Curve collision identification method, device and equipment and storage medium

Abstract

The invention discloses a curve collision identification method and device, equipment and a storage medium. The curve collision method comprises the steps that under the condition that a vehicle runs on a curve, the motion type of an obstacle is determined according to the distance between the obstacle and the vehicle, the speed of the vehicle and the yaw velocity of the vehicle collected at at least two sampling moments; based on the distance between the vehicle and the obstacle and the movement direction, determining the movement track of the vehicle and the movement track of the obstacle by adopting a track calculation scheme corresponding to the movement type; according to the self-vehicle motion trail and the obstacle motion trail, curve collision recognition is carried out. According to the technical scheme of the embodiment of the invention, the accuracy of curve collision identification can be improved.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving technology, and in particular to a curve collision recognition method, device, equipment and storage medium. Background Art

[0002] As cars become more intelligent, the popularity of assisted driving functions is also increasing. As one of the important functions of assisted driving, the Autonomous Emergency Braking (AEB) system has greatly improved driving safety.

[0003] The AEB function mainly provides emergency braking for longitudinal and horizontal collision scenarios. In the case of a curve, the vehicle's coordinate system deflects during the turn, which can easily cause the sensor detection accuracy to deteriorate. That is, the speed, acceleration, and orientation angle of the obstacle in the vehicle's coordinate system have large measurement errors when the vehicle deflects, which increases the difficulty of collision recognition in the curve. How to improve the accuracy of curve collision recognition is very important to ensure the safety of driving on a curve. Summary of the invention

[0004] The present invention provides a curve collision recognition method, device, equipment and storage medium to solve the problem of low curve collision recognition accuracy due to the influence of curve measurement error.

[0005] According to one aspect of the present invention, a curve collision recognition method is provided, comprising:

[0006] When the vehicle is traveling on a curve, determining the movement type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed, and the yaw rate of the vehicle collected at least at two sampling moments;

[0007] Based on the distance between the ego vehicle and the obstacle and the direction of movement, a trajectory calculation scheme corresponding to the movement type is used to determine the movement trajectory of the ego vehicle and the movement trajectory of the obstacle;

[0008] Curve collision recognition is performed according to the vehicle motion trajectory and the obstacle motion trajectory.

[0009] According to another aspect of the present invention, there is provided a curve collision recognition device, comprising:

[0010] A motion type determination module, used to determine the motion type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed and the yaw rate of the vehicle collected at least two sampling moments when the vehicle is traveling on a curve;

[0011] A trajectory calculation module, for determining the motion trajectory of the vehicle and the motion trajectory of the obstacle based on the distance between the vehicle and the obstacle and the motion direction, using a trajectory calculation scheme corresponding to the motion type; the posture information includes the current position and the motion direction;

[0012] The curve collision recognition module is used to perform curve collision recognition according to the motion trajectory of the vehicle and the motion trajectory of the obstacle.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the curve collision recognition method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the curve collision recognition method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for identifying a curve collision according to any embodiment of the present disclosure is implemented.

[0019] The technical solution of the embodiment of the present invention is to determine the movement type of the obstacle according to the distance between the obstacle and the self-vehicle, the self-vehicle speed and the self-vehicle yaw rate collected at least two consecutive moments when the self-vehicle is traveling on a curve, and then determine the movement trajectory of the self-vehicle and the movement trajectory of the obstacle based on the distance and the movement direction of the self-vehicle and the self-vehicle using a trajectory calculation scheme corresponding to the movement type. Finally, curve collision recognition is performed based on the movement trajectory of the self-vehicle and the movement trajectory of the obstacle. The movement trajectory can be calculated only based on the distance between the vehicle and the obstacle and the movement direction information. A small amount of measurement data is introduced in the calculation process, so that the movement trajectory calculation is less affected by measurement errors, thereby improving the accuracy of curve collision recognition.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a curve collision recognition method provided according to Embodiment 1 of the present invention;

[0023] Figure 2a is a flow chart of a curve collision identification method provided according to Embodiment 2 of the present invention;

[0024] Figure 2b is a schematic diagram of obstacle motion type determination according to Embodiment 2 of the present invention;

[0025] Figure 2c is a schematic diagram of trajectory calculation of an obstacle moving obliquely according to the second embodiment of the present invention;

[0026] Figure 3a is a flow chart of a curve collision identification method provided according to Embodiment 3 of the present invention;

[0027] Figure 3b is a schematic diagram of trajectory calculation of horizontal movement of an obstacle provided in accordance with Embodiment 3 of the present invention;

[0028] Figure 4 is a schematic structural diagram of a curve collision recognition device provided according to a fourth embodiment of the present invention;

[0029] Figure 5 It is a schematic diagram of the structure of an electronic device for implementing the curve collision identification method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 A flowchart of a curve collision recognition method is provided for the first embodiment of the present invention. This embodiment can be applied to the case of recognizing a curve collision by calculating a curve motion trajectory. The method can be executed by a curve collision recognition device. The curve collision recognition device can be implemented in the form of hardware and / or software. The curve collision recognition device can be configured in various general computing devices. Figure 1 As shown, the method includes:

[0034] S110: When the vehicle is traveling on a curve, determine the movement type of the obstacle according to the distance between the obstacle and the vehicle, the speed of the vehicle, and the yaw rate of the vehicle collected at least at two sampling moments.

[0035] When the vehicle is in a curve, the local coordinate system of the vehicle, i.e. the ego vehicle coordinate system, will deflect accordingly, causing the problem of poor sensor detection accuracy. In other words, when the vehicle is turning, the speed, acceleration, and orientation angle of obstacles detected by the sensor in the ego vehicle coordinate system will have greater errors than when the vehicle is driving in a straight line, which increases the difficulty of identifying curve collisions.

[0036] In an embodiment of the present invention, when the vehicle is traveling on a curve, in order to accurately identify the curve collision, it is necessary to determine the movement type of the obstacle. The movement type of the obstacle may include horizontal movement and oblique movement in the geodetic coordinate system. The geodetic coordinate system is a coordinate system with the horizontal axis of the vehicle's driving direction and the vertical axis to the left of the vehicle as the vertical axis before the vehicle enters the curve. The geodetic coordinate system is a temporary geodetic coordinate system, which is valid only during a turning process when the vehicle changes from a straight-line driving state to a curve driving state and finally to a straight-line driving state.

[0037] Specifically, in order to determine the movement type of the obstacle, at least two frames of the distance between the obstacle and the vehicle can be collected by a perception sensor, for example, a camera, millimeter wave radar, laser radar or infrared camera can be used to collect the distance between the obstacle and the vehicle at at least two sampling moments. The distance between the obstacle and the vehicle is the horizontal distance and the longitudinal distance in the vehicle coordinate system. Then, the movement type of the obstacle is determined based on the distance between the obstacle and the vehicle, the vehicle speed and the yaw rate of the vehicle collected at at least two sampling moments.

[0038] In a specific example, by integrating the yaw angular velocity of the ego vehicle in the time dimension, the orientation angle of the ego vehicle at the above two sampling moments can be obtained. According to the orientation angle of the ego vehicle at each sampling moment, as well as the horizontal distance and longitudinal distance between the obstacle and the ego vehicle, the distance between the obstacle and the ego vehicle in the geodetic coordinate system is determined at the above two sampling moments. At the same time, the longitudinal distance of the ego vehicle in the geodetic coordinate system at the above two sampling moments can be calculated based on the ego vehicle speed and the orientation angle of the ego vehicle running between the two sampling moments. Finally, the movement type of the obstacle is determined based on the longitudinal distance between the obstacle and the ego vehicle in the geodetic coordinate system at the two sampling moments, and the longitudinal distance of the ego vehicle in the geodetic coordinate system at the two sampling moments.

[0039] In another specific example, the longitudinal distance between the obstacle and the vehicle in the geodetic coordinate system at two sampling moments, and the longitudinal distance of the vehicle in the geodetic coordinate system at two sampling moments, can be used to calculate the movement direction of the obstacle in the geodetic coordinate system. The movement type of the obstacle can be determined based on the movement direction.

[0040] S120: Based on the distance between the ego vehicle and the obstacle and the direction of movement, a trajectory calculation scheme corresponding to the movement type is used to determine the movement trajectory of the ego vehicle and the movement trajectory of the obstacle.

[0041] The ego vehicle motion trajectory refers to the arc segment from the current position of the vehicle to the intersection of the ego vehicle predicted trajectory and the obstacle predicted trajectory. The obstacle motion trajectory refers to the straight line segment from the current position of the obstacle to the intersection of the ego vehicle predicted trajectory and the obstacle predicted trajectory.

[0042] In an embodiment of the present invention, based on the distance and movement direction between the ego vehicle and the obstacle, a trajectory calculation scheme corresponding to the movement type is used to determine the ego vehicle movement trajectory and the obstacle movement trajectory. Specifically, if the movement type of the obstacle is oblique movement, the intersection point of the ego vehicle prediction trajectory and the obstacle prediction trajectory is determined, and according to the intersection point, the line connecting the ego vehicle current position and the intersection point is determined as the prediction line segment. Among them, the ego vehicle prediction trajectory defaults to circular motion, and the obstacle prediction trajectory defaults to linear motion. According to the current local horizontal distance, current local longitudinal distance, current global longitudinal distance, current ego vehicle orientation angle, ego vehicle movement radius, and the angle between the obstacle movement direction and the horizontal axis of the earth coordinate system, the target angle between the ego vehicle current movement direction and the prediction line segment is determined. Further, according to the target angle and the ego vehicle movement radius, the arc length calculation formula is used to determine the ego vehicle movement trajectory between the ego vehicle current position and the intersection point. According to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current ego vehicle heading angle, the angle between the obstacle movement direction and the horizontal axis of the earth coordinate system, the target angle and the predicted line segment, the obstacle movement trajectory from the current position to the intersection point is determined. The ego vehicle movement radius can be determined according to the ego vehicle wheelbase and the ego vehicle turning angle.

[0043] If the movement type of the obstacle is horizontal movement, determine the intersection point of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle, and determine the line connecting the current position of the ego vehicle and the intersection point as the predicted line segment based on the intersection point. Further, determine the target angle between the current movement direction of the ego vehicle and the predicted line segment based on the current local horizontal distance, current local longitudinal distance, ego vehicle movement radius and current orientation angle of the ego vehicle in the ego vehicle coordinate system, and determine the ego vehicle movement trajectory between the current position of the ego vehicle and the intersection point based on the target angle and the ego vehicle movement radius. Finally, determine the obstacle movement trajectory from the current position of the obstacle to the intersection point based on the current local horizontal distance, current local longitudinal distance, current orientation angle of the ego vehicle and the obstacle in the ego vehicle coordinate system, target angle, and the predicted line segment.

[0044] S130: Perform curve collision recognition based on the vehicle's motion trajectory and the obstacle's motion trajectory.

[0045] In the embodiment of the present invention, after the movement trajectory of the self-vehicle and the movement trajectory of the obstacle are determined, the time for the self-vehicle to reach the intersection from the current position is determined according to the movement trajectory of the self-vehicle and the speed of the self-vehicle. At the same time, the time for the obstacle to reach the intersection from the current position is determined according to the movement trajectory and the movement speed of the obstacle. Finally, when the time for the self-vehicle and the obstacle to reach the intersection is the same, it is determined that the self-vehicle will collide with the curve. Among them, the speed of the self-vehicle is determined according to the current driving state of the self-vehicle, which can be uniform speed, uniform acceleration or uniform deceleration, etc. The movement speed of the obstacle is determined according to the current movement state of the obstacle, which can be uniform speed, uniform acceleration or uniform deceleration, etc.

[0046] The technical solution of the embodiment of the present invention is to determine the movement type of the obstacle according to the distance between the obstacle and the self-vehicle, the self-vehicle speed and the self-vehicle yaw rate collected at least two sampling moments when the self-vehicle is traveling on a curve, and then determine the movement trajectory of the self-vehicle and the movement trajectory of the obstacle based on the distance and the movement direction of the self-vehicle and the obstacle by adopting a trajectory calculation scheme corresponding to the movement type, and finally perform curve collision recognition according to the movement trajectory of the self-vehicle and the movement trajectory of the obstacle. The movement trajectory can be calculated only based on the distance between the vehicle and the obstacle and the movement direction information. The amount of measurement data introduced in the calculation process is small, so that the movement trajectory calculation is less affected by the measurement error, thereby improving the accuracy of curve collision recognition.

[0047] Embodiment 2

[0048] Figure 2a This is a flowchart of a curve collision identification method provided in the second embodiment of the present invention. This embodiment further refines the above embodiment and provides specific steps for determining the motion type of the obstacle based on the distance between the obstacle and the vehicle, the vehicle speed and the yaw rate of the vehicle collected at least two sampling moments, and specific steps for determining the motion trajectory of the vehicle and the obstacle using a trajectory calculation scheme corresponding to the motion type based on the distance between the vehicle and the obstacle and the motion direction. Figure 2a As shown, the method includes:

[0049] S210. When the vehicle is traveling on a curve, obtain a first local horizontal distance and a first local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at a first sampling moment; the vehicle coordinate system is a coordinate system with the center of mass of the vehicle as the origin, ignoring the sideslip angle of the center of mass, with the current driving direction of the vehicle as the vertical axis, and with the lateral direction to the left of the center of mass as the horizontal axis.

[0050] The ego vehicle coordinate system is a coordinate system with the ego vehicle's center of mass as the origin, the vehicle's current driving direction as the vertical axis, and the center of mass to the left as the horizontal axis. The ego vehicle coordinate system changes as the vehicle's direction angle changes during the ego vehicle's turning process.

[0051] In the embodiment of the present invention, when the vehicle is traveling on a curve, the first local horizontal distance and the first local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at the first sampling moment are obtained; the vehicle coordinate system is a coordinate system with the center of mass of the vehicle as the origin, the current driving direction of the vehicle as the longitudinal axis, and the leftward direction of the center of mass as the horizontal axis. Specifically, the first local horizontal distance and the first local longitudinal distance from the vehicle to the obstacle can be detected at the first sampling moment by using a camera, a millimeter wave radar, a laser radar, or an infrared camera.

[0052] S220: Obtain a second local horizontal distance and a second local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at the second sampling moment.

[0053] In the embodiment of the present invention, the second local horizontal distance and the second local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at the second sampling time are taken. Similarly, the second local horizontal distance and the second local longitudinal distance between the vehicle and the obstacle can be detected at the second sampling time by using a camera, a millimeter wave radar, a laser radar or an infrared camera. Among them, the first sampling time is earlier than the second sampling time, and the first sampling time and the second sampling time can be two consecutive sampling times, or two different sampling times separated by several sampling times.

[0054] S230: Determine the movement type of the obstacle according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, and the second local longitudinal distance.

[0055] In the embodiment of the present invention, the movement type of the obstacle is determined according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance and the second local longitudinal distance. Specifically, the orientation angle of the vehicle at the first sampling moment and the second sampling moment is obtained by integrating the yaw rate of the vehicle in the time dimension. And according to the first local horizontal distance, the first local longitudinal distance and the orientation angle of the vehicle at the first sampling moment, the first global longitudinal distance between the vehicle and the obstacle in the geodetic coordinate system is calculated; at the same time, according to the second local horizontal distance, the second local longitudinal distance and the orientation angle of the vehicle at the second sampling moment, the second global longitudinal distance between the vehicle and the obstacle in the geodetic coordinate system at the second sampling moment is determined. Further, according to the speed of the vehicle and the orientation angle of the vehicle between the first sampling moment and the second sampling moment, the third global longitudinal distance of the vehicle in the geodetic coordinate system at the first sampling moment and the second sampling moment is determined. Finally, according to the first global longitudinal distance, the second global longitudinal distance and the third global longitudinal distance, the movement type of the obstacle is determined.

[0056] Specifically, it can be determined whether the result obtained by summing the third global longitudinal distance and the second global longitudinal distance is the same as the first global longitudinal distance. If they are the same, it indicates that the obstacle has not undergone any longitudinal position change during the movement, and it is determined that the movement type of the obstacle is horizontal movement; if they are not the same, it is determined that the movement type of the obstacle is oblique movement.

[0057] Optionally, determining the movement type of the obstacle according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, and the second local longitudinal distance includes:

[0058] Determine a first vehicle heading angle of the vehicle at the first sampling moment according to the yaw angular velocity of the vehicle from the moment the vehicle enters the curve to the first sampling moment;

[0059] Determine a second vehicle heading angle of the vehicle at the second sampling moment according to the yaw angular velocity of the vehicle from the moment the vehicle enters the curve to the second sampling moment;

[0060] Determine the third global longitudinal distance of the vehicle at the first sampling moment and the second sampling moment in the geodetic coordinate system according to the vehicle speed and the vehicle heading angle of the vehicle between the first sampling moment and the second sampling moment; the geodetic coordinate system is a coordinate system with the horizontal axis of the vehicle's driving direction and the vertical axis of the vehicle's lateral direction to the left before the vehicle enters the curve;

[0061] Determine a first global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a first sampling moment according to the first local horizontal distance, the first local longitudinal distance, and the first ego vehicle heading angle;

[0062] Determine a second global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a second sampling moment according to the second local horizontal distance, the second local longitudinal distance, and the second ego vehicle heading angle;

[0063] A movement type of the obstacle is determined according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance.

[0064] In this optional embodiment, a specific method for determining the movement type of the obstacle is provided according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance and the second local longitudinal distance, as follows: Figure 2b As shown: after Δt time, the vehicle travels from pe1 to pe2, and the obstacle travels from pt1 to pt2, x1 is the first local horizontal distance between the obstacle and the vehicle collected at the first sampling moment, y1 is the first local longitudinal distance, x2 is the second local horizontal distance between the obstacle and the vehicle collected at the second sampling moment, and y2 is the second local longitudinal distance.

[0065] First, the yaw rate of the vehicle from the time it enters the curve (t0) to the first sampling time (t1) is integrated to obtain the first vehicle heading angle θ1 of the vehicle at the first sampling time. The specific calculation formula is as follows:

[0066]

[0067] Wherein, t0 is the moment when the vehicle enters the curve, t1 is the first sampling moment, and ω is the yaw rate of the vehicle (in degrees / second or radians / second).

[0068] Furthermore, the yaw angular velocity of the vehicle from the time the vehicle enters the curve to the second sampling time is integrated to obtain the second vehicle heading angle θ2 of the vehicle at the second sampling time. The specific calculation formula is as follows:

[0069]

[0070] Wherein, t0 is the moment when the vehicle enters the curve, t2 is the second sampling moment, and ω is the yaw rate of the vehicle (in degrees / second or radians / second).

[0071] Furthermore, according to the vehicle speed and the vehicle heading angle of the vehicle between the first sampling time and the second sampling time, the third global longitudinal distance h of the vehicle in the geodetic coordinate system at the first sampling time and the second sampling time is determined. The specific calculation formula is as follows:

[0072]

[0073] Among them, t θ1 is the moment when the vehicle’s heading angle is θ1 (i.e., the first sampling moment), t θ2 is the moment when the vehicle's heading angle is θ2 (i.e., the second sampling moment), v is the vehicle's speed (in meters per second), and θ is the vehicle's heading angle.

[0074] Among them, the geodetic coordinate system is a coordinate system with the horizontal axis of the vehicle's travel direction and the vertical axis to the left of the vehicle before the vehicle enters the curve.

[0075] Furthermore, according to the first local horizontal distance, the first local longitudinal distance and the first ego vehicle heading angle, the first global longitudinal distance h1 between the ego vehicle and the obstacle in the geodetic coordinate system at the first sampling moment is determined. The specific calculation formula is as follows:

[0076]

[0077] Among them, x1 is the first local horizontal distance, y1 is the first local longitudinal distance, and θ1 is the first ego vehicle heading angle.

[0078] Furthermore, according to the second local horizontal distance, the second local longitudinal distance and the second ego vehicle heading angle, the second global longitudinal distance h2 between the ego vehicle and the obstacle in the geodetic coordinate system at the second sampling moment is determined. The specific calculation formula is as follows:

[0079]

[0080] Among them, x2 is the second local horizontal distance, y2 is the second local longitudinal distance, and θ2 is the second ego vehicle heading angle.

[0081] It should be noted that in the ego-vehicle coordinate system, the distance between the obstacle and the ego-vehicle can be positive or negative, and the yaw angular velocity ω of the ego-vehicle can also be positive or negative. A positive ω indicates that the ego-vehicle rotates counterclockwise, and a negative ω indicates that the ego-vehicle rotates clockwise.

[0082] Finally, the movement type of the obstacle is determined based on the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance. Specifically, it can be determined whether the sum of the third global longitudinal distance and the second global longitudinal distance is the same as the first global longitudinal distance. If they are the same, it indicates that the obstacle has no longitudinal position change during the movement, and the movement type of the obstacle is determined to be horizontal movement; if they are not the same, the movement type of the obstacle is determined to be oblique movement.

[0083] Optionally, determining the movement type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance includes:

[0084] When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is the same as the first global longitudinal distance, determining that the movement type of the obstacle is horizontal movement;

[0085] When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is different from the first global longitudinal distance, it is determined that the movement type of the obstacle is oblique movement.

[0086] In this optional embodiment, a specific method for determining the movement type of an obstacle based on the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance is provided: the result of summing the third global longitudinal distance and the second global longitudinal distance is calculated, and the summation result is compared with the first global longitudinal distance. The specific calculation formula is as follows:

[0087] If h1=h+h2, it indicates that the obstacle does not undergo any longitudinal position change during the movement, thereby determining that the movement type of the obstacle is horizontal movement; if h1≠h+h2, it is determined that the movement type of the obstacle is oblique movement.

[0088] Optionally, determining the movement type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance further includes:

[0089] Calculate the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system according to the first global longitudinal distance, the second global longitudinal distance, the third global longitudinal distance, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, the second local longitudinal distance, the first ego vehicle heading angle, the second ego vehicle heading angle, and the ego vehicle speed and the ego vehicle heading angle during driving at the first sampling time and the second sampling time;

[0090] When the angle between the obstacle's moving direction and the horizontal axis of the geodetic coordinate system is 0, it is determined that the obstacle's moving type is horizontal.

[0091] When the angle between the obstacle's moving direction and the horizontal axis of the geodetic coordinate system is not 0, it is determined that the obstacle's moving type is oblique moving.

[0092] In this optional embodiment, another specific method for determining the movement type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance is provided: according to the first global longitudinal distance, the second global longitudinal distance, the third global longitudinal distance, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, the second local longitudinal distance, the first self-vehicle heading angle, the second self-vehicle heading angle, and the self-vehicle speed and the self-vehicle heading angle during driving at the first sampling time and the second sampling time, the angle α between the obstacle movement direction and the horizontal axis of the geodetic coordinate system is calculated, and the specific calculation formula is as follows:

[0093]

[0094] Among them, h1 is the first global longitudinal distance, h2 is the second global longitudinal distance, h is the third global longitudinal distance, x1 is the first local horizontal distance, y1 is the first local longitudinal distance, x2 is the second local horizontal distance, y2 is the second local longitudinal distance, θ1 is the first ego vehicle heading angle, θ2 is the second ego vehicle heading angle, and v is the ego vehicle speed.

[0095] Furthermore, when the angle between the obstacle's movement direction and the horizontal axis of the geodetic coordinate system is 0, the obstacle's movement type is determined to be horizontal movement; when the angle between the obstacle's movement direction and the horizontal axis of the geodetic coordinate system is not 0, the obstacle's movement type is determined to be oblique movement.

[0096] S240: Determine the intersection point of the predicted trajectory of the vehicle and the predicted trajectory of the obstacle, and determine, based on the intersection point, a line connecting the current position of the vehicle and the intersection point as a predicted line segment.

[0097] like Figure 2cAs shown, the predicted trajectory of the vehicle is an arc determined based on the radius R of the vehicle and at least two position points (e.g., point A and point C) of the vehicle during the turning process. In this embodiment, it is assumed that the vehicle moves in a circle. The predicted trajectory of the obstacle is a straight line determined based on at least two position points (e.g., point D and point C) of the obstacle during the turning process of the vehicle. In this embodiment, it is assumed that the obstacle moves in a straight line. The predicted trajectory of the vehicle and the predicted trajectory of the obstacle intersect at point C. The trajectory of the vehicle is the arc length corresponding to the line segment AC, and the trajectory of the obstacle is the line segment CD. The center of the circular motion of the vehicle is point O. Line segment OB is perpendicular to line segment AC, and line segment OE is perpendicular to the horizontal axis of the geodetic coordinate system; line segment CF is perpendicular to the horizontal axis of the geodetic coordinate system.

[0098] In the embodiment of the present invention, after determining the movement type of the obstacle, it is necessary to continue calculating the movement trajectory of the ego vehicle and the movement trajectory of the obstacle. First, the predicted trajectory of the ego vehicle is determined based on at least two positions of the ego vehicle during the turning process, and the predicted trajectory of the obstacle is determined based on the predicted trajectory of the obstacle according to at least two positions of the obstacle during the turning process of the vehicle. Then, the intersection point of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle is calculated, and based on the intersection point C, the line AC connecting the current position of the ego vehicle and the intersection point is determined as the predicted line segment, and according to Figure 2c The geometric relationship in can be obtained as follows:

[0099] AC=2Rsinγ

[0100] Among them, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment AC.

[0101] The specific calculation formula for the vehicle's motion radius is as follows:

[0102]

[0103] Where L is the wheelbase of the vehicle, and δ is the wheel angle of the vehicle (which can be converted from the steering wheel angle).

[0104] S250. When the motion type is oblique motion, determine the target angle between the current motion direction of the ego vehicle and the predicted line segment according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current global longitudinal distance, the current ego vehicle heading angle, the ego vehicle motion radius, and the angle between the obstacle motion direction and the horizontal axis of the earth coordinate system.

[0105] In the embodiment of the present invention, when the motion type is oblique motion, the target angle γ between the current motion direction of the ego vehicle and the predicted line segment AC is determined according to the current local horizontal distance x between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance y, the current global longitudinal distance h between the obstacle and the ego vehicle in the geodetic coordinate system, the current ego vehicle heading angle θ, the ego vehicle motion radius R, and the angle α between the obstacle motion direction and the horizontal axis of the geodetic coordinate system.

[0106] Optionally, when the motion type is oblique motion, the specific calculation formula of the target angle is as follows:

[0107] [(y-xtanθ)cosθ-2Rsinγcos(θ+γ)]tanα+h=2Rsinγ*sin(θ+γ)

[0108] Among them, x is the current local horizontal distance, y is the current local longitudinal distance, h is the current global longitudinal distance, θ is the current ego vehicle heading angle, R is the ego vehicle motion radius, α is the angle between the obstacle motion direction and the horizontal axis of the geodetic coordinate system, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0109] This formula is obtained by combining the following two formulas:

[0110] CF=[(y-xtanθ)cosθ-2R sinγcos(θ+γ)]tanα+h

[0111] CF=2R sinγ*sin(θ+γ)

[0112] S260: Determine the movement trajectory of the vehicle from the current position of the vehicle to the intersection point according to the target angle and the movement radius of the vehicle.

[0113] In the embodiment of the present invention, the motion trajectory of the vehicle between the current position of the vehicle and the intersection point is determined according to the target angle and the motion radius of the vehicle based on the arc length calculation formula.

[0114] Optionally, when the motion type is oblique motion, the specific calculation formula of the ego vehicle motion trajectory is as follows:

[0115]

[0116] Among them, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0117] S270, determining the obstacle motion trajectory of the obstacle from the current position to the intersection point according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current ego vehicle heading angle, the angle between the obstacle motion direction and the horizontal axis of the earth coordinate system, the target angle, and the predicted line segment.

[0118] In the embodiment of the present invention, the obstacle motion trajectory from the current position to the intersection point is determined based on the current local horizontal distance x between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance y, the current ego vehicle heading angle θ, the angle α between the obstacle movement direction and the horizontal axis of the earth coordinate system, the target angle γ and the predicted line segment AC.

[0119] Optionally, when the motion type is oblique motion, the specific calculation formula of the motion trajectory of the obstacle is as follows:

[0120]

[0121] Among them, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current vehicle heading angle, α is the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system, γ is the target angle, and AC is the predicted line segment.

[0122] S280: Perform curve collision recognition based on the vehicle's motion trajectory and the obstacle's motion trajectory.

[0123] The technical solution of the embodiment of the present invention determines the movement type of the obstacle according to the distance between the obstacle and the self-vehicle, the speed of the self-vehicle and the yaw angular velocity of the self-vehicle collected at least two sampling moments, and then determines the movement trajectory of the self-vehicle and the movement trajectory of the obstacle based on the distance and movement direction of the self-vehicle and the obstacle by adopting a trajectory calculation scheme corresponding to the movement type, and finally performs curve collision recognition according to the trajectory. Curve collision recognition can be achieved only based on the speed of the self-vehicle, the yaw angular velocity of the self-vehicle, the distance between the obstacle and the self-vehicle and the movement direction, thereby avoiding the increase of errors caused by introducing too many measurement parameters and improving the accuracy of curve collision recognition.

[0124] Embodiment 3

[0125] Figure 3a This is a flowchart of a method for identifying a curve collision provided in the third embodiment of the present invention. This embodiment further refines the above embodiment and provides specific steps for determining the motion trajectory of the vehicle and the obstacle based on the distance and motion direction between the vehicle and the obstacle using a trajectory calculation scheme corresponding to the motion type, specific steps for identifying a curve collision based on the motion trajectory of the vehicle and the obstacle, and specific steps before determining the motion type of the obstacle. Figure 3a As shown, the method includes:

[0126] S310: When the vehicle is traveling on a curve, determine the movement type of the obstacle according to the distance between the obstacle and the vehicle, the speed of the vehicle, and the yaw rate of the vehicle collected at least at two sampling moments.

[0127] Optionally, before determining the movement type of the obstacle, the following is also included:

[0128] Whether the vehicle is driving on a curve is determined based on the steering wheel angle, steering wheel angle speed and yaw rate of the vehicle within a set time.

[0129] In this optional embodiment, before determining the movement type of the obstacle, the steering wheel angle, steering wheel angular velocity and yaw angular velocity of the vehicle are collected according to the set sampling period within the set time. Further, after each acquisition of the above signal, the currently collected signal is compared with the corresponding signal threshold. If at least one of the steering wheel angle, steering wheel angular velocity and yaw angular velocity of the vehicle exceeds the signal threshold for a set number of consecutive times (for example, 3 times), it is determined that the vehicle is turning. Exemplarily, in 3 consecutive sampling periods, if the steering wheel angle exceeds the set threshold, it is determined that the vehicle is turning.

[0130] After determining that the vehicle is traveling on a curve, the vehicle's perception sensors can also be used to detect obstacles in the vehicle's environment. If there are multiple obstacles, subsequent collision recognition calculations are performed for each obstacle.

[0131] In addition, the vehicle speed can also be collected during driving as auxiliary information for judging whether the vehicle is turning. For example, if the steering wheel angle exceeds the set threshold and the vehicle speed is less than the preset speed threshold in three consecutive sampling periods, it is determined that the vehicle is turning.

[0132] S320, determining an intersection point between the predicted trajectory of the vehicle and the predicted trajectory of the obstacle, and based on the intersection point, determining a line connecting the current position of the vehicle and the intersection point as a predicted line segment.

[0133] like Figure 3b As shown, the predicted trajectory of the ego vehicle is an arc determined based on the radius R of the ego vehicle and at least two position points (e.g., point A and point C) of the ego vehicle during the turning process. In this embodiment, it is assumed that the vehicle moves in a circle. The predicted trajectory of the obstacle is a straight line determined based on at least two position points (e.g., point D and point C) of the obstacle during the turning process of the vehicle. In this embodiment, it is assumed that the obstacle moves in a straight line. The predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle intersect at point C. The trajectory of the ego vehicle is the arc length corresponding to the line segment AC, and the trajectory of the obstacle is the line segment CD. The center of the circular motion of the ego vehicle is point O, and the line segment OB is perpendicular to the line segment AC.

[0134] In the embodiment of the present invention, after determining the movement type of the obstacle, it is necessary to continue to calculate the movement trajectory of the ego vehicle and the movement trajectory of the obstacle. First, the predicted trajectory of the ego vehicle is determined based on at least two position points of the ego vehicle during the turning process, and the predicted trajectory of the obstacle is determined based on at least two positions of the obstacle during the turning process of the vehicle. Then, the intersection point of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle is calculated, and based on the intersection point C, the line AC connecting the current position of the ego vehicle and the intersection point is determined as the predicted line segment.

[0135] S330: When the motion type is horizontal motion, determine the target angle between the current motion direction of the ego vehicle and the predicted line segment according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the ego vehicle motion radius, and the current orientation angle of the ego vehicle.

[0136] In this embodiment of the present invention, when the motion type is horizontal motion, the target angle γ between the current motion direction of the ego vehicle and the predicted line segment AC is determined based on the current local horizontal distance x, the current local longitudinal distance y, the ego vehicle motion radius R and the current ego vehicle heading angle θ between the ego vehicle and the obstacle in the ego vehicle coordinate system.

[0137] Optionally, when the motion type is horizontal motion, the specific calculation formula of the target angle is as follows:

[0138]

[0139] Wherein, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current orientation angle of the ego vehicle, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0140] This formula is obtained by combining the following two formulas:

[0141]

[0142] AC=2Rsinγ

[0143] S340: Determine the movement trajectory of the vehicle from the current position of the vehicle to the intersection point according to the target angle and the movement radius of the vehicle.

[0144] In the embodiment of the present invention, the motion trajectory of the vehicle between the current position of the vehicle and the intersection point is determined according to the target angle and the motion radius of the vehicle based on the arc length calculation formula.

[0145] Optionally, when the motion type is horizontal motion, the specific calculation formula of the ego vehicle motion trajectory is as follows:

[0146]

[0147] Among them, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0148] S350, determining the obstacle motion trajectory of the obstacle from the current position to the intersection point according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current orientation angle of the ego vehicle, the target angle, and the predicted line segment.

[0149] In the embodiment of the present invention, the obstacle motion trajectory from the current position to the intersection point is determined based on the current local horizontal distance x, the current local longitudinal distance y, the current vehicle heading angle θ, the target angle γ and the predicted line segment AC between the ego vehicle and the obstacle in the ego vehicle coordinate system.

[0150] Optionally, when the motion type is horizontal motion, the specific calculation formula of the motion trajectory of the obstacle is as follows:

[0151] CD=(y-xtanθ)cosθ-AC cos(γ+θ)

[0152] Among them, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current vehicle heading angle, γ is the target angle, and AC is the predicted line segment.

[0153] S360: Determine the time it takes for the vehicle to travel from its current position to the intersection point based on the vehicle's motion trajectory and speed.

[0154] In the embodiment of the present invention, the time for the vehicle to travel from the current position to the intersection is calculated based on the vehicle's motion trajectory and the vehicle's speed. For example, the vehicle's speed may be uniform motion, uniform acceleration motion, or uniform deceleration motion.

[0155] S370: Determine the time it takes for the obstacle to move from the current position to the intersection point according to the obstacle's movement trajectory and movement speed.

[0156] In the embodiment of the present invention, the time for the obstacle to move from the current position to the intersection is determined according to the obstacle's movement trajectory and movement speed. For example, the movement speed of the obstacle can be uniform movement, uniform acceleration movement or uniform deceleration movement.

[0157] S380: When the time for the ego vehicle and the obstacle to arrive at the intersection is the same, it is determined that the ego vehicle will have a curve collision.

[0158] In the embodiment of the present invention, if the time at which the ego vehicle and the obstacle arrive at the intersection is the same, it is determined that the ego vehicle will collide with the curve. In the case where the ego vehicle is predicted to collide with the curve, the braking control is applied through the deceleration control instruction, so that the ego vehicle chassis actuator executes the deceleration instruction to achieve the braking effect and avoid the curve collision.

[0159] It is worth noting that the curve collision recognition method provided in the embodiment of the present invention can be applicable to the vehicle left-turning obstacle movement collision scenario, the vehicle left-turning obstacle movement collision scenario, the vehicle right-turning obstacle movement collision scenario and the vehicle right-turning obstacle movement collision scenario.

[0160] The technical solution of the embodiment of the present invention determines the movement type of the obstacle according to the distance between the obstacle and the self-vehicle, the speed of the self-vehicle and the yaw angular velocity of the self-vehicle collected at least two sampling moments, and then determines the movement trajectory of the self-vehicle and the movement trajectory of the obstacle based on the distance and movement direction of the self-vehicle and the obstacle by adopting a trajectory calculation scheme corresponding to the movement type, and finally performs curve collision recognition according to the trajectory. Curve collision recognition can be achieved only based on the speed of the self-vehicle, the yaw angular velocity of the self-vehicle, the distance between the obstacle and the self-vehicle and the movement direction, thereby avoiding the increase of errors caused by introducing too many measurement parameters and improving the accuracy of curve collision recognition.

[0161] Embodiment 4

[0162] Figure 4 A schematic structural diagram of a curve collision recognition device provided in Embodiment 4 of the present invention.

[0163] like Figure 4 As shown, the device comprises:

[0164] The motion type determination module 410 is used to determine the motion type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed and the yaw rate of the vehicle collected at least two sampling moments when the vehicle is traveling on a curve;

[0165] A trajectory calculation module 420, configured to determine the ego vehicle's motion trajectory and the obstacle's motion trajectory using a trajectory calculation scheme corresponding to the motion type based on the distance between the ego vehicle and the obstacle and the motion direction;

[0166] The curve collision recognition module 430 is used to perform curve collision recognition according to the vehicle motion trajectory and the obstacle motion trajectory.

[0167] The technical solution of the embodiment of the present invention is to determine the movement type of the obstacle according to the distance between the obstacle and the self-vehicle, the self-vehicle speed and the self-vehicle yaw rate collected at least two sampling moments when the self-vehicle is traveling on a curve, and then determine the movement trajectory of the self-vehicle and the movement trajectory of the obstacle based on the distance and the movement direction of the self-vehicle and the obstacle by adopting a trajectory calculation scheme corresponding to the movement type, and finally perform curve collision recognition according to the movement trajectory of the self-vehicle and the movement trajectory of the obstacle. The movement trajectory can be calculated only based on the distance between the vehicle and the obstacle and the movement direction information. The amount of measurement data introduced in the calculation process is small, so that the movement trajectory calculation is less affected by the measurement error, thereby improving the accuracy of curve collision recognition.

[0168] Optionally, the motion type determination module 410 includes:

[0169] A first local distance acquisition unit is used to acquire a first local horizontal distance and a first local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at the first sampling moment; the vehicle coordinate system is a coordinate system with the center of mass of the vehicle as the origin, the current driving direction of the vehicle as the longitudinal axis, and the lateral direction to the left of the center of mass as the horizontal axis;

[0170] A second local distance acquisition unit, used for acquiring a second local horizontal distance and a second local longitudinal distance between the obstacle and the ego vehicle in the ego vehicle coordinate system collected at a second sampling moment;

[0171] The motion type determination unit is used to determine the motion type of the obstacle based on the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance and the second local longitudinal distance.

[0172] Optionally, the motion type determination unit includes:

[0173] A first heading angle determination subunit is used to determine a first heading angle of the vehicle at a first sampling moment according to a yaw angular velocity of the vehicle from a moment when the vehicle enters the curve to a first sampling moment;

[0174] A second heading angle determination subunit is used to determine a second heading angle of the vehicle at a second sampling moment according to the yaw angular velocity of the vehicle from the moment the vehicle enters the curve to the second sampling moment;

[0175] A third global distance determination subunit is used to determine a third global longitudinal distance of the vehicle at the first sampling moment and the second sampling moment in a geodetic coordinate system according to the vehicle speed and the vehicle heading angle of the vehicle between the first sampling moment and the second sampling moment; the geodetic coordinate system is a coordinate system with the vehicle travel direction as the horizontal axis and the vehicle sideways to the left as the vertical axis before the vehicle enters the curve;

[0176] A first global distance determination subunit is used to determine a first global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a first sampling moment according to the first local horizontal distance, the first local longitudinal distance and the first ego vehicle heading angle;

[0177] A second global distance determination subunit is used to determine a second global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a second sampling moment according to the second local horizontal distance, the second local longitudinal distance and the second ego vehicle heading angle;

[0178] The motion type determination subunit is used to determine the motion type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance and the third global longitudinal distance.

[0179] Optionally, a motion type determination subunit is used to:

[0180] When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is the same as the first global longitudinal distance, determining that the movement type of the obstacle is horizontal movement;

[0181] When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is different from the first global longitudinal distance, it is determined that the movement type of the obstacle is oblique movement.

[0182] Optionally, the motion type determination subunit is further specifically used for:

[0183] Calculate the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system according to the first global longitudinal distance, the second global longitudinal distance, the third global longitudinal distance, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, the second local longitudinal distance, the first ego vehicle heading angle, the second ego vehicle heading angle, and the ego vehicle speed and the ego vehicle heading angle during driving at the first sampling time and the second sampling time;

[0184] When the angle between the obstacle's moving direction and the horizontal axis of the earth coordinate system is 0, determining that the obstacle's moving type is horizontal moving;

[0185] When the angle between the obstacle's moving direction and the horizontal axis of the earth coordinate system is not 0, it is determined that the movement type of the obstacle is oblique movement.

[0186] Optionally, the trajectory calculation module 430 includes:

[0187] A first predicted line segment determination unit, used to determine an intersection point between the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle, and determine, based on the intersection point, a line connecting the current position of the ego vehicle and the intersection point as a predicted line segment;

[0188] a first target angle determination unit, configured to determine, when the motion type is an oblique motion, a target angle between the current motion direction of the ego vehicle and the predicted line segment according to a current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, a current local longitudinal distance, a current global longitudinal distance, a current ego vehicle heading angle, a ego vehicle motion radius, and an angle between the obstacle motion direction and the horizontal axis of the earth coordinate system;

[0189] A first ego vehicle trajectory determination unit, configured to determine the ego vehicle motion trajectory between the ego vehicle current position and the intersection point according to the target angle and the ego vehicle motion radius;

[0190] The first obstacle trajectory determination unit is used to determine the obstacle motion trajectory of the obstacle from the current position to the intersection point according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current ego vehicle heading angle, the angle between the obstacle motion direction and the horizontal axis of the earth coordinate system, the target angle and the predicted line segment.

[0191] Optionally, the trajectory calculation module 420 further includes:

[0192] A second predicted line segment determination unit is used to determine an intersection point between the predicted trajectory of the vehicle and the predicted trajectory of the obstacle, and determine, based on the intersection point, a line connecting the current position of the vehicle and the intersection point as a predicted line segment;

[0193] A second target angle determination unit is used to determine, when the motion type is horizontal motion, a target angle between the current motion direction of the ego vehicle and the predicted line segment according to a current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, a current local longitudinal distance, a motion radius of the ego vehicle, and a current orientation angle of the ego vehicle;

[0194] A second ego vehicle trajectory determination unit, configured to determine the ego vehicle motion trajectory between the ego vehicle current position and the intersection point according to the target angle and the ego vehicle motion radius;

[0195] The second obstacle trajectory determination unit is used to determine the obstacle motion trajectory of the obstacle from the current position to the intersection point according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current heading angle of the ego vehicle, the target angle, and the predicted line segment.

[0196] Optionally, the curve collision recognition module 430 is specifically used for:

[0197] Determine the time it takes for the vehicle to travel from its current position to the intersection point based on the vehicle's motion trajectory and speed;

[0198] Determine the time it takes for the obstacle to move from its current position to the intersection point based on the obstacle's movement trajectory and movement speed;

[0199] When the time for the ego vehicle and the obstacle to arrive at the intersection is the same, it is determined that the ego vehicle will collide with the curve.

[0200] Optionally, when the motion type is oblique motion, the specific calculation formula of the target angle is as follows:

[0201] [(y-xtanθ)cosθ-2Rsinγcos(θ+γ)]tanα+h=2Rsinγ*sin(θ+γ)

[0202] Among them, x is the current local horizontal distance, y is the current local longitudinal distance, h is the current global longitudinal distance, θ is the current ego vehicle heading angle, R is the ego vehicle motion radius, α is the angle between the obstacle motion direction and the horizontal axis of the geodetic coordinate system, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0203] Optionally, when the motion type is horizontal motion, the specific calculation formula of the target angle is as follows:

[0204]

[0205] Wherein, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current orientation angle of the ego vehicle, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

[0206] Optionally, when the motion type is oblique motion, the specific calculation formula of the vehicle motion trajectory is as follows:

[0207]

[0208] Where R is the moving radius of the ego vehicle, and γ is the target angle between the current moving direction of the ego vehicle and the predicted line segment;

[0209] When the motion type is oblique motion, the specific calculation formula of the motion trajectory of the obstacle is as follows:

[0210]

[0211] Among them, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current vehicle heading angle, α is the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system, γ is the target angle, and AC is the predicted line segment.

[0212] Optionally, the curve collision recognition device further includes:

[0213] The curve identification module is used to determine whether the vehicle is traveling on a curve based on the steering wheel angle, steering wheel angular velocity and yaw angular velocity of the vehicle within a set time before determining the movement type of the obstacle.

[0214] The curve collision recognition device provided in the embodiment of the present invention can execute the curve collision recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0215] In the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0216] Embodiment 5

[0217] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0218] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, applicators, blade applicators, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0219] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0220] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0221] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a curve collision recognition method.

[0222] In some embodiments, the curve collision recognition method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the curve collision recognition method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the curve collision recognition method in any other appropriate manner (e.g., by means of firmware).

[0223] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0224] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or application.

[0225] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0226] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0227] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data applier), or a computing system that includes a middleware component (e.g., an application applier), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0228] A computing system may include a client and an application server. The client and the application server are generally remote from each other and usually interact through a communication network. The relationship between the client and the application server is generated by computer programs running on corresponding computers and having a client-application server relationship with each other. The application server may be a cloud application server, also known as a cloud computing application server or a cloud host, which is a host product in a cloud computing application system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS applications.

[0229] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0230] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying a curve collision, characterized in that: include: When the vehicle is traveling on a curve, determining the movement type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed, and the yaw rate of the vehicle collected at least at two sampling moments; Based on the distance between the ego vehicle and the obstacle and the direction of movement, a trajectory calculation scheme corresponding to the movement type is used to determine the movement trajectory of the ego vehicle and the movement trajectory of the obstacle; Curve collision recognition is performed according to the vehicle motion trajectory and the obstacle motion trajectory.

2. The method according to claim 1, characterized in that Determining the motion type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed, and the yaw rate of the vehicle collected at least two sampling moments includes: Obtaining a first local horizontal distance and a first local longitudinal distance between the obstacle and the vehicle in the vehicle coordinate system collected at the first sampling moment; the vehicle coordinate system is a coordinate system with the center of mass of the vehicle as the origin, the current driving direction of the vehicle as the longitudinal axis, and the leftward direction of the center of mass as the horizontal axis; Obtaining a second local horizontal distance and a second local longitudinal distance between the obstacle and the ego vehicle in the ego vehicle coordinate system collected at a second sampling moment; The movement type of the obstacle is determined according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, and the second local longitudinal distance.

3. The method according to claim 2, characterized in that The movement type of the obstacle is determined according to the yaw rate of the vehicle, the speed of the vehicle, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, and the second local longitudinal distance, including: Determine a first vehicle heading angle of the vehicle at the first sampling moment according to the yaw angular velocity of the vehicle from the moment the vehicle enters the curve to the first sampling moment; Determine a second vehicle heading angle of the vehicle at the second sampling moment according to the yaw angular velocity of the vehicle from the moment the vehicle enters the curve to the second sampling moment; Determine, according to the vehicle speed and the heading angle of the vehicle between the first sampling time and the second sampling time, a third global longitudinal distance of the vehicle in a geodetic coordinate system at the first sampling time and the second sampling time; the geodetic coordinate system is a coordinate system with the horizontal axis of the vehicle's driving direction and the vertical axis to the left of the vehicle as the longitudinal axis before the vehicle enters the curve; Determine a first global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a first sampling moment according to the first local horizontal distance, the first local longitudinal distance, and the first ego vehicle heading angle; Determine a second global longitudinal distance between the ego vehicle and the obstacle in the geodetic coordinate system at a second sampling moment according to the second local horizontal distance, the second local longitudinal distance, and the second ego vehicle heading angle; A movement type of the obstacle is determined according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance.

4. The method according to claim 3, characterized in that Determining a movement type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance includes: When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is the same as the first global longitudinal distance, determining that the movement type of the obstacle is horizontal movement; When a result obtained by summing the third global longitudinal distance and the second global longitudinal distance is different from the first global longitudinal distance, it is determined that the movement type of the obstacle is oblique movement.

5. The method according to claim 3, characterized in that: Determining the movement type of the obstacle according to the first global longitudinal distance, the second global longitudinal distance, and the third global longitudinal distance also includes: Calculate the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system according to the first global longitudinal distance, the second global longitudinal distance, the third global longitudinal distance, the first local horizontal distance, the first local longitudinal distance, the second local horizontal distance, the second local longitudinal distance, the first ego vehicle heading angle, the second ego vehicle heading angle, and the ego vehicle speed and the ego vehicle heading angle during driving at the first sampling time and the second sampling time; When the angle between the obstacle's moving direction and the horizontal axis of the earth coordinate system is 0, determining that the obstacle's moving type is horizontal moving; When the angle between the obstacle's moving direction and the horizontal axis of the earth coordinate system is not 0, it is determined that the movement type of the obstacle is oblique movement.

6. The method according to claim 1, characterized in that Based on the distance between the ego vehicle and the obstacle and the direction of movement, a trajectory calculation scheme corresponding to the movement type is used to determine the ego vehicle movement trajectory and the obstacle movement trajectory, including: Determine the intersection point of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle, and determine, based on the intersection point, a line connecting the current position of the ego vehicle and the intersection point as a predicted line segment; In the case where the motion type is oblique motion, determining a target angle between the current motion direction of the ego vehicle and the predicted line segment according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current global longitudinal distance, the current ego vehicle heading angle, the ego vehicle motion radius, and the angle between the obstacle motion direction and the horizontal axis of the earth coordinate system; Determine the movement trajectory of the vehicle from the current position of the vehicle to the intersection point according to the target angle and the movement radius of the vehicle; The obstacle motion trajectory from the current position to the intersection point is determined according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current ego vehicle heading angle, the angle between the obstacle movement direction and the horizontal axis of the earth coordinate system, the target angle and the predicted line segment.

7. The method according to claim 1, characterized in that Based on the distance between the vehicle and the obstacle and the direction of movement, a trajectory calculation scheme corresponding to the movement type is used to determine the movement trajectory of the vehicle and the movement trajectory of the obstacle, and further includes: Determine the intersection point of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle, and determine, based on the intersection point, a line connecting the current position of the ego vehicle and the intersection point as a predicted line segment; When the motion type is horizontal motion, determining a target angle between the current motion direction of the ego vehicle and the predicted line segment according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the ego vehicle motion radius, and the current orientation angle of the ego vehicle; Determine the movement trajectory of the vehicle from the current position of the vehicle to the intersection point according to the target angle and the movement radius of the vehicle; The obstacle motion trajectory from the current position to the intersection point is determined according to the current local horizontal distance between the ego vehicle and the obstacle in the ego vehicle coordinate system, the current local longitudinal distance, the current orientation angle of the ego vehicle, the target angle, and the predicted line segment.

8. The method according to claim 1, characterized in that According to the vehicle motion trajectory and the obstacle motion trajectory, curve collision recognition is performed, including: Determine the time it takes for the vehicle to travel from its current position to the intersection point based on the vehicle's motion trajectory and speed; Determine the time it takes for the obstacle to move from its current position to the intersection point based on the obstacle's movement trajectory and movement speed; When the time for the ego vehicle and the obstacle to arrive at the intersection is the same, it is determined that the ego vehicle will collide with the curve.

9. The method according to claim 6, characterized in that When the motion type is an oblique motion, the specific calculation formula of the target angle is as follows: [(y-xtanθ)cosθ-2Rsinγcos(θ+γ)]tanα+h=2Rsinγ*sin(θ+γ)wherein, x is the current local horizontal distance, y is the current local longitudinal distance, h is the current global longitudinal distance, θ is the current heading angle of the vehicle, R is the radius of motion of the vehicle, α is the angle between the obstacle motion direction and the horizontal axis of the geodetic coordinate system, and γ is the target angle between the current motion direction of the vehicle and the predicted line segment.

10. The method according to claim 7, characterized in that When the motion type is horizontal motion, the specific calculation formula of the target angle is as follows: Wherein, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current orientation angle of the ego vehicle, R is the ego vehicle motion radius, and γ is the target angle between the ego vehicle's current motion direction and the predicted line segment.

11. The method according to claim 6, characterized in that When the motion type is oblique motion, the specific calculation formula of the vehicle motion trajectory is as follows: Where R is the moving radius of the ego vehicle, and γ is the target angle between the current moving direction of the ego vehicle and the predicted line segment; When the motion type is oblique motion, the specific calculation formula of the motion trajectory of the obstacle is as follows: Among them, x is the current local horizontal distance, y is the current local longitudinal distance, θ is the current vehicle heading angle, α is the angle between the obstacle movement direction and the horizontal axis of the geodetic coordinate system, γ is the target angle, and AC is the predicted line segment.

12. The method according to claim 1, characterized in that Before determining the movement type of the obstacle, the method further includes: Whether the vehicle is driving on a curve is determined based on the steering wheel angle, steering wheel angle speed and yaw rate of the vehicle within a set time.

13. A curve collision recognition device, characterized in that: include: A motion type determination module, used to determine the motion type of the obstacle according to the distance between the obstacle and the vehicle, the vehicle speed and the yaw rate of the vehicle collected at least two sampling moments when the vehicle is traveling on a curve; A trajectory calculation module, used to determine the movement trajectory of the ego vehicle and the movement trajectory of the obstacle based on the distance between the ego vehicle and the obstacle and the movement direction, using a trajectory calculation scheme corresponding to the movement type; The curve collision recognition module is used to perform curve collision recognition according to the motion trajectory of the vehicle and the motion trajectory of the obstacle.

14. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the curve collision recognition method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the curve collision recognition method according to any one of claims 1 to 12 when executed.

Images