications may be controlled, in part or in whole, by one LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of one chip so as to include part or all of the functional blocks. The LSI may have data input and output. Depending on the degree of integration, the LSI may also be referred to as an IC, a system LSI, a super LSI, or an ultra LSI.

[0143] However, the method of integrating into an integrated circuit is not limited to LSI, and it may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Further, after manufacturing the LSI, an FPGA (Field Programmable Gate Array) that can be programmed, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used. Each process of the object detection device according to the above-described embodiments and modifications may be realized as digital processing or analog processing.

[0144] Furthermore, if a technology for integrating into an integrated circuit that replaces the LSI appears due to the progress of semiconductor technology or another derived technology, naturally, the technology may be used to integrate the functional blocks. The application of biotechnology and the like may be possible.

Industrial Applicability

[0145] The object identification device of the present disclosure is useful as an object identification device, a vehicle, and an object identification method capable of stably identifying an object.

Explanation of Signs

[0146] 1 Vehicle 10 Acceleration unit 20 Braking unit 30 Vehicle speed information acquisition unit 40 Object detection unit 41, 41a, 41b, 41c, 41d Transmission / reception wave sensor 100 Vehicle control unit 110 Identification unit 120 Shape determination unit 130 Modification unit 140 Region determination unit 150 Control unit

Claims

1. An area determination circuit that determines whether an object detected based on a detection wave transmitted and received by a sensor mounted on a moving body is located within a predetermined area in front of the moving body; When it is determined by the area determination circuit that the object is located within the predetermined area, based on the difference between the first coordinates of the first reflection point of the object of the detection wave received by the moving body at the first position at the first time and the second coordinates of the second reflection point of the object of the detection wave received by the moving body at the second position at the second time after the first time, an identification circuit that identifies whether the object is a control target object, and when the difference between the first coordinates and the second coordinates is equal to or less than a predetermined value, identifies that the object is a non-control target object; An object identification device comprising the above.

2. When it is determined by the area determination circuit that the object is located within the predetermined area, the identification circuit determines whether the object is a control target object based on the time-series change of the coordinates of the object at three or more times. The object identification device according to Claim 1.

3. When the number of times the identification circuit determines that the object is a non-control target object is a plurality of times, the identification circuit identifies that the object is a non-control target object. The object identification device according to Claim 1 or 2.

4. The predetermined area is an area separated from the side surface of the moving body by a predetermined width. The object identification device according to any one of Claims 1 to 3.

5. When an object located within the predetermined area is identified as an object that is not a control target object, the area determination circuit narrows the predetermined area so that the position of the object is outside the predetermined area. The object identification device according to Claim 4.

6. The object identification device according to any one of Claims 1 to 5, A sensor that transmits and receives the detection wave, An object detection unit that detects the object based on the detection wave, A moving body comprising the above.

7. An object identification method, comprising: Determining whether an object detected based on a detection wave transmitted and received by a sensor mounted on a moving body is located within a predetermined area in front of the moving body; When it is determined that the object is located within the predetermined area, Based on the difference between the first coordinates of the first reflection point of the object in the detected wave received by the moving body at the first position at the first time and the second coordinates of the second reflection point of the object in the detected wave received by the moving body at the second position at the second time after the first time, identify whether the object is a control target object, When the difference between the first coordinates and the second coordinates is less than or equal to a predetermined value, identify that the object is a non-control target object, Object identification method.

8. Whether the object is the control target object, When it is determined that the object is located within the predetermined region, it is determined based on the time-series change of the coordinates of the object at three or more times. The object identification method according to claim 7.

9. The object is, When the number of times it is determined that the object is a non-control target object is multiple times, it is identified as a non-control target object. The object identification method according to claim 7 or 8.

10. The predetermined region is a region at a predetermined width away from the side surface of the moving body. The object identification method according to any one of claims 7 to 9.

11. When an object located within the predetermined region is identified as an object that is not the control target object, the predetermined region is narrowed so that the position of the object is outside the predetermined region. The object identification method according to claim 10.

12. A sensor that transmits and receives detection waves, An object detection unit that detects an object based on the detection wave, A moving body comprising: A moving body that uses the object identification method according to any one of claims 7 to 11.

Images