Collision detection methods, devices, electronic equipment and storage media for dynamic obstacles

Abstract

This disclosure provides a collision detection method for dynamic obstacles, comprising: determining the space occupied by the obstacle based on the obstacle's moving speed and size, wherein the obstacle-occupied space includes sequentially connected safe areas, occupied areas, and predicted areas; and calculating the distance from a target point on the vehicle to the obstacle-occupied space to determine the collision distance between the vehicle and the obstacle. This disclosure also provides a collision detection device, electronic device, and storage medium for dynamic obstacles. This disclosure can effectively improve the efficiency and accuracy of dynamic obstacle collision detection, while enhancing the mobility of obstacle prediction and reducing hardware resource requirements.

Description

Technical Field

[0001] This disclosure relates to a method, apparatus, electronic device, and storage medium for collision detection of dynamic obstacles. Background Technology

[0002] The obstacle space occupancy model is the input to the decision-making and planning modules of autonomous vehicles. A stable and reliable obstacle model is the foundation for the normal operation of autonomous vehicle systems.

[0003] Obstacle space occupancy models determine the space occupied by obstacles based on their geometric dimensions and positions obtained by the perception module in an autonomous driving system. Currently, commonly used obstacle geometries in autonomous driving are... Figure 1 The diagram shows rectangles, circles, and shapes where a rectangle meets two semicircles. Rectangles are commonly used to represent static obstacles, circles to represent obstacles or pedestrians with approximate length and width, and shapes where a rectangle meets two semicircles to represent obstacles such as vehicles. Compared to rectangles, shapes where a rectangle meets two semicircles add a safety margin in front of and behind the obstacle. However, none of these obstacle geometry models consider the obstacle's speed or other motion information, and therefore cannot predict the space the obstacle will occupy in the future.

[0004] The main method for dynamic obstacle spatial prediction is: after selecting an obstacle model, add time information to obtain... Figure 2 The obstacle prediction trajectory is shown. The disadvantages of this trajectory prediction method are as follows: 1) It requires recording historical obstacle information, resulting in huge data storage and high storage space requirements; 2) Prediction accuracy is highly dependent on the prediction model. Commonly used prediction models are learning-based models, and insufficient sample size or poor sample quality can lead to low prediction accuracy, resulting in low accuracy in dynamic obstacle spatial prediction; 3) In low-speed scenarios, obstacles are highly maneuverable. Over-reliance on historical information in prediction models reduces the confidence of the predicted trajectory, leading to significant differences between the predicted situation and the actual obstacle movement, which can easily cause errors in trajectory planning and decision-making, potentially negatively impacting driving safety. Summary of the Invention

[0005] To address at least one of the aforementioned technical problems, this disclosure provides a method, apparatus, electronic device, and storage medium for detecting collisions of dynamic obstacles.

[0006] According to one aspect of this disclosure, a collision detection method for dynamic obstacles is provided, comprising:

[0007] The space occupied by an obstacle is determined based on its moving speed and size. The space occupied by the obstacle includes a safe area, an occupied area, and a predicted area that are connected in sequence.

[0008] Calculate the distance from the target point on the vehicle to the space occupied by the obstacle to determine the collision distance between the vehicle and the obstacle.

[0009] According to at least one embodiment of the collision detection method for dynamic obstacles of the present disclosure, the length of the safe zone in the direction parallel to the movement direction of the obstacle is calculated based on the movement speed of the obstacle, and the length of the safe zone in the direction perpendicular to the movement direction of the obstacle is determined by the size of the obstacle.

[0010] According to at least one embodiment of the collision detection method for dynamic obstacles of this disclosure, the axial length of the safe zone parallel to the direction of obstacle movement is calculated by the following formula:

[0011]

[0012] Among them, a r The axis length of the safe zone is parallel to the direction of the obstacle's movement. a1, b1, and c1 are the axis length calibration parameters of the safe zone, v is the speed of the obstacle's movement, and e is a natural constant.

[0013] According to at least one embodiment of the collision detection method for dynamic obstacles of the present disclosure, the axial length of the prediction region parallel to the direction of obstacle movement is calculated based on the moving speed of the obstacle, and the axial length of the prediction region perpendicular to the direction of obstacle movement is determined by the size of the obstacle.

[0014] According to at least one embodiment of the collision detection method for dynamic obstacles of this disclosure, the axial length of the prediction region parallel to the direction of obstacle movement is calculated by the following formula:

[0015]

[0016] Among them, a f denoted as the axis length of the predicted region parallel to the direction of obstacle movement, a2, b2, and c2 represent the axis length calibration parameters of the predicted region, v represents the speed of the obstacle movement, and e is a natural constant.

[0017] According to at least one embodiment of the collision detection method for dynamic obstacles of the present disclosure, the length and width of the occupied area are determined by the size of the obstacle.

[0018] According to at least one embodiment of the collision detection method for dynamic obstacles of the present disclosure, the target points on the vehicle include all points on the outline of the vehicle or selected points on the outline of the vehicle.

[0019] According to at least one embodiment of the collision detection method for dynamic obstacles in this disclosure, the minimum value among all distances from the target point to the space occupied by the obstacle is taken as the collision distance between the vehicle and the obstacle.

[0020] According to at least one embodiment of the collision detection method for dynamic obstacles of this disclosure, the step of calculating the distance from a target point on the vehicle to the space occupied by the obstacle includes:

[0021] Obtain the location information of the target point on this vehicle, and convert the location information of the target point on this vehicle into the coordinate system of the space occupied by the obstacle;

[0022] Calculate the distance from the target point on the vehicle to the space occupied by the obstacle in the obstacle-occupied space coordinate system.

[0023] According to at least one embodiment of the collision detection method for dynamic obstacles of this disclosure, the step of calculating the distance from a target point on the vehicle to the space occupied by the obstacle includes:

[0024] The collision region of the target point is determined based on the x-axis coordinate of the target point in the obstacle-occupied space coordinate system and the length of the obstacle. The collision region includes one of the safe region, the occupied region, and the predicted region.

[0025] Based on the coordinates of the target point in the obstacle-occupied space coordinate system, calculate the distance from the target point to the safe area, occupied area, or predicted area in its collision region, and use the distance from the target point to the safe area, occupied area, or predicted area in its collision region as the distance from the target point to the obstacle-occupied space.

[0026] According to at least one embodiment of the collision detection method for dynamic obstacles of this disclosure, when the collision area includes a safe area or a predicted area, the calculation of the distance from the target point on the vehicle to the space occupied by the obstacle includes:

[0027] The angle between the vector formed by the geometric center of the safe or predicted area and the target point and the X-axis is determined by the bisection method.

[0028] Determine the coordinates of the boundary points corresponding to the included angle in the safe area or the predicted area;

[0029] The distance between the target point and the boundary point is calculated based on the coordinates of the target point and the boundary point, and the distance between the target point and the boundary point is used as the distance from the target point to the space occupied by the obstacle.

[0030] According to at least one embodiment of the collision detection method for dynamic obstacles of the present disclosure, when the collision area includes an occupied area, the calculation of the distance from the target point on the vehicle to the space occupied by the obstacle includes: taking the difference between the y-axis coordinate of the target point in the coordinate system of the obstacle occupied space and half the width of the obstacle as the distance from the target point to the space occupied by the obstacle.

[0031] According to at least one embodiment of the collision detection method for dynamic obstacles in this disclosure, the calculation of the distance from the target point on the vehicle to the space occupied by the obstacle further includes: determining whether the target point belongs to the space occupied by the obstacle based on the coordinates of the target point, and determining that the distance from the target point to the space occupied by the obstacle is zero when the target point belongs to the space occupied by the obstacle.

[0032] According to a second aspect of this disclosure, a collision detection device for dynamic obstacles is provided, comprising:

[0033] The determining unit is used to determine the space occupied by the obstacle based on the obstacle's moving speed and size, wherein the space occupied by the obstacle includes a safe area, an occupied area, and a predicted area that are connected in sequence.

[0034] The calculation unit is used to calculate the distance from the target point on the vehicle to the space occupied by the obstacle, so as to determine the collision distance between the vehicle and the obstacle.

[0035] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0036] Memory, the memory storing execution instructions; and

[0037] A processor that executes the execution instructions stored in the memory, causing the processor to perform the collision detection method for dynamic obstacles as described above.

[0038] According to a fourth aspect of this disclosure, a readable storage medium is provided that stores executable instructions, which, when executed by a processor, are used to implement the collision detection method for dynamic obstacles as described above.

[0039] The embodiments disclosed herein can improve the efficiency and accuracy of dynamic obstacle collision detection while reducing the amount of data, reducing computational complexity, reducing storage resource requirements and computing resource consumption, and also improving the mobility of obstacle prediction. Attached Figure Description

[0040] The accompanying drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0041] Figure 1 This is a schematic diagram of an obstacle model commonly used in related technologies.

[0042] Figure 2 This is a schematic diagram of dynamic obstacle trajectory prediction in related technologies.

[0043] Figure 3 This is a flowchart illustrating a dynamic obstacle collision detection method according to one embodiment of the present disclosure.

[0044] Figure 4 This is a schematic diagram of the space occupied by an obstacle according to one embodiment of the present disclosure.

[0045] Figure 5 This is a schematic diagram of an obstacle-occupied space coordinate system according to one embodiment of the present disclosure.

[0046] Figure 6 This is a schematic diagram showing the relationship between the axis length of the safe area and the speed of the obstacle according to one embodiment of the present disclosure.

[0047] Figure 7 This is a schematic diagram of the relationship between the axis length of the predicted region and the speed of the obstacle according to one embodiment of the present disclosure.

[0048] Figure 8 This is a schematic diagram of the space occupied by various specific speed obstacles according to one embodiment of the present disclosure.

[0049] Figure 9 This is a schematic diagram of the collision area according to one embodiment of the present disclosure.

[0050] Figure 10 This is an example diagram of a dynamic obstacle collision detection device using a hardware implementation of a processing system according to one embodiment of the present disclosure. Detailed Implementation

[0051] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the disclosure. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the accompanying drawings.

[0052] It should be noted that, where there is no conflict, the embodiments and features described in this disclosure can be combined with each other. The technical solutions of this disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0053] Unless otherwise stated, the exemplary implementations / embodiments shown are to be understood as providing exemplary features of various details that provide ways in which the technical concepts of this disclosure can be implemented in practice. Therefore, unless otherwise stated, the features of various implementations / embodiments may be additionally combined, separated, interchanged and / or rearranged without departing from the technical concepts of this disclosure.

[0054] The use of crosshairs and / or shading in the accompanying drawings is generally used to clarify the boundaries between adjacent components. Thus, unless otherwise stated, the presence or absence of crosshairs or shading does not convey or indicate any preference or requirement for the specific material, material properties, dimensions, proportions, commonalities between the illustrated components, or any other characteristics, properties, etc., of the components. Furthermore, in the accompanying drawings, the dimensions and relative dimensions of components may be exaggerated for clarity and / or descriptive purposes. When exemplary embodiments can be implemented differently, a specific process sequence may be performed in a different order than that described. For example, two consecutively described processes may be performed substantially simultaneously or in the reverse order of their description. Furthermore, the same reference numerals denote the same components.

[0055] When a component is referred to as being "on" or "above" another component, "connected to," or "joined to" another component, the component may be directly on, directly connected to, or directly joined to the other component, or there may be intermediate components. However, when a component is referred to as being "directly on" another component, "directly connected to," or "directly joined to" another component, there are no intermediate components. Therefore, the term "connection" can refer to a physical connection, an electrical connection, etc., and may or may not have intermediate components.

[0056] The terminology used herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “a” and “the” are intended to include the plural forms as well. Furthermore, when the terms “comprising” and / or “including” and variations thereof are used in this specification, it indicates the presence of the stated features, integrals, steps, operations, parts, components, and / or groups thereof, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, parts, components, and / or groups thereof. It should also be noted that, as used herein, the terms “substantially,” “about,” and other similar terms are used as approximate terms rather than as terms of degree, thus explaining the inherent biases in measurements, calculated values, and / or provided values ​​that would be recognized by one of ordinary skill in the art.

[0057] As described in the background art, commonly used obstacle models cannot predict the space occupied by dynamic obstacles, and the prediction of dynamic obstacle space mainly relies on trajectory prediction, which has problems such as large data storage, low prediction accuracy, poor accuracy, and low confidence. In view of this, the embodiments of this disclosure provide the following dynamic obstacle collision detection method, device, electronic device and storage medium with high accuracy and strong adaptability.

[0058] This disclosure proposes a novel dynamic obstacle space occupancy model that considers movement speed. It expands the space occupied by obstacles in the speed direction, achieving real-time prediction of obstacle space occupancy. Addressing the problems of large data volume, over-reliance on historical obstacle information, and high maneuverability of low-speed obstacles caused by calculating obstacle space occupancy through trajectory prediction, this disclosure's obstacle space occupancy model only needs to consider the current speed information of obstacles, resulting in less data volume and effectively reducing data storage space requirements while improving the predictive maneuverability of obstacles. Furthermore, this disclosure's obstacle space occupancy model also determines safe zones in real time based on obstacle speed, effectively improving safety.

[0059] The specific implementation methods of the embodiments disclosed herein will be described in detail below.

[0060] Figure 3 This is a schematic flowchart of a collision detection method for dynamic obstacles according to one embodiment of the present disclosure. Figure 3 As shown, the dynamic obstacle collision detection method of this disclosure embodiment may include steps S302 to S304:

[0061] Step S302: Determine the space occupied by the obstacle based on the obstacle's moving speed and size. The space occupied by the obstacle includes a safe area, an occupied area, and a predicted area that are connected in sequence.

[0062] The size of obstacles can be selected according to the obstacle category using the corresponding default configuration. For example, images containing obstacles can be captured by the vehicle's cameras and other sensors. The category of the obstacle can be determined through image processing, and the size of the corresponding obstacle category can be retrieved from the pre-stored obstacle size data to obtain the obstacle's size and other data.

[0063] Assuming the obstacle is classified as a vehicle, its shape is typically a quadrilateral by default, and its dimensions can include information such as its length and width. Similarly, assuming the obstacle is classified as a person, its shape can also be a quadrilateral by default, and its dimensions can also include information such as its length and width.

[0064] Of course, algorithms such as object detection can also be used to process images containing obstacles to obtain real-time obstacle size information. This disclosure does not limit the way obstacle size is expressed, its specific content, or its acquisition method.

[0065] The moving speed of an obstacle can be its absolute speed, that is, the speed of its movement relative to the ground. The moving speed of an obstacle can also be obtained through image processing of an image containing the obstacle. This disclosure does not limit the method used to obtain the moving speed of the obstacle.

[0066] Figure 4 A schematic diagram showing the space occupied by obstacles according to an embodiment of the present disclosure is shown. Figure 5 A coordinate system diagram showing the space occupied by obstacles is shown. Figure 5 The obstacle occupies a Cartesian coordinate system, which is a right-handed coordinate system. The origin is the geometric center of the obstacle, the positive x-axis is the direction of the obstacle's movement, the positive z-axis (not shown in the figure) is the direction perpendicular to the ground and pointing to the sky, and the positive y-axis is perpendicular to the direction of the obstacle's movement.

[0067] like Figure 4 and Figure 5 As shown, the space occupied by obstacles in this embodiment of the present disclosure may include three closely connected areas: a safe area, an occupied area, and a predicted area.

[0068] The safe zone has a semi-elliptical geometry and is located behind the occupied area relative to the direction of obstacle movement. The length of the safe zone's axis parallel to the obstacle's movement direction can be calculated based on the obstacle's speed, while the length of the safe zone's axis perpendicular to the obstacle's movement direction can be determined by the obstacle's dimensions. For example, the length of the safe zone's axis perpendicular to the obstacle's movement direction can be equal to half the obstacle's width.

[0069] The occupied area is rectangular in shape and located at the center. Both the length and width of the occupied area can be determined by the dimensions of the obstacle. Specifically, the length of the occupied area parallel to the direction of obstacle movement is equal to the length of the obstacle, and the length of the occupied area perpendicular to the direction of obstacle movement is equal to the width of the obstacle.

[0070] The predicted region is geometrically a semi-ellipse. Relative to the obstacle's movement direction, the predicted region lies in front of the occupied region. The axis length of the predicted region is determined similarly to that of the safe region; that is, the axis length parallel to the obstacle's movement direction can be calculated based on the obstacle's speed, while the axis length perpendicular to the obstacle's movement direction can be determined by the obstacle's dimensions. For example, the axis length perpendicular to the obstacle's movement direction can be equal to half the obstacle's width.

[0071] Figure 5 In the diagram, points p1 to p6 are key points in the space occupied by obstacles, and they are the vertices of the safe area, the occupied area, and the predicted area, respectively. p4, p3, and p5 are the vertices of the safe area, p3, p5, p6, and p2 are the vertices of the occupied area, and p1, p6, and p2 are the vertices of the predicted area.

[0072] For ease of explanation, assume the obstacle has a width of 2W and a length of 2L. Figure 5 In the diagram, the coordinates of p1 to p6 are as follows: p1(L+a f ,0),p2(L,W),p3(-L,W),p4(-La r ,0), p5(-L,-W), p6(L,-W).

[0073] The elliptic parametric equation of the safe region is expressed as equation (1).

[0074]

[0075] In equation (1), (x,y) represents the coordinates of the boundary point in the safe region, that is, it represents the coordinates of the point on the side of half of the ellipse of the safe region, and θ represents the angle between the vector formed by the point (x,y) and the geometric center of the safe region (i.e., the center point of the ellipse) and the x-axis.

[0076] The parametric equation of the elliptic region is expressed as follows (2):

[0077]

[0078] In equation (2), (x,y) represents the coordinates of the boundary point of the prediction region, that is, represents the coordinates of the point on the ellipse of the prediction region, and θ represents the angle between the vector formed by the point (x,y) and the geometric center of the prediction region (i.e., the center point of the ellipse) and the x-axis.

[0079] The x-axis length of the safety zone, that is, the length of the safety zone in the direction parallel to the movement of the obstacle, can be obtained by the following formula (3):

[0080]

[0081] The x-axis length of the prediction region, that is, the length of the prediction region in the direction parallel to the obstacle's movement, can be obtained by the following formula (4):

[0082]

[0083] The meanings of the symbols in formulas (1) to (4) are as follows:

[0084] W represents half the width of the obstacle, L represents half the length of the obstacle, θ represents the angle between the vector formed by the point (x,y) and the geometric center of the corresponding region (i.e., the center of the ellipse) and the x-axis, and a f a represents the x-axis length of the predicted region. r The x-axis represents the axis length of the safe zone, a1, b1, and c1 represent the axis length calibration parameters of the safe zone, a2, b2, and c2 represent the axis length calibration parameters of the predicted zone, v represents the moving speed of the obstacle, and e is a natural constant.

[0085] As can be seen from equation (3), the shape of the safe zone is a semi-ellipse, and the parameters of this ellipse depend on information such as the size and speed of the obstacle. The length of the ellipse along the direction of obstacle movement first increases with the increase of the obstacle's speed, and then gradually decreases when the obstacle's speed reaches the preset speed calibration value.

[0086] As can be seen from equation (4), the shape of the predicted area is a semi-ellipse, and its parameters depend on the size and speed information of the obstacle. The length of the ellipse in the speed direction gradually increases with the increase of speed. When the speed reaches the calibration value, the length of the ellipse remains approximately unchanged.

[0087] As can be seen from equations (3) to (4), the obstacle occupancy space adopted in this embodiment determines the predicted area by predicting the space occupancy in the direction of the obstacle's speed based on the obstacle's current speed information, and calculates the safe area in the opposite direction of the speed based on the obstacle's current speed information. The obstacle occupancy space does not depend on the obstacle's historical information, has a small data volume, is simple to operate, and has the characteristics of small storage space requirements and high operation efficiency.

[0088] For example, the axis length calibration parameters a1, b1, and c1 of the safety zone can be pre-calibrated using test data of the obstacle. The axis length calibration parameters a1, b1, and c1 of the safety zone can be determined by the size of the obstacle, a preset speed calibration value, and a preset safety distance.

[0089] For example, the axis length calibration parameters a2, b2, and c2 of the predicted region can be pre-calibrated using the test data of the obstacle. The axis length calibration parameters a2, b2, and c2 of the predicted region can be determined by the size of the obstacle, a preset speed calibration value, and a preset safety distance.

[0090] For example, assuming the obstacle is a vehicle, the width 2W of the obstacle can be set to 2 meters by default, and the length 2L can be set to 4 meters.

[0091] Assuming the obstacle is a vehicle, the preset safety distance is 0.2m, and the preset speed calibration value is 10m / s, then the maximum value of the x-axis length of the safe zone (i.e., the length parallel to the direction of obstacle movement) is equal to half the width W of the obstacle. The x-axis length of the safe zone reaches its maximum value when the obstacle's speed equals the preset speed calibration value of 10m / s. When the obstacle's speed is 0 (i.e., when the obstacle is stationary), the x-axis length of the safe zone equals the preset safety distance of 0.2m. From these data, the calibration parameters for the safe zone's axis length are: a1 = 1, b1 = 10, c1 = 62.13.

[0092] By using equation (3) and the axis length calibration parameters of the safety zone, we can obtain... Figure 6 The curve showing the relationship between the x-axis length of the safety zone and the obstacle's moving speed (e.g., vehicle speed). Figure 6 As shown, the x-axis length of the safety zone initially increases and then decreases as the obstacle's speed increases. Therefore, at lower obstacle speeds, the obstacle may stop abruptly, and to maintain a safe distance, the x-axis length of the safety zone will initially increase. When the obstacle's speed exceeds a preset calibration value (e.g., 10 m / s), the likelihood of the obstacle stopping abruptly is considered low. In this case, to allow the vehicle more decision-making flexibility, the x-axis length of the obstacle's safety zone can be gradually reduced. When the obstacle's speed is zero, the x-axis length of the obstacle's safety zone can be equal to the preset safe distance (e.g., 0.2 m).

[0093] Assuming the obstacle is a vehicle, the preset safety distance is 0.2m, and the preset speed calibration value is 10m / s, when the obstacle's speed is 5m / s, the x-axis length of the predicted area is equal to half the obstacle's length L. When the obstacle's speed is equal to the preset speed calibration value of 10m / s, the x-axis length of the predicted area is equal to the obstacle's length 2L. When the obstacle's speed is 0, the x-axis length of the predicted area is equal to the safety distance of 0.2m. Therefore, the x-axis length calibration parameters for the predicted area are: a2 = 0.21, b2 = 0.05, c2 = 0.58. The relationship curve between the x-axis length of the predicted area and the obstacle's speed (i.e., vehicle speed) is shown below. Figure 7 As shown. Figure 7 As shown, the x-axis length of the predicted region gradually increases with the obstacle's moving speed, exhibiting a trend of first increasing and then remaining constant. Thus, the higher the obstacle's moving speed, the larger the space it may occupy in the future within a limited time. However, once the speed reaches a certain value (e.g., a preset speed calibration value), the occupied space will also reach its maximum, after which the occupied space will remain essentially unchanged.

[0094] Figure 8The diagram illustrates the space occupied by obstacles at several specific speeds. For example... Figure 8 As shown, the area occupied by an obstacle is only related to its size, and the area occupied by the obstacle corresponds to its shape at different moving speeds. When the obstacle's moving speed is 0, the x-axis lengths of both the safe area and the predicted area are safe distances. When the obstacle's moving speed is between 0 and 10 m / s, the x-axis lengths of both the safe area and the predicted area increase with increasing obstacle speed, and the areas of both the safe area and the predicted area increase with increasing obstacle speed. When the obstacle's moving speed reaches the calibrated value of 10 m / s, the areas of both the safe area and the predicted area reach their maximum. When the obstacle's moving speed exceeds 10 m / s, the x-axis length of the safe area gradually decreases with increasing obstacle speed, while the x-axis length of the predicted area remains at the calibrated value of 10 m / s. The area of ​​the safe area gradually decreases with increasing obstacle speed, while the area of ​​the predicted area remains unchanged.

[0095] Step S304: Calculate the distance from the target point on the vehicle to the space occupied by the obstacle in order to determine the collision distance between the vehicle and the obstacle.

[0096] The target points on the vehicle can be freely selected as needed. In some embodiments, the target points on the vehicle may include all points or a portion of selected points on the vehicle's outline. These selected points may be key points on the vehicle's outline, such as vertices or points spaced at predetermined intervals. Of course, the target points on the vehicle may also be other points on the vehicle body or within the vehicle. For example, when the distance between the vehicle and the obstacle is large enough that the vehicle's shape can be ignored, the target points on the vehicle may be the vehicle's geometric center, center of gravity, or the origin of the vehicle's coordinate system. This disclosure does not limit the selection of target points.

[0097] In step S304, the collision distance between the vehicle and the obstacle can be determined based on the distances from all target points on the vehicle to the space occupied by the obstacle. For example, the minimum distance among all target points to the space occupied by the obstacle can be taken as the collision distance between the vehicle and the obstacle. Of course, the collision distance between the vehicle and the obstacle can also be selected as, for example, the average distance of all target points to the space occupied by the obstacle. This embodiment of the present disclosure does not limit how the collision distance between the vehicle and the obstacle is specifically selected. In specific applications, the collision distance between the vehicle and the obstacle can be flexibly selected according to actual scenario requirements, obstacle type, etc.

[0098] In some implementations, the process of calculating the distance from each target point on the vehicle to the space occupied by the obstacle in step S304 may include the following steps a1 to a2:

[0099] Step a1: Obtain the location information of the target point on the vehicle and convert the location information of the target point on the vehicle into the coordinate system of the space occupied by the obstacle;

[0100] Step a2: Calculate the distance from the target point on the vehicle to the space occupied by the obstacle in the obstacle-occupied space coordinate system.

[0101] The location information of the target point on the vehicle is usually represented by coordinates in the vehicle's coordinate system. This embodiment transforms the target point on the vehicle to a coordinate system with the geometric center of the obstacle as the origin (i.e., Figure 5 The calculation is performed in the coordinate system shown, and the distance from the target point to the space occupied by the obstacle is calculated in this coordinate system. Compared with other coordinate systems (such as the vehicle coordinate system of this vehicle), the amount of computation and data is greatly reduced, and the computational complexity is also greatly reduced. This can significantly improve the calculation efficiency of collision distance. At the same time, because the calculation is relatively simple and the error is small, it can also improve the detection accuracy of collision distance.

[0102] In practical applications, the location information of the target point on the vehicle can be obtained through sensors installed on the vehicle, such as cameras, lidar, and GPS. This disclosure does not limit the method used to obtain the location information of the target point on the vehicle.

[0103] In some implementations, step a2 may include the following steps a21 to a22:

[0104] Step a21: Determine the collision area of ​​the target point based on the x-axis coordinate of the target point in the obstacle-occupied space coordinate system and the length of the obstacle. The collision area includes one of the safe area, the occupied area, and the predicted area.

[0105] Step a22: In the obstacle-occupied space coordinate system, calculate the distance from the target point to the safe area, occupied area or predicted area in its collision area, and use the distance from the target point to the safe area, occupied area or predicted area in its collision area as the distance from the target point to the obstacle-occupied space.

[0106] Considering that the space occupied by the obstacle is symmetrical about the x-axis in the coordinate system of the obstacle space, in order to further simplify the calculation process of the collision distance, all target points can be transformed to the upper half of the x-axis in advance. That is, the coordinates of the target points are processed by the operation shown in equation (5). In this way, only the distance between the target point and the upper half of the space occupied by the obstacle needs to be calculated.

[0107] If y < 0, then y = -y (5)

[0108] Figure 9 A schematic diagram of the collision area of ​​the target point is shown. It is assumed that the target point is in the space coordinate system occupied by the obstacle (i.e., Figure 5The coordinates in the coordinate system are (x, y). In step a21, the collision area can be determined based on the x-axis coordinates of the target point and the length of the obstacle. Specifically, as... Figure 8 As shown, if x < -L, the collision region is determined to be region I, which includes the safe region; if -L <= x <= L, the collision region is determined to be region II, which includes the occupied region; if x > L, the collision region is region III, which includes the predicted region.

[0109] In step a22, collision detection calculations are performed based on the collision area determined in step a21. Different collision algorithms are used to calculate the distance depending on the collision area.

[0110] In some implementations, when the collision area includes a safe area or a predicted area, step a22 may include: first, using a bisection method to determine the angle between the vector formed by the geometric center of the safe area or predicted area and the target point and the X-axis; then, determining the coordinates of the boundary points of the corresponding angle in the safe area or predicted area; and finally, calculating the distance between the target point and the boundary points based on the coordinates of the target point and the boundary points, using the distance between the target point and the boundary points as the distance from the target point to the space occupied by the obstacle.

[0111] In some implementations, when the collision area includes the occupied area, step a22 may include: using the difference between the y-axis coordinate of the target point in the obstacle occupied space coordinate system and the width of the obstacle as the distance from the target point to the obstacle occupied space.

[0112] In some implementations, step a22 may further include: determining whether the target point belongs to the obstacle-occupied space based on the coordinates of the target point in the obstacle-occupied space coordinate system; if the target point belongs to the obstacle-occupied space, determining that the distance from the target point to the obstacle-occupied space is zero. If the target point does not belong to the obstacle-occupied space, other implementations described above may be used to determine the distance from the target point to the obstacle-occupied space.

[0113] When the collision area includes a safe area, the target point can be determined by the following formula (6) to determine whether it belongs to the space occupied by the obstacle. When the collision area includes an occupied area, the target point can be determined by judging whether “y<=W” is satisfied. When the collision area includes a prediction area, the target point can be determined by the following formula (16) to determine whether it belongs to the space occupied by the obstacle.

[0114] by Figure 9 For example, when the collision area is area I, the calculation process of the distance from the target point to the space occupied by the obstacle may include the following steps:

[0115] Step b1: Determine whether the target point (x,y) satisfies the following formula (6). If it does, the target point belongs to the safe area and the distance d from the target point to the space occupied by the obstacle is determined to be 0. Otherwise, continue to execute steps b2 to b7.

[0116]

[0117] In equation (6), x is the x-axis coordinate of the target point, y is the y-axis coordinate of the target point, L is half the length of the obstacle, W is half the width of the obstacle, and a r This represents the length of the safe zone along the axis parallel to the direction of obstacle movement, i.e., the length of the safe zone along the x-axis.

[0118] Step b2: Set the angle θ between the vector formed by the geometric center point (-L,0) of the safe area and the target point (x,y) and the x-axis to the initial value;

[0119] The initial value of the angle θ between the vector formed by the geometric center point (-L,0) of the safe area and the target point (x,y) and the x-axis is estimated by the following formula (7).

[0120]

[0121] In equation (7), x is the x-axis coordinate of the target point, y is the y-axis coordinate of the target point, and L is half the length of the obstacle.

[0122] Step b3, calculate the coordinates (x, y) of the boundary point corresponding to the included angle θ in the safe area using the following formulas (8) to (9). e ,y e );

[0123] x e =-L+a r coseθ (8)

[0124] y e =Wcosθ (9)

[0125] In equations (8) to (9), x e Let x and y be the x-coordinates of the boundary points corresponding to the included angle θ within the safe zone. e Let be the y-axis coordinate of the boundary point corresponding to the included angle θ within the safe zone, L be half the length of the obstacle, W be half the width of the obstacle, and a be the y-axis coordinate of the boundary point corresponding to the included angle θ within the safe zone. r This represents the length of the safe zone along the axis parallel to the direction of obstacle movement, i.e., the length of the safe zone along the x-axis.

[0126] Step b4: Calculate the projection p of the tangent line of the ellipse to which the target point belongs in the safe area using the following formula (10), and update the search boundary angle (θ) based on the projection p using the following formulas (11) to (12). r ,θ l);

[0127] p = -sinθ(xx) e )+cosθ(yy e (10)

[0128] If p>0, then θ l =π,θ r =θ (11)

[0129] If p < 0, then

[0130] Where p represents the projection of the target point onto the tangent of the ellipse within the safe zone, and θ l Let θ represent the right boundary angle of the vector formed by the geometric center point (-L,0) of the safe zone and the target point (x,y) with the x-axis. r The angle θ between the vector formed by the geometric center point (-L,0) of the safe zone and the target point (x,y) and the x-axis represents the left boundary angle.

[0131] If p = 0, it means that the current value of the angle θ between the vector formed by the geometric center point (-L,0) of the safe area and the target point (x,y) and the x-axis is the true value of the angle θ, and we can directly jump to step b7.

[0132] Step b5: Reset the angle θ between the vector formed by the geometric center point (-L,0) of the safe area and the target point (x,y) and the x-axis to (θ). r ,θ l The middle angle θ m After repeating steps b3 to b4, continue to step b6;

[0133] Among them, the intermediate angle θ m It can be calculated using the following formula (13).

[0134]

[0135] Step b6, based on the updated search boundary angle (θ) r ,θ l Determine whether the termination condition is met. If the termination condition is met, continue to step b7; otherwise, repeat step b5 until the termination condition is met.

[0136] For example, the termination condition can be set as follows (14), that is, the termination condition can be: when the difference between the right boundary and the left boundary is less than the pre-calibrated convergence tolerance θ t If the process terminates, it will not terminate; otherwise, it will continue to execute step b5.

[0137] θ l -θ r <θt (14)

[0138] Where, θ t It is the convergence tolerance, taken as the calibration value.

[0139] Step b7: Calculate the distance d from the target point to the space occupied by the obstacle, that is, the collision distance d between the target point and the obstacle;

[0140] For example, the distance d from the target point to the boundary point of the safe area corresponding to its included angle θ can be calculated by the following formula (15). This distance d is the distance from the target point to the space occupied by the obstacle, which is also the collision distance from the target point to the obstacle.

[0141]

[0142] In equation (15), x is the x-axis coordinate of the target point in the obstacle-occupied space coordinate system, and y is the y-axis coordinate of the target point in the obstacle-occupied space coordinate system. e Let x be the x-axis coordinate of the boundary point in the safe area corresponding to the included angle θ in the obstacle-occupied space coordinate system, and y be the x-axis coordinate of the boundary point in the safe area. e Let θ be the y-axis coordinate of the boundary point in the safe area corresponding to the included angle θ in the obstacle-occupied space coordinate system.

[0143] by Figure 9 For example, when the collision area is region II, the calculation process of the collision distance may include the following steps c1 to c2:

[0144] Step c1: Determine if the target point satisfies y <= W. If it does, the target point belongs to the occupied area, and the distance d from the target point to the space occupied by the obstacle is 0. Otherwise, continue to step c2.

[0145] Where y is the y-axis coordinate of the target point in the coordinate system of the space occupied by the obstacle, and W is half the width of the obstacle.

[0146] Step c2: If y > w, then the distance d from the target point to the space occupied by the obstacle is yW.

[0147] by Figure 9 For example, when the collision area is region III, the calculation process of the collision distance may include the following steps d1 to d7:

[0148] Step d1: Determine whether the target point (x,y) satisfies the following formula (16). If it does, the target point belongs to the prediction area and the distance d from the target point to the space occupied by the obstacle is determined to be 0. Otherwise, continue to execute steps d2 to d7.

[0149]

[0150] In equation (16), x is the x-axis coordinate of the target point, y is the y-axis coordinate of the target point, L is half the length of the obstacle, W is half the width of the obstacle, and a f This represents the axial length of the predicted region in the direction parallel to the obstacle's movement, i.e., the x-axis axial length of the safe region.

[0151] Step d2: Set the angle θ between the vector formed by the geometric center point (L,0) of the prediction region and the target point (x,y) and the x-axis to the initial value;

[0152] The initial value of the angle θ between the vector formed by the geometric center point (L,0) of the prediction region and the target point (x,y) and the x-axis is estimated by the following formula (17).

[0153]

[0154] In equation (17), x is the x-axis coordinate of the target point, y is the y-axis coordinate of the target point, and L is half the length of the obstacle.

[0155] Step d3, calculate the coordinates (x, y, y) of the boundary points corresponding to the included angle θ in the predicted region using the following formulas (18) to (19). e ,y e );

[0156] x e =L+a f cosθ (18)

[0157] y e =W cosθ (19)

[0158] In equations (18) to (19), x e Let x and y be the x-axis coordinates of the boundary points corresponding to the included angle θ in the prediction region. e Let be the y-axis coordinate of the boundary point corresponding to the included angle θ in the predicted region, L be half the length of the obstacle, W be half the width of the obstacle, and a be the y-axis coordinate of the boundary point corresponding to the included angle θ in the predicted region. f This represents the axial length of the predicted region in the direction parallel to the obstacle's movement, i.e., the x-axis axial length of the predicted region.

[0159] Step d4: Calculate the projection p of the tangent line of the ellipse to which the target point belongs in the prediction area using the following formula (20), and update the search boundary angle (θ) based on the projection p using the following formulas (21) to (22). r ,θ l );

[0160] p = -sinθ(xx) e )+cosθ(yy e (20)

[0161] If p > 0, then

[0162] If p < 0, then

[0163] Where p represents the projection of the target point onto the tangent of the ellipse to which the prediction region belongs, and θ l The right boundary angle θ represents the angle between the vector formed by the geometric center point (L,0) of the prediction region and the target point (x,y) and the x-axis. r The angle θ represents the left boundary angle between the vector formed by the geometric center point (L,0) of the prediction region and the target point (x,y) and the x-axis.

[0164] If p = 0, it means that the current value of the angle θ between the vector formed by the geometric center point (-L,0) of the prediction region and the target point (x,y) and the x-axis is the true value of the angle θ, and we can directly jump to step d7.

[0165] Step d5: Reset the angle θ between the vector formed by the geometric center point (L,0) of the prediction region and the target point (x,y) and the x-axis to (θ). r ,θ l The middle angle θ m After repeating steps d3 to d4, continue to step d6;

[0166] Step d6, based on the updated search boundary angle (θ) r ,θ l Determine whether the termination condition is met. If the termination condition is met, continue to step d7; otherwise, repeat step d5 until the termination condition is met.

[0167] The termination condition in this step can also be Equation (14), but the convergence tolerance θ t The values ​​can be different.

[0168] Step d7: Calculate the distance d from the target point to the space occupied by the obstacle, that is, the collision distance d between the target point and the obstacle;

[0169] For example, the distance d from the target point to the boundary point of the safe area corresponding to its included angle θ can be calculated by the following formula (23). This distance d is the distance from the target point to the space occupied by the obstacle, which is also the collision distance from the target point to the obstacle.

[0170]

[0171] In equation (23), x is the x-axis coordinate of the target point in the obstacle-occupied space coordinate system, and y is the y-axis coordinate of the target point in the obstacle-occupied space coordinate system. e Let x be the x-axis coordinate of the boundary point corresponding to the included angle θ in the obstacle-occupied space coordinate system, and y be the x-axis coordinate of the boundary point in the predicted region. eThis is the y-axis coordinate of the boundary point corresponding to the included angle θ in the predicted region within the obstacle-occupied space coordinate system.

[0172] Figure 9 In the example, the minimum distance d from all target points to the space occupied by the obstacle can be taken as the collision distance between the vehicle and the obstacle.

[0173] As can be seen from the above, in this embodiment of the present disclosure, the collision distance detection between the vehicle and the obstacle is converted into the distance detection from the target point on the vehicle to the space occupied by the obstacle. This eliminates the need to use historical data, significantly reduces the amount of data, and greatly reduces the computational complexity. As a result, the collision detection efficiency and accuracy can be significantly improved, and high accuracy and high efficiency detection of dynamic obstacle collision distances can be achieved.

[0174] The collision detection method of this disclosure has the following advantages:

[0175] 1) Based on the real-time speed information of obstacles, the predicted space is determined by predicting future occupancy. The size of the predicted area gradually increases with increasing speed, and remains approximately constant once the speed reaches a calibrated value. A safe area is calculated based on the real-time speed of the obstacles. The area of ​​the safe area gradually increases with increasing speed, and decreases gradually once the speed exceeds a calibrated value. Therefore, the obstacle occupancy space in this embodiment better conforms to the actual movement patterns of obstacles, accurately reflects the actual situation of obstacle occupancy space changes with speed, and can incorporate the sudden stops of low-speed moving obstacles into the obstacle occupancy space, effectively avoiding collision detection errors caused by sudden stops of low-speed moving obstacles.

[0176] 2) The collision distance detection in this embodiment does not rely on historical information of obstacles, has good real-time performance, high computational efficiency, low computational complexity, small data volume, small data storage space requirements, and low consumption of computing resources. While improving the efficiency and accuracy of collision distance detection, it can also reduce hardware costs.

[0177] Figure 10 An example diagram of a dynamic obstacle collision detection device using a hardware implementation of a processing system is shown.

[0178] The apparatus may include corresponding modules that perform one or more steps in the flowchart above. Therefore, each or more steps in the flowchart above can be performed by a corresponding module, and the apparatus may include one or more of these modules. A module may be one or more hardware modules specifically configured to perform a corresponding step, or implemented by a processor configured to perform a corresponding step, or stored in a computer-readable medium for implementation by a processor, or implemented through some combination thereof.

[0179] This hardware architecture can be implemented using a bus architecture. The bus architecture can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the hardware. Bus 1100 connects various circuits, including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400, such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0180] Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one connection line is used in this diagram, but this does not imply that there is only one bus or only one type of bus.

[0181] Any process or method description in the flowcharts or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain. The processor performs the various methods and processes described above. For example, the method embodiments of this disclosure may be implemented as software programs tangibly contained in a machine-readable medium, such as memory. In some embodiments, part or all of the software program may be loaded and / or installed via memory and / or a communication interface. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform one of the methods described above by any other suitable means (e.g., by means of firmware).

[0182] The logic and / or steps represented in the flowchart or otherwise described herein may be specifically implemented in any readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0183] For the purposes of this specification, a "readable storage medium" can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM). Furthermore, a readable storage medium can even be paper or other suitable media on which a program can be printed, since a program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in memory.

[0184] It should be understood that various parts of this disclosure can be implemented in hardware, software, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0185] Those skilled in the art will understand that all or part of the steps of the methods described above can be implemented by a program instructing related hardware. The program can be stored in a readable storage medium, and when executed, the program includes one or a combination of the steps of the method implementation.

[0186] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a single processing module, or each unit can exist physically separately, or two or more units can be integrated into a single module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. The storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0187] Figure 10 This is a schematic diagram of a dynamic obstacle collision detection device 1000 according to one embodiment of the present disclosure. Figure 10 As shown, the dynamic obstacle collision detection device 1000 according to this disclosure may include:

[0188] The determining unit 1002 is used to determine the space occupied by the obstacle based on the moving speed and size of the obstacle. The space occupied by the obstacle includes a safe area, an occupied area and a predicted area that are connected in sequence.

[0189] The calculation unit 1004 is used to calculate the distance from the target point on the vehicle to the space occupied by the obstacle, so as to determine the collision distance between the vehicle and the obstacle.

[0190] In some embodiments, the determining unit 1002 may be used to: calculate the axial length of the safe area in the direction parallel to the moving direction of the obstacle based on the moving speed of the obstacle; and determine the axial length of the safe area in the direction perpendicular to the moving direction of the obstacle based on the size of the obstacle.

[0191] Specifically, the determining unit 1002 can be used to determine the axis length of the safety zone in the direction parallel to the movement of the obstacle using equation (3).

[0192] In some implementations, the determining unit 1002 may be used to: calculate the axial length of the predicted region in the direction parallel to the moving direction of the obstacle based on the moving speed of the obstacle; and determine the axial length of the predicted region in the direction perpendicular to the moving direction of the obstacle based on the size of the obstacle.

[0193] Specifically, the determining unit 1002 can be used to determine the axis length of the prediction region in the direction parallel to the movement of the obstacle using equation (4).

[0194] In some implementations, the determining unit 1002 may be used to determine the length and width of the occupied area based on the size of the obstacle.

[0195] In some embodiments, the calculation unit 1004 may be used to: obtain the position information of the target point on the vehicle and convert the position information of the target point on the vehicle to the obstacle-occupied space coordinate system; and, in the obstacle-occupied space coordinate system, calculate the distance from the target point on the vehicle to the obstacle-occupied space.

[0196] In some embodiments, the calculation unit 1004 may be used to: determine the collision region of the target point based on the x-axis coordinate of the target point in the obstacle-occupied space coordinate system and the length of the obstacle, wherein the collision region includes one of the safe region, the occupied region, and the predicted region; and calculate the distance from the target point to the safe region, the occupied region, or the predicted region in its collision region based on the coordinate of the target point in the obstacle-occupied space coordinate system, and use the distance from the target point to the safe region, the occupied region, or the predicted region in its collision region as the distance from the target point to the obstacle-occupied space.

[0197] In some implementations, the calculation unit 1004 may be used to: when the collision area includes a safe area or a predicted area, use a bisection method to determine the angle between the vector formed by the geometric center of the safe area or predicted area and the target point and the X-axis; determine the coordinates of the boundary points in the safe area or predicted area corresponding to the angle; and calculate the distance between the target point and the boundary points based on the coordinates of the target point and the coordinates of the boundary points, and use the distance between the target point and the boundary points as the distance from the target point to the space occupied by the obstacle.

[0198] In some implementations, the calculation unit 1004 may be used to: when the collision area includes an occupied area, take the difference between the y-axis coordinate of the target point in the obstacle occupied space coordinate system and half the width of the obstacle as the distance from the target point to the obstacle occupied space.

[0199] In some implementations, the calculation unit 1004 may also be used to: determine whether the target point belongs to the space occupied by the obstacle based on the coordinates of the target point, and determine that the distance from the target point to the space occupied by the obstacle is zero when the target point belongs to the space occupied by the obstacle.

[0200] This disclosure also provides an electronic device, including: a memory storing execution instructions; and a processor or other hardware module executing the execution instructions stored in the memory, causing the processor or other hardware module to perform the above-described dynamic obstacle collision detection method.

[0201] This disclosure also provides a readable storage medium storing execution instructions, which, when executed by a processor, are used to implement the above-described collision detection method for dynamic obstacles.

[0202] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment / mode or example is included in at least one embodiment / mode or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.

[0203] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0204] Those skilled in the art should understand that the above embodiments are merely for illustrating the present disclosure and are not intended to limit the scope of the disclosure. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present disclosure.

Claims

1. A method of collision detection of a dynamic obstacle, characterized in that, The application relates to a method for determining the collision distance between a vehicle and an obstacle. The method comprises: determining the obstacle occupation space according to the moving speed of the obstacle and the size of the obstacle, wherein the obstacle occupation space comprises a safety region, an occupied region and a predicted region in sequence; calculating the distance between the target point on the vehicle and the obstacle occupation space to determine the collision distance between the vehicle and the obstacle; the axis length of the safety region in the direction parallel to the moving direction of the obstacle is calculated according to the moving speed of the obstacle, and the axis length of the safety region in the direction perpendicular to the moving direction of the obstacle is determined according to the size of the obstacle; the axis length of the predicted region in the direction parallel to the moving direction of the obstacle is calculated according to the moving speed of the obstacle, and the axis length of the predicted region in the direction perpendicular to the moving direction of the obstacle is determined according to the size of the obstacle; the length and width of the occupied region are determined according to the size of the obstacle; the minimum value of the distances between all target points on the vehicle and the obstacle occupation space is taken as the collision distance between the vehicle and the obstacle; wherein denotes the axial length of the safety area in the direction parallel to the movement direction of the obstacle, , , denote the axial length scaling parameters of the safety area, respectively, denotes the movement speed of the obstacle, is a natural constant.

2. The method of claim 1, wherein the dynamic obstacle collision detection method is characterized by, the axis length of the safety region in the direction parallel to the moving direction of the obstacle is calculated according to the following formula: wherein, denotes the axis length of the prediction region in parallel to the moving direction of the obstacle, , , denote the axis length calibration parameters of the prediction region, respectively, denotes the moving speed of the obstacle, is a natural constant.

3. The method of claim 1, wherein the dynamic obstacle collision detection method is characterized by, the axis length of the predicted region in the direction parallel to the moving direction of the obstacle is calculated according to the following formula:

4. The method of claim 1, wherein the dynamic obstacle collision detection method is characterized by, the target point on the vehicle comprises all points on the contour of the vehicle or part of the selected points on the contour of the vehicle. The method for calculating the distance between the target point on the vehicle and the obstacle occupation space comprises: obtaining the position information of the target point on the vehicle and converting the position information of the target point on the vehicle into the obstacle occupation space coordinate system; 5. The method of collision detection of a dynamic obstacle according to claim 1 or 4, wherein, calculating the distance between the target point on the vehicle and the obstacle occupation space in the obstacle occupation space coordinate system. The method for calculating the distance between the target point on the vehicle and the obstacle occupation space comprises: determining the collision region of the target point according to the x-axis coordinate of the target point in the obstacle occupation space coordinate system and the length of the obstacle, wherein the collision region comprises one of the safety region, the occupied region and the predicted region; 6. The method of collision detection of a dynamic obstacle according to claim 5, wherein, calculating the distance between the target point and the safety region, the occupied region or the predicted region in the collision region of the target point according to the coordinate of the target point in the obstacle occupation space coordinate system, and taking the distance between the target point and the safety region, the occupied region or the predicted region in the collision region of the target point as the distance between the target point and the obstacle occupation space. When the collision region comprises the safety region or the predicted region, the method for calculating the distance between the target point on the vehicle and the obstacle occupation space comprises: determining the included angle between the vector formed by the geometric center of the safety region or the predicted region and the target point and the x-axis by using the dichotomy method; determining the coordinate of the boundary point corresponding to the included angle in the safety region or the predicted region; 7. The method of claim 5, wherein the dynamic obstacle collision detection method is characterized by, calculating the distance between the target point and the boundary point according to the coordinate of the target point and the coordinate of the boundary point, and taking the distance between the target point and the boundary point as the distance between the target point and the obstacle occupation space. When the collision region comprises the occupied region, the method for calculating the distance between the target point on the vehicle and the obstacle occupation space comprises: taking the difference between the y-axis coordinate of the target point in the obstacle occupation space coordinate system and half of the width of the obstacle as the distance between the target point and the obstacle occupation space.

8. The method according to claim 6 or 7, wherein The calculating the distance from the target point on the vehicle to the obstacle occupation space further includes: determining whether the target point belongs to the obstacle occupation space according to the coordinates of the target point, and determining the distance from the target point to the obstacle occupation space as zero when the target point belongs to the obstacle occupation space.

9. A dynamic obstacle collision detection apparatus, characterized by, The method comprises: The determining unit is configured to determine the obstacle occupation space according to the moving speed of the obstacle and the size of the obstacle, the obstacle occupation space comprising a safety region, an occupied region and a prediction region connected in sequence; The calculating unit is configured to calculate the distance from the target point on the vehicle to the obstacle occupation space to determine the collision distance between the vehicle and the obstacle; The axis length of the safety region in the direction parallel to the moving direction of the obstacle is calculated according to the moving speed of the obstacle, and the axis length of the safety region in the direction perpendicular to the moving direction of the obstacle is determined according to the size of the obstacle; The axis length of the prediction region in the direction parallel to the moving direction of the obstacle is calculated according to the moving speed of the obstacle, and the axis length of the prediction region in the direction perpendicular to the moving direction of the obstacle is determined according to the size of the obstacle; The length and width of the occupied region are determined according to the size of the obstacle; The minimum value of the distances from all the target points to the obstacle occupation space is taken as the collision distance between the vehicle and the obstacle; The axis length of the safety region in the direction parallel to the moving direction of the obstacle is calculated according to the following formula: wherein denotes the axial length of the safety zone in the direction parallel to the movement direction of the obstacle, denote the axial length scaling parameters of the safety zone, respectively, denotes the movement speed of the obstacle, is a natural constant.​​ 10. An electronic device, comprising: The method comprises: The memory stores execution instructions; And The processor executes the execution instructions stored in the memory, so that the processor executes the method in any one of claims 1 to 8.

11. A readable storage medium, characterized by, The readable storage medium stores execution instructions, and the execution instructions are executed by the processor to implement the method in any one of claims 1 to 8.

Images