Security area determination method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a security area determination method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring a reference position point in a to-be-smoothed path and obstacle position information in an automatic driving scene; based on the reference position point and the obstacle position information, determining a target ellipse which contains the reference position point and is not intersected with the obstacle; rotating the target ellipse for multiple times, and determining a to-be-selected safety area which is not intersected with the obstacle based on the target ellipse after each rotation and the obstacle position information; determining a target circle center and a target radius of a maximum inscribed circle of each to-be-selected safety area; and determining a target safety area corresponding to the reference position point based on the target circle center, the target radius and the reference position point. Through the technical scheme of the embodiment of the invention, the safety area more suitable for path smoothing can be determined, and the path smoothing effect is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to autonomous driving technology, and more particularly to a method, apparatus, device, medium and program product for determining a safe area. Background Art

[0002] With the rapid development of autonomous driving technology, it is usually necessary to plan the driving path of unmanned vehicles. By discretizing the space and performing heuristic search considering factors such as obstacle avoidance and safety constraints, a feasible approximate path is obtained. However, this path is often tortuous and uneven. Due to physical limitations, unmanned vehicles cannot drive along this path well, so this path needs to be smoothed.

[0003] At present, path smoothing is usually performed based on a safe area that does not intersect with obstacles. However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] The existing method only considers the area of ​​the safe area to determine the safe area with the largest area. However, the safe area determined by this method is often not suitable for path smoothing. Figure 1 As shown, the reference point to be smoothed is located at the edge of the largest safety area, and the body of the unmanned vehicle cannot be completely contained in the safety area, thereby reducing the path smoothing effect. Summary of the invention

[0005] The embodiments of the present invention provide a method, apparatus, device, medium and program product for determining a safe area to determine a safe area that is more suitable for path smoothing and improve the path smoothing effect.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining a security area, including:

[0007] Obtaining reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene;

[0008] Based on the reference position point and the obstacle position information, determining a target ellipse that includes the reference position point and does not intersect with the obstacle;

[0009] Rotating the target ellipse multiple times, and determining a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information;

[0010] Determine the target center and target radius of the maximum inscribed circle of each candidate safety area;

[0011] Based on the target circle center, the target radius and the reference position point, a target safety area corresponding to the reference position point is determined from a plurality of candidate safety areas.

[0012] In a second aspect, an embodiment of the present invention further provides a security area determination device, including:

[0013] A reference position point acquisition module is used to obtain reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene;

[0014] A target ellipse determination module, configured to determine a target ellipse that includes the reference position point and does not intersect with the obstacle based on the reference position point and the obstacle position information;

[0015] A module for determining a safe area to be selected, used for rotating the target ellipse multiple times, and determining a safe area to be selected that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information;

[0016] A maximum inscribed circle determination module is used to determine the target center and target radius of the maximum inscribed circle of each selected safety area;

[0017] The target safety area determination module is used to determine the target safety area corresponding to the reference position point from multiple candidate safety areas based on the target circle center, the target radius and the reference position point.

[0018] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0019] one or more processors;

[0020] A memory for storing one or more programs;

[0021] When the one or more programs are executed by the one or more processors, the one or more processors implement the security area determination method provided by any embodiment of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a security area determination method as provided in any embodiment of the present invention.

[0023] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the security area determination method provided by any embodiment of the present invention.

[0024] One embodiment of the above invention has the following advantages or beneficial effects:

[0025] Based on the reference position point in the path to be smoothed and the obstacle position information in the autonomous driving scene, a target ellipse that includes the reference position point and does not intersect with the obstacle is determined; the target ellipse is rotated multiple times, and based on the target ellipse after each rotation and the obstacle position information, a candidate safety area that does not intersect with the obstacle is determined; the target center and target radius of the maximum inscribed circle of each candidate safety area are determined, so that based on the target center, target radius and reference position point, the distance between the center of the safety area and the reference position point and the area of ​​the safety area can be considered at the same time, and a target safety area that is more suitable for smoothing can be determined from multiple candidate safety areas, thereby improving the path smoothing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 This is an example diagram of a safety area with the largest area in the prior art;

[0028] Figure 2 is a flow chart of a method for determining a safe area provided by an embodiment of the present invention;

[0029] Figure 3 is an example diagram of a safe area more suitable for path smoothing involved in an embodiment of the present invention;

[0030] Figure 4 is a flow chart of another method for determining a safe area provided by an embodiment of the present invention;

[0031] Figure 5 is an example diagram of adding a virtual obstacle in an autonomous driving scene according to an embodiment of the present invention;

[0032] Figure 6 is a schematic structural diagram of a security area determination device provided by an embodiment of the present invention;

[0033] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0035] Figure 2 This is a flow chart of a method for determining a safe area provided by an embodiment of the present invention. This embodiment is applicable to the case of determining a safe area corresponding to a reference position point to be smoothed. The method can be executed by a safe area determination device, which can be implemented by software and / or hardware and integrated in an electronic device. Figure 2 As shown, the method specifically comprises the following steps:

[0036] S110: Obtain reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene.

[0037] The path to be smoothed can be a rough path obtained by path search when planning the path of the unmanned vehicle. The rough path is relatively tortuous and not smooth, so it is necessary to smooth the rough path so that the unmanned vehicle can better drive along the smoothed path, thereby realizing the automatic driving of the unmanned vehicle from point A to point B. The reference position point refers to the position point that needs to be smoothed in the path to be smoothed. The path to be smoothed is a discretized path. The path to be smoothed includes multiple discrete reference position points. For example, the path to be smoothed is: r0, r1, ..., r M , where r0 refers to the current position of the unmanned vehicle and does not require smoothing, i.e. r0 = p A Indicates that the unmanned vehicle starts from point A, r1,…,r M Refers to the M reference position points that need to be smoothed.

[0038] The obstacle position information in the autonomous driving scene may refer to the position information of all physical obstacles that the unmanned vehicle may encounter in the autonomous driving scene. The shape of each obstacle may be a convex polygon, and the obstacle position information may be represented by the equation of the convex polygon. For example, based on the coordinates of all vertices of each obstacle, the equation of each edge in the convex polygon corresponding to each obstacle may be determined. For example, the i-th edge of the convex polygon is a i x+b i y+c i =0, x is the horizontal coordinate of the location point, y is the vertical coordinate of the location point.

[0039] Specifically, the unmanned vehicle needs to travel to different positions at different times k, so it is necessary to determine the safe areas that do not collide with obstacles at different times k. In other words, it is necessary to determine the safe areas corresponding to each reference position point in the path to be smoothed. It should be noted that the determination process of the safe areas corresponding to each reference position point is the same, and can be determined by the following steps S120-S150. In this embodiment, the reference position point r at time k is determined. k The corresponding security area is used as an example for explanation.

[0040] S120: Based on the reference position point and the obstacle position information, determine a target ellipse that includes the reference position point and does not intersect with the obstacle.

[0041] Specifically, given the obstacle position information O1, O2, ..., O L and reference position point, a region containing the reference position point r can be determined. k But the target ellipse E does not intersect any obstacles k For example, based on the reference position point, the obstacle position information and the preset major-minor axis ratio information, a coordinate system that meets the preset major-minor axis ratio information and includes the reference position point r k But the target ellipse E does not intersect any obstacles k That is, the target ellipse E k The ratio of the major and minor axes is the preset ratio information of the major and minor axes, and the reference position point r k Located at the target ellipse E k Inside, and the target ellipse E k There is no intersection with the convex polygons of all obstacles, that is, the target ellipse E k All position points within the space will not collide with any obstacles.

[0042] The preset major-minor axis ratio information may be the ratio information between the major axis and the minor axis of the ellipse, which is determined in advance based on the obstacle distribution. By adjusting the preset major-minor axis ratio information, the ratio of the "length" to the "width" of the safety area can be indirectly controlled, thereby adapting to different obstacle distributions and obtaining greater degrees of freedom.

[0043] S130: rotating the target ellipse multiple times, and determining a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information.

[0044] The candidate safety region refers to an optional region that will not collide with any obstacles at time k. Each rotation determines a candidate safety region. The number of candidate safety regions is equal to the number of rotations. The candidate safety region can be a convex polygon, so that the candidate safety region can be characterized by an inequality.

[0045] Specifically, the target ellipse is rotated multiple times at different rotation angles, wherein the minimum rotation angle is 0 and the maximum rotation angle is less than 360 degrees, so that the target ellipse in different postures within one rotation can be obtained through multiple rotations, so as to determine the selected safe areas in different postures. For the target ellipse after each rotation, the selected safe area that does not collide with all obstacles is determined based on the target ellipse after the current rotation and the position information of all obstacles. It should be noted that the size and shape of the target ellipse are the same, but the orientation of the major axis is different through rotation, so the corresponding generated selected safe area (such as a convex polygon) that does not collide with all obstacles is also different, and the shape of the convex polygon corresponding to the selected safe area also tends to be "longer" in the direction of the major axis.

[0046] Exemplarily, “rotating the target ellipse multiple times” in step S130 may include: determining an angle of each rotation based on a preset number of rotations, and rotating the target ellipse clockwise based on the angle of each rotation.

[0047] Specifically, 2π may be divided by the preset number of rotations to obtain the increment of the rotation angle required for each rotation, and the rotation order k of the current time may be multiplied by the increment of the rotation angle, and the multiplication result obtained is the angle required for the kth rotation, and based on the angle of the kth rotation, the target ellipse is rotated clockwise for the kth time, so that the increment of each rotation angle within a circle of 2π is the same. For example, if the preset number of rotations is 4 times, the angles of the target ellipse rotated clockwise each time are: 0, 90 degrees, 180 degrees, and 270 degrees, respectively.

[0048] S140: Determine the target center and target radius of the maximum inscribed circle of each to-be-selected safety area.

[0049] Specifically, after each selected safety area is determined, the target center and target radius of the maximum inscribed circle of the selected safety area (such as a convex polygon) can be determined by linear programming. The target center of the maximum inscribed circle can be regarded as the center position of the selected safety area. The target radius of the maximum inscribed circle can be used to measure the area size of the selected safety area.

[0050] Exemplarily, step S140 may include: taking the constraint that the circle determined by the selected center and the selected radius is located inside the current selected safety area, maximizing the selected radius to determine the target center and target radius of the maximum inscribed circle of the current selected safety area.

[0051] Specifically, the radius to be selected and the center to be selected are variables that need to be solved. The current safe area to be selected can be characterized by the inequality of convex polygons. The circle determined by the center c and the radius R to be selected is located inside the current safe area to be selected as a constraint condition, so as to limit the circle to be inside the safe area to be selected, and by maximizing the radius to be selected, the circle is made the maximum inscribed circle of the safe area to be selected, thereby obtaining the target center and target radius of the maximum inscribed circle. For example, the constraint condition can be expressed as: Among them, a i x+b i y+c i = 0 represents the i-th side of the convex polygon corresponding to the selected safe area. Maximize the selected radius R, that is, maximize the area of ​​the circle, and solve it by using linear programming The target center and target radius of the maximum inscribed circle of the current selected safety area can be quickly obtained.

[0052] S150 : Based on the target circle center, the target radius and the reference position point, determine a target safety area corresponding to the reference position point from a plurality of candidate safety areas.

[0053] The target safety area can be the reference position point r k The final safety area is determined, such as a convex polygon. Specifically, the target circle center and the reference position point r based on the maximum inscribed circle are k The distance between the center of the safety area and the reference position point can be taken into account. The area of ​​the safety area can be taken into account based on the target radius of the maximum inscribed circle. Thus, all candidate safety areas are screened from two dimensions: the distance between the center of the safety area and the reference position point and the area of ​​the safety area. The center of the safety area is as close to the reference position point as possible. k The target safety area is as large as possible, and the calculation time is short, which improves the efficiency of determining the safety area, and then the reference position point can be smoothed based on the target safety area. Since the center of the determined target safety area can be closer to the reference position point r k And the area is large enough to be more suitable for the reference position point r k Smoothing improves the path smoothing effect, thereby better meeting the actual driving needs of unmanned vehicles. Figure 3 As shown in the figure, two obstacles form a narrow passage through which the unmanned vehicle needs to pass. By using the target center and target radius of the largest inscribed circle, a convex safety area with a center closer to the reference point (i.e., the reference position point) and as large an area as possible can be determined. Figure 1 As for the safe area in Figure 3 The center of the safety area is determined to be closer to the reference position point, so Figure 3The safe area in is more suitable for path smoothing.

[0054] Exemplarily, after determining the target safety area corresponding to each reference position point in the path to be smoothed, the path to be smoothed can be smoothed and optimized based on the obstacle avoidance constraints of the unmanned vehicle and the physical limit constraints of the control amount to achieve path smoothing. For example, the objective function to be optimized is determined based on the path between the smoothed position point and the position point before smoothing at each moment and the control amount of the unmanned vehicle at each moment, and the objective function is minimized on the basis of satisfying the obstacle avoidance constraints of the unmanned vehicle and the physical limit constraints of the control amount to obtain the final smoothed position point.

[0055] Exemplarily, the optimization function can be expressed as follows:

[0056]

[0057] Among them, p k represents the smoothed position of the unmanned vehicle at time k; u k represents the control quantity of the unmanned vehicle at time k, such as forward speed, front wheel angle, etc.; r k represents the reference position of the unmanned vehicle before smoothing at time k; ‖p k -r k ‖ is used to penalize the deviation between the smoothed position point and the reference position point; ‖u k ‖ is used to penalize large control inputs in order to reduce fuel consumption and make the path more linear and smoother. r0=p0=p A It means the unmanned vehicle starts from point A and no smoothing is required at time 0. k+1 =f(p k ,u k ), function f represents the kinematic model of the unmanned vehicle.

[0058] The obstacle avoidance constraint of the unmanned vehicle can be expressed as: g k (p k )<0, the physical limit constraint of the control quantity can be expressed as: h k (u k )<0, for example, the front wheel turning angle cannot be too large. Since the target safety area is a set of position points that are not collided with all obstacles, it can be limited by p k At the reference position r k The corresponding target safety area is characterized by satisfying the obstacle avoidance constraints of the unmanned vehicle, that is, g k (p k )<0. Since the target safety area can be represented by a convex polygon, g k (p k )<0 is a series of inequalities, namely:

[0059]

[0060] Among them, a i x+b i y+c i =0 is the i-th edge of the convex polygon corresponding to the target safety area, x is p k The horizontal axis, y is p k By using the gradient descent method or Newton's method, the objective function is minimized under the constraint of obstacle avoidance and the physical limit constraint of the control quantity, and the position point p under the minimum value is k As the final smoothed position point, a smoother path is obtained, thereby improving the path smoothing effect.

[0061] The technical solution of this embodiment is to determine a target ellipse that contains the reference position point and does not intersect with the obstacle based on the reference position point in the path to be smoothed and the obstacle position information in the autonomous driving scene; rotate the target ellipse multiple times, and determine a candidate safety area that does not intersect with the obstacle based on the target ellipse and the obstacle position information after each rotation; determine the target center and target radius of the maximum inscribed circle of each candidate safety area, so that based on the target center, target radius and reference position point, the distance between the center of the safety area and the reference position point and the area of ​​the safety area can be considered at the same time, and a target safety area that is more suitable for smoothing can be determined from multiple candidate safety areas, thereby improving the path smoothing effect.

[0062] Figure 4 A flowchart of another method for determining a safety zone provided by an embodiment of the present invention. Based on the above embodiments, this embodiment optimizes the step of "determining a candidate safety zone that does not intersect with an obstacle based on the target ellipse and obstacle position information after each rotation" and the step of "determining a target safety zone corresponding to a reference position point from multiple candidate safety zones based on the target circle center, target radius and reference position point". The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0063] See also Figure 4 Another method for determining a safe area provided in this embodiment specifically includes the following steps:

[0064] S210: Obtain reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene.

[0065] S220: Based on the reference position point and the obstacle position information, determine a target ellipse that includes the reference position point and does not intersect with the obstacle.

[0066] S230, rotating the target ellipse multiple times.

[0067] S240: Based on the target ellipse after the current rotation and the obstacle position information, determine the current ellipse position point and the current obstacle position point that are closest to the target ellipse after the current rotation and the current obstacle.

[0068] The current obstacle may refer to an obstacle currently referenced in the autonomous driving scene. L The target half-plane area not including the current obstacles is determined one by one as the current obstacles.

[0069] Specifically, for the current obstacle O in the autonomous driving scene j For example, based on the target ellipse after the rotation and the current obstacle position information, the two points closest to the target ellipse after the rotation and the current obstacle are determined as the current ellipse position point and the current obstacle position point, respectively. That is to say, the distance between the current ellipse position point on the target ellipse after the rotation and the current obstacle position point on the current obstacle is the smallest.

[0070] S250: Translate the tangent line passing through the current ellipse position point to obtain a target straight line passing through the current obstacle position point, and determine a target half-plane area that does not include the current obstacle based on the target straight line.

[0071] Specifically, the tangent of the currently rotated target ellipse at the current ellipse position point is determined, and the switch is translated so that the translated tangent passes through the current obstacle position point, and the tangent passing through the current obstacle position point is used as the target straight line. Since the target straight line can divide the plane into upper and lower parts, the plane that does not contain the current obstacle O j The half-plane area is determined as the target half-plane area.

[0072] It should be noted that by placing each obstacle O1, O2, ..., O L By repeatedly performing the operations of steps S240 and S250 one by one as the current obstacle, a target half-plane area that does not include the obstacle can be determined for each obstacle.

[0073] S260: Determine a candidate safety area that does not intersect with the obstacle based on the target half-plane area that does not include the current obstacle.

[0074] Specifically, the candidate safety area that does not intersect with obstacles can be a closed area or a non-closed area. For example, the overlapping area between the target semi-plane areas corresponding to all obstacles can be directly determined as the candidate safety area that does not intersect with all obstacles. Alternatively, in order to be able to use a closed convex polygon to represent the safety area, the overlapping and closed area between the target semi-plane areas corresponding to all obstacles is determined as the candidate safety area that does not intersect with all obstacles.

[0075] Exemplarily, step S260 may include: if the overlapping area between the target half-plane areas corresponding to all obstacles is a non-closed area, determining a virtual half-plane area that does not include the current virtual obstacle based on the target ellipse after the current rotation and the position information of multiple virtual obstacles; and determining the overlapping area between the target half-plane areas corresponding to all obstacles and the virtual half-plane areas corresponding to all virtual obstacles as a candidate safety area that does not intersect with the obstacles.

[0076] Among them, multiple virtual obstacles can enclose a closed area, and the closed area includes all obstacles in the autonomous driving scene. Virtual obstacles are virtual obstacles that do not actually exist. All obstacles in the autonomous driving scene are real obstacles that actually exist. For example, see Figure 5 , set 4 virtual obstacles O around the reference point L+1 ,O L+2 ,O L+3 ,O L+4 , so that their edges form a closed rectangle large enough to ensure that a closed safe area can be found, that is, a closed convex polygon.

[0077] Specifically, if the overlapping area between the target half-plane areas corresponding to all obstacles is a non-closed area, each virtual obstacle can be used as the current obstacle one by one, and the operations of steps S240 and S250 can be repeatedly performed, so that a virtual half-plane area that does not contain the virtual obstacle can be determined for each virtual obstacle. The overlapping area between the target half-plane areas corresponding to all obstacles and the virtual half-plane areas corresponding to all virtual obstacles is determined as a candidate safety area that does not intersect with the obstacles. Since the virtual obstacles enclose a closed area, the overlapping area between the target half-plane areas corresponding to all obstacles and the virtual half-plane areas corresponding to all virtual obstacles is a closed area. By using the constructed virtual obstacles, it can be ensured that the safety area finally determined is a closed convex polygon, so as to facilitate path smoothing.

[0078] For example, multiple virtual obstacles can be directly added to the autonomous driving scene to obtain all obstacles in the autonomous driving scene, namely, O1, O2, ..., O L ,O L+1,O L+2 ,O L+3 ,O L+4 According to the distance between the target ellipse after the rotation and each obstacle, all obstacles are sorted from small to large to obtain a sequence of obstacles with larger distances, such as O ′ 1,O ′ 2,…,O ′ L ,O ′ L+1 ,O ′ L+2 ,O ′ L+3 ,O ′ L+4 . Take each obstacle in the obstacle sequence as the current obstacle in turn and perform the operations of steps S240 and S250 to determine the target half-plane area that does not contain the current obstacle. Detect whether the overlapping area between the target half-plane area corresponding to the current obstacle and the target half-plane areas corresponding to all obstacles before the current obstacle is a closed area. If so, the closed area can be directly determined as the candidate safety area after the current rotation. If not, take the next obstacle in the obstacle sequence as the current obstacle and return to perform the operations of steps S240 and S250 until the overlapping area between the target half-plane area corresponding to the current obstacle and the target half-plane areas corresponding to all obstacles before the current obstacle is a closed area. By performing closed detection according to the obstacle sequence, the closed candidate safety area can be determined more quickly, thereby further improving the efficiency of determining the safety area.

[0079] S270: Determine the target center and target radius of the maximum inscribed circle of each to-be-selected safety area.

[0080] S280: Determine the target distance between the target circle center corresponding to each to-be-selected safety area and the reference position point.

[0081] Specifically, for each selected safety area, based on the coordinates of the target circle center corresponding to the selected safety area and the coordinates of the reference position point, the target distance between the target circle center and the reference position point can be determined, that is, the target distance between the center of the selected safety area and the reference position point.

[0082] S290: Determine a target safety area corresponding to the reference position point from a plurality of candidate safety areas based on the target distance and the target radius.

[0083] Specifically, each time the target ellipse is rendered, a different candidate safety area is determined. Based on the target distance and target radius corresponding to each candidate safety area, a target safety area with the smallest possible distance and the largest possible radius is determined from all candidate safety areas, so that the distance between the center of the safety area and the reference position point and the radius of the safety area can be balanced, thereby obtaining a target safety area that is more suitable for smoothing.

[0084] Exemplarily, step S290 may include: determining a reference value corresponding to each candidate safety zone based on the target distance and the target radius; and determining the candidate safety zone with the largest reference value as the target safety zone corresponding to the reference position point.

[0085] The reference value is inversely proportional to the target distance, and is proportional to the target radius. The reference value can be used to comprehensively reflect the degree to which the center of the safety zone is close to the reference position point and the size of the area. The larger the target distance, the smaller the reference value. The smaller the target radius, the smaller the reference value, so that the reference value can be used to accurately screen out the target safety zone whose center is as close to the reference position point as possible and whose area is as large as possible.

[0086] Specifically, the target distance can be added to a preset value (such as 1) to obtain an addition result, and the target radius is divided by the addition result to obtain a reference value corresponding to the selected safety area. For example, the reference value f corresponding to the i-th selected safety area is k,i for: Among them, R k,i and c k,i They are the candidate safe areas P k,i Alternatively, the target distance may be multiplied by a weight value w, and the multiplication result may be added to a preset value (such as 1) to obtain an addition result, and the target radius may be divided by the addition result to obtain a reference value corresponding to the selected safety area. For example, the reference value f corresponding to the i-th selected safety area is k,i for: By using the weight value w, the weight of the target distance between the center of the candidate safety area and the reference position point can be adjusted, thereby increasing the degree of freedom and further determining the target safety area that better meets the business needs. By determining the candidate safety area with the largest reference value as the target safety area corresponding to the reference position point, a target safety area with a center as close to the reference position point as possible and as large an area as possible can be obtained.

[0087] The technical solution of this embodiment is to determine the current ellipse position point and the current obstacle position point of the target ellipse after the current rotation that are closest to the current obstacle based on the target ellipse and obstacle position information after the current rotation; translate the tangent through the current ellipse position point to obtain the target straight line through the current obstacle position point, and determine the target semi-plane area that does not contain the current obstacle based on the target straight line. Based on the target semi-plane area that does not contain the current obstacle, the candidate safety area that does not intersect with the obstacle can be accurately determined, thereby ensuring the accuracy of the determination of the target safety area. Based on the target distance and target radius between the target circle center and the reference position point corresponding to each candidate safety area, a target safety area with the smallest possible distance and the largest possible radius is determined from all candidate safety areas, so that the distance between the center of the safety area and the reference position point and the area of ​​the safety area can be balanced, thereby obtaining a target safety area that is more suitable for smoothing.

[0088] The following is an embodiment of a security area determination device provided in an embodiment of the present invention. The device and the security area determination methods of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the security area determination device, reference can be made to the embodiment of the above-mentioned security area determination method.

[0089] Figure 6 FIG. 1 is a schematic diagram of a structure of a safety area determination device provided by an embodiment of the present invention. This embodiment is applicable to the case of determining a safety area corresponding to a reference position point to be smoothed. Figure 6 As shown, the device specifically includes: a reference position point acquisition module 310, a target ellipse determination module 320, a candidate safety area determination module 330, a maximum inscribed circle determination module 340 and a target safety area determination module 350.

[0090] Among them, the reference position point acquisition module 310 is used to obtain the reference position point in the path to be smoothed and the obstacle position information in the automatic driving scene; the target ellipse determination module 320 is used to determine the target ellipse that contains the reference position point and does not intersect with the obstacle based on the reference position point and the obstacle position information; the selected safety area determination module 330 is used to rotate the target ellipse multiple times, and determine the selected safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information; the maximum inscribed circle determination module 340 is used to determine the target center and target radius of the maximum inscribed circle of each selected safety area; the target safety area determination module 350 is used to determine the target safety area corresponding to the reference position point from multiple selected safety areas based on the target center, the target radius and the reference position point.

[0091] The technical solution of this embodiment is to determine a target ellipse that includes a reference position point and does not intersect with the obstacle based on the reference position point in the path to be smoothed and the obstacle position information in the autonomous driving scene; rotate the target ellipse multiple times, and determine a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information; determine the target center and target radius of the maximum inscribed circle of each candidate safety area, so that based on the target center, target radius and reference position point, the distance between the center of the safety area and the reference position point and the area of ​​the safety area can be considered at the same time, and a target safety area that is more suitable for smoothing can be determined from multiple candidate safety areas, thereby improving the path smoothing effect.

[0092] Optionally, the module 330 for determining the safe area to be selected is specifically configured to:

[0093] The angle of each rotation is determined based on a preset number of rotations, and the target ellipse is rotated clockwise based on the angle of each rotation.

[0094] Optionally, the module for determining the safe area to be selected 330 includes:

[0095] A current position point determination unit, used to determine the current ellipse position point and the current obstacle position point that are closest to the target ellipse after the current rotation and the current obstacle based on the target ellipse after the current rotation and the obstacle position information;

[0096] a target half-plane region determining unit, configured to translate a tangent line passing through the current ellipse position point to obtain a target straight line passing through the current obstacle position point, and determine a target half-plane region that does not include the current obstacle based on the target straight line;

[0097] The candidate safety region determining unit is used to determine a candidate safety region that does not intersect with the obstacle based on a target half-plane region that does not contain the current obstacle.

[0098] Optionally, the to-be-selected safe area determination unit is specifically configured to:

[0099] If the overlapping area between the target half-plane areas corresponding to all obstacles is a non-closed area, a virtual half-plane area that does not include the current virtual obstacle is determined based on the target ellipse after the current rotation and the position information of multiple virtual obstacles, wherein the multiple virtual obstacles enclose a closed area, and the closed area includes all obstacles in the autonomous driving scene; the overlapping area between the target half-plane areas corresponding to all obstacles and the virtual half-plane areas corresponding to all virtual obstacles is determined as a candidate safety area that does not intersect with the obstacles.

[0100] Optionally, the maximum inscribed circle determination module 340 is specifically configured to:

[0101] Taking the constraint condition that the circle determined by the candidate center and the candidate radius is located inside the current candidate safety area, the candidate radius is maximized to determine the target center and target radius of the maximum inscribed circle of the current candidate safety area.

[0102] Optionally, the target security area determination module 350 includes:

[0103] A target distance determination unit, used to determine the target distance between the target circle center corresponding to each selected safety area and the reference position point;

[0104] A target safety area determination unit is used to determine a target safety area corresponding to the reference position point from a plurality of candidate safety areas based on the target distance and the target radius.

[0105] Optionally, the target security area determination unit is specifically configured to:

[0106] Based on the target distance and the target radius, a reference value corresponding to each candidate safety area is determined, wherein the reference value is inversely proportional to the target distance, and the reference value is directly proportional to the target radius; and the candidate safety area with the largest reference value is determined as the target safety area corresponding to the reference position point.

[0107] The security area determination device provided in the embodiment of the present invention can execute the security area determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the security area determination method.

[0108] It is worth noting that in the embodiment of the above-mentioned security area determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0109] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 7 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 7 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0110] like Figure 7 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0111] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0112] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0113] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 (RAM) and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0114] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0115] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0116] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a method for determining a security area provided by any embodiment of the present invention, the method comprising:

[0117] Obtaining reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene;

[0118] Based on the reference position point and the obstacle position information, determining a target ellipse that includes the reference position point and does not intersect with the obstacle;

[0119] Rotating the target ellipse multiple times, and determining a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information;

[0120] Determine the target center and target radius of the maximum inscribed circle of each candidate safety area;

[0121] Based on the target circle center, the target radius and the reference position point, a target safety area corresponding to the reference position point is determined from a plurality of candidate safety areas.

[0122] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the security area determination method provided by any embodiment of the present invention.

[0123] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method for determining a security area provided in any embodiment of the present invention are implemented. The method includes:

[0124] Obtaining reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene;

[0125] Based on the reference position point and the obstacle position information, determining a target ellipse that includes the reference position point and does not intersect with the obstacle;

[0126] Rotating the target ellipse multiple times, and determining a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information;

[0127] Determine the target center and target radius of the maximum inscribed circle of each candidate safety area;

[0128] Based on the target circle center, the target radius and the reference position point, a target safety area corresponding to the reference position point is determined from a plurality of candidate safety areas.

[0129] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0130] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0132] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the security area determination method provided by any embodiment of the present invention.

[0134] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0135] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0136] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a safe area, characterized in that: include: Obtaining reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene; Based on the reference position point and the obstacle position information, determining a target ellipse that includes the reference position point and does not intersect with the obstacle; Rotating the target ellipse multiple times, and determining a candidate safety area that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information; Determine the target center and target radius of the maximum inscribed circle of each candidate safety area; Based on the target circle center, the target radius and the reference position point, a target safety area corresponding to the reference position point is determined from a plurality of candidate safety areas.

2. The method according to claim 1, characterized in that The step of rotating the target ellipse multiple times comprises: The angle of each rotation is determined based on a preset number of rotations, and the target ellipse is rotated clockwise based on the angle of each rotation.

3. The method according to claim 1, characterized in that The step of determining a candidate safety area that does not intersect with an obstacle based on the target ellipse after each rotation and the obstacle position information includes: Based on the target ellipse after the current rotation and the obstacle position information, determine the current ellipse position point and the current obstacle position point that are closest to the target ellipse after the current rotation; Translating the tangent line passing through the current ellipse position point to obtain a target straight line passing through the current obstacle position point, and determining a target half-plane area that does not include the current obstacle based on the target straight line; Based on the target half-plane area that does not contain the current obstacle, a candidate safety area that does not intersect with the obstacle is determined.

4. The method according to claim 3, characterized in that The step of determining a candidate safety area that does not intersect with the obstacle based on a target half-plane area that does not contain the current obstacle includes: If the overlapping area between the target half-plane areas corresponding to all obstacles is a non-closed area, then based on the target ellipse after the current rotation and the position information of multiple virtual obstacles, determine a virtual half-plane area that does not contain the current virtual obstacle, wherein the multiple virtual obstacles enclose a closed area, and the closed area includes all obstacles in the autonomous driving scene; An overlapping area between the target half-plane areas corresponding to all obstacles and the virtual half-plane areas corresponding to all virtual obstacles is determined as a candidate safety area that does not intersect with the obstacles.

5. The method according to claim 1, characterized in that The step of determining the target center and target radius of the maximum inscribed circle of each selected safety area includes: Taking the constraint condition that the circle determined by the candidate center and the candidate radius is located inside the current candidate safety area, the candidate radius is maximized to determine the target center and target radius of the maximum inscribed circle of the current candidate safety area.

6. The method according to claim 1, characterized in that The determining, based on the target circle center, the target radius and the reference position point, from a plurality of candidate safety areas, a target safety area corresponding to the reference position point comprises: Determine the target distance between the target circle center and the reference position point corresponding to each selected safety area; Based on the target distance and the target radius, a target safety area corresponding to the reference position point is determined from a plurality of candidate safety areas.

7. The method according to claim 6, characterized in that The determining, based on the target distance and the target radius, a target safety area corresponding to the reference position point from a plurality of candidate safety areas comprises: Based on the target distance and the target radius, determining a reference value corresponding to each to-be-selected safety area, wherein the reference value is inversely proportional to the target distance, and the reference value is proportional to the target radius; The candidate safety area with the largest reference value is determined as the target safety area corresponding to the reference position point.

8. A safe area determination device, characterized in that: include: A reference position point acquisition module is used to obtain reference position points in the path to be smoothed and obstacle position information in the autonomous driving scene; A target ellipse determination module, configured to determine a target ellipse that includes the reference position point and does not intersect with the obstacle based on the reference position point and the obstacle position information; A module for determining a safe area to be selected, used for rotating the target ellipse multiple times, and determining a safe area to be selected that does not intersect with the obstacle based on the target ellipse after each rotation and the obstacle position information; A maximum inscribed circle determination module is used to determine the target center and target radius of the maximum inscribed circle of each selected safety area; The target safety area determination module is used to determine the target safety area corresponding to the reference position point from multiple candidate safety areas based on the target circle center, the target radius and the reference position point.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the security area determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the security area determination method as described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the security area determination method according to any one of claims 1 to 7.

Images