• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    An object recognition device is provided with: a sensor (2) that detects a lead vehicle (V) and a static object (O) on a road; a first path computation section (11) that on the basis of the history of the detected position of the lead vehicle (V), computes a relative movement path (Tv) of the lead vehicle (V), said movement path (Tv) being relative to a host vehicle (1); a second path computation section (12) that on the basis of the history of the detected position of the static object (O), computes a relative movement path (To) of the static object (O), said movement path (To) being relative to the host vehicle (1); and an object recognition section (14) that, if the movement paths (Tv, To) intersect each other, recognizes the static object (O) as an object that will not impede travel.
    公开号:AU2012367661A1
    申请号:U2012367661
    申请日:2012-01-26
    公开日:2014-08-14
    发明作者:Hiroyasu Ichida
    申请人:Toyota Motor Corp；
    IPC主号:G08G1-16
    专利说明:
    TSN2011G2030 TFN140392 1 DESCRIPTION TITLE OF THE INVENTION: OBJECT RECOGNITION DEVICE AND VEHICLE CONTROLLER 5 TECHNICAL FIELD [0001] The present invention relates to an object recognition device and a vehicle controller. 10 BACKGROUND ART [0002] In the related art, for example, as disclosed in JP 2006-127194 A, an object recognition device is known which recognizes a preceding vehicle, which is 15 referred to in controlling traveling of a vehicle, in distinction from a fixed object or the like on a road. [0003] The object recognition device stores a position of an object detected by a radar device, sets a determination area centered on the detected position, and determines a passing direction when one object passes through the determination area set on the 20 other object. An object of which the passing direction is a direction approaching the vehicle is recognized as a fixed object or the like on a road. Citation List Patent Literature [0004] PTL 1: Japanese Patent Application Publication No. 2006-127194 (JP 25 2006-127194 A) SUMMARY OF THE INVENTION TSN2011G2030 TFN140392 2 Technical Problem [0005] However, in the related art, when an object not serving as an obstacle in traveling of a vehicle needs to be recognized, there is room for improvement in recognition accuracy and rate. 5 [0006] For example, when an object is recognized using a millimeter wave sensor, an iron plate, a road sign, or the like on a road may be recognized as an object serving as an obstacle in traveling. When reflected waves of millimeter waves are analyzed to recognize an object, detection of an object close to a preceding vehicle may be delayed and thus the analysis may not be sufficiently analyzed. 10 [0007] Therefore, an object of the present invention is to provide an object recognition device that can appropriately recognize an object not serving as an obstacle in traveling of a vehicle and a vehicle controller that can appropriately control traveling of a vehicle. Solution to Problem 15 [0008] According to an aspect of the present invention, there is provided an object recognition device including: an object detecting unit that detects a preceding vehicle and a stationary object on a road; a first locus calculating unit that calculates a relative movement locus of the preceding vehicle to a vehicle on the basis of a history of a detected position of the preceding vehicle; a second locus calculating unit that 20 calculates a relative movement locus of the stationary object to the vehicle on the basis of a history of a detected position of the stationary object; and an object recognizing unit that recognizes the stationary object as an object not serving as an obstacle in traveling when the movement loci intersect each other. [0009] The object recognition device according to the present invention can easily 25 determine whether the preceding vehicle passes through the stationary object by determining whether the movement locus of the preceding vehicle and the movement locus of the stationary object intersect each other, and can rapidly recognize an object not serving as an obstacle in traveling of the vehicle with high accuracy.
    TSN2011G2030 TFN140392 3 [0010] The second locus calculating unit may estimate the position of the stationary object at a time point before the stationary object is detected, and may calculate the movement locus of the stationary object on the basis of the detected position and the estimated position of the stationary object. Accordingly, it is possible to 5 appropriately recognize an object not serving as an obstacle even when the detection of the stationary object is delayed. [0011] The object recognition device may further include an intersection determining unit that determines whether the positions of the preceding vehicle and the stationary object coincide with each other when the movement loci intersect each other 10 and the preceding vehicle and the stationary object are closest to each other, and the object recognizing unit may recognize the stationary object as an object not serving as an obstacle in traveling when the positions of the preceding vehicle and the stationary object coincide with each other. Accordingly, it is possible to accurately recognize an object not serving as an obstacle. 15 [0012] The second locus calculating unit may calculate the movement locus of the stationary object on the basis of a road shape in front of the vehicle. Accordingly, it is possible to calculate the movement locus of the stationary object with high accuracy and to appropriately recognize an object not serving as an obstacle. [0013] The first locus calculating unit may calculate the movement locus of the 20 preceding vehicle on the basis of movement histories of a plurality of points set on the preceding vehicle. Accordingly, it is possible to calculate the movement locus of the preceding vehicle with high accuracy and to accurately recognize an object not serving as an obstacle. [0014] According to another aspect of the present invention, there is provided a 25 vehicle controller including: an object detecting unit that detects a preceding vehicle and a stationary object on a road; a first locus calculating unit that calculates a relative movement locus of the preceding vehicle to a vehicle on the basis of a history of a detected position of the preceding vehicle; a second locus calculating unit that calculates TSN2011G2030 TFN140392 4 a relative movement locus of the stationary object to the vehicle on the basis of a history of a detected position of the stationary object; and a traveling control unit that suppresses performing of a collision avoiding control when the movement loci intersect each other. [0015] The vehicle controller according to the present invention can easily 5 determine whether the preceding vehicle passes through the stationary object by determining whether the movement locus of the preceding vehicle and the movement locus of the stationary object intersect each other, and can control traveling of the vehicle on the basis of the determination result. Advantageous Effects 10 [0016] According to the present invention, it is possible to provide an object recognition device that can appropriately recognize an object not serving as an obstacle in traveling of a vehicle and a vehicle controller that can appropriately control traveling of a vehicle. 15 BRIEF DESCRIPTION OF THE DRAWINGS [0017] [FIG. 1] FIG. 1 is a block diagram illustrating a configuration of a vehicle controller according to an embodiment of the present invention. [FIG. 2] FIG. 2 is a flowchart illustrating an operation of an object 20 recognition device. [FIG. 3] FIG 3 is a diagram illustrating a method of setting a presence area of a preceding vehicle. [FIG. 4] FIG. 4 is a diagram illustrating a method of calculating a movement locus of a stationary object on a straight road on the basis of a detected position. 25 [FIG. 5] FIG. 5 is a diagram illustrating a method of calculating a movement locus of a stationary object on a straight road on the basis of a detected position and an estimated position. [FIG. 6] FIG. 6 is a diagram illustrating a method of calculating a movement TSN2011G2030 TFN140392 5 locus of a stationary object on a curved road on the basis of a detected position and an estimated position. [FIG. 7] FIG. 7 is a diagram illustrating a method of calculating a relative transverse position of a stationary object on a curved road. 5 [FIG. 8] FIG. 8 is a diagram illustrating a method of determining passability. [FIG. 9] FIG 9 is a diagram illustrating a passage determining method. [FIG. 10] FIG. 10 is a diagram illustrating a modification example of a passability determining method. 10 MODES FOR CARRYING OUT THE INVENTION [0018] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the below description with reference to the drawings, identical elements will be referenced by identical reference 15 signs and description thereof will not be repeated. [0019] First, the configuration of a vehicle controller according to an embodiment of the present invention will be described below with reference to FIG. 1. The vehicle controller is a device that controls traveling of a vehicle 1 by determining whether a preceding vehicle passes through a stationary object depending on whether a movement 20 locus of the preceding vehicle and a movement locus of the stationary object intersect each other. [0020] As illustrated in FIG. 1, the vehicle controller includes a sensor 2 and an electronic control unit (ECU) 10. [0021] The sensor 2 constitutes an object detecting unit that detects a preceding 25 vehicle and a stationary object on a road. Here, examples of the stationary object include fixed objects or installed objects (such as an iron plate, a draining trench, a road illumination, a traffic strip, a road sign, and a road bridge) and dropped objects on a road. [0022] The sensor 2 includes, for example, a millimeter wave radar, but may TSN2011G2030 TFN140392 6 include another sensor such as a laser sensor as long as it can detect an object. The sensor 2 transmits detection waves to the front side of the vehicle 1, receives reflected waves from an object on the front side, and detects a position of an object, which includes a preceding vehicle and a stationary object 0, by detecting a distance between the vehicle 5 1 and the object and a relative speed of the object to the vehicle 1. It is determined which of a preceding vehicle, a stationary object 0, and an oncoming vehicle the object is on the basis of the variation of the detected value. [0023] The position of an object is specified by a relative distance indicating a gap from the vehicle 1 in the traveling direction (longitudinal direction) of the vehicle 1 10 and a relative transverse position indicating a gap to the vehicle 1 in the width direction (transverse direction) of the vehicle 1. For example, the position of an object is specified by coordinates using the traveling direction (longitudinal direction) of the vehicle 1 as a y axis and the width direction (transverse direction) of the vehicle 1 as an x axis with respect to the center of the front part of the vehicle 1. 15 [0024] The ECU 10 is an onboard controller including a CPU, a ROM, and a RAM. The ECU 10 includes a first locus calculating unit 11, a second locus calculating unit 12, an intersection determining unit 13, an object recognizing unit 14, and a traveling control unit 15. Here, the first locus calculating unit 11, the second locus calculating unit 12, the intersection determining unit 13, and the object recognizing unit 14 constitute 20 an object recognition device along with the sensor 2. The traveling control unit 15 constitutes a vehicle controller along with the sensor 2 and the constituent units 11 to 14 of the object recognition device. The constituent units 11 to 15 are embodied by software that is executed by the ECU 10. The constituent units 11 to 15 may be distributed to two or more ECUs. 25 [0025] The first locus calculating unit 11 calculates a relative movement locus of a preceding vehicle to the vehicle 1 on the basis of the history of the detected position of the preceding vehicle. The movement locus of the preceding vehicle is calculated as a line segment connecting the current detected position of the preceding vehicle and the TSN2011G2030 TFN140392 7 detected position thereof before a predetermined time. The current time is a time point at which it is determined whether the movement locus of the preceding vehicle and the movement locus of a stationary object intersect each other, and the predetermined time is a time (retroactive time) required for determination of the intersection and is generally set 5 to a time longer than the sampling period of the sensor 2. For example, the position of a preceding vehicle is detected as the center, the left end, and the right end of the preceding vehicle when seen from the vehicle 1. [0026] The second locus calculating unit 12 calculates a relative movement locus of a stationary object to (movement of) the vehicle 1 on the basis of the history of the 10 detected position of the stationary object. In this case, the movement locus of the stationary object is calculated as a line segment connecting the current detected position of the stationary object and the detected position thereof before a predetermined time. The second locus calculating unit 12 estimates the position of the stationary object at a time point before detecting the stationary object and calculates the movement locus of the 15 stationary object on the basis of the detected position and the estimated position of the stationary object. In this case, the movement locus of the stationary object is calculated as a line segment connecting the current detected position and the estimated position before a predetermined time. For example, the position of a stationary object is detected or estimated as the center, the left end, and the right end of the stationary object when 20 seen from the vehicle 1. [0027] The intersection determining unit 13 determines whether the movement locus of the preceding vehicle and the movement locus of the stationary object intersect each other. Whether the movement loci intersect each other is determined, for example, by solving simultaneous equations relevant to the line segment of the movement locus of 25 the preceding vehicle and the line segment of the movement locus of the stationary object. The intersection determining unit 13 determines whether the positions of the preceding vehicle and the stationary object coincide with each other when both are closest to each other. Whether both positions coincide with each other is determined, for example, by TSN2011G2030 TFN140392 8 comparing the position of the stationary object with a presence area of the preceding vehicle. [0028] The object recognizing unit 14 recognizes the stationary object as object not serving as an obstacle in traveling when the movement locus of the preceding vehicle 5 and the movement locus of the stationary object intersect each other. The object recognizing unit 14 may recognize the stationary object as an object not serving as an obstacle in traveling when the positions of the preceding vehicle and the stationary object coincide with each other at the time of getting closest to each other. [0029] The traveling control unit 15 suppresses performing of a collision avoiding 10 control when the movement locus of the preceding vehicle and the movement locus of the stationary object intersect each other. That is, the traveling control unit 15 normally performs a predetermined control of outputting a control signal to a braking mechanism and a steering mechanism (both of which are not illustrated) or the like so as to avoid a collision with an obstacle, but does not perform such a control when the movement locus 15 of the preceding vehicle and the movement locus of the stationary object intersect each other. The traveling control unit 15 may suppress performing the collision avoiding control when the positions of the preceding vehicle and the stationary object coincide with each other at the time of getting closest to each other. [0030] Operations of the object recognition device and the vehicle controller will 20 be described below with reference to FIGS. 2 to 9. [0031] FIG. 2 is a flowchart illustrating the operation of the object recognition device. For symbols in FIG. 2, referring to FIG. 4 and the like is recommended. The object recognition device repeatedly performs a series of processes illustrated in FIG 2, for example, with a predetermined cycle of about 10 ms to 100 ins. As illustrated in FIG. 25 2, in step S11, the sensor 2 detects a preceding vehicle V and a stationary object 0 and the ECU 10 stores histories of the detection positions thereof. [0032] That is, the sensor 2 detects the relative position (relative distance, relative transverse position) of the preceding vehicle V and the stationary object 0 to the vehicle TSN2011G2030 TFN140392 9 1. In parallel with detection by the sensor 2, the ECU 10 acquires steering angle information from a steering angle sensor (not illustrated) and acquires vehicle speed information from a vehicle wheel speed sensor (not illustrated). The ECU 10 stores the detected values at least for a predetermined time T. The predetermined time T is a time 5 (retroactive time) required for determination of the intersection and is set to a shorter time as the vehicle speed of the vehicle 1 becomes higher, for example, to 0.5 s to 1.0 s. [0033] In step S12, the ECU 10 determines whether a preceding vehicle V and a stationary object 0 are detected. Here, the determination of intersection of step S13 and steps subsequent thereto is performed when it is determined that a preceding vehicle V 10 and a stationary object 0 are detected, and the process flow ends when it is determined that both are not detected. [0034] Here, before performing the determination of intersection of step S13 and steps subsequent thereto, it is preferable that the ECU 10 perform the following processes. 15 [0035] Firstly, the ECU 10 preferably determines whether the vehicle speed, the relative distance to the object, the average steering angle within the predetermined time T, and the like satisfy set threshold values. When the values satisfy the set threshold values, the recognition process is effectively performed and thus the determination of intersection is performed. When the values do not satisfy the set threshold values, the 20 process flow ends. [0036] Secondly, the ECU 10 preferably excludes a specific object from the determination target. Here, the determination of intersection is basically performed on all combinations of the preceding vehicles V and the stationary objects 0 having been detected. That is, for example, when four preceding vehicles V and four stationary 25 objects 0 are detected, 16 sets of determination of intersection are basically performed. However, exceptionally, a preceding vehicle V of which the position before the predetermined time T is not detected is not effectively subjected to the recognition process and thus is excluded from the determination target. A stationary object 0 TSN2011G2030 TFN140392 10 recognized in advance to be an obstacle or not is excluded from the determination target, as long as it is newly detected as a preceding vehicle V or an oncoming vehicle or is not detected as an object (is lost). [0037] Thirdly, as will be described below, the ECU 10 preferably sets the 5 presence area A of a preceding vehicle V and determines whether a stationary object 0 is located in the presence area A. The stationary object 0 located in the presence area A is determined to be passed by the preceding vehicle V and is excluded from the determination target. [0038] The presence area A of the preceding vehicle V is set to a rectangular area 10 defined by positions Pbl, Pbr, Pfl, and Pfr expressed by Expressions (1) to (4) when the current detected position (x, y) is the center of the rear part of the preceding vehicle V as illustrated in FIG. 3. Pbl=(x-w/2-Aw, y) ... (1) Pbr=(x+w/2+Aw, y) ... (2) 15 Pfl=(x-w/2-Aw, y+l) ...(3) Pfr=(x+w/2+Aw, y+l) ... (4) [0039] Here, regarding symbols in Expressions (1) to (4), 1 represents the total length of the preceding vehicle V, w represents the vehicle width, and Aw represents the correction value of the vehicle width. In the expressions, 1~2.5 m, w~1.8 m, and 20 Aw~0.2 m to 0.3 m are set, for example, for a general automobile. The vehicle width correction value Aw is set to a relatively small value when plural objects are grouped in the recognition process. [0040] In step S13 of FIG 2, when it is determined in step S12 that the preceding vehicle V and the stationary object 0 are detected, the first locus calculating unit 11 25 calculates the movement locus Tv of the preceding vehicle V for a predetermined time T. The movement locus Tv of the preceding vehicle V is calculated as a line segment connecting the current detected position and the detected position before the predetermined time T.
    TSN2011G2030 TFN140392 11 [0041] In step S14, the ECU 10 determines whether the stationary object 0 is detected before the predetermined time T. When it is determined that the stationary object 0 is detected, the second locus calculating unit 12 calculates the movement locus To of the stationary object 0 for the predetermined time T in step S16. In this case, the 5 movement locus To of the stationary object 0 is calculated as a line segment connecting the current detected position and the detected position before the predetermined time T. [0042] On the other hand, when it is determined that the stationary object 0 is not detected, the second locus calculating unit 12 estimates the position of the stationary object 0 before the predetermined time T, that is, the position of the stationary object 0 at 10 a time point before the stationary object 0 is detected, in step S15. The position estimating method will be described later. In step S16, the second locus calculating unit 12 calculates the movement locus To of the stationary object 0 for the predetermined time T. In this case, the movement locus To of the stationary object 0 is calculated as a line segment connecting the current detected position and the estimated position before 15 the predetermined time T. [0043] The method f calculating the movement locus Tv of a preceding vehicle V and the movement locus To of an stationary object 0 will be described below with reference to FIGS. 4 to 7. FIG. 4 is a diagram illustrating a method of calculating the movement locus To of a stationary object 0 on a straight road on the basis of the detected 20 position. FIG. 4(a) illustrates the history of the detected position Do of the stationary object 0 along with the relative positional relationship of the preceding vehicle V and the stationary object 0 to the vehicle 1. In this example, the preceding vehicle V moves from the detected position D to the detected position C with a constant inter-vehicle gap from the vehicle 1. The stationary object 0 moves from the detected position B to the 25 detected position A for the predetermined time T with the traveling of the vehicle 1, as can be seen from the history of the detected position Do. [0044] FIG. 4(b) illustrates the movement locus To of the preceding vehicle V and the stationary object 0. A position A(xl, yl) represents the current position of the TSN2011G2030 TFN140392 12 stationary object 0 and a position B(x2, y2) represents the position before the predetermined time T. A position C(x3, y3) represents the current position of the preceding vehicle V and a position D(x4, y4) represents the position before the predetermined time T. The movement locus Tv of the preceding vehicle V is calculated 5 as a line segment CD connecting the detected position C and the detected position D, and the movement locus To of the stationary object 0 is calculated as a line segment AB connecting the detected position A and the detected position B. [0045] FIG. 5 is a diagram illustrating a method of calculating the movement locus To of the stationary object 0 on a straight road on the basis of the detected position 10 Do and the estimated position Eo. FIG. 5(a) illustrates the detected position Do and the estimated position Eo of the stationary object 0 along with the relative positional relationship of the preceding vehicle V and the stationary object 0 to the vehicle 1. In this example, the preceding vehicle V moves from the detected position D to the detected position C with a constant inter-vehicle gap from the vehicle 1. The stationary object 0 15 is first detected at the detected position A and thus the position B before the predetermined time T is estimated retroactively from the position A. [0046] Here, the estimated position B(x2, y2) on the straight road is calculated using the average vehicle speed of the vehicle 1. The average vehicle speed is calculated on the basis of vehicle speed information acquired for the predetermined time 20 T. The estimated value y2 is calculated by multiplying the average vehicle speed by the predetermined time T to obtain the displacement in the y direction and adding the displacement to the current detected value yl. When the steering angle is changed for the predetermined time T, the estimated value x2 is calculated by calculating the displacement in the x direction on the basis of the average steering angle and the 25 displacement in the y direction and adding the displacement to the current detected value x1. [0047] FIG. 5(b) illustrates the movement loci Tv and To of the preceding vehicle V and the stationary object 0. The movement locus Tv of the preceding vehicle V is TSN2011G2030 TFN140392 13 calculated as a line segment CD connecting the detected position C(x3, y3) and the detected position D(x4, y4), and the movement locus To of the stationary object 0 is calculated as a line segment AB connecting the detected position A(xl, yl) and the estimated position B(x2, y2). 5 [0048] FIG. 6 is a diagram illustrating a method of calculating the movement locus To of the stationary object 0 on a curved road on the basis of the detected position Do and the estimated position Eo. FIG 6(a) illustrates the relative positional relationship of the preceding vehicle V and the stationary object 0 to the vehicle 1. In this example, the preceding vehicle V moves from the detected position D to the detected 10 position C with a constant inter-vehicle gap from the vehicle 1. The stationary object 0 is first detected at the detected position A and thus the position B before the predetermined time T is estimated retroactively from the position A. [0049] Here, the estimated position B on the curved road is calculated using the average vehicle speed of the vehicle 1 and the curvature radius R. The curvature radius 15 R is estimated on the basis of the steering angle information acquired for the predetermined time T. The estimated value y2 of the relative distance is calculated in the same way as in the straight road. The estimated value x2 of the relative transverse position is calculated as follows in consideration of the curvature radius R of the curved road. 20 [0050] FIG. 7 is a diagram illustrating a method of calculating the relative transverse position of the stationary object 0 on the curved road. As illustrated in FIG. 7, the coordinate in the x direction of a second position with respect to a first position (x, y) on the curved road is expressed by the left side of Expression (5). Here, the curvature radius of the curved road is defined as R, the angular displacement is defined as $, and 25 the arc length is defined as L (~y). x-(R-Rcos$)=x-R(1-cos$) ... (5) cos$ in Expression (5) is Taylor-expanded, the following expression is obtained. cos*=1- 2 /2!+$e/4!+...
    TSN2011G2030 TFN140392 14 +(-1)"$2n/(2n)!+... ... (6) Here, since $=IJR, an error due to omission of higher-order terms decreases by L<<R. Accordingly, Expression (5) is converted into Expression (7). x-(R-Rcos$)~x-R[1-{1-L2/(2!-R2)1 5 =x-L 2 /(2R) ... (7) [0051] Therefore, the estimated value x2 is calculated by substituting the detected value x1 for x on the right side of Expression (7), substituting the displacement in the y direction calculated in the same way as in the straight road for L, and substituting the curvature radius R. 10 [0052] Accordingly, as illustrated in FIG. 6(b), the movement locus To of the stationary object 0 is calculated as the line segment AB connecting the detected position A(xl, yl) and the estimated position B(x2, y2) in the same way as in the straight road. The detected position B(x2, y2) is similarly calculated using the method of calculating the movement locus To of the stationary object 0 on the basis of the detected position Do 15 on the curved road. [0053] When the movement loci Tv, To are calculated, the intersection determining unit 13 determines whether the movement loci Tv, To intersect each other in step S17 of FIG. 2. Accordingly, the passability of the preceding vehicle V through the stationary object 0 is determined. 20 [0054] FIG. 8 is a diagram illustrating a passability determining method. A point P on the line segment AB connecting the position A(xl, yl) and the position B(x2, y2) and a point Q on the line segment CD connecting the position C(x3, y3) and the position D(x4, y4) are expressed by Expressions (8) and (9). Here, r represents the ratio of the length from the position A to the point P to the length of the line segment AB (Osrs1) and 25 s represents the ratio of the length from the position C to the point Q to the length of the line segment CD (Oss1). P=A+r(B-A) ... (8) Q=C+s(D-C) ... (9) TSN2011G2030 TFN140392 15 [0055] In this case, the intersection of the line segment AB and the line segment CD can be determined using Expressions (10) to (13). P=Q ...(10) By substituting Expressions (8) and (9) for Expression (10), Expression (11) is 5 obtained. A+r(B-A)=C+s(D-C) ... (11) By inputting the coordinates of the positions A, B, C, and D for Expressions (11), Expressions (12) and (13) are obtained. xl+r(x2-xl)=x3+s(x4-x3) ... (12) 10 yl+r(y 2 -yl)=y3+s(y4-y3) ... (13) [0056] The intersection of the line segment AB and the line segment CD is determined on the basis of the solutions to the simultaneous equations including Expressions (12) and (13). That is, when conditions of 0<r<1 and 0<s<1 are satisfied, it is determined that the line segments AB and CD intersect each other. On the other hand, 15 when any condition of rs0, ra1, ss0, and sal is satisfied, it is determined that the line segments AB and CD do not intersect each other. [0057] In step S18 of FIG 2, when it is determined in step S17 that the movement loci Tv, To intersect each other, the intersection determining unit 13 determines whether the positions of the preceding vehicle V and the stationary object 0 coincide with each 20 other at the time of getting closest to each other. Accordingly, when it is determined that there is a possibility that the preceding vehicle V passes through the stationary object 0, it is determined whether the preceding vehicle V actually passes through the stationary object 0. [0058] FIG. 9 is a diagram illustrating a passage determining method. As 25 illustrated in FIG. 9, when the preceding vehicle V moves transversely in a place apart from the stationary object 0, the preceding vehicle V does not pass through the stationary object 0 but the movement loci Tv, To may intersect each other. Accordingly, in order to prevent erroneous determination in the determination of passability, a passage TSN2011G2030 TFN140392 16 determination process is performed. [0059] Accordingly, the position I(x5, y5) of the stationary object 0 at the time point getting closest to the preceding vehicle V is calculated from Expressions (14), (15) with reference to FIG. 8. The time point Tp (retroactive time up to the time point at 5 which both is closest to each other) of getting closest to each other is calculated from Expression (16). Here, r in Expressions (14) to (16) is calculated using Expressions (8), (9). x5=(x2-xl)r+xl ... (14) y5=(y2-y1)r+yl ... (15) 10 Tp=Txr ... (16) [0060] Then, as described with reference to FIG 3, the presence area A of the preceding vehicle V at the time point is set on the basis of the detected position (position I) at the time of getting closest to each other. When the stationary object 0 is located in the presence area A of the preceding vehicle V, it is determined that both positions 15 coincide with each other at the time of getting closest to each other, that is, that the preceding vehicle V passes through the stationary object 0. [0061] In step S19 of FIG. 2, when it is determined in step S18 that the positions of the preceding vehicle V and the stationary object 0 coincide with each other at the time of getting closest to each other, that is, when it is determined that the preceding 20 vehicle V passes through the stationary object 0, the object recognizing unit 14 recognizes the stationary object 0 as an object not serving as an obstacle in traveling of the vehicle 1. On the other hand, when it is determined in step S17 that the movement loci Tv, To do not intersect each other, or when it is determined in step S18 that the positions of the preceding vehicle V and the stationary object 0 do not coincide with each 25 other at the time of getting closest to each other, the process flow ends. [0062] Then, when it is determined in step S18 that the positions of the preceding vehicle V and the stationary object 0 coincide with each other at the time of getting closest to each other, the traveling control unit 15 does not perform a predetermined TSN2011G2030 TFN140392 17 control of outputting a control signal to the brake mechanism and the steering mechanism or the like so as to avoid a collision with the obstacle. After it is determined in step S19 that the preceding vehicle V passes through the stationary object 0, the traveling control unit 15 may suppress the performing of the collision avoiding control. 5 [0063] FIG 10 is a diagram illustrating a modification example of the passability determining method. In the above-mentioned method, the movement locus Tv of the preceding vehicle V is calculated on the basis of the movement locus of one point on the preceding vehicle V such as the center of the rear part of the vehicle body. Accordingly, depending on the positional relationship between the preceding vehicle V and the 10 stationary object 0, the preceding vehicle V has passed through the stationary object 0 but the movement loci Tv, To may not intersect each other. [0064]. Accordingly, plural points, for example, first and second points, including the point corresponding to the detected position or the estimated position are set on the vehicle body of the preceding vehicle V. Then, a first movement locus connecting the 15 current first point and the second point before the predetermined time T and a second movement locus connecting the current second point and the first point before the predetermined time T are calculated. It is determined whether any of the first and second movement loci intersects the movement locus To of the stationary object 0. Here, it is preferable that the plural points be set so that the plural movement loci 20 intersect each other. [0065] For example, in the example illustrated in FIG. 10, first, two points (left points Cl, DI, right points Cr, Dr) are set to both sides with the vehicle width interposed therebetween in addition to the detection point (central points Cc, Dc) at the center of the rear part of the vehicle body. Then, in addition to a first movement locus Tv1 25 connecting the central points Cc, Dc, a second movement locus Tv2 connecting the current left point Cl and the right point Dr before the predetermined time T and a third movement locus Tv3 connecting the right point Cr and the left point Dl are calculated. It is determined whether any of the first to third movement loci Tv1 to Tv3 passes TSN2011G2030 TFN140392 18 through the movement locus To of the stationary object 0. [0066] For example, as illustrated in FIG. 10(a), in a situation in which the inter-vehicle distance increases, the third movement locus Tv3 intersects the movement locus To of the stationary object 0 with the passage of the preceding vehicle V through 5 the stationary object 0. Similarly, as illustrated in FIG. 10(b), in a situation in which the inter-vehicle distance decreases, the second movement locus Tv2 intersects the movement locus To of the stationary object 0 with the passage of the preceding vehicle V through the stationary object 0. In this way, by calculating the movement loci Tv1 to Tv3 of the preceding vehicle V on the basis of the movement loci of plural points set on 10 the preceding vehicle V such as the rear-left part and the rear-right part of the vehicle body, it is possible to determine whether the movement loci Tv, To intersect each other with high accuracy. [0067] As described up to now, the object recognition device according to this embodiment can easily determine whether the preceding vehicle V passes through the 15 stationary object 0 by determining whether the movement locus Tv of the preceding vehicle V and the movement locus To of the stationary object 0 intersect each other, and can rapidly recognize an object not serving as an obstacle in traveling of the vehicle 1 with high accuracy. [0068] By estimating the position of the stationary object 0 at a time point before 20 the stationary object 0 and calculating the movement locus To of the stationary object 0, it is possible to appropriately recognize an object not serving as an obstacle even when the detection of the stationary object 0 is delayed. [0069] When the movement loci Tv, To intersect each other, it is possible to accurately recognize an object not serving as an obstacle, by determining whether the 25 positions of the preceding vehicle V and the stationary object 0 coincide with each other when the preceding vehicle V and the stationary object 0 are closest to each other and recognizing the stationary object. [0070] By calculating the movement locus To of the stationary object 0 on the TSN2011G2030 TFN140392 19 basis of a road shape in front of the vehicle 1, it is possible to calculate the movement locus To of the stationary object 0 with high accuracy and to appropriately recognize an object not serving as an obstacle. [0071] By calculating the movement locus Tv of the preceding vehicle V on the 5 basis of the movement histories of plural points set on the preceding vehicle V, it is possible to calculate the movement locus Tv of the preceding vehicle V with high accuracy and to accurately recognize an object not serving as an obstacle. [0072] The vehicle controller according to this embodiment can easily determine whether the preceding vehicle V passes through the stationary object 0 by determining 10 whether the movement locus Tv of the preceding vehicle V and the movement locus To of the stationary object 0 intersect each other, and can control the traveling of the vehicle 1 on the basis of the determination result. [0073] The above-mentioned embodiment describes a best mode of the object recognition device and the vehicle controller according to the present invention, and the 15 object recognition device and the vehicle controller according to the present invention are not limited to the description of this embodiment. The object recognition device and the vehicle controller according to the present invention can be embodied by modifying or applying the object recognition device and the vehicle controller according to this embodiment to other devices without departing from the gist of the appended claims. 20 [0074] The present invention may be applied to a program for appropriately recognizing an object not serving as an obstacle in traveling of the vehicle 1 or a computer-readable recording medium having the program recorded thereon in the same way as described above. The present invention may be applied to a program for controlling the traveling of the vehicle 1 or a computer-readable recording medium 25 having the program recorded thereon in the same way as described above. Reference Signs List [0075] 1: vehicle 2: sensor TSN2011G2030 TFN140392 20 10: ECU 11: first locus calculating unit 12: second locus calculating unit 13: intersection determining unit 5 14: object recognizing unit 15: traveling control unit V: preceding vehicle 0: stationary object Tv: movement locus of preceding vehicle 10 To: movement locus of stationary object
    权利要求:
    Claims (6)
    [1] 1. An object recognition device comprising: an object detecting unit that detects a preceding vehicle and a stationary object on 5 a road; a first locus calculating unit that calculates a relative movement locus of the preceding vehicle to a vehicle on the basis of a history of a detected position of the preceding vehicle; a second locus calculating unit that calculates a relative movement locus of the 10 stationary object to the vehicle on the basis of a history of a detected position of the stationary object; and an object recognizing unit that recognizes the stationary object as an object not serving as an obstacle in traveling when the movement loci intersect each other. 15
    [2] 2. The object recognition device according to claim 1, wherein the second locus calculating unit estimates the position of the stationary object at a time point before the stationary object is detected, and calculates the movement locus of the stationary object on the basis of the detected position and the estimated position of the stationary object. 20
    [3] 3. The object recognition device according to claim 1 or 2, further comprising an intersection determining unit that determines whether the positions of the preceding vehicle and the stationary object coincide with each other when the movement loci intersect each other and the preceding vehicle and the stationary object are closest to each other, 25 wherein the object recognizing unit recognizes the stationary object as an object not serving as an obstacle in traveling when the positions of the preceding vehicle and the stationary object coincide with each other. TSN2011G2030 TFN140392 22
    [4] 4. The object recognition device according to any one of claims 1 to 3, wherein the second locus calculating unit calculates the movement locus of the stationary object on the basis of a road shape in front of the vehicle.
    [5] 5 5. The object recognition device according to any one of claims 1 to 4, wherein the first locus calculating unit calculates the movement locus of the preceding vehicle on the basis of movement histories of a plurality of points set on the preceding vehicle.
    [6] 6. A vehicle controller comprising: 10 an object detecting unit that detects a preceding vehicle and a stationary object on a road; a first locus calculating unit that calculates a relative movement locus of the preceding vehicle to a vehicle on the basis of a history of a detected position of the preceding vehicle; 15 a second locus calculating unit that calculates a relative movement locus of the stationary object to the vehicle on the basis of a history of a detected position of the stationary object; and a traveling control unit that suppresses performing of a collision avoiding control when the movement loci intersect each other. 20
    类似技术:
    公开号 | 公开日 | 专利标题
    AU2012367661B2|2015-04-23|Object recognition device and vehicle control device
    CN108238047B|2021-02-02|Driving support device
    CN103842228B|2016-09-07|The drive assist system of vehicle
    JP5878491B2|2016-03-08|Driving assistance device
    JP5083404B2|2012-11-28|Pre-crash safety system
    EP2571004B1|2016-03-09|System for predicting a driver&#39;s intention to change lanes
    KR101690352B1|2016-12-27|Collision monitor for a motor vehicle
    US9481364B2|2016-11-01|Drive assist device
    US9896073B2|2018-02-20|Method and device for carrying out collision-avoiding measures
    US9594166B2|2017-03-14|Object detecting apparatus
    KR101356203B1|2014-01-24|Aytomomous travelling controll system
    JP2013518333A|2013-05-20|Driver support method for detecting side objects
    JP5852036B2|2016-02-03|In-vehicle device
    JP2013511755A|2013-04-04|Method and driving support system for warning an object around a vehicle
    WO2016017494A1|2016-02-04|Driving assistance apparatus
    CN104756174A|2015-07-01|Collision avoidance assist device and collision avoidance assist method
    KR20120063626A|2012-06-18|Apparatus for controlling exterior air-bag and method thereof
    JP2009070094A|2009-04-02|Running safety device for vehicle
    JP5899761B2|2016-04-06|Driving support device and driving support method
    KR20160134830A|2016-11-23|Method and system to assess the risk of change of traffic lane during the driving of a leading vehicle on a roadway with at least two neighbouring traffic lanes method and system to assess the risk of change of traffic lane during the driving of a leading vehicle on a roadway with at least two neighbouring traffic lanes
    KR20180039900A|2018-04-19|Apparatus and method for determining collision possibility according to traveling path scenario and controlling a vehicle
    US20190092324A1|2019-03-28|System and method for determining collision point of vehicle
    KR101816317B1|2018-01-09|A dangerous vehicle detect system by calculation of collision probability
    JP6988717B2|2022-01-05|Collision detection device
    JP6582746B2|2019-10-02|Monitoring judgment apparatus and monitoring judgment method
    同族专利:
    公开号 | 公开日
    EP2808853A4|2015-07-08|
    RU2014130232A|2016-03-20|
    AU2012367661B2|2015-04-23|
    CN104067329A|2014-09-24|
    US20140341432A1|2014-11-20|
    JPWO2013111310A1|2015-05-11|
    JP5751350B2|2015-07-22|
    WO2013111310A1|2013-08-01|
    KR20140107619A|2014-09-04|
    US9384388B2|2016-07-05|
    EP2808853A1|2014-12-03|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    JP3411866B2|1999-10-25|2003-06-03|株式会社日立製作所|Millimeter wave radar device|
    JP3822515B2|2002-03-29|2006-09-20|株式会社東芝|Obstacle detection device and method|
    JP4210640B2|2004-10-29|2009-01-21|本田技研工業株式会社|Vehicle control object determination device and vehicle control device|
    US7729857B2|2005-08-18|2010-06-01|Gm Global Technology Operations, Inc.|System for and method of detecting a collision and predicting a vehicle path|
    US7865277B1|2007-05-07|2011-01-04|The United States Of America As Represented By The Secretary Of The Navy|Obstacle avoidance system and method|
    JP2009031053A|2007-07-25|2009-02-12|Fujitsu Ten Ltd|Device for detecting forward obstacle|
    JP4978494B2|2008-02-07|2012-07-18|トヨタ自動車株式会社|Autonomous mobile body and control method thereof|
    JP2009252198A|2008-04-11|2009-10-29|Suzuki Motor Corp|Travel environment presuming device, method and program, and traffic lane deviation alarm device and steering assisting apparatus|
    JP5094658B2|2008-09-19|2012-12-12|日立オートモティブシステムズ株式会社|Driving environment recognition device|
    WO2010070708A1|2008-12-18|2010-06-24|トヨタ自動車株式会社|Radar system|
    JP4957747B2|2009-05-18|2012-06-20|トヨタ自動車株式会社|Vehicle environment estimation device|
    JP5655297B2|2009-12-07|2015-01-21|トヨタ自動車株式会社|Object detection device, vehicle safety system equipped with object detection device|
    JP2011227582A|2010-04-15|2011-11-10|Toyota Motor Corp|Vehicle collision prediction apparatus|US9446711B2|2012-05-09|2016-09-20|Toyota Jidosha Kabushiki Kaisha|Driving assist device|
    US9135798B2|2012-09-01|2015-09-15|Honda Motor Co., Ltd.|Vehicle periphery monitoring device|
    US9558659B1|2014-08-29|2017-01-31|Google Inc.|Determining the stationary state of detected vehicles|
    JP6408860B2|2014-10-22|2018-10-17|株式会社デンソー|Object detection device|
    JP6027659B1|2015-08-27|2016-11-16|富士重工業株式会社|Vehicle travel control device|
    JP6580982B2|2015-12-25|2019-09-25|日立建機株式会社|Off-road dump truck and obstacle discrimination device|
    ITUA20163205A1|2016-05-06|2017-11-06|Cnh Ind Italia Spa|Method and system for mapping a workplace.|
    MX2019003386A|2016-09-26|2019-06-06|Nissan Motor|Route setting method and route setting device.|
    CN106379298B|2016-10-14|2019-12-06|畅加风行智能科技有限公司|Intelligent brake control method based on target moving body and automobile time calculation|
    DE112016007351T5|2016-10-18|2019-07-04|Honda Motor Co., Ltd.|Vehicle control device|
    JP6805105B2|2017-09-28|2020-12-23|株式会社デンソー|Control target vehicle setting device, control target vehicle setting system, and control target vehicle setting method|
    US10227039B1|2018-02-19|2019-03-12|Delphi Technologies, Llc|Warning system|
    US10782699B2|2018-03-10|2020-09-22|Baidu Usa Llc|Real-time perception adjustment and driving adaption based on surrounding vehicles' behavior for autonomous driving vehicles|
    JP6596534B2|2018-04-06|2019-10-23|株式会社デンソーテン|Radar apparatus, vehicle control system, and signal processing method|
    CN109709961B|2018-12-28|2021-12-07|百度在线网络技术（北京）有限公司|Road obstacle detection method and device and automatic driving automobile|
    法律状态:
    2015-08-20| FGA| Letters patent sealed or granted (standard patent)|
    优先权:
    申请号 | 申请日 | 专利标题
    PCT/JP2012/051704|WO2013111310A1|2012-01-26|2012-01-26|Object recognition device and vehicle control device|
    [返回顶部]