JP6593682B2 - Collision prediction system - Google Patents

Description

  The present invention relates to a collision prediction system that predicts whether a vehicle will collide with a protective equipment.

  Conventionally, it is predicted whether a vehicle traveling in a lane will collide with a protection facility (for example, a protection wall, a protection fence, a guard rail, etc. provided in a roadside zone or a median separation zone) provided on the side of the lane along the lane. A collision prediction system is known. For example, in the collision prediction system described in Patent Document 1, the distance between the vehicle and the protective equipment is detected based on an image obtained by photographing the front in the traveling direction with a camera. Then, based on the detected distance between the vehicle and the protective equipment and the state quantity (vehicle speed and yaw angle) of the vehicle, it is predicted whether the vehicle will collide with the protective equipment.

JP 2013-242670 A

  However, in the collision prediction system described in Patent Document 1, since the position of the protective equipment is detected based on the image captured by the camera, when the vehicle travels at night, the vehicle travels through the tunnel. If the vehicle speed is relatively high, the position of the protective equipment may fail to be detected. For this reason, there is a possibility that a collision with the protective equipment of the vehicle cannot be predicted well, and there is room for improvement in reliability.

  Then, an object of this invention is to provide the collision prediction system which can improve the reliability in collision prediction.

  The collision prediction system of the present invention is a collision prediction system that predicts whether a vehicle traveling in a lane will collide with a protective equipment provided on the side of the lane along the lane, and the protective equipment on the side of the vehicle. Based on the position of the protective equipment stored in the storage, the radar that detects the position of the vehicle, the storage unit that stores the position of the protective equipment detected by the radar, the vehicle state quantity detection unit that detects the state quantity of the vehicle Estimating the position of the protective equipment in front of the traveling direction, estimating the future traveling position of the vehicle based on the vehicle state quantity detected by the vehicle state quantity detection unit, And a determination unit that determines whether the vehicle collides with the protective equipment based on the estimated future travel position of the vehicle.

  According to this collision prediction system, since the position of the protective equipment is detected by the radar, even when the vehicle travels at night, when the vehicle travels through a tunnel, and when the vehicle speed is relatively high, The position of the protective equipment can be detected well. However, since the radar detects the position of the detection target by receiving the reflected wave from the detection target, it is difficult to detect the position of the protective equipment in front of the traveling direction. In this respect, in this collision prediction system, the position of the protective equipment in the traveling direction is estimated based on the position of the protective equipment on the side of the vehicle detected in the past, and the vehicle is protected using the estimated position of the protective equipment. Predict whether the equipment will collide. Thereby, prediction of the collision with respect to the protection equipment of a vehicle is realizable, using a radar. Therefore, according to this collision prediction system, it is possible to improve the reliability in collision prediction.

  In the collision prediction system of the present invention, the determination unit has a distance between the position of the protective equipment in front of the traveling direction and the future traveling position of the vehicle equal to or less than the first threshold, and the current vehicle and the protective equipment. If the distance to the position is equal to or less than the second threshold, it may be determined that the vehicle collides with the protective equipment. According to this collision prediction system, it is possible to predict a collision with respect to the protective equipment of the vehicle satisfactorily, and it is possible to improve the reliability in the collision prediction.

  The collision prediction system of the present invention further includes a lane departure detection unit that detects a departure from the lane of the vehicle, and the determination unit detects the departure from the lane of the vehicle by the lane departure detection unit, and the traveling direction The distance between the position of the protective equipment on the side where the vehicle deviates from the lane ahead and the future travel position of the vehicle is equal to or less than the first threshold, and the vehicle and the side where the vehicle deviates from the lane at the present time If the distance from the position of the protective equipment is equal to or smaller than the second threshold value, it may be determined that the vehicle collides with the protective equipment. Even in a situation where it can be predicted that the vehicle will collide with the protective equipment from the position of the protective equipment in front of the traveling direction and the future traveling position of the vehicle, there are cases where normal operation is performed. In this respect, according to this collision prediction system, since the vehicle deviates from the lane is used as a condition for determining that the vehicle collides with the protective equipment, the reliability in the collision prediction can be further improved. it can. Moreover, since the collision of the vehicle against the protective equipment is predicted using the position of the protective equipment on the side where the vehicle deviates from the lane, the collision prediction is simplified and compared with the case where the positions of the protective equipment on both the left and right sides are used. It can be done reliably.

  In the collision prediction system of the present invention, the radar may be a laser radar. According to this collision prediction system, the position of the protective equipment can be detected well even when the vehicle speed is relatively high, and the reliability in collision prediction can be further improved.

  Further, in the collision prediction system of the present invention, when the position of the protective equipment detected by the radar when the vehicle travels in the travel section from the predetermined point in the rearward direction to the current location is set as the rear protective equipment position, the determination unit Fitting a multi-order curve to the rear protection equipment position stored in the storage unit, and when the standard deviation between the obtained multi-order curve and the rear protection equipment position is less than or equal to the third threshold, the vehicle travels from the multi-order curve. The position of the protective equipment in the front direction may be estimated. According to this collision prediction system, the position of the protective equipment in the traveling direction forward can be suitably estimated based on the position of the protective equipment detected in the past, and the reliability in the collision prediction can be further improved. Become.

  ADVANTAGE OF THE INVENTION According to this invention, the collision prediction system which can improve the reliability in collision prediction can be provided.

1 is a schematic configuration diagram of a collision prediction system according to an embodiment of the present invention. It is explanatory drawing explaining the attachment position and detection range of the radar of FIG. (A) And (b) is explanatory drawing explaining the estimation method of the position of the protection equipment ahead of the running direction by the collision prediction system of FIG. It is explanatory drawing explaining an example of the condition judged that the vehicle collides with a protective equipment in the collision prediction system of FIG. It is a flowchart which shows the process sequence of the collision prediction method by the collision prediction system of FIG.

  Hereinafter, embodiments according to the present invention will be described in detail with reference to the drawings. In the following description, the same reference numerals are used for the same or corresponding elements, and duplicate descriptions are omitted.

  A collision prediction system 1 shown in FIG. 1 is mounted on a vehicle 2. The applied vehicle is a commercial vehicle such as a truck or a bus in this example. The collision prediction system 1 is a system for predicting whether or not the vehicle 2 traveling in the lane 4 collides with the protective equipment 8 provided on the side of the lane 4 along the lane 4 (FIGS. 2 to 4). reference). Examples of the protective equipment 8 include a protective wall, a protective fence, or a guard rail provided in a roadside band or a central separation band. The lane 4 is divided by a lane line 6.

  As shown in FIG. 1, the collision prediction system 1 includes a radar 10, a storage unit 12, a vehicle state quantity detection unit 14, a lane departure detection unit 16, and a determination unit 18. The vehicle state quantity detection unit 14 includes, for example, a vehicle speed sensor 22, a yaw rate sensor 24, and a steering angle sensor 26.

  The radar 10 detects the position of the protective equipment 8 (obstacle) on the side of the vehicle 2. As shown in FIG. 2, the radar 10 is attached to, for example, a front outer surface of the vehicle 2 (for example, a position slightly behind the cab in the truck frame). The radar 10 is provided on each of the left side surface and the right side surface of the vehicle 2. The radar 10 emits measurement waves to the side of the vehicle 2 and receives reflected waves from the protective equipment 8 to detect the positions of the protective equipment 8 on both the left and right sides of the vehicle 2. In this example, the radar 10 is a laser radar that emits a laser beam having a frequency of 79 GHz as a measurement wave.

  The storage unit 12 is a storage medium (memory) that stores the position of the protective equipment 8 detected by the radar 10. The storage unit 12 stores, for example, the first rear protection equipment position, which is the position of the protection equipment 8 detected by the radar 10 when the vehicle 2 travels in the first travel section from the first point behind the travel direction to the current location. I remember it. In the present embodiment, as an example, the first point is set as a point 100 m behind the current location, and the latest traveling section of the past 100 m is set as the first traveling section. The storage unit 12 may be a semiconductor memory, a magnetic storage device, or the like, or an external storage device (for example, a hard disk).

  The vehicle state quantity detection unit 14 includes various sensors that detect the state quantity of the vehicle 2. The vehicle speed sensor 22 is a sensor that detects the vehicle speed of the vehicle 2. The yaw rate sensor 24 is a sensor that detects the yaw rate of the vehicle 2. The steering angle sensor 26 is a sensor that detects the steering angle of the vehicle 2 (the turning angle of the tire 2A). That is, in the present embodiment, the vehicle state quantity detection unit 14 detects the vehicle speed, the yaw rate, and the steering angle as the state quantities of the vehicle 2.

  The lane departure detection unit 16 is a device that detects the departure of the vehicle 2 from the lane 4, and includes, for example, a lane departure warning device (LDWS: Lane Departure Warning System) using an in-vehicle camera. When the vehicle 2 deviates from the lane 4, the lane departure detection unit 16 outputs a signal indicating that the vehicle 2 deviates from the lane 4 and the direction (left or right) from which the vehicle 2 deviates to the determination unit 18. For example, as shown in FIG. 4 to be described later, the lane departure detection unit 16 detects the vehicle 2 from the lane 4 when the tire 2A crosses the lane marking 6 on one side (left side in the example of FIG. 4). It is determined that it has deviated to the side.

  The determination unit 18 is an electronic control unit (ECU) configured by a computer including, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The determination unit 18 is electrically connected to the radar 10, the storage unit 12, the vehicle state quantity detection unit 14, and the lane departure detection unit 16.

  The determination unit 18 estimates the position of the protective equipment 8 in the traveling direction forward based on the position of the protective equipment 8 stored in the storage unit 12 (first rear protective equipment position). Further, the future travel position of the vehicle 2 is estimated based on the state quantity of the vehicle 2 detected by the vehicle state quantity detection unit 14. Then, based on the estimated position of the protective equipment 8 in front of the traveling direction and the estimated future traveling position of the vehicle 2, it is determined whether the vehicle 2 collides with the protective equipment 8.

  A method for estimating the position of the protective equipment 8 ahead in the traveling direction will be described with reference to FIG. In the collision prediction system 1, as shown in FIG. 3A, as described above, it is the position of the protective equipment 8 detected by the radar 10 when the vehicle 2 travels in the first travel section (past 100 m). The first rear protection equipment position 32 is sequentially stored in the storage unit 12. The first rear protective equipment position 32 stored in the storage unit 12 is updated every time the vehicle 2 travels and the radar 10 newly detects the position of the protective equipment 8, and is always the latest data.

ｘｉ：検出された防護設備８の位置（第１後方防護設備位置３２）
ｙｉ：二次曲線３４で表される防護設備８の位置 In the method for estimating the position of the protective equipment 8 in the front in the traveling direction, first, a quadratic curve is fitted to the first rear protective equipment position 32. Specifically, as shown in FIG. 3B, when it is assumed that n detection points are stored in the storage unit 12 as data representing the first back protection equipment position 32, the n detections are performed. A quadratic curve is fitted to the points using, for example, the least square method. And when the standard deviation (sigma) of the obtained secondary curve 34 and the 1st back protection equipment position 32 is smaller than threshold value S1 (3rd threshold value), the position of the protection equipment 8 in the running direction ahead from the said secondary curve 34 Is estimated. For example, assuming that the protective equipment 8 is also positioned in front of the traveling direction on the obtained quadratic curve 34, the position of the protective equipment 8 in front of the traveling direction is estimated. Here, the standard deviation σ is calculated by the following formula 1.

xi: the position of the detected protective equipment 8 (first rear protective equipment position 32)
yi: position of the protective equipment 8 represented by the quadratic curve 34

  On the other hand, if the standard deviation σ is equal to or greater than the threshold value S1 as a result of the fitting, the fitting is performed while shortening the traveling section to be fitted by a predetermined value (for example, 2 m) until the standard deviation σ becomes smaller than the threshold value S1. Do it recursively. That is, as a result of fitting a quadratic curve to the first rearward protection equipment position 32, when the standard deviation σ is equal to or greater than the threshold value S1, the second traveling section from the second point closer to the current location to the current location than the first location Fit a quadratic curve to the second back protection facility position. The second rear protection equipment position is a lane line position detected by the radar 10 when the vehicle 2 travels in the second travel section.

  For example, if the standard deviation σ is equal to or greater than the threshold value S1 as a result of fitting a quadratic curve to n detection points (first rear protection equipment position 32) in the first traveling section of 100 m in the past, A quadratic curve is fitted to n-1 detection points (second rear protection equipment positions) in the travel section (for example, when the detection interval of the radar 10 is 2 m). And when standard deviation (sigma) is smaller than threshold value S1, the position of the protection equipment 8 in the running direction front is estimated from the obtained quadratic curve. That is, in this example, the second point is a point 98 m behind the current location, and the latest traveling section of the past 98 m is the second traveling section.

  The second rear protection equipment position can be obtained from the first rear protection equipment position 32 stored in the storage unit 12. Further, as a result of fitting the quadratic curve to the second rear protection equipment position, if the standard deviation σ is equal to or greater than the threshold value S1, the traveling section is further shortened and fitting is performed again. For example, a quadratic curve is fitted to n-2 detection points in the third traveling section of the past 96 m.

  In this way, in the collision prediction system 1, the position of the protective equipment 8 ahead (the future) in the traveling direction is obtained by fitting a quadratic curve to the position of the protective equipment 8 on the side of the vehicle detected in the past. Is estimated. Further, the length of the travel section to be referred to at the time of fitting is determined according to the standard deviation σ. In a portion where the curvature of the road is constant, such as in the middle of a straight line or curve, the standard deviation σ does not increase even if fitting is performed for a long traveling section. However, in a portion where the curvature is changing, such as at the beginning of the curve or at the end of the curve, the standard deviation σ increases when fitting to a long traveling section. The large standard deviation σ means that the fitting shift is large, and in this case, there is a possibility that the position of the protective equipment 8 in front of the traveling direction cannot be estimated correctly. Therefore, the fitting of the quadratic curve is recursively performed while shortening the travel section referred to at the time of fitting until the standard deviation σ becomes smaller than the threshold value S1.

  In the collision prediction, it is preferable to estimate the position of the protective equipment 8 to the point where the vehicle 2 travels after 2 to 3 seconds. For example, when it is assumed that the vehicle 2 is traveling at 100 km / h, It is preferable to estimate the position of the protective equipment 8 up to a point about 85 m away.

  Next, the operation of the collision prediction system 1 will be described with reference to FIGS. 4 and 5. FIG. 4 is an explanatory diagram for explaining an example of a situation in which it is determined that the vehicle 2 collides with the protective equipment 8 in the collision prediction system 1. FIG. 5 is a flowchart showing the processing procedure of the collision prediction method by the collision prediction system 1. It is. Each process of FIG. 5 is executed by the determination unit 18.

  First, it is determined whether or not a departure from the lane 4 of the vehicle 2 is detected by the lane departure detection unit 16 (S11). If a departure from the lane 4 of the vehicle 2 is detected (YES in S11), the process proceeds to step S12. If a departure from the lane 4 of the vehicle 2 is not detected (NO in S11), the process returns to step S11. Execute the process.

  In step S12, the position of the protective equipment 8 ahead of the traveling direction is estimated based on the position of the protective equipment 8 stored in the storage unit 12 by the estimation method described above. In the present embodiment, the position of the protective equipment 8 in front of the traveling direction is estimated on the side where the vehicle 2 departs from the lane 4 (left side in the example of FIG. 4) in step S11. This is because it is considered that there is a high probability that the vehicle 2 will collide with the protective equipment 8 on the side where the vehicle 2 deviates from the lane 4. In FIG. 4, an example of the position (trajectory) of the protective equipment 8 in front of the estimated traveling direction is indicated by a symbol A.

  Next, the future traveling position of the vehicle 2 is estimated based on the vehicle state quantity detected by the vehicle state quantity detection unit 14 (S13). For example, assuming that the current state quantity (vehicle speed, yaw rate, steering angle) does not change, the arrival position after a certain time (for example, after 2 seconds) is estimated. At this time, the future traveling position of the vehicle 2 may be estimated as a relative position with respect to the protective equipment 8, for example. Moreover, you may estimate the future driving | running | working position of the vehicle 2 by the method similar to the steering control for automatic driving | running | working, for example. In FIG. 4, an example of the estimated future travel position (arrival position) of the vehicle 2 is indicated by a symbol B.

  Next, it is determined whether or not the distance (gap) between the position A of the protective equipment 8 in front of the traveling direction and the future traveling position B of the vehicle 2 is equal to or less than a threshold value S2 (first threshold value, for example, 2 m). (S14). If the distance is less than or equal to the threshold S2 (YES in S14), the process proceeds to step S15. If the distance is greater than the threshold S2 (NO in S14), the process returns to step S11.

  In step S15, the current distance L between the vehicle 2 and the position of the protective equipment 8 on the side where the vehicle 2 has deviated from the lane 4 (see FIG. 4) is equal to or less than the threshold value S3 (second threshold value, for example, 3 m). It is determined whether or not there is. If the distance L is less than or equal to the threshold S3 (YES in S15), the process proceeds to step S16. If the distance L is greater than the threshold S3 (NO in S15), the process returns to step S11.

  In step S16, it is determined that the vehicle 2 collides with the protective equipment 8. When it is determined that the vehicle 2 collides with the protective equipment 8, for example, a brake actuator (not shown) is operated so that the speed of the vehicle 2 decreases. Further, instead of or in addition to this, a warning means may be notified to the driver by operating a notification means by voice or the like. Thereby, it becomes possible to avoid the collision of the vehicle 2 with the protective equipment 8. Or it becomes possible to reduce the damage when the vehicle 2 collides with the protective equipment 8. Thereafter, the process ends.

  According to the collision prediction system 1 described above, since the position of the protective equipment 8 is detected by the radar 10, the vehicle 2 travels at night, the vehicle 2 travels through a tunnel, and the vehicle speed is relatively high. Even if it is large, the position of the protective equipment 8 can be detected well. However, since the radar 10 detects the position of the detection target by receiving the reflected wave from the detection target, it is difficult to detect the position of the protective equipment 8 in front of the traveling direction. In this respect, the collision prediction system 1 estimates the position of the protective equipment 8 in the traveling direction forward based on the position of the protective equipment 8 on the side of the vehicle detected in the past, and uses the estimated position of the protective equipment 8. Whether the vehicle 2 collides with the protective equipment 8 is predicted. Thereby, it is possible to realize the prediction of the collision of the vehicle 2 with respect to the protective equipment 8 while using the radar 10, and it is possible to improve the reliability in the collision prediction.

  In the collision prediction system 1, the determination unit 18 determines that the distance between the position of the protective equipment 8 ahead of the traveling direction and the future traveling position of the vehicle 2 is equal to or less than the threshold value S2 (first threshold value), and It is determined that the vehicle 2 collides with the protective equipment 8 when the distance between the vehicle 2 and the position of the protective equipment 8 is equal to or less than the threshold value S3 (second threshold value). For this reason, according to the collision prediction system 1, the collision with respect to the protective equipment 8 of the vehicle 2 can be estimated favorably, and the reliability in the collision prediction can be improved.

  In the collision prediction system 1, the determination unit 18 detects the departure of the vehicle 2 from the lane 4 by the lane departure detection unit 16, and the protective equipment 8 on the side where the vehicle 2 departs from the lane 4 in the front in the traveling direction. Between the current position of the vehicle 2 and the future travel position of the vehicle 2 is equal to or less than the threshold value S2, and the current position between the vehicle 2 and the position of the protective equipment 8 on the side where the vehicle 2 has deviated from the lane 4 Is less than the threshold value S3, it is determined that the vehicle 2 collides with the protective equipment 8. Even in a situation where it can be predicted that the vehicle 2 will collide with the protective equipment 8 from the position of the protective equipment 8 in front of the traveling direction and the traveling position of the vehicle 2, there is a case where normal operation is performed. In this respect, according to the collision prediction system 1, since the vehicle 2 deviates from the lane 4 is a condition for determining that the vehicle 2 collides with the protective equipment 8, the reliability in the collision prediction is further increased. Can be improved. Further, since the collision of the vehicle 2 with respect to the protective equipment 8 is predicted using the position of the protective equipment 8 on the side where the vehicle 2 has deviated from the lane 4, compared to the case where the positions of the protective equipment 8 on both the left and right sides are used, Collision prediction can be performed easily and reliably.

  Further, according to the collision prediction system 1, the radar 10 is a laser radar and reacts even if the vehicle speed of the vehicle 2 is relatively high. Therefore, the position of the protective equipment 8 is good even when the vehicle speed is relatively high. Therefore, the reliability in collision prediction can be further improved.

  In the collision prediction system 1, the determination unit 18 fits a quadratic curve to the first rear protection equipment position 32 stored in the storage unit 12, and the obtained secondary curve 34 and the first rear protection equipment position 32. When the standard deviation σ is equal to or less than the threshold value S1, the position of the protective equipment 8 ahead of the traveling direction is estimated from the quadratic curve. For this reason, according to the collision prediction system 1, the position of the protective equipment 8 ahead in the traveling direction can be suitably estimated based on the position of the protective equipment 8 detected in the past, and the reliability in the collision prediction is further improved. It is possible to do.

  The preferred embodiments of the present invention have been described above. However, the present invention is not limited to the above-described embodiments. The present invention can be modified without departing from the scope described in the claims or applied to other embodiments. May be.

  For example, the applied vehicle 2 may be a large vehicle, a medium vehicle, a normal passenger vehicle, a small vehicle, a light vehicle, or the like. As the radar 10, a millimeter wave radar or the like may be applied, or a radar apparatus that uses radio waves, light, ultrasonic waves, or the like as measurement waves may be applied. Further, the frequency of the measurement wave emitted from the radar 10 is preferably equal to or higher than a predetermined frequency at which the position of the protective equipment 8 can be satisfactorily detected even when the vehicle speed is relatively high, and may be, for example, 24 GHz. . The vehicle state quantity detection unit 14 may detect a state quantity other than, for example, the vehicle speed, the yaw rate, and the steering angle, or detects the steering angle if the future traveling position of the vehicle 2 can be estimated from the vehicle speed and the yaw rate. You don't have to. The lane departure detection unit 16 need only be able to detect the departure of the vehicle 2 from the lane 4 and may not be a lane departure warning device (LDWS). Further, when the process of step S11 is omitted as described below, the lane departure detection unit 16 may be omitted.

  In the above embodiment, the lane departure detection unit 16 determines whether or not the departure of the vehicle 2 from the lane 4 is detected (S11). However, this process is omitted, and whether or not the vehicle 2 departs from the lane 4. Regardless of this, the processing of steps S12 to S16 may be executed. In this case, in steps S12 to S16, whether or not the vehicle 2 collides with the protective equipment 8 using not only the position of the protective equipment 8 on the side where the vehicle 2 has deviated from the lane 4 but also the positions of the protective equipment 8 on the left and right sides. Can be judged. That is, in the above embodiment, the position of the protective equipment 8 on the side where the vehicle 2 deviates from the lane 4 in the traveling direction is estimated (S12), and the distance between the position and the future traveling position of the vehicle 2 is a threshold value. It is determined whether or not it is equal to or less than S2 (S14). In step S12, the positions of the protective equipment 8 on both the left and right sides in front of the traveling direction are estimated. In step S14, each of the positions and the future of the vehicle 2 are estimated. What is necessary is just to determine whether the distance between driving | running | working positions is below threshold value S2. Further, in this case, in step S15, it is determined whether or not the current distance L between the vehicle 2 and the respective positions of the left and right protective equipment 8 is equal to or less than the threshold value S3. In step S16, the distance L What is necessary is just to judge that the vehicle 2 collides with the protective equipment 8 in the side by which became below threshold value S3.

  Moreover, in the said embodiment, although the process of step S12-S16 was performed on condition that the departure from the lane 4 of the vehicle 2 was detected by the lane departure detection part 16 (it is YES at S11), the process of step S11 and When the processes of steps S12 to S16 are performed independently, the deviation of the vehicle 2 from the lane 4 is detected in step S11, and the vehicle 2 is determined to collide with the protective equipment 8 in step S16. May collide with the protective equipment 8. In this case, in steps S12 to S16, it is only necessary to determine whether or not the vehicle 2 collides with the protective equipment 8 using the positions of the protective equipment 8 on both the left and right sides as in the above case.

  Moreover, in the said embodiment, the arrival position after fixed time is estimated as a future driving | running | working position of the vehicle 2 (S13), and the distance between the said arriving position and the position of the protective equipment 8 ahead of a driving | running | working direction is below threshold value S2. (S14), in step S13, the travel trajectory (traveling direction) up to a certain time later is estimated. In step S14, the travel trajectory and the position of the protective equipment 8 in front of the travel direction are determined. It may be determined whether or not the distance between is less than or equal to the threshold value S2. More specifically, when the position of the protective equipment 8 in the traveling direction front is estimated as a trajectory as in the above embodiment, it is determined whether or not these trajectories intersect (collision). Good.

  Further, in the method of estimating the position of the protective equipment 8 in front of the traveling direction, the fitting is performed using the quadratic curve in the above embodiment, but a cubic or higher-order curve may be used. Further, as described above, when the standard curve σ is equal to or greater than the threshold S1 as a result of fitting the quadratic curve to the first rear protection equipment position 32, the second rear protection equipment position stored in the storage unit 12 is second. When the standard curve σ between the obtained quadratic curve and the second rear protective equipment position is smaller than the threshold value S1, the position of the protective equipment 8 ahead in the traveling direction is estimated from the secondary curve. Also good.

DESCRIPTION OF SYMBOLS 1 ... Collision prediction system, 2 ... Vehicle, 4 ... Lane, 8 ... Protection equipment, 10 ... Radar, 12 ... Memory | storage part, 14 ... Vehicle state quantity detection part, 16 ... Lane departure detection part, 18 ... Judgment part, 32 ... 1st rear protection equipment position, 34 ... quadratic curve.

Claims (4)

A collision prediction system that predicts whether a vehicle traveling in a lane collides with a protective equipment provided on a side of the lane along the lane,
A radar for detecting the position of the protective equipment on the side of the vehicle;
A storage unit for storing the position of the protective equipment detected by the radar;
A vehicle state quantity detection unit for detecting a state quantity of the vehicle;
The position of the protective equipment in front of the traveling direction is estimated based on the position of the protective equipment stored in the storage unit, and the future of the vehicle based on the vehicle state quantity detected by the vehicle state quantity detection unit. And a determination unit that determines whether the vehicle collides with the protective equipment based on the estimated position of the protective equipment in front of the traveling direction and the estimated future driving position of the vehicle. , equipped with a,
The determination unit
A distance between the position of the protective equipment in front of the traveling direction and the future traveling position of the vehicle is equal to or less than a first threshold; and
If the distance between the position of the protective equipment and the vehicle at the current is not higher than the second threshold, it determined that the vehicle will collide with the protective equipment, the collision prediction system. A collision prediction system that predicts whether a vehicle traveling in a lane collides with a protective equipment provided on a side of the lane along the lane,
A radar for detecting the position of the protective equipment on the side of the vehicle;
A storage unit for storing the position of the protective equipment detected by the radar;
A vehicle state quantity detection unit for detecting a state quantity of the vehicle;
The position of the protective equipment in front of the traveling direction is estimated based on the position of the protective equipment stored in the storage unit, and the future of the vehicle based on the vehicle state quantity detected by the vehicle state quantity detection unit. And a determination unit that determines whether the vehicle collides with the protective equipment based on the estimated position of the protective equipment in front of the traveling direction and the estimated future driving position of the vehicle. ,
And a lane deviation detector for detecting a deviation from the lane of the vehicle,
The determination unit
A deviation from the lane of the vehicle is detected by the lane departure detection unit; and
A distance between the position of the protective equipment on the side where the vehicle deviates from the lane in the traveling direction and the future traveling position of the vehicle is equal to or less than a first threshold; and
The current, and said vehicle, when the distance between the protective equipment position on the side where the vehicle deviates the lane is equal to or less than the second threshold value, determines that the vehicle collides with the protective equipment, the collision prediction system. A collision prediction system that predicts whether a vehicle traveling in a lane collides with a protective equipment provided on a side of the lane along the lane,
A radar for detecting the position of the protective equipment on the side of the vehicle;
A storage unit for storing the position of the protective equipment detected by the radar;
A vehicle state quantity detection unit for detecting a state quantity of the vehicle;
The position of the protective equipment in front of the traveling direction is estimated based on the position of the protective equipment stored in the storage unit, and the future of the vehicle based on the vehicle state quantity detected by the vehicle state quantity detection unit. And a determination unit that determines whether the vehicle collides with the protective equipment based on the estimated position of the protective equipment in front of the traveling direction and the estimated future driving position of the vehicle. With
When the position of the protective equipment detected by the radar when the vehicle travels a travel section from a predetermined point in the rearward direction of travel to the current location, as a rear protective equipment position,
The determination unit fits a multi-order curve to the rear protection equipment position stored in the storage unit, and a standard deviation between the obtained multi-order curve and the rear protection equipment position is a third threshold value or less. , estimates the position of the protection systems in the traveling direction forward from the multi-order curve, the collision prediction system. The collision prediction system according to claim 1, wherein the radar is a laser radar.

Images