JP2004184332A - Object recognition apparatus for motor vehicle and apparatus for controlling distance between motor vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve recognition accuracy at the recognition of whether an reflecting object is a motor vehicle or not through the use of the intensity of reflected waves from the reflecting object. <P>SOLUTION: In the case that a plurality of reflected waves from reflecting objects are received when a plurality of transmission waves are irradiated, it is determined whether the reflecting objects which have generated the plurality of reflected waves are a single body or not. When it is determined that the reflecting objects are a single body by the determination, the maximum intensity among the intensities of the reflected waves reflected by the reflecting object is compared with a reference intensity for determining whether the reflecting object is a motor vehicle or not. In this way, it is possible to univocally determine whether the reflecting object is highly possibly a motor vehicle or highly possibly not a motor vehicle for every reflecting object determined as a single body. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention provides a vehicle object that irradiates a plurality of transmission waves within a predetermined angle range in each of a vehicle width direction and a height direction and recognizes a reflection object such as a preceding vehicle ahead of the host vehicle based on the reflected waves. The present invention relates to a recognition device and a headway control device that controls a headway between a recognized vehicle and a preceding vehicle.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, as disclosed in Patent Document 1, for example, an object recognition device that irradiates a transmission wave such as a light wave or a millimeter wave to the front of a vehicle and detects a reflected wave to recognize an object in front of the vehicle has been considered. ing. This type of device is applied to, for example, a device that detects that the distance from a preceding vehicle has become short and generates an alarm, and a device that controls the vehicle speed so as to maintain a predetermined distance between the preceding vehicle and the like. And is used for recognizing a preceding vehicle as a control target thereof.
[0003]
In the object recognition device described above, for example, a laser radar sensor irradiates the front of the vehicle with a plurality of laser beams within a predetermined angle range in each of the vehicle width direction and the height direction, and based on the reflected light, radiates the vehicle ahead by three. Recognize dimensionally. At this time, if there is a reflective object at a height or range that cannot be present with a normal vehicle, it is necessary to distinguish between a vehicle and a non-vehicle in order to recognize that it is not a vehicle. The non-vehicle determination map was used to identify the non-vehicle. Here, the non-vehicle determination map corresponds to the area where the reflective object exists when the vehicle width, the vehicle height, and the vehicle forward direction are set to the X axis, the Y axis, and the Z axis, respectively, as shown in FIG. 4 is a three-dimensional map in which the range of the received light intensity of reflected light for distinguishing between a vehicle and a non-vehicle is set.
[0004]
A method for distinguishing between a vehicle and a non-vehicle using the non-vehicle determination map will be described. First, it is determined which area of the non-vehicle determination map corresponds to the distance measurement data of the laser radar sensor. At this time, if the distance measurement data belongs to the non-vehicle range, the distance measurement data is deleted. On the other hand, when the distance measurement data corresponds to a range that is not a non-vehicle, the distance measurement data is held, and the distance measurement data is output to an inter-vehicle control ECU that executes determination of a preceding vehicle and inter-vehicle control.
[0005]
As shown in FIG. 5, the non-vehicle determination map is divided into an area near the center, an area around the center, and a lowermost area in the XY directions. The correspondence between the direction position and the received light intensity is set as shown in (a) to (c). The area near the center in the XY directions corresponds to the correspondence shown in FIG. 7B, the area around it corresponds to the correspondence shown in FIG. 9A, and the lowermost area corresponds to the correspondence shown in FIG.
[0006]
Here, the correspondence between the position in the Z direction and the received light intensity will be described. (A), (b), and (c) basically show the received light intensity of the reflected light within a predetermined distance in the Z direction. Are set as non-vehicles within a predetermined range, and the others are set as vehicles. This is because there is a difference in the reflection intensity between the vehicle and the non-vehicle, and the reflection intensity of the vehicle is considered to be higher than the reflection intensity of the non-vehicle. By setting the light receiving intensity for discriminating between a vehicle and a non-vehicle for each reflection object existing area, more appropriate discrimination between a vehicle and a non-vehicle can be performed. In other words, in an area where the possibility that a vehicle is present is large, the distance measurement data is retained even if the received light intensity is relatively small, while, in an area where the possibility that the vehicle is present is small, the received light intensity is not relatively large. As long as the distance measurement data is deleted. As a result, only the distance measurement data from the reflector that is highly likely to be a vehicle can be output to the headway control ECU.
[0007]
[Patent Document 1] JP-A-2002-40139
[0008]
[Problems to be solved by the invention]
As described above, in the conventional object recognition device, a plurality of laser beams are sequentially emitted from the laser radar sensor, and when the reflected waves are detected, based on the non-vehicle determination map, each reflected wave is detected. It is determined whether the received light intensity corresponds to a vehicle or a non-vehicle.
[0009]
However, the determination method in the conventional object recognition device may not be able to sufficiently secure the determination accuracy of the vehicle / non-vehicle. For example, when mud or the like adheres to a part of a vehicle and is contaminated, not all of the reflected light reflected by the vehicle has a high light receiving intensity. That is, even if the reflecting object is a vehicle, it may include distance measurement data based on reflected light having a low received light intensity. In this case, if it is determined that the distance measurement data based on the reflected light with low received light intensity corresponds to the non-vehicle and the measurement data is deleted, the distance measurement data for determining the reflection object as a vehicle is insufficient, and the vehicle is a vehicle. May not be correctly recognized.
[0010]
The present invention provides a vehicular object recognition device capable of improving the recognition accuracy when recognizing whether a reflection object is a vehicle or a non-vehicle by utilizing the intensity of a reflected wave from the reflection object. This is the first object. It is a second object of the present invention to provide an inter-vehicle distance control device capable of suitably controlling the inter-vehicle distance with a preceding vehicle by utilizing the intensity of a reflected wave when the reflecting object is a preceding vehicle. I do.
[0011]
[Means for Solving the Problems]
In order to achieve the first object, the vehicle object recognition device according to claim 1 irradiates a plurality of transmission waves over a predetermined angle range in each of a vehicle width direction and a height direction. Radar means for detecting a distance to a reflecting object, an angle in the two directions of the vehicle width direction and the height direction based on the reflected waves, and an intensity of the reflected waves,
When the plurality of reflectors satisfy a predetermined integration condition, determining means for determining the plurality of reflectors as an integrated reflector,
Selection means for selecting the maximum intensity among the intensities of the reflected waves corresponding to the respective reflection objects constituting the reflection object integratedly determined by the determination means,
Based on the distance and the angle in the two directions, which are the detection results of the radar means, the reflecting object is recognized, and when the maximum intensity selected by the selecting means is smaller than a predetermined reference intensity, the reflecting object is regarded as a non-vehicle. A recognition unit that increases the probability of recognition.
[0012]
As described above, in the object recognition device for a vehicle according to the first aspect, when a plurality of transmission waves are irradiated and a plurality of reflected waves are received, first, the reflection that causes the plurality of reflected waves is generated. It is determined whether the object is one. If it is determined that the reflection object is an integral reflection object, the maximum intensity of the reflected waves by the respective reflection objects constituting the reflection object is compared with a reference intensity for determining whether the vehicle is a vehicle or a non-vehicle. It is. In this way, it is possible to uniquely determine whether each of the reflective objects determined to be integrated is likely to be a vehicle or non-vehicle. Further, since the determination is made based on the maximum reflected wave intensity of each reflecting object, accurate determination can be made even when a part of the vehicle is dirty.
[0013]
As described in claim 2, it is preferable that the predetermined reference intensity is set to be smaller when the distance to the reflecting object is long than when the distance is short. This is because, even if the reflection intensity of the reflection object is the same, the reflection light intensity decreases as the distance from the reflection object increases.
[0014]
According to a third aspect of the present invention, there is provided a shape calculating means for calculating the shape of the reflecting object based on the distance detected by the radar means and the angle in the two directions, wherein the recognizing means has a maximum intensity higher than a predetermined reference intensity. Is smaller and the shape of the reflecting object is different from the vehicle shape, it is preferable to increase the probability that the reflecting object is recognized as a non-vehicle. In this way, by considering the shape of the reflecting object in addition to the intensity of the reflected wave, it is possible to more accurately determine whether the vehicle is likely to be a vehicle or a non-vehicle. it can.
[0015]
As described in claim 4, it is preferable that the recognition unit determines that the shape of the reflective object is different from the vehicle shape when the lateral width in the shape of the reflective object is shorter than the lateral width in the vehicle shape. When the width of the reflecting object is shorter than the width of the vehicle, the reflecting object is often a non-vehicle such as a tree or grass in a planting on the side of a road or a splash or dust flying on a road. That's why.
[0016]
As described in claim 5, the recognition means performs processing for increasing the probability of determining the reflection object as a non-vehicle based on the maximum intensity of the reflected wave when the distance to the reflection object is within a predetermined short distance. It is preferred to do so. This is because, even when the maximum reflected wave intensity is selected, as the distance to the reflecting object increases, the intensity of the reflected wave also decreases, making it difficult to distinguish between a vehicle and a non-vehicle.
[0017]
Further, in order to achieve the second object, an inter-vehicle distance control device according to claim 6 is provided.
In each of the vehicle width direction and the height direction, a plurality of transmission waves are irradiated over a predetermined angle range, and a distance to a reflection object based on the reflected waves, the two in the vehicle width direction and the height direction. Radar means for detecting the angle of the direction, and the intensity of the reflected wave,
When the plurality of reflectors satisfy a predetermined integration condition, determining means for determining the plurality of reflectors as an integrated reflector,
Selection means for selecting the maximum intensity among the intensities of the reflected waves corresponding to the respective reflection objects constituting the reflection object determined to be integrated,
Based on at least the shape of the reflective object, a recognition unit that recognizes that the reflective object is a preceding vehicle,
Calculating means for calculating a relative speed with respect to the preceding vehicle in a time series based on a change in a distance to the preceding vehicle, and calculating an average relative speed obtained by averaging a plurality of relative speeds calculated in the time series; ,
An inter-vehicle control unit that performs inter-vehicle control based on the distance to the preceding vehicle and the average relative speed;
A maximum strength of the reflected wave selected by the selection means with respect to the preceding vehicle, based on whether or not greater than a predetermined reference strength, comprising stability determination means for determining the recognition stability of the preceding vehicle,
When the stability determining unit determines that the recognition stability of the preceding vehicle is high, the calculating unit increases the influence of the latest relative speed when calculating the average relative speed.
[0018]
As described above, in the headway control device according to claim 6, when the maximum strength of the reflected wave by the reflecting object recognized as the preceding vehicle is higher than the predetermined reference intensity, the recognition stability of the preceding vehicle is determined to be high. judge. In other words, the vehicle has a higher reflection intensity than the non-vehicle, but if the maximum intensity of the actually detected reflected wave has a level that can be clearly distinguished from the non-vehicle, It is possible to continue to recognize the preceding vehicle stably in distinction from other reflective objects.
[0019]
When the reflection intensity is high, the S / N ratio related to the reflection wave intensity increases, so that the accuracy of the distance measurement data such as the distance to the preceding vehicle also improves.
[0020]
Here, in order to control the inter-vehicle distance to the preceding vehicle to the target distance, it is necessary to calculate a relative speed that is a speed difference between the own vehicle and the preceding vehicle (the own vehicle speed-the preceding vehicle). That is, in order to approach the preceding vehicle, the traveling speed of the own vehicle is controlled so that the relative speed becomes positive, and in order to increase the distance to the preceding vehicle, the relative speed is controlled so that the relative speed becomes negative. is there. Regarding the calculation of the relative speed, an average relative speed is usually calculated based on a plurality of relative speeds calculated in time series in order to eliminate the influence of noise, ranging error, and the like. Then, headway control is performed based on the average relative speed. However, if the headway control is performed using the average relative speed, a deviation from the actual relative speed occurs, and the responsiveness of the headway control is reduced.
[0021]
Therefore, in the following distance control device, when the accuracy of the distance measurement data is improved, the average relative speed is calculated by increasing the degree of influence of the latest relative speed. As a result, the average relative speed can be made closer to the latest relative speed, so that the responsiveness of the headway control can be improved.
[0022]
As described in claim 7, the influence of the latest relative speed on the average relative speed can be increased by reducing the number of relative speeds used in calculating the average relative speed by the calculation means. Further, as described in claim 8, when calculating the average relative speed, the weighting coefficient of the latest relative speed may be increased to calculate the weighted average relative speed. The effect of the relative speed can be increased.
[0023]
As described in claim 9, the stability determining means further recognizes the preceding vehicle based on whether a temporal change in the shape of the reflecting object corresponding to the preceding vehicle is smaller than a predetermined reference value. It is preferable to determine the degree of stability. Considering not only the maximum intensity of the reflected wave of the reflecting object that has been determined to be integrated but also the temporal change in the shape of the reflecting object, the accuracy of determining the recognition stability is improved. It should be noted that the temporal change in the shape of the reflecting object is specifically determined based on whether or not the change in the width of the reflecting object is within a predetermined length, whether or not the depth of the reflecting object is within a predetermined length, and the like.
[0024]
Similarly, as set forth in claim 10, the stability determining means is further based on whether or not the position of the preceding vehicle is within a predetermined distance in the lateral direction from an extension of the traveling direction of the own vehicle. It is preferable to determine the recognition stability of the preceding vehicle. This is because the closer the preceding vehicle is on the extension of the traveling direction of the own vehicle, the lower the possibility that the preceding vehicle goes out of the irradiation range of the laser means, and the relative speed can be calculated with the highest accuracy based on the distance measurement data.
[0025]
Further, as described in claim 11, the stability determination means may further determine the recognition stability of the preceding vehicle based on the continuation time of recognizing the preceding vehicle. This is because if the duration of actually recognizing the vehicle is long, it is highly likely that the vehicle is recognized stably.
[0026]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, a headway control device according to an embodiment of the present invention will be described.
[0027]
In the present embodiment, a vehicular object recognition device is applied to the inter-vehicle control device 1, and the inter-vehicle control device 1 also has a function of outputting a warning when an obstacle exists in an area to be warned. Things.
[0028]
FIG. 1 is a system block diagram of the headway distance control device 1. The inter-vehicle control device 1 is mainly configured by a recognition and inter-vehicle control ECU 3. The recognition / vehicle distance control ECU 3 has a microcomputer as a main component, and is provided with an input / output interface (I / O) and various drive circuits and detection circuits. Since these hardware configurations are general, detailed description will be omitted.
[0029]
The recognition / interval control ECU 3 receives detection signals from the laser radar sensor 5, the vehicle speed sensor 7, the brake switch 9, and the throttle opening sensor 11, and outputs an alarm sound generator 13, a distance display 15, a sensor abnormality display. 17, a drive signal is output to the brake driver 19, the throttle driver 21, and the automatic transmission controller 23. The recognition / interval control ECU 3 includes an alarm volume setting device 24 for setting an alarm volume, an alarm sensitivity setting device 25 for setting sensitivity in an alarm determination process, a cruise control switch 26, and a steering for detecting an operation amount of a steering wheel (not shown). A sensor 27 and a yaw rate sensor 28 for detecting a yaw rate generated in the vehicle are connected. The recognition / interval control ECU 3 includes a power switch 29, and starts a predetermined process when the power switch 29 is turned on.
[0030]
As shown in FIG. 2, the laser radar sensor 5 mainly includes a light emitting unit, a light receiving unit, a laser radar CPU 70, and the like. The light emitting section includes a semiconductor laser diode (hereinafter simply referred to as a laser diode) 75 that emits a pulsed laser beam through a light emitting lens 71, a scanner 72, and a glass plate 77. The laser diode 75 is connected to a laser radar CPU 70 via a laser diode drive circuit 76, and emits (emits) laser light in response to a drive signal from the laser radar CPU 70. A polygon mirror 73 is provided on the scanner 72 so as to be rotatable about a vertical axis. When a drive signal from a laser radar CPU 70 is input via a motor drive unit 74, the polygon mirror 73 is driven by a motor (not shown). Rotated by driving force. The rotation position of the motor is detected by a motor rotation position sensor 78 and output to the laser radar CPU 70.
[0031]
Since the polygon mirror 73 of the present embodiment includes six mirrors having different surface inclination angles, the polygon mirror 73 sweeps (irradiates) and scans (scans) the laser beam discontinuously within the predetermined angle ranges in the vehicle width direction and the vehicle height direction. Output. The laser beam is two-dimensionally scanned as described above. The scanning pattern will be described with reference to FIG. In FIG. 3, the pattern 92 of the emitted laser beam is shown only when it is emitted to the right end and the left end in the measurement area 91, and is omitted in the middle. In addition, the outgoing laser beam pattern 92 is shown in FIG. 3 as an example of a substantially circular shape, but is not limited to this shape and may be an elliptical shape, a rectangular shape, or the like. Further, instead of using laser light, radio waves such as millimeter waves or ultrasonic waves may be used. It is not necessary to stick to the scanning method, and any method may be used as long as it can measure two directions other than the distance.
[0032]
As shown in FIG. 3, when the center direction of the measurement area is the Z axis, predetermined areas in the XY plane perpendicular to the Z axis are sequentially scanned. In the present embodiment, the Y axis, which is the height direction, is the reference direction, and the X axis, which is the vehicle width direction, is the scanning direction. The scan area is 0.15 deg × 105 points = 16 deg in the X axis direction. In the direction, 0.7 deg × 6 lines = 4 deg. The scanning direction is from left to right in FIG. 3 for the X-axis direction, and from top to bottom in FIG. 3 for the Y-axis direction. Specifically, first, the first scanning line located at the uppermost position as viewed in the Y-axis direction is scanned at intervals of 0.15 ° in the X-axis direction. As a result, detection for one scanning line is performed, so that the second scanning line at the next position as viewed in the Y-axis direction is similarly scanned at intervals of 0.15 ° in the X-axis direction. Thus, the same scan is repeated up to the sixth scan line. Therefore, scanning is performed in order from the upper left to the lower right, and data for 630 points (105 points × 6 lines) is obtained.
[0033]
By such a two-dimensional scan, scan angles θx and θy indicating the scan direction and the measured distance r are obtained. The two scan angles θx and θy are the vertical scan angle θy, which is the angle between the emitted laser beam, the line projected on the YZ plane, and the Z axis, and the line projected on the XZ plane, respectively. The angle with the axis is defined as a horizontal scan angle θx.
[0034]
The light receiving unit of the laser radar sensor 5 includes a light receiving element 83 that receives a laser beam reflected by an object (not shown) through a light receiving lens 81 and outputs a voltage corresponding to the intensity of the laser beam. Then, the output voltage of the light receiving element 83 is output to the comparator 87 after being amplified by the amplifier 85. The comparator 87 compares the output voltage of the amplifier 85 with the reference voltage, and outputs a predetermined light receiving signal to the time measurement circuit 89 when the output voltage> the reference voltage.
[0035]
A drive signal output from the laser radar CPU 70 to the laser diode drive circuit 76 is also input to the time measurement circuit 89. Then, as shown in FIG. 2B, the driving signal is a start pulse PA, the light receiving signal is a stop pulse PB, and the phase difference between the two pulses PA and PB (that is, the time T0 when the laser light is emitted and the reflection The time difference ΔT from the time T1 at which the light was received is encoded into a binary digital signal. Further, the time during which the stop pulse PB is equal to or higher than the reference voltage is measured as the pulse width of the stop pulse PB. Then, these values are encoded into a binary digital signal and output to the laser radar CPU 70. The laser radar CPU 70 calculates the distance r to the object from the input time difference ΔT between the two pulses PA and PB input from the time measurement circuit 89, and calculates the position based on the distance r and the corresponding scan angles θx and θy. Create data. That is, the coordinates are converted into XYZ orthogonal coordinates with the center of the laser radar as the origin (0, 0, 0), the X axis in the vehicle width direction, the Y axis in the vehicle height direction, and the Z axis in the forward direction of the vehicle. The (X, Y, Z) data converted into the XYZ rectangular coordinates and the received light intensity data (corresponding to the pulse width of the stop pulse PB) are output to the recognition / inter-vehicle control ECU 3 as distance measurement data.
[0036]
Here, the received light intensity data will be described. FIG. 2C shows stop pulses PB of two reflected lights having different received light intensities. In FIG. 2C, a curve L1 corresponds to a stop pulse PB of reflected light having a relatively high received light intensity, and a curve L2 corresponds to a stop pulse PB of reflected light having a relatively low received light intensity.
[0037]
In the rising process of the curve L1 in FIG. 12, the time at which the reference voltage V0 is input to the comparator 87 is crossed at t11, the time at which the curve L1 crosses the reference voltage V0 at the falling process is t12, and the time at t11 and time t12 is calculated. Let the time difference be Δt1. Also, the time at which the curve L2 rises crosses the reference voltage V0 is t21, the time at which the curve L2 falls crosses the reference voltage V0 is t22, and the time difference between time t21 and time t22 is Δt2. Note that the reference voltage V0 is set to a magnitude that can avoid the influence of the noise component.
[0038]
As is clear from FIG. 2C, the time difference Δt1 which is the pulse width of the stop pulse PB of the reflected light having a strong received light intensity and the time difference which is the pulse width of the stop pulse PB of the reflected light having a weak received light intensity. Comparing with Δt2, the relationship of Δt1> Δt2 is established. That is, the pulse width of the stop pulse PB of the reflected light corresponds to the received light intensity. When the received light intensity is low, the pulse width is short, and when the received light intensity is high, the pulse width is long. Therefore, the time difference (Δt1, Δt2), which is the pulse width, is an index characterizing the intensity of the received reflected light.
[0039]
Note that the received light intensity changes depending on the reflection intensity of the reflecting object and the distance to the reflecting object. That is, when the reflection intensity of the reflection object is high or the distance to the reflection object is short, the light reception intensity of the reflected light increases, and when the reflection intensity is low or the distance to the reflection object is long, the reflection intensity increases. The light reception intensity of the light decreases.
[0040]
The recognition / inter-vehicle control ECU 3 recognizes an object based on the distance measurement data from the laser radar sensor 5, and adjusts the brake driver 19, the throttle driver 21 and the automatic transmission in accordance with the situation of the preceding vehicle obtained from the recognized object. A so-called inter-vehicle control for controlling the vehicle speed by outputting a drive signal to the transmission controller 23 is performed. In addition, an alarm determination process for issuing an alarm when a recognition object is present in a predetermined alarm area for a predetermined time is performed at the same time. In this case, the object corresponds to a preceding vehicle traveling in front of the own vehicle or a preceding vehicle that is stopped.
[0041]
Next, the internal configuration of the recognition / interval control ECU 3 will be described as a control block. The distance measurement data output from the laser radar sensor 5 is sent to the object recognition block 43. In the object recognition block 43, based on the three-dimensional position data obtained as the distance measurement data, the center position (X, Y, Z) of the object and the size (W, D, H). Further, based on a temporal change of the center position (X, Y, Z) of the object, a relative speed (Vx, Vy, Vz) of the object with respect to the own vehicle position is obtained. Further, in the object recognition block 43, based on the vehicle speed (own vehicle speed) output from the vehicle speed calculation block 47 based on the detection value of the vehicle speed sensor 7 and the obtained relative speed (Vx, Vy, Vz), the object is a stationary object. Identification of whether the object is a moving object is performed. An object that affects the traveling of the host vehicle is selected based on the identification result and the center position of the object, and the distance is displayed on the distance display 15.
[0042]
A steering angle is calculated in a steering angle calculation block 49 based on a signal from the steering sensor 27, and a yaw rate is calculated in a yaw rate calculation block 51 based on a signal from the yaw rate sensor 28. In a curve radius (curvature radius) calculation block 57, a curve radius (curvature radius) R is calculated based on the vehicle speed from the vehicle speed calculation block 47, the steering angle from the steering angle calculation block 49, and the yaw rate from the yaw rate calculation block 51. calculate. Then, the object recognition block 43 calculates the vehicle shape probability and the own lane probability based on the curve radius R and the center position coordinates (X, Z). The vehicle shape probability and the own lane probability will be described later.
[0043]
A model of an object having such data is referred to as a “target model”. The sensor abnormality detection block 44 detects whether the data obtained in the object recognition block 43 is in an abnormal range, and if the data is in an abnormal range, the sensor abnormality display 17 indicates the fact. Is made.
[0044]
On the other hand, in the preceding vehicle determination block 53, a preceding vehicle is selected based on various data obtained from the object recognition block 43, and a distance Z and a relative speed Vz in the Z-axis direction with respect to the preceding vehicle are obtained. Then, the inter-vehicle control unit and the alarm determination unit block 55 determine the distance Z from the preceding vehicle, the relative speed Vz, the setting state of the cruise control switch 26, the depressed state of the brake switch 9, the opening from the throttle opening sensor 11, Based on the sensitivity set value by the alarm sensitivity setting device 25, it is determined whether or not an alarm is to be issued if an alarm is determined, and the content of vehicle speed control is determined if a cruise determination is made. The result is output to the alarm sound generator 13 if an alarm is required. If the cruise is determined, a control signal is output to the automatic transmission controller 23, the brake driver 19, and the throttle driver 21 to perform necessary control. At the time of executing these controls, a necessary display signal is output to the distance display 15 to notify the driver of the situation.
[0045]
In such inter-vehicle control and alarm determination, it is important that the object recognition, which is the premise thereof, more specifically, the recognition of the vehicle as the object to be recognized is properly performed. Therefore, a description will be given of a process related to object recognition performed in the object recognition block 43 of the recognition / interval control ECU 3 in order to appropriately perform the vehicle recognition.
[0046]
FIG. 4A shows a main process relating to object recognition. In step S110 of FIG. 4A, the distance measurement data for one scan is read from the laser radar sensor 5. The scan cycle in the laser radar sensor 5 is set to 100 msec, and data is taken in every 100 msec.
[0047]
In step S120, data segmentation is performed. As described above, the segments are formed by grouping the three-dimensional position data obtained as the distance measurement data. In this segmentation, data that meets predetermined connection conditions (integration conditions) is collected to generate one piece of pre-segment data, and a predetermined connection condition (integration conditions) is used among the pre-segment data. Are collected into one main segment data. For example, if the pre-segment data satisfies both the conditions that the distance △ X in the X-axis direction between point-recognized data in the X-axis direction is 0.2 m or less and the distance △ Z in the Z-axis direction is 2 m or less, the point set is integrated. And ask for it. In this embodiment. Since there are six scan lines in the Y-axis direction, pre-segmentation generates pre-segment data for each line. Next, in the main segmentation, adjacent presegment data in a three-dimensional (X, Y, Z) space are integrated (main segmentation). This segment data is a rectangular parallelepiped region having three sides parallel to the X-axis, the Y-axis, and the Z-axis, and the center coordinates (X, Y, Z) and the length of the three sides (X, Y, Z) for indicating the size ( W, H, D) are data contents. This segment (data) is simply referred to as a segment (data) unless otherwise specified.
[0048]
In step S130, target recognition processing is performed to target individual vehicles to be recognized. A target is a model of an object created for a set of segments. This targeting process will be described with reference to the flowchart of FIG.
[0049]
In the target processing, first, a corresponding segment of the target model is searched (S131). This is a process for searching which of the segments detected this time the target model obtained up to the previous time matches. The segment corresponding to the target model is defined as follows. First, assuming that the target model has moved from the position at the time of the previous processing at the relative speed at the time of the previous processing, an estimated position where the target model will be present is calculated. Subsequently, an estimated moving range having a predetermined width in each of the X-axis, Y-axis, and Z-axis directions is set around the estimated position. Then, a segment at least partially included in the estimated moving range is set as a corresponding segment.
[0050]
In step S132, a data update process of the target model is executed. In this process, if there is a corresponding segment, the past data of the target model is updated based on the current data. The data to be updated include center coordinates (X, Y, Z), width W, height H, depth D, relative speeds (Vx, Vy, Vz) in the X-axis, Y-axis, and Z-axis directions, and center coordinates. Data of the past four times (X, Y, Z), the own lane probability, and the like. If there is no corresponding segment, the data of the target model is not updated and registered as a new target model.
[0051]
After that, the vehicle shape probability is calculated in step S133. The vehicle shape probability is an index indicating the probability that the target model is a vehicle, and is calculated based on the relative acceleration, shape, position, received light intensity, and detection time. The vehicle shape probability will be described in detail below.
[0052]
In the case where a large number of delineators are installed at a narrow interval on the road side or when a guardrail is detected, there is a possibility that these stationary objects may be erroneously recognized as moving objects. This is because, by always detecting something at the same position, it is determined that a vehicle running at the same speed as the own vehicle exists at that position. Therefore, the vehicle shape probability is calculated so that the target model erroneously recognized as a moving object is not erroneously determined as the preceding vehicle in the preceding vehicle determination block 53. If the preceding vehicle determination block 53 determines that the vehicle is a roadside object when the vehicle shape probability is, for example, less than 50%, it is possible to prevent a repeatedly appearing stationary object from being erroneously determined as a preceding vehicle.
[0053]
The possible range of the vehicle shape probability is 0 to 100%. When the vehicle shape probability instantaneous value is calculated for each target model, weighting is performed as in Expression 1 in order to reduce the effects of instantaneous noise and variations. Find on average.
[0054]
[Formula 1] Current vehicle shape probability = previous value × α + current instantaneous value × (1−α)
For example, the initial value is set to 50%, and α is set to 0.8.
[0055]
The instantaneous value of the vehicle shape probability is calculated as a sum of those values, with respect to each of the relative acceleration, the shape, the position, the received light intensity, and the detection time.
[0056]
For the relative acceleration, for example, | αj |> α0 + αn / j ² Is set to -50% if the above equation is satisfied for two or more relative accelerations αj, and -10% if one relative acceleration αj is satisfied. In the case of non-establishment, it is left as it is (neither plus nor minus). Here, αj is the calculated relative acceleration, α0 is the allowable relative acceleration, and αn is the value at the time of the noise sampling period due to the distance measurement error. This equation is the same as the equation shown in step 307 of FIG. 7 of Japanese Patent Application Laid-Open No. 9-178848, and a detailed description thereof will be omitted.
[0057]
Further, regarding the shape of the vehicle, if the width W belongs to a predetermined range (for example, 1.2 m ≦ W ≦ 2.8 m) and the depth D is within a first predetermined length (for example, 3 m), the vehicle is likely to be a vehicle. Since it is an object, the adjustment is + 30%. Further, even when the width W is out of the above range (1.2 m> W or W> 2.8 m), the depth D of the second predetermined length (for example, longer than the first predetermined length) If the distance is within 5 m), the object is an object such as a motorcycle or a large truck. Further, when the width W belongs to a predetermined range (for example, 1.2 m ≦ W ≦ 2.8 m) and the depth D belongs to between the first and second predetermined lengths (for example, 3 m ≦ D <5 m). Since the object is a truck, the amount of adjustment is + 10%.
[0058]
On the other hand, when the depth D is long (for example, D> 5 m) and the aspect ratio D / W is large (for example, 8 or more), since the object is a vertically long object such as a guardrail, the amount of adjustment is -50%.
[0059]
Next, the setting of the likelihood of being a vehicle based on the position of the target model and the received light intensity of the reflected wave will be described.
[0060]
Since the rear surface of the vehicle is formed of a metal surface and has a reflector, the rear surface of the vehicle basically has a higher reflection intensity than objects other than the vehicle (grass, trees, splash, dust, etc.). Therefore, it is possible to discriminate between a vehicle and a non-vehicle based on the intensity of the laser light reflected by the object.
[0061]
However, when mud or the like adheres to the rear surface of the vehicle, the received light intensity of the reflected wave reflected by the vehicle does not always increase. Therefore, in order to accurately determine the reflection intensity of each object, in the present embodiment, the maximum received light intensity is extracted from the received light intensity of the ranging data corresponding to the target model of each object, and the maximum received light intensity is extracted. It is decided to discriminate between a vehicle and a non-vehicle based on the.
[0062]
Specifically, the maximum received light intensity of reflected light from an object existing within a first distance (for example, 15 m) is compared with a first predetermined intensity. When the maximum received light intensity of the reflected light is equal to or less than the first predetermined intensity, the maximum received light intensity is low irrespective of the short distance, so that the reflection intensity of grass, trees, and the like existing on the side of the road (roadside) is low. It can be inferred that the object is a non-vehicle. Therefore, the adjustment in this case is -30%. At this time, if it can be confirmed that the position of the object is on the side of the road, the object can be more accurately identified as grass or a tree on the side of the road. A condition that the vehicle is separated from the traveling direction by a predetermined distance (for example, 1 m) or more in the lateral direction may be added. Further, a condition that the width W of the object is smaller than a predetermined width (for example, 0.1 m) smaller than the width of the vehicle may be added. When the width W of the reflecting object is shorter than the width of the vehicle, the reflecting object may be a non-vehicle such as a tree or grass in a planting on the side of a road or a splash or dust flying on a road. Because there are many.
[0063]
As for the width W, for example, a plurality of widths may be set (for example, 0.1 m and 0.5 m), and the larger the width, the smaller the minus value due to the amount of adjustment may be made. That is, when the width W is smaller than 0.1 m, it is very likely that the object is an object other than a vehicle. Therefore, as described above, the adjustment is set to −30%, and 0.1 ≦ W <0.5. In the case of (1), the adjustment is set to, for example, -10%.
[0064]
Further, the maximum received light intensity of reflected light from an object existing within a second distance (for example, 3 m) closer than the first distance (15 m) described above and a second light intensity smaller than the first predetermined intensity. Compare with a predetermined strength. If the maximum received light intensity of the reflected light is smaller than the second predetermined intensity, it can be assumed that the reflection object is an object having a very low reflection intensity such as splash or dust. Therefore, also in this case, the adjustment is set to, for example, -10%. Also at this time, by confirming the size of the reflecting object, the accuracy of estimating that the object is a splash or dust can be improved. For example, the condition that the width W is smaller than a predetermined width (eg, 0.5 m) is set. May be added.
[0065]
In the present embodiment, since the received light intensity of the reflected light is indicated by the pulse width of the stop pulse PB, both the maximum received light intensity of the reflected light and the first and second predetermined intensities to be compared with the maximum received light intensity. , Pulse width time.
[0066]
Further, the first and second predetermined intensities described above may be changed according to the distance to the reflecting object. That is, the first and second predetermined intensities may be set so as to decrease as the distance to the actually detected reflection object increases. This is because, even if the reflection intensity of the reflection object is the same, the reflection light intensity decreases as the distance from the reflection object increases.
[0067]
Next, as for the detection time, for example, when the detection time is 2 seconds or longer, the amount of addition and subtraction is + 20%, and when the detection time is 5 seconds or longer, + 50%. When the vehicle is following the preceding vehicle, the preceding vehicle can be detected stably for a long time. On the other hand, when the roadside delineators and guardrails are detected, the same detection state is not detected for a long time. Because it does not last, many target models disappear and disappear or new ones appear. Therefore, it can be said that a target model that has been detected for a long time is likely to be a traveling vehicle, and it is preferable to increase or decrease the amount according to the detection time.
[0068]
Next, in step S134, the own lane probability is calculated. The own lane probability is a parameter indicating the likelihood that the target model is a vehicle running on the same lane as the own vehicle. In the present embodiment, after calculating the instantaneous value of the own lane probability (the value calculated based on the detection data at that instant), a predetermined filter process is performed to obtain the own lane probability.
[0069]
First, the position of the target model is converted into a position on a straight road based on the curve radius calculated by the curve radius calculation block 57. The position obtained by converting to the straight lane in this way is superimposed on the own lane probability map, and the own lane probability instantaneous value of the target model is obtained. In addition, the own lane probability map divides a predetermined range in front of the own vehicle (for example, 5 m on each side and 100 m in front) into a plurality of regions, and the closer the distance in front is, and the closer the vehicle is on the course of the own vehicle, It is a map to which each region probability is given so that the probability is high.
[0070]
After obtaining the instantaneous value of the own lane probability, as shown in Expression 2, filter processing is performed by a weighted average to obtain the own lane probability.
[0071]
[Equation 2] Own lane probability = the previous value of own lane probability × α + the instantaneous value of own lane probability × (1−α)
Here, α may be a constant value, or may change according to the distance from the target model or the area where the target model exists. Note that the method of calculating the own lane probability is described in detail in paragraph numbers 0050 to 0056 of JP-A-2002-40139, and therefore, further detailed description will be omitted.
[0072]
Next, in step S135, the recognition stability is determined. This recognition stability determination processing is for determining the recognition stability indicating how stably each target model can be recognized. The recognition stability is determined in a plurality of steps (for example, four steps) based on the intensity of the reflected light, the temporal change in the shape of the target model, the location of the target model, the detection time, and the range of the target model shape. ). In the state where the recognition stability is the lowest (stability 0), if at least one of the above-described conditions such as the abnormality of the relative acceleration and the detection time is shorter than a predetermined time (for example, 4 seconds) is satisfied, the stability becomes stable. The degree is determined to be 0.
[0073]
Regarding the received light intensity of the reflected light, at least two levels of reference intensity (first reference intensity and second reference intensity) are set and compared with the maximum received light intensity among the received light intensities of the plurality of reflected lights by the target model. I do. Then, if the maximum light receiving intensity of the reflected light is greater than the first reference intensity, it is determined that one of the stability establishment conditions for the highest stability 3 is satisfied. Hereinafter, sequentially, when the maximum light receiving intensity is higher than the second reference intensity smaller than the first reference intensity, it is determined that one of the conditions for determining stability 2 is satisfied, and the maximum light receiving intensity is higher than the second reference intensity. If smaller, it is determined that the stability is 1.
[0074]
The reason why the magnitude of the maximum received light intensity is used for determining the recognition stability is as follows. First, vehicles have higher reflection intensity than non-vehicles, but if the maximum intensity of the actually detected reflected light is large enough to be clearly distinguished from non-vehicles Thus, the target model of the preceding vehicle can be stably recognized while being distinguished from the target model of another reflective object. Further, when the received light intensity is high, the S / N ratio relating to the received light intensity of the reflected wave is increased, so that the accuracy of detecting distance measurement data such as the distance of the preceding vehicle from the target model is also improved.
[0075]
Next, regarding the temporal change of the shape of the target model, the previous calculated value of the target model calculated based on the distance measurement data detected at a predetermined interval (100 msec) and the current calculated value of the target model are calculated. If the difference is less than the predetermined length, it is determined that one of the conditions for satisfying the determination of stability 3 is satisfied. If the difference is not less than the predetermined length, it is determined that stability 2 or less. Specifically, the width W and depth D are adopted as the shape of the target model, and the difference between the previously calculated width W and the currently calculated width W is less than a predetermined length (for example, 0.5 m). If the difference between the depth D calculated last time and the depth D calculated this time is less than a predetermined length (for example, 0.5 m), it is determined that one of the conditions for determining stability 3 is satisfied. .
[0076]
When the shape of the target model formed based on the distance measurement data measured at different timings is substantially the same, a plurality of reflected lights corresponding to the target model can be stably detected. Means that. Therefore, in such a case, it can be determined that the recognition stability is high.
[0077]
Regarding the existence position of the target model, whether or not the target model is present within a range of a predetermined distance in the lateral direction from an extension of the traveling direction of the own vehicle is set as a condition for establishing each recognition stability. Specifically, two types of distances (first distance: for example, 1 m each for the left and right, and second distance: for example, 1.5 m for each of the left and right) are used as distances for determining the deviation of the host vehicle from the extension of the traveling direction in the lateral direction. ) Is set. When the target model exists within the range of the first distance, one of the conditions for determining the stability 3 is satisfied, and when the target model exists within the range of the second distance, the stability of the stability 2 is satisfied. If one of the conditions for the determination is satisfied and is out of the second distance range, the stability is determined to be 1.
[0078]
As described above, the reason for using the target position of the target model for the recognition stability determination is that the closer the preceding vehicle is to the extension of the traveling direction of the own vehicle, the more the preceding vehicle is traveling in the same lane as the own vehicle. This is because there is a high possibility, and in this case, there is a low possibility of going out of the irradiation range of the laser radar sensor 5, and the relative speed Vz can be calculated with the highest accuracy based on the distance measurement data.
[0079]
Regarding the detection time, a plurality of reference times (first reference time: for example, 20 seconds, second reference time: for example, 10 seconds) are set. When the continuous detection time of the target model is equal to or longer than the first reference time, one of the conditions for determining stability 3 is satisfied. When the detection time is equal to or longer than the second reference time, one of the conditions for determining stability 2 is satisfied. If one is satisfied and is equal to or less than the second reference time, it is determined that the stability is 1. That is, when the duration of the actual detection of the target model is long, the target model is considered to be the preceding vehicle and is likely to be stably recognized.
[0080]
Finally, as the shape of the target model falls within the range of a more vehicle-like shape, it is determined that one of the conditions for establishing a higher recognition stability is satisfied. For example, when the width W of the target model is larger than 1.3 m and smaller than 2.6 m, and the depth D of the target model is 0.5 m or less, the target model indicates the rear surface of the vehicle. Since the possibility is high, it is determined that one of the conditions for determining stability 3 is satisfied. Further, for example, when the width W of the target model is larger than 0.5 m and smaller than 2.8 m and the depth D is 1.0 m or less, it is determined that one of the conditions for determining stability 2 is satisfied, and the width of the target model is satisfied. If W or depth D is out of the range, it is determined that the stability is 1.
[0081]
Recognition stability 3 or recognition stability 2 is determined when all of the above-described conditions are satisfied, and when at least one of the conditions is not satisfied, it is determined to be a lower stability.
[0082]
However, regarding the determination of the recognition stability, it is not necessary to make a determination with respect to all of the above-described conditions, and other conditions may be used as necessary while using at least the maximum received light intensity of a plurality of reflected lights from the target model. It may be used additionally. Further, in addition to the above-described determination conditions, for example, the vehicle shape probability of the target model or the distance to the target model may be used. That is, it may be determined that the higher the vehicle shape probability and the shorter the distance, the higher the condition for establishing stability is satisfied.
[0083]
The recognition stability determined in this way is used when the preceding vehicle determination block 53 calculates the relative speed Vz of the target model. Hereinafter, a method of calculating the relative speed Vz in consideration of the recognition stability in the preceding vehicle determination block 53 will be described.
[0084]
In order to control the inter-vehicle distance with the preceding vehicle to the target distance, it is necessary to calculate a relative speed Vz, which is a speed difference between the own vehicle and the preceding vehicle (the own vehicle speed-the preceding vehicle). That is, in order to approach the preceding vehicle, the traveling speed of the own vehicle is controlled so that the relative speed Vz becomes positive, and in order to increase the distance from the preceding vehicle, the relative speed Vz is controlled so that the relative speed Vz becomes negative. I do. Therefore, since the relative speed Vz which is the basis for performing such control needs to be calculated accurately, usually, in order to eliminate the influence of noise, ranging error, and the like, as shown in Expression 3, The average relative speed Vzave is calculated based on the N relative speeds Vz calculated in time series.
[0085]
## EQU3 ## Vzave = (Vz1 + Vz2 +... + VzN) / N
Then, the average relative speed Vzave is used as the relative speed Vz for the following distance control. However, if the headway control is performed using the average relative speed Vzave, a deviation from the actual relative speed occurs, and the responsiveness of the headway control is reduced.
[0086]
Therefore, in the present embodiment, as described above, the recognition stability of the target model that is the preceding vehicle is determined using the maximum received light intensity of the reflected light. If it is considered that the recognition stability is high and the accuracy of the distance measurement data is improved, the average relative speed Vzave is calculated by increasing the degree of influence of the latest relative speed Vz1. As a result, the average relative speed Vzave can be made closer to the latest relative speed Vz1, so that the responsiveness of the headway control can be improved.
[0087]
Specifically, the number N of relative speeds Vz used when calculating the average relative speed Vzave is set to four levels based on the above-described determination result of the recognition stability. That is, the average relative speed Vzave is calculated based on the largest relative speed Vz when the stability is 0, and the number N of the relative speeds Vz decreases as the recognition stability increases.
[0088]
As shown in Expression 4, the average relative speed Vzave may be obtained by a weighted average calculation, and the weight α may be increased as the recognition stability increases. Also in this case, as the recognition stability increases, the influence of the latest relative speed Vz1 on the average relative speed Vzave can be increased.
[0089]
Vzave (N) = Vzave (N-1) × (1-α) + Vz1 × α
The preceding vehicle determination block 53 outputs, from the object recognition block 43 shown in FIG. 1, data of the target model including the above-described vehicle shape probability and the own lane probability in addition to the recognition stability. Then, in the preceding vehicle determination block 53, for example, in a target model in which the vehicle shape probability is equal to or more than a predetermined threshold (for example, 50%) and the own lane probability is equal to or more than a predetermined threshold (for example, 50%), The vehicle with the minimum distance Z is determined to be the preceding vehicle. Then, the average relative speed Vzave with respect to the preceding vehicle is calculated while changing the calculation method of the average relative speed Vzave according to the recognition stability of the target model of the preceding vehicle. The calculated average relative speed Vzave is output to the inter-vehicle control unit and the alarm determination unit block 55 together with the distance Z to the preceding vehicle as the relative speed Vz. Thus, the inter-vehicle control unit and the alarm determination unit block 55 can execute the inter-vehicle control process and the alarm determination process based on the distance Z to the preceding vehicle and the relative speed Vz.
[0090]
It should be noted that the present invention is not limited to such embodiments at all, and can be implemented in various forms without departing from the gist of the present invention.
[0091]
In the above embodiment, the pulse width of the stop pulse PB is used as an index indicating the light receiving intensity, but another index may be used. For example, a peak value detection circuit that detects the peak value of the stop pulse PB is provided, and this peak value can be used as an index indicating the received light intensity. Further, the rising angle of the stop pulse PB, that is, the time from the start of the rising of the stop pulse PB to a predetermined reference voltage may be adopted as an index indicating the received light intensity.
[0092]
In the above embodiment, the polygon mirror 73 having a different tilt angle is used to perform the two-dimensional scanning of the laser light. However, for example, a galvanometer mirror that can scan in the vehicle width direction is used, and the tilt angle of the mirror surface can be changed. The same can be realized by using a simple mechanism. However, in the case of the polygon mirror 73, there is an advantage that a two-dimensional scan can be realized only by rotational driving.
[0093]
In the above embodiment, the distance and the corresponding scan angles θx and θy are converted from the polar coordinate system to the XYZ orthogonal coordinate system inside the laser radar sensor 5, but the processing may be performed in the object recognition block 43.
[0094]
In the above embodiment, the laser radar sensor 5 using a laser beam is employed, but a radio wave such as a millimeter wave, an ultrasonic wave, or the like may be used. Further, it is not necessary to stick to the scanning method, and any method may be used as long as it can measure the azimuth other than the distance. For example, when an FMCW radar or a Doppler radar is used for millimeter waves, the distance information from the reflected wave (received wave) to the preceding vehicle and the relative speed information of the preceding vehicle can be obtained at one time. The process of calculating the relative speed based on the distance information as in the case where there is no need to do so is required.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of an inter-vehicle control device to which the present invention is applied.
2A is a configuration diagram showing a configuration of a laser radar sensor, FIG. 2B is an explanatory diagram for explaining a distance detection method in the laser radar sensor, and FIG. 2C is an index showing received light intensity; FIG. 6 is an explanatory diagram for explaining a pulse width of a stop pulse as a pulse width.
FIG. 3 is a perspective view showing an irradiation area of the laser radar sensor.
FIG. 4A is a flowchart illustrating a process relating to object recognition, and FIG. 4B is a flowchart illustrating a target conversion process executed in the flowchart of FIG.
FIG. 5 is an explanatory diagram showing a non-vehicle determination map according to the related art.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Vehicle control apparatus, 3 ... Recognition and headway control ECU, 5 ... Laser radar sensor, 7 ... Vehicle speed sensor, 9 ... Brake switch, 11 ... Throttle opening degree sensor, 13 ... Alarm sound generator, 15 ... Distance display, 17: Sensor abnormality indicator, 19: Brake driver, 21: Throttle driver, 23: Automatic transmission controller, 24: Alarm volume setting device, 25: Alarm sensitivity setting device, 26: Cruise control switch, 27: Steering Sensor, 28: Yaw rate sensor, 29: Power switch, 30: Wiper switch, 43: Object recognition block, 44: Sensor abnormality detection block, 47: Vehicle speed calculation block, 49: Steering angle calculation block, 51: Yaw rate calculation block, 53 ····································································································································································. Reference numeral 70: laser radar CPU, 71: light emitting lens, 72: scanner, 73: mirror, 74: motor drive circuit, 75: semiconductor laser diode, 76: laser diode drive circuit, 77: glass plate, 81: light receiving lens, 83 ... Light receiving element, 85 ... Amplifier, 87 ... Comparator, 89 ... Time measuring circuit

Claims (11)

In each of the vehicle width direction and the height direction, a plurality of transmission waves are irradiated over a predetermined angle range, and a distance to a reflection object based on the reflected waves, the two in the vehicle width direction and the height direction. Radar means for detecting the angle of the direction, and the intensity of the reflected wave,
When the plurality of reflectors satisfy a predetermined integration condition, a determination unit that determines the plurality of reflectors as an integrated reflector,
Selection means for selecting the maximum intensity among the intensities of the reflected waves corresponding to the respective reflection objects constituting the reflection object integratedly determined by the determination means,
The reflection object is recognized based on the distance and the angle in the two directions which are the detection results of the radar means, and when the maximum intensity selected by the selection means is smaller than a predetermined reference intensity, the reflection object is detected. And a recognizing means for increasing a probability of recognizing the object as a non-vehicle. 2. The vehicle object recognition device according to claim 1, wherein the predetermined reference intensity is set to be smaller when the distance to the reflecting object is long than when the distance is short. A shape calculating unit configured to calculate a shape of the reflective object based on the distance and the angle in two directions detected by the radar unit;
The recognition means increases the probability that the reflection object is recognized as a non-vehicle when the maximum intensity is smaller than a predetermined reference intensity and the shape of the reflection object is different from the vehicle shape. The vehicle object recognition device according to claim 1 or 2. The vehicle according to claim 3, wherein the recognition unit determines that the shape of the reflection object is different from the vehicle shape when the width of the shape of the reflection object is shorter than the width of the vehicle shape. Object recognition device. The recognition unit performs a process of increasing the probability of determining the reflection object as a non-vehicle based on the maximum intensity of the reflected wave when the distance to the reflection object is within a predetermined short distance. The vehicle object recognition device according to any one of claims 1 to 4. In each of the vehicle width direction and the height direction, a plurality of transmission waves are irradiated over a predetermined angle range, and a distance to a reflection object based on the reflected waves, the two in the vehicle width direction and the height direction. Radar means for detecting the angle of the direction, and the intensity of the reflected wave,
When the plurality of reflectors satisfy a predetermined integration condition, a determination unit that determines the plurality of reflectors as an integrated reflector,
Among the intensities of the reflected waves corresponding to the respective reflecting objects constituting the reflecting object, selecting means for selecting the maximum intensity,
Based on at least the shape of the reflective object, recognition means for recognizing that the reflective object is a preceding vehicle,
Based on a change in the distance to the preceding vehicle, a relative speed with respect to the preceding vehicle is calculated in a time series, and an average relative speed obtained by averaging a plurality of relative speeds calculated in the time series is calculated. Means,
An inter-vehicle control unit that performs inter-vehicle control based on the distance to the preceding vehicle and the average relative speed;
Stability determining means for determining the recognition stability of the preceding vehicle based on whether or not the maximum intensity of the reflected wave selected by the selecting means with respect to the preceding vehicle is larger than a predetermined reference intensity,
When the stability determining means determines that the recognition stability of the preceding vehicle is high, the calculating means increases the influence of the latest relative speed when calculating the average relative speed. . 7. The method according to claim 6, wherein the calculating unit increases the influence of the latest relative speed on the average relative speed by reducing the number of relative speeds used in calculating the average relative speed. Inter-vehicle control device. 7. The method according to claim 6, wherein, when calculating the average relative speed, the influence of the latest relative speed on the relative speed is increased by increasing a weight coefficient of the latest relative speed. An inter-vehicle control device as described in the above. The stability determination unit may further determine the recognition stability of the preceding vehicle based on whether a temporal change in the shape of the reflecting object corresponding to the preceding vehicle is smaller than a predetermined reference value. The inter-vehicle control device according to claim 6, wherein: The stability determining means further determines the recognition stability of the preceding vehicle based on whether or not the position of the preceding vehicle is within a predetermined distance laterally from an extension of the traveling direction of the own vehicle. The inter-vehicle control device according to claim 6 or 9, wherein: The said stability determination means determines the recognition stability of the said preceding vehicle further based on the continuation time which recognizes the said preceding vehicle, The said Claim 9 or Claim 10 characterized by the above-mentioned. The inter-vehicle control device according to any one of the above.

Images