Method and apparatus for vehicle collision prediction with a vehicle to be monitored

Abstract

The application discloses a kind of vehicle and the method and device of the collision prediction of vehicle to be monitored.Therein, the method comprises: obtaining the virtual safety lane width of vehicle, wherein the virtual safety lane width is the lane width of road for the safe driving of vehicle;When it is detected that vehicle travels to the intersection position between the driving path of vehicle and the driving path of vehicle to be monitored in future period, it is determined that the collision duration of collision between vehicle and vehicle to be monitored in future period, and the first duration of vehicle to be monitored entering virtual safety lane width and the second duration of vehicle to be monitored leaving virtual safety lane width are obtained;Based on collision duration, first duration and second duration, it is determined whether collision between vehicle and vehicle to be monitored in future period will occur.The application solves the technical problem of low efficiency of vehicle and crossing vehicle collision prediction.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a method and apparatus for predicting collisions between a vehicle and a vehicle to be monitored. Background Technology

[0002] Currently, the emergency braking system is mainly used to effectively identify collision risks during vehicle operation. However, when there are vehicles crossing the road while the vehicle is in motion, the emergency braking system cannot effectively identify collision risks, resulting in a technical problem of low collision prediction efficiency between the vehicle and the crossing vehicle.

[0003] There is currently no effective solution to the technical problem of low efficiency in predicting collisions between vehicles and crossing vehicles. Summary of the Invention

[0004] This invention provides a method and apparatus for predicting collisions between a vehicle and a vehicle to be monitored, thereby at least addressing the technical problem of low efficiency in predicting collisions between a vehicle and a vehicle crossing the road.

[0005] According to one aspect of the present invention, a method for predicting collisions between a vehicle and a vehicle to be monitored is provided. The method includes: acquiring a virtual safe lane width for the vehicle, wherein the virtual safe lane width is the lane width of a road used for safe driving of the vehicle, and the vehicle to be monitored is the vehicle to be monitored that is suspected of colliding with the vehicle; when the vehicle is detected to be traveling to the intersection of its travel path and the travel path of the vehicle to be monitored in a future time period, determining the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period, and acquiring a first duration for the vehicle to be monitored to enter the virtual safe lane width and a second duration for the vehicle to be monitored to leave the virtual safe lane width; and determining whether a collision will occur between the vehicle and the vehicle to be monitored in the future time period based on the collision duration, the first duration, and the second duration.

[0006] Optionally, obtaining the virtual safe lane width of the vehicle includes: when the vehicle is detected to be traveling on a straight road at the current moment, determining the virtual safe lane width based on the vehicle's size and a safe distance threshold; when the vehicle is detected to be traveling on a curved road at the current moment, determining the virtual safe lane width based on the vehicle's turning radius, the vehicle's outer sweep radius, and the vehicle's inner sweep radius.

[0007] Optionally, the collision duration of a future collision between a vehicle and a vehicle to be monitored can be determined, including: determining the collision duration based on the distance between the vehicle and the intersection point in the coordinate system and the vehicle's speed.

[0008] Optionally, obtaining the first duration of the vehicle to be monitored entering the virtual safe lane width and the second duration of the vehicle leaving the virtual safe lane width includes: when the vehicle to be monitored is detected to be traveling on a straight road in a future time period, obtaining the lateral distance, lateral speed, vehicle size and safe distance threshold of the vehicle to be monitored; and performing linear processing on the lateral distance, lateral speed, vehicle size and safe distance threshold of the vehicle to be monitored to obtain the first duration and the second duration.

[0009] Optionally, obtaining the first duration for the vehicle to enter the virtual safe lane width and the second duration for leaving the virtual safe lane width includes: when the vehicle to be monitored is detected traveling on a curved road in a future time period, determining the coordinates of a first intersection point between the vehicle and another vehicle based on the vehicle's travel path and the vehicle's driving path; determining a first distance from the vehicle to the intersection point coordinates based on the vehicle's position and the first intersection point coordinates; determining the first duration based on the first distance, the vehicle's lateral speed, and its longitudinal speed; when the vehicle to be monitored is detected traveling on a curved road in a future time period, determining the coordinates of a second intersection point between the vehicle and another vehicle based on the vehicle's travel path and the vehicle's driving path; determining the second distance from the vehicle to the intersection point coordinates based on the vehicle's position and the second intersection point coordinates; and determining the second duration based on the second distance, the vehicle's lateral speed, and its longitudinal speed.

[0010] Optionally, based on the collision duration, the first duration, and the second duration, it is determined whether the vehicle and the vehicle under monitoring will collide in the future, including: determining that the vehicle and the vehicle under monitoring collide in response to the collision duration being greater than the first duration and less than the second duration; and determining that the vehicle and the vehicle under monitoring do not collide in response to the collision duration being greater than the second duration or the collision duration being less than the first duration.

[0011] Optionally, determining that a collision has occurred between a vehicle and a vehicle under monitoring in response to a collision duration greater than a first duration and less than a second duration includes: determining that a collision has occurred between a vehicle and a vehicle under monitoring in response to a number of collision durations greater than the first duration and less than the second duration being greater than a number threshold.

[0012] According to another aspect of the present invention, an apparatus for predicting collisions between a vehicle and a vehicle to be monitored is also provided, comprising: an acquisition unit, configured to acquire a virtual safe lane width of the vehicle, wherein the virtual safe lane width is the lane width of a road used to enable the vehicle to travel safely; a processing unit, configured to, when detecting that the vehicle travels to the intersection of the vehicle's travel path and the vehicle to be monitored's travel path in a future time period, determine the collision duration in which the vehicle and the vehicle to be monitored will collide in the future time period, and acquire a first duration for the vehicle to be monitored to enter the virtual safe lane width and a second duration for the vehicle to be monitored to leave the virtual safe lane width; and a determination unit, configured to, based on the collision duration, the first duration, and the second duration, determine whether the vehicle and the vehicle to be monitored will collide in the future time period.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the vehicle-to-vehicle collision prediction method of the present invention.

[0014] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the vehicle-to-vehicle collision prediction method of the present invention during runtime.

[0015] In this embodiment of the invention, the virtual safe lane width of the vehicle is obtained, wherein the virtual safe lane width is the lane width of the road used to ensure the safe driving of the vehicle; when the vehicle is detected to reach the intersection of the vehicle's driving path and the driving path of the vehicle to be monitored in a future time period, the collision duration of the vehicle colliding with the vehicle to be monitored in the future time period is determined, and the first duration of the vehicle to be monitored entering the virtual safe lane width and the second duration of the vehicle leaving the virtual safe lane width are obtained; based on the collision duration, the first duration and the second duration, it is determined whether the vehicle and the vehicle to be monitored will collide in the future time period. That is to say, this embodiment of the invention first calculates the virtual safe lane width of the vehicle traveling on straight roads and curved roads; secondly, it calculates the time when the vehicle travels to the intersection of the vehicle's path and the path of the vehicle to be monitored, and then calculates the first duration and the second duration of other vehicles around the vehicle entering and leaving the virtual safe lane width; finally, it determines the relationship between the intersection time and the first duration and the second duration to achieve the purpose of avoiding collision risk when the vehicle crosses, thereby solving the technical problem of low collision prediction efficiency between the vehicle and the vehicle crossing, and achieving the technical effect of improving the collision prediction efficiency between the vehicle and the vehicle crossing. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a collision prediction method between a vehicle and a vehicle to be monitored according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of a system architecture for predicting collisions between a vehicle and a vehicle to be monitored, according to an embodiment of the present invention.

[0019] Figure 3 This is a schematic diagram of a vehicle traveling on a straight road according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of a vehicle traveling on a curved road according to an embodiment of the present invention;

[0021] Figure 5 This is a schematic diagram of a target vehicle crossing to the right of a vehicle at an intersection, according to an embodiment of the present invention.

[0022] Figure 6 This is a schematic diagram of a vehicle-to-vehicle collision prediction device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of the present invention, a method for predicting collisions between a vehicle and a vehicle to be monitored is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a collision prediction method between a vehicle and a vehicle to be monitored according to an embodiment of the present invention, such as... Figure 1 As shown, the method may include the following steps:

[0028] Step S101: Obtain the virtual safe lane width of the vehicle, wherein the virtual safe lane width is the lane width of the road used to enable the vehicle to drive safely.

[0029] In the technical solution provided by step S101 of the present invention, the vehicle's safe lane is estimated by the vehicle's collision prediction module to obtain the vehicle's virtual safe lane width. The vehicle's virtual safe lane width can be the straight virtual safe lane width when the vehicle is driving on a straight road, or the curved virtual safe lane width when the vehicle is driving on a curved road.

[0030] Step S102: When it is detected that the vehicle has traveled to the intersection of the vehicle's travel path and the vehicle to be monitored in the future time period, the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period is determined, and the first duration of the vehicle to be monitored entering the width of the virtual safe lane and the second duration of the vehicle to be monitored leaving the width of the virtual safe lane are obtained, wherein the vehicle to be monitored is the vehicle that will collide with the vehicle in the future time period.

[0031] In the technical solution provided by step S102 of the present invention, when the vehicle's perception sensor detects that the vehicle has traveled to the intersection of the vehicle's travel path and the travel path of the vehicle to be monitored in a future time period, the collision prediction module calculates the vehicle's travel path and the travel path of the vehicle to be monitored in the future time period to obtain the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period, wherein the collision duration is the time taken for the vehicle to travel to the intersection at a certain moment in the future time period; the vehicle's collision prediction module calculates the first time for the vehicle to be monitored to enter the virtual safety lane of the straight road and the second time for the vehicle to leave the virtual safety lane of the straight road; the vehicle collision prediction module calculates the first time for the vehicle to be monitored to enter the virtual safety lane of the curved road and the second time for the vehicle to leave the virtual safety lane of the straight road.

[0032] Step S103: Based on the collision duration, the first duration, and the second duration, determine whether the vehicle and the vehicle to be monitored will collide in the future.

[0033] In the technical solution provided by step S103 of the present invention, when the vehicle and the vehicle to be monitored are traveling on a straight road in the future, the collision duration, the first duration, and the second duration are judged to determine whether the vehicle and the vehicle to be monitored will collide in the future; when the vehicle and the vehicle to be monitored are traveling on a curved road in the future, the collision duration, the first duration, and the second duration are judged to determine whether the vehicle and the vehicle to be monitored will collide in the future.

[0034] In the embodiments of this invention, steps S101 to S103 described above involve obtaining the virtual safe lane width of a vehicle, where the virtual safe lane width is the lane width of the road used to ensure safe vehicle travel. When a vehicle is detected to reach the intersection of its travel path and the travel path of a vehicle to be monitored in a future time period, the collision duration of the vehicle colliding with the vehicle to be monitored in the future time period is determined, and a first duration for the vehicle to be monitored to enter the virtual safe lane width and a second duration for it to leave the virtual safe lane width are obtained. Based on the collision duration, the first duration, and the second duration, it is determined whether a collision will occur between the vehicle and the vehicle to be monitored in the future time period. In other words, the embodiments of this invention first calculate the virtual safe lane width for vehicles traveling on straight and curved roads; secondly, they calculate the time it takes for the vehicle to reach the intersection of its path and the path of the vehicle to be monitored; then, they calculate the first and second durations for other vehicles around the vehicle to enter and leave the virtual safe lane width; finally, they determine the relationship between the intersection time and the first and second durations to avoid collision risks when a vehicle crosses the road, thereby solving the technical problem of low collision prediction efficiency between vehicles and crossing vehicles and achieving the technical effect of improving the collision prediction efficiency between vehicles and crossing vehicles.

[0035] The method described in this embodiment will be further described below.

[0036] As an optional embodiment, step 101, obtaining the virtual safe lane width of the vehicle, includes: when the vehicle is detected to be traveling on a straight road at the current moment, determining the virtual safe lane width based on the vehicle's size and a safe distance threshold; when the vehicle is detected to be traveling on a curved road at the current moment, determining the virtual safe lane width based on the vehicle's turning radius, the vehicle's outer sweep radius, and the vehicle's inner sweep radius.

[0037] In this embodiment, when the vehicle's sensors detect that the vehicle is traveling on a straight road at the current moment, the vehicle's collision prediction module performs linear processing on the vehicle's size and a safe distance threshold to obtain the vehicle's virtual safe lane width, wherein the safe distance threshold is an adjustable value. When the vehicle's sensors detect that the vehicle is traveling on a curved road at the current moment, a center is defined based on the vehicle's trajectory. The distance from the center of the vehicle's size to the center of the circle is the vehicle's turning radius, the distance from the outer side of the vehicle to the center of the circle is the vehicle's outer sweep radius, and the distance from the inner side of the vehicle to the center of the circle is the vehicle's inner sweep radius. The turning radius, the outer sweep radius, and the inner sweep radius of the vehicle are linearly processed to obtain the vehicle's virtual safe lane width.

[0038] For example, when a vehicle's sensors detect that it is traveling on a straight road at the current moment, the vehicle's dimensions are 1.8 meters, and the vehicle's safe distance threshold is 1.6 meters. The vehicle's collision prediction module sums the vehicle's dimensions (1.8 meters) and the safe distance threshold to obtain a virtual lane width of 3.2 meters. When a vehicle's sensors detect that it is traveling on a curved road at the current moment, a center is defined based on the vehicle's trajectory. The distance from the center of the vehicle's dimensions to the center of the circle is the vehicle's turning radius, which is the quotient of the vehicle's speed and angular velocity. The vehicle's outer sweep radius is calculated by taking the difference between the vehicle's length and the length from the rear axle to the rear of the vehicle as one leg of a right triangle, and the sum of the vehicle's turning radius and half of its dimensions as the other leg of the right triangle. The back leg theorem is then applied to the two legs of the right triangle. The vehicle's inner sweep radius is the difference between the vehicle's turning radius and half of its dimensions. In other words, the vehicle's virtual safe lane width is the difference between the outer sweep radius and the inner sweep radius.

[0039] As an optional embodiment, step 102, determining the collision duration of a future collision between the vehicle and the vehicle to be monitored, includes: determining the collision duration based on the distance between the vehicle and the intersection point in the coordinate system and the vehicle's speed.

[0040] In this embodiment, the vehicle's collision prediction module determines the collision duration by dividing the distance between the intersection point of the vehicle in the Cartesian coordinate system and the vehicle's speed.

[0041] For example, the vehicle's position in the Cartesian coordinate system is (60, 80), the intersection point's position in the Cartesian coordinate system is (60, 85), the distance between the vehicle and the intersection point in the coordinate system is 5 kilometers, the vehicle's speed is 40 kilometers per hour, and the collision duration is 7.5 minutes.

[0042] As an optional embodiment, step 102, obtaining the first duration of the vehicle to be monitored entering the virtual safe lane width and the second duration of the vehicle leaving the virtual safe lane width, includes: when the vehicle to be monitored is detected traveling on a straight road in a future time period, obtaining the lateral distance, lateral speed, vehicle size and safe distance threshold of the vehicle to be monitored; and performing linear processing on the lateral distance, lateral speed, vehicle size and safe distance threshold of the vehicle to be monitored to obtain the first duration and the second duration.

[0043] In this embodiment, when the vehicle's sensors detect that the vehicle to be monitored is traveling on a straight road at a future time, the acquired lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored are transmitted to the vehicle's collision prediction module. The vehicle's collision prediction module performs a first linear processing on the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored to obtain a first duration; the vehicle's collision prediction module performs a second linear processing on the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored to obtain a second duration.

[0044] For example, when the vehicle to be monitored is traveling on a straight road at a future time, the lateral distance of the vehicle to be monitored is 2 kilometers, the lateral speed is 5 kilometers per hour, the size of the vehicle is 1.8 meters, and the safe distance threshold is 0.2 kilometers. The sum of half the vehicle size and the safe distance threshold is the first sum, which is 200.9 meters. The difference between the lateral distance and the first sum is the first difference, which is 1.7991 kilometers. The quotient between the first difference and the lateral speed is the first duration, which is 0.89955 hours. The sum of the lateral distance and the first sum is the second sum, which is 2.2009 kilometers. The quotient between the second sum and the lateral speed is the second duration, which is 0.44018 hours.

[0045] As an optional embodiment, step 102, obtaining the first duration of the monitored vehicle entering the virtual safe lane width and the second duration of the monitored vehicle leaving the virtual safe lane width, includes: when the monitored vehicle is detected traveling on a curved road in a future time period, determining the coordinates of a first intersection point between the monitored vehicle and another vehicle based on the monitored vehicle's travel path and the vehicle's driving path; determining a first distance from the monitored vehicle to the intersection point coordinates based on the monitored vehicle's position and the first intersection point coordinates; determining a first duration based on the first distance, the monitored vehicle's lateral speed, and its longitudinal speed; when the monitored vehicle is detected traveling on a curved road in a future time period, determining the coordinates of a second intersection point between the monitored vehicle and another vehicle based on the monitored vehicle's travel path and the vehicle's driving path; determining a second distance from the monitored vehicle to the intersection point coordinates based on the monitored vehicle's position and the second intersection point coordinates; and determining a second duration based on the second distance, the monitored vehicle's lateral speed, and its longitudinal speed.

[0046] In this embodiment, the vehicle's sensors detect the intersection of the vehicle's travel path and the vehicle's inner lateral sweep radius travel path when the vehicle is traveling on a curved road in a future time period. When the vehicle reaches the intersection, the first distance between the vehicle's current position and the intersection position in the coordinate system is obtained. The square root of the sum of the squares of the vehicle's lateral velocity and longitudinal velocity is used to obtain the total velocity. The quotient between the first distance and the total velocity is the first duration, and the quotient between the second distance and the total velocity is the second duration.

[0047] As an optional embodiment, step 102, based on the collision duration, the first duration, and the second duration, determines whether the vehicle and the vehicle to be monitored will collide in the future, including: in response to the collision duration being greater than the first duration and less than the second duration, determining that the vehicle and the vehicle to be monitored have collided; in response to the collision duration being greater than the second duration or the collision duration being less than the first duration, determining that the vehicle and the vehicle to be monitored have not collided.

[0048] In this embodiment, if the vehicle's collision prediction module detects that the vehicle collision duration is greater than a first duration and less than a second duration, it determines that the vehicle has collided with the vehicle to be monitored, and the vehicle's execution module does not perform emergency braking on the vehicle; if the vehicle's collision prediction module detects that the vehicle collision duration is greater than the second duration or less than the first duration, it determines that the vehicle has not collided with the vehicle to be monitored, and the vehicle continues to travel according to its driving path.

[0049] As an optional embodiment, determining that a collision has occurred between a vehicle and a vehicle under monitoring in response to a collision duration greater than a first duration and less than a second duration includes: determining that a collision has occurred between a vehicle and a vehicle under monitoring in response to a number of collision durations greater than the first duration and less than the second duration being greater than a number threshold.

[0050] In this embodiment, the vehicle's collision prediction module detects that the number of times the collision duration is greater than the first duration and less than the second duration is greater than a number threshold, wherein the number threshold is three times. When the vehicle collides with the vehicle to be monitored, the vehicle's execution module performs emergency braking on the vehicle to avoid a collision between the vehicle and the vehicle to be monitored.

[0051] In this embodiment of the invention, the width of the virtual safe lane for vehicles traveling on straight and curved roads is first calculated; second, the time it takes for the vehicle to reach the intersection of its path and the path of the vehicle to be monitored is calculated; then, the first and second durations for other vehicles around the vehicle to enter and exit the virtual safe lane are calculated; finally, the relationship between the intersection time and the first and second durations is determined to avoid collision risks when vehicles cross the road, thereby solving the technical problem of low collision prediction efficiency between vehicles and crossing vehicles, and achieving the technical effect of improving the collision prediction efficiency between vehicles and crossing vehicles.

[0052] Example 2

[0053] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0054] In daily life, vehicles have become an essential part of people's daily travel. During driving, there are inevitably scenarios where drivers are unable to brake to vehicles that suddenly cross the road due to various reasons. A typical scenario is at an intersection. This poses a significant threat to the personal safety and property of drivers on both sides of the road. To address this scenario, this paper predicts whether a collision will occur when a vehicle crosses the road and outputs the prediction results to the control system, which will effectively prevent collisions.

[0055] With the development of intelligent driving technology in automobiles, various countries have begun to increase the installation rate of intelligent driver assistance systems by formulating regulations. Among them, the automatic emergency braking system, as a driver assistance system, can effectively identify collision risks and assess the risks that are about to occur. If there is a risk of collision, the system will brake to effectively avoid the collision. However, the proposed system does not have the ability to predict and avoid collisions in scenarios where the vehicle is crossing the road.

[0056] Therefore, this invention proposes a vehicle-to-vehicle collision prediction system. Figure 2 This is a schematic diagram of a system architecture for predicting collisions between a vehicle and a vehicle to be monitored according to an embodiment of the present invention, such as... Figure 2 As shown, the system may include:

[0057] The sensor module 201 has a camera installed at the rearview mirror position to record road traffic information ahead and surrounding environmental information, including lane line information and lane line width; a millimeter-wave radar is installed in the vehicle's air intake grille to measure the relative position of surrounding targets; and a lidar is installed on the top of the vehicle to scan the surrounding environment information 360 degrees.

[0058] The data processing module 202 processes the sensor measurement data to accurately calculate the specific motion state of the target vehicle due to errors generated by sensor perception.

[0059] The state variables of the target vehicle can be written as

[0060] S c =[V c A c ,ω c ]

[0061] |ω c |≤ω0:x=V c t+1 / 2×A c t 2

[0062]

[0063] In the above formula, Vc can be used to represent the velocity of the target vehicle, Ac can be used to represent the acceleration of the target vehicle, and ω c ω0 can be used to represent the acceleration of the target vehicle, and ω0 can be used to represent a certain angular velocity of the target vehicle, which is an empirical value.

[0064] The collision prediction module 203 first needs to estimate the potential collision area—that is, calculate the width of the virtual safe lane. Figure 3 This is a schematic diagram of a vehicle traveling on a straight road according to an embodiment of the present invention, as shown below. Figure 3 As shown.

[0065] from Figure 3 It can be seen that the width of the virtual safe lane is d.

[0066] d = w + s

[0067] Among them, the width of the vehicle is w, the length of the vehicle is L, the distance from the rear axle of the vehicle to the rear of the vehicle is m, and s is the safety distance threshold, which is an adjustable amount.

[0068] Figure 4 This is a schematic diagram of a vehicle traveling on a curved road according to an embodiment of the present invention, as shown below. Figure 4 As shown.

[0069] from Figure 4 It can be seen that R is the turning radius of the vehicle.

[0070]

[0071] In the above formula, V can be used to represent the vehicle's speed, and ω can be used to represent the vehicle's angular velocity.

[0072] R max R is the sweep radius of the outermost vehicle.min inner sweep radius

[0073]

[0074]

[0075] d = R max -R min

[0076] The safe lane width for a vehicle during a turn is:

[0077] d=(Lm) 2 +2Rw

[0078] After the collision prediction module 203 calculates the safe virtual lane width, it is necessary to calculate the collision risk of the vehicle.

[0079] First, it is necessary to calculate the time it takes for the vehicle to reach the intersection of its own path and the target vehicle's path, which is the collision time.

[0080]

[0081] In the above formula, S rel v represents the distance between the vehicle and the intersection point in a rectangular coordinate system. rel The speed of the vehicle.

[0082] Secondly, it is necessary to calculate the time T for the target vehicle to enter and leave the virtual safe lane width. apr With T dpt

[0083] For the target vehicle traveling on a straight road:

[0084]

[0085]

[0086] In the above formula, x pl v represents the lateral distance to the target vehicle. pl Let ω be the lateral velocity of the target vehicle, s be the safe distance threshold, and ω be the angular velocity of the target vehicle.

[0087] The target vehicle is traveling on a curved road. Figure 5 This is a schematic diagram illustrating a situation where, at an intersection according to an embodiment of the present invention, a target vehicle crosses to the right of a vehicle while the vehicle itself is traveling. Figure 5 As shown.

[0088] The equation of motion for a vehicle can be expressed as:

[0089]

[0090] In the above formula, x plong It can be used to represent the longitudinal distance of a vehicle, v plong It can be used to represent the longitudinal speed of a vehicle.

[0091]

[0092]

[0093] Solving the simultaneous equations yields the coordinates of the intersection point, allowing us to calculate the distances in the rectangular coordinate system between the target vehicle and the intersection point of the two circles. These distances are represented by L. min and L max express.

[0094] T apr It can be used to represent the motion equations of the target vehicle moving to the self vehicle and R. min The time at the intersection point is similarly T. dpt It can be used to represent the vehicle's position moving to its own position, and the vehicle's motion equations and R. max The time at the intersection.

[0095]

[0096]

[0097] If T apr Collision time <T dpt The risk of a collision between the target vehicle and the vehicle itself when the target vehicle crosses the virtual lane is indicated if the collision time is greater than T. dpt or collision time <T apr If the target vehicle crosses the virtual lane, there is no risk of collision with the vehicle itself. To ensure stable execution, the actuator response T... apr Collision time <T dpt If the number of count cycles exceeds 3, then a collision risk is calculated.

[0098] Execution module 204 performs emergency braking when there is a risk of collision between the self-vehicle and the target vehicle to prevent a collision between the self-vehicle and the target vehicle.

[0099] In this embodiment, the potential collision area is first estimated, and the time it takes for the vehicle to reach the intersection of its own path and the target vehicle's path (i.e., the collision time) is calculated. The time it takes for the target vehicle to enter and leave the virtual safe lane is also calculated. The relationship between the collision time and the time it takes for the target vehicle to enter and leave the virtual safe lane is determined, thus determining whether there is a risk of collision between the vehicle and the target vehicle. This solves the technical problem of low collision prediction efficiency between vehicles and crossing vehicles and achieves the technical effect of improving the collision prediction efficiency between vehicles and crossing vehicles.

[0100] Example 3

[0101] According to embodiments of the present invention, an apparatus for predicting collisions between a vehicle and a vehicle to be monitored is also provided. It should be noted that this apparatus for predicting collisions between a vehicle and a vehicle to be monitored can be used to execute the method for predicting collisions between a vehicle and a vehicle to be monitored in Embodiment 1.

[0102] Figure 6 This is a schematic diagram of a vehicle-to-vehicle collision prediction device according to an embodiment of the present invention. Figure 6 As shown, the device 600 for predicting collisions between a vehicle and a vehicle to be monitored may include: an acquisition unit 601, a processing unit 602, and a determination unit 603.

[0103] The acquisition unit 601 is used to acquire the virtual safe lane width of the vehicle, wherein the virtual safe lane width is the lane width of the road used to enable the vehicle to drive safely.

[0104] The processing unit 602 is used to determine the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period when the vehicle is detected to be traveling to the intersection of the vehicle's travel path and the vehicle to be monitored in the future time period, and to obtain the first moment when the vehicle to be monitored enters the width of the virtual safe lane and the second moment when it leaves the width of the virtual safe lane.

[0105] The determination unit 603 is used to determine whether a collision will occur between the vehicle and the vehicle to be monitored in the future time period based on the collision duration, the first moment, and the second moment.

[0106] Optionally, the acquisition unit 601 may include: a first processing module, configured to determine the width of a virtual safe lane based on the vehicle's size and a safe distance threshold when the vehicle is currently traveling on a straight road; and a second processing module, configured to determine the width of a virtual safe lane based on the vehicle's turning radius, the vehicle's outer sweep radius, and the vehicle's inner sweep radius when the vehicle is currently traveling on a curved road.

[0107] Optionally, the processing unit 602 may include a determination module for determining the collision duration based on the distance between the vehicle and the intersection point in the coordinate system and the vehicle's speed.

[0108] Optionally, the processing unit 602 may include: a first processing module, used to obtain the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle when it is detected that the vehicle to be monitored is traveling on a straight road in a future time period; and a second processing module, used to perform linear processing on the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored to obtain a first time and a second time.

[0109] Optionally, the processing unit 602 may further include: a third processing module, configured to determine the coordinates of a first intersection point between the monitored vehicle and another vehicle based on the monitored vehicle's travel path and the vehicle's travel path when the monitored vehicle is detected traveling on a curved road in a future time period; a first determining module, configured to determine a first distance from the monitored vehicle to the intersection point coordinates based on the monitored vehicle's position and the first intersection point coordinates; a second determining module, configured to determine a first moment based on the first distance, the monitored vehicle's lateral velocity, and its longitudinal velocity; a fourth processing module, configured to determine the coordinates of a second intersection point between the monitored vehicle and another vehicle based on the monitored vehicle's travel path and the vehicle's travel path when the monitored vehicle is detected traveling on a curved road in a future time period; a third determining module, configured to determine a second distance from the monitored vehicle to the intersection point coordinates based on the monitored vehicle's position and the second intersection point coordinates; and a fourth determining module, configured to determine a second moment based on the second distance, the monitored vehicle's lateral velocity, and its longitudinal velocity.

[0110] Optionally, the determining unit 603 may include: a first processing module, configured to determine that a collision has occurred between the vehicle and the vehicle to be monitored in response to a collision duration greater than a first moment and less than a second moment; and a second processing module, configured to determine that a collision has not occurred between the vehicle and the vehicle to be monitored in response to a collision duration greater than a second moment or a collision duration less than a first moment.

[0111] Optionally, the determining unit 603 may further include: a third processing module, used to determine that a collision has occurred between the vehicle and the vehicle to be monitored in response to the number of times the collision duration is greater than the first moment and less than the second moment being greater than a number threshold.

[0112] In this embodiment, the acquisition unit is used to acquire the virtual safe lane width of the vehicle, wherein the virtual safe lane width is the lane width of the road used to enable the vehicle to drive safely; the processing unit is used to determine the collision duration of the vehicle colliding with the vehicle under test in the future time period when the vehicle is detected to be traveling to the intersection of the vehicle's travel path and the travel path of the vehicle under test in the future time period, and to acquire the first moment when the vehicle under test enters the virtual safe lane width and the second moment when it leaves the virtual safe lane width, wherein the vehicle under test is the vehicle that will collide with the vehicle; the determination unit is used to determine whether the vehicle will collide with the vehicle under test in the future time period based on the collision duration, the first moment and the second moment, thereby solving the technical problem of low collision prediction efficiency between the vehicle and the vehicle crossing the road, and achieving the technical effect of improving the collision prediction efficiency between the vehicle and the vehicle crossing the road.

[0113] Example 4

[0114] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the vehicle-to-vehicle collision prediction method of Embodiment 1.

[0115] Example 5

[0116] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the vehicle-to-vehicle collision prediction method of Embodiment 1 during runtime.

[0117] Example 6

[0118] According to an embodiment of the present invention, a vehicle is also provided for performing the vehicle-to-vehicle collision prediction method in embodiment 1.

[0119] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0125] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for predicting collisions between a vehicle and a vehicle to be monitored, characterized in that, include: Obtain the virtual safe lane width of the vehicle, wherein the virtual safe lane width is the lane width of the road used to enable the vehicle to drive safely; When the vehicle is detected to be traveling to the intersection of the vehicle's travel path and the vehicle to be monitored in a future time period, the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period is determined, and the first duration of the vehicle to be monitored entering the width of the virtual safe lane and the second duration of the vehicle leaving the width of the virtual safe lane are obtained. Based on the collision duration, the first duration, and the second duration, it is determined whether the vehicle and the vehicle to be monitored will collide in the future time period; The process of obtaining the virtual safe lane width of a vehicle includes: when the vehicle is detected to be traveling on a straight road at the current moment, determining the virtual safe lane width based on the vehicle's size and a safe distance threshold; and when the vehicle is detected to be traveling on a curved road at the current moment, linearly processing the vehicle's turning radius, outer sweep radius, and inner sweep radius to obtain the virtual safe lane width. The method further includes: defining a center point based on the vehicle's driving trajectory; determining the distance from the center of the dimension to the center point as the turning radius; determining the distance from the outer side of the vehicle to the center point as the outer sweep radius; and determining the distance from the inner side of the vehicle to the center point as the inner sweep radius. Obtaining the first duration for the vehicle to be monitored to enter the width of the virtual safe lane and the second duration for the vehicle to leave the width of the virtual safe lane includes: when the vehicle to be monitored is detected by the vehicle's sensors to be traveling on a straight road in the future time period, obtaining the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored; and performing linear processing on the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored to obtain the first duration and the second duration.

2. The method according to claim 1, characterized in that, Determining the collision duration of the vehicle colliding with the vehicle under monitoring in the future time period includes: The collision duration is determined based on the distance between the vehicle and the intersection point in the coordinate system and the vehicle's speed.

3. The method according to claim 1, characterized in that, Acquiring the first duration of the vehicle under monitoring entering the width of the virtual safe lane and the second duration of the vehicle leaving the width of the virtual safe lane also includes: When the vehicle under monitoring is detected to be traveling on a curved road in the future time period, the coordinates of the first intersection point between the vehicle under monitoring and the vehicle are determined based on the vehicle's travel path and the vehicle's driving path. Based on the position of the vehicle to be monitored and the coordinates of the first intersection point, determine the first distance the vehicle to be monitored travels to the coordinates of the intersection point; The first duration is determined based on the first distance, the lateral speed and the longitudinal speed of the vehicle to be monitored; When the vehicle under monitoring is detected to be traveling on a curved road in the future time period, the coordinates of the second intersection point between the vehicle under monitoring and the vehicle are determined based on the travel path of the vehicle under monitoring and the travel path of the vehicle. Based on the position of the vehicle to be monitored and the coordinates of the second intersection point, determine the second distance the vehicle to be monitored travels to the coordinates of the intersection point; The second duration is determined based on the second distance, the lateral speed and the longitudinal speed of the vehicle to be monitored.

4. The method according to claim 1, characterized in that, Based on the collision duration, the first duration, and the second duration, determining whether the vehicle and the vehicle to be monitored will collide in the future time period includes: In response to the collision duration being greater than the first duration and less than the second duration, it is determined that the vehicle has collided with the vehicle under monitoring; In response to the collision duration being greater than the second duration or the collision duration being less than the first duration, it is determined that the vehicle and the vehicle to be monitored did not collide.

5. The method according to claim 4, characterized in that, In response to a collision duration greater than the first duration and less than the second duration, determining that the vehicle has collided with the vehicle under monitoring includes: In response to a number of times the collision duration is greater than the first duration and less than the second duration being greater than a number threshold, it is determined that the vehicle has collided with the vehicle to be monitored.

6. A device for predicting collisions between a vehicle and a vehicle to be monitored, characterized in that, include: An acquisition unit is used to acquire the virtual safe lane width of a vehicle, wherein the virtual safe lane width is the lane width of the road used to enable the vehicle to drive safely; The processing unit is configured to, when the vehicle is detected to be traveling to the intersection of the vehicle's travel path and the vehicle to be monitored in a future time period, determine the collision duration of the collision between the vehicle and the vehicle to be monitored in the future time period, and obtain the first duration of the vehicle to be monitored entering the width of the virtual safe lane and the second duration of the vehicle to be monitored leaving the width of the virtual safe lane. The determining unit is configured to determine, based on the collision duration, the first duration, and the second duration, whether the vehicle and the vehicle to be monitored will collide in the future time period; The acquisition unit is also used to determine the virtual safe lane width based on the vehicle's size and a safe distance threshold when the vehicle is currently traveling on a straight road; and to perform linear processing on the vehicle's turning radius, outer sweep radius, and inner sweep radius to obtain the virtual safe lane width when the vehicle is currently traveling on a curved road. The acquisition unit is further configured to define a center of a circle based on the vehicle's driving trajectory; determine the distance from the center of the dimension to the center of the circle as the turning radius; determine the distance from the outer side of the vehicle to the center of the circle as the outer sweep radius; and determine the distance from the inner side of the vehicle to the center of the circle as the inner sweep radius. The processing unit is further configured to obtain the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle when the vehicle to be monitored is detected by the vehicle's sensors traveling on a straight road in the future time period; and to perform linear processing on the lateral distance, lateral speed, vehicle size, and safe distance threshold of the vehicle to be monitored to obtain the first duration and the second duration.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 5.

8. A vehicle, characterized in that, The vehicle is used to perform the method according to any one of claims 1 to 5.

Images