Method and device for determining detour path of intelligent trolley

Abstract

The invention provides a method and a device for determining a detour path of an intelligent trolley. The method comprises the following steps: acquiring second sensing information of static obstacles acquired by at least one intelligent trolley passing around in response to acquiring first sensing information of static obstacles in front of a driving path sensed by a target intelligent trolley; generating a three-dimensional local contour of the static obstacle in a three-dimensional electronic map based on the first sensing information and second sensing information of the at least one intelligent trolley; and based on the local contour in the three-dimensional electronic map, determining a bypassing path of obstacle avoidance of the target intelligent trolley. The high-reliability detour path is obtained, the success rate of detour is improved, and the operation efficiency of the target intelligent trolley is improved.

Description

Technical Field

[0001] This application relates to the field of navigation technology, and more specifically, to a method, apparatus, medium, and electronic device for determining the detour path of an intelligent vehicle. Background Technology

[0002] Intelligent Guided Vehicles (IGVs) are unmanned transport devices used in automated terminals and smart factories. They achieve autonomous navigation and obstacle avoidance through technologies such as the BeiDou Navigation Satellite System, LiDAR, and visual SLAM. They possess high flexibility, intelligent navigation, and superior performance. IGVs typically follow navigation information provided by QR code strips or matrix QR codes.

[0003] Currently, when an IGV encounters a static obstacle on its route, it stops because it cannot accurately determine the size of the obstacle and therefore cannot determine a detour path. It can only wait for the obstacle to be cleared before continuing. To address this, existing technologies have proposed obstacle avoidance methods for IGVs. However, the incomplete obstacle information hinders the reliability of the detour path, resulting in a low success rate.

[0004] Therefore, this application provides a method for determining the detour path of an intelligent vehicle to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, medium, and electronic device for determining the detour path of an intelligent vehicle, which can solve at least one of the aforementioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of this application, in a first aspect, this application provides a method for determining the detour path of an intelligent vehicle, comprising:

[0007] In response to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and acquiring second perception information of the static obstacles acquired by at least one intelligent vehicle passing by in the vicinity;

[0008] Based on the first and second perception information, a three-dimensional local outline of the static obstacle in the three-dimensional electronic map is generated;

[0009] The obstacle avoidance detour path of the target intelligent vehicle is determined based on the local contours in the three-dimensional electronic map.

[0010] Optionally, determining the obstacle avoidance detour path of the target intelligent vehicle based on the local contours in the three-dimensional electronic map includes:

[0011] The local contour is matched with the global contour of each digital model in the material and equipment digital library to obtain the target digital model with the highest matching degree.

[0012] When the matching degree value of the target digital model is greater than or equal to the preset matching degree threshold, the local contour and the global contour are vertically divided into two local sub-contours and a global sub-contour corresponding to the local sub-contour based on the virtual driving path of the target intelligent vehicle in the three-dimensional electronic map.

[0013] In the three-dimensional electronic map, reliability scores are performed based on the two global sub-contours and their respective local sub-contours to obtain the reliability values ​​of the two local sub-contours.

[0014] The obstacle avoidance detour path of the target intelligent vehicle is determined based on the outer region of the local sub-contour with the highest reliability value among the two local sub-contours.

[0015] Optionally, the step of scoring the reliability of the two local sub-contours based on the two global sub-contours in the three-dimensional electronic map to obtain the reliability values ​​of the two local sub-contours includes:

[0016] In the preset three-dimensional coordinate system where the three-dimensional electronic map is located, the target plane is determined based on the virtual driving path;

[0017] Each global sub-contour and its corresponding local sub-contour are projected onto the target plane to obtain the global connected region of each global sub-contour and the at least one local connected region of the corresponding local sub-contour.

[0018] The reliability value of the corresponding local sub-contour is obtained based on the global connected region of each global sub-contour and the at least one local connected region of the corresponding local sub-contour.

[0019] Optionally, determining the target plane based on the virtual driving path in the preset three-dimensional coordinate system where the three-dimensional electronic map is located includes:

[0020] Determine the path segment in the virtual driving path that divides the two global sub-contours;

[0021] The path segment is projected onto two candidate planes to obtain two projected line segments. The two candidate planes are planes formed by two coordinate axes in the preset three-dimensional coordinate system where the three-dimensional electronic map is located. Both candidate planes include the vertical axis in the preset three-dimensional coordinate system.

[0022] The candidate plane containing the longest projected line segment is determined as the target plane.

[0023] Optionally, obtaining the reliability value of the corresponding local sub-contour based on the globally connected region of each global sub-contour and the at least one locally connected region of the corresponding local sub-contour includes:

[0024] Based on the area of ​​each of the at least one locally connected regions of each local sub-contour, a first total area of ​​the corresponding local sub-contour is obtained, and a second total area of ​​each global sub-contour is calculated.

[0025] Calculate the ratio of the first total area of ​​each local sub-contour to the second total area of ​​the corresponding global sub-contour to obtain the effective area ratio of the corresponding local sub-contour;

[0026] Based on the ratio of the number of at least one locally connected region of each local sub-contour to the total number of all locally connected regions of all local sub-contours, the effective quantity ratio of each local sub-contour is obtained.

[0027] Based on the first sum of the shortest neighbor distances between adjacent local connected regions of each local sub-contour and the second sum of the shortest neighbor distances of all local sub-contours, the ratio of the first sum to the second sum is calculated to obtain the effective distance percentage of each local sub-contour.

[0028] Based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value, the preset effective quantity weight value, and the preset effective distance weight value of the effective distance ratio, the reliability value of the corresponding local sub-contour is obtained.

[0029] Optionally, the reliability value of the corresponding local sub-contour is obtained based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value of the effective area ratio, the preset effective quantity weight value of the effective quantity ratio, and the preset effective distance weight value of the effective distance ratio, including the following formula:

[0030] R = c1 x P s xc2x(1-P) n )ⅹc3ⅹ(1-P d );

[0031] Where R represents the reliability value of the local sub-profile, and P s P represents the effective area percentage of the local sub-contour. n P represents the effective quantity percentage of the local sub-contours. dc1 represents the effective distance percentage of the local sub-contour, c2 represents the preset effective area weight value of the effective area percentage, c3 represents the preset effective quantity weight value of the effective quantity percentage, and c3 represents the preset effective distance weight value of the effective distance percentage.

[0032] Optionally, before obtaining the reliability value of the corresponding local sub-contour based on the globally connected region of each global sub-contour and the at least one locally connected region of the corresponding local sub-contour, the method further includes:

[0033] When any local sub-contour includes only two local connected regions in at least one local connected region, determine the shortest adjacent distance value and the interval region between the two local connected regions.

[0034] When the shortest adjacent distance value is less than or equal to a preset adjacent distance threshold, and the interval area is biased towards one side of the target intelligent vehicle, the adjustment position of the target intelligent vehicle is determined;

[0035] When the target intelligent vehicle obtains the third perception information fed back at the adjusted position, the any local sub-contour is repaired based on the third perception information.

[0036] The repaired local sub-contour is projected onto the target plane to obtain at least one locally connected region of the local sub-contour.

[0037] Optionally, determining the obstacle avoidance detour path of the target intelligent vehicle based on the outer region of the local sub-contour with the highest reliability value among the two local sub-contours includes:

[0038] Determine the maximum reliability value among the reliability values ​​of the two local sub-profiles;

[0039] When the maximum reliability value is greater than or equal to the preset reliability threshold, the obstacle avoidance detour path of the target intelligent vehicle is determined based on the outer region where the local sub-contour corresponding to the maximum reliability value is located.

[0040] According to a specific embodiment of this application, in a second aspect, this application provides a device for determining the detour path of an intelligent vehicle, comprising:

[0041] The response unit is configured to respond to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and to acquire second perception information of the static obstacles acquired by at least one intelligent vehicle passing by.

[0042] The contour generation unit is used to generate a three-dimensional local contour of the static obstacle in a three-dimensional electronic map based on the first perception information and the second perception information.

[0043] The path determination unit is used to determine the obstacle avoidance detour path of the target intelligent vehicle based on the local contours in the three-dimensional electronic map.

[0044] According to a specific embodiment of this application, in a third aspect, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method for determining the detour path of an intelligent vehicle as described in any of the preceding claims.

[0045] According to a specific embodiment of this application, in a fourth aspect, this application provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method for determining the detour path of an intelligent vehicle as described in any of the preceding claims.

[0046] Compared with the prior art, the above-described solutions of this application have at least the following beneficial effects:

[0047] This application provides a method, apparatus, medium, and electronic device for determining the detour path of an intelligent vehicle. The application responds to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's travel path, and second perception information of the static obstacles acquired by at least one other intelligent vehicle passing by; based on the first perception information and the second perception information of each of the at least one intelligent vehicle, a three-dimensional local contour of the static obstacle is generated in a three-dimensional electronic map; and based on the local contour in the three-dimensional electronic map, a detour path for obstacle avoidance of the target intelligent vehicle is determined. This results in a highly reliable detour path, improves the success rate of detours, and increases the operating efficiency of the target intelligent vehicle. Attached Figure Description

[0048] Figure 1 A flowchart illustrating a method for determining the detour path of an intelligent vehicle according to an embodiment of this application is shown;

[0049] Figure 2 A block diagram of a device for determining the detour path of an intelligent vehicle according to an embodiment of this application is shown. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0052] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0053] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0054] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0055] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0056] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0057] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0058] The embodiments provided in this application are embodiments of a method for determining the detour path of an intelligent vehicle.

[0059] The following is combined Figure 1 The embodiments of this application will be described in detail.

[0060] Step S101: In response to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and acquiring second perception information of the static obstacles acquired by at least one intelligent vehicle passing by.

[0061] The intelligent vehicle can be an Automated Guided Vehicle (AGV) or an In-Ground Vehicle (IGV).

[0062] The target intelligent vehicle includes a variety of perception sensors, such as LiDAR, binocular cameras, depth cameras and / or ultrasonic sensors.

[0063] LiDAR (Light Detection and Ranging) is a laser detection and ranging system that integrates laser, GPS, and inertial measurement technologies. Unaffected by ambient light, LiDAR can perceive environmental information in real time and obtain accurate and reliable 3D data models of the external environment through frame point clouds.

[0064] Binocular cameras simulate human binocular vision by using two cameras to simultaneously capture images and calculate parallax, achieving three-dimensional spatial depth perception based on the principle of triangulation.

[0065] The data acquired by the depth camera accurately determines the distance of each point in the image from the camera. Adding this distance to the (x, y) coordinates of that point in the 2D image allows us to obtain the 3D spatial coordinates of each point. These 3D coordinates can then be used to reconstruct the real-world scene, enabling applications such as scene modeling.

[0066] An ultrasonic sensor is a sensor that converts ultrasonic signals into other energy signals (usually electrical signals), and its modeling principle is similar to that of lidar.

[0067] Multiple sensing sensors perceive the surrounding environment in real time. Both the first and second sensing information include: identified static obstacles, their location, and approximate outlines. Simultaneously, the target intelligent vehicle also includes a positioning module, capable of accurately acquiring its real-time location and driving status, such as speed and direction.

[0068] The target intelligent vehicle performs multiple pose detections on obstacles in a short period of time. When the pose of an obstacle does not change, it confirms that the obstacle is static, thus eliminating dynamic interference.

[0069] When the target intelligent vehicle senses a static obstacle in its path, it stops driving and uploads the initial sensing information.

[0070] The at least one intelligent vehicle passing by, for example, an intelligent vehicle traveling in the opposite direction along a parallel path, collects second perception information of static obstacles through its own perception sensors and uploads it.

[0071] If the second sensing information cannot be obtained, the target intelligent vehicle will wait in place until the static obstacle is removed to ensure the safe operation of the target intelligent vehicle.

[0072] Step S102: Generate a three-dimensional local outline of the static obstacle in the three-dimensional electronic map based on the first perception information and the second perception information.

[0073] A 3D electronic map is an electronic map built on a preset 3D coordinate system. The preset 3D coordinate system includes the world coordinate system.

[0074] For example, when a lidar irradiates the surface of an object, the reflected laser carries information such as orientation and distance. If the laser beam is scanned along a certain trajectory, the information of the reflected laser points will be recorded while scanning. Because the scanning is extremely precise, a large number of laser points can be obtained, thus forming a point cloud. Lidar collects point clouds of the surrounding environment, including point clouds of static obstacles. The point cloud of the surrounding environment can be matched with the point cloud map in a three-dimensional electronic map to determine the position of the static obstacle. The point cloud of the static obstacle can be used to construct the three-dimensional local outline of the static obstacle in the three-dimensional electronic map.

[0075] Due to limitations in the acquisition of first and second perception information—for example, the target intelligent vehicle can only collect frontal information of static obstacles, while an oncoming intelligent vehicle can collect back and side information of static obstacles—the first and second perception information cannot completely construct the entire outline of the target intelligent vehicle. A portion of the outline is missing, resulting in a partial 3D outline in the 3D electronic map.

[0076] Step S103: Determine the obstacle avoidance detour path of the target intelligent vehicle based on the local contour in the three-dimensional electronic map.

[0077] Although the target intelligent vehicle may have multiple detour routes, they can be summarized into two detour routes: one is to detour around the static obstacle from the left; the other is to detour around the static obstacle from the right.

[0078] The detour path can be understood as the path with high reliability obtained from the two detour paths, which improves the success rate of detour and improves the operating efficiency of the target intelligent vehicle.

[0079] Once a reliable local contour is obtained, the method for determining the detour path is the same as the method for determining the detour path through the global contour. Both methods determine the detour path by determining the environment around the contour. Please refer to existing technologies; they will not be elaborated here.

[0080] In some specific embodiments, determining the obstacle avoidance detour path of the target intelligent vehicle based on the local contours in the three-dimensional electronic map includes:

[0081] Step S103-1: Match the local contour with the global contour of each digital model in the material and equipment digital library to obtain the target digital model with the highest matching degree value.

[0082] The global contour and the local contour have the same pose.

[0083] The pose includes position and orientation angle.

[0084] In other words, the global contour is placed in the position of the local contour, and the direction angles of the global contour and the local contour are the same. By comparing it with the local contour, the target digital model is the digital model with the highest matching degree.

[0085] The digital models include: material digital models, equipment digital models, and intelligent vehicle digital models. This application's embodiments are not limited to these; in short, they include all objects used in the smart factory. These models originate from the digital models designed by the smart factory's design department.

[0086] Step S103-2: When the matching degree value of the target digital model is greater than or equal to the preset matching degree threshold, the local contour and the global contour are vertically divided into two local sub-contours and a global sub-contour corresponding to the local sub-contour based on the virtual driving path of the target intelligent vehicle in the three-dimensional electronic map.

[0087] Only when the matching degree value of the target digital model is greater than or equal to the preset matching degree threshold can the obstacle avoidance candidate path be determined; otherwise, wait for further improvement of the local contour or manual intervention.

[0088] The virtual driving path is the mapping path of the target intelligent vehicle's driving path in a 3D electronic map. The virtual driving path forms a vertical segmentation plane perpendicular to the horizontal plane of the 3D electronic map (i.e., the vertical segmentation plane includes the virtual driving path), dividing the local and global contours of the same pose into two. The vertical segmentation plane represents the spatial position of the driving path. Both the local and global sub-contours are 3D. The virtual driving path includes two key points: the two intersection points of the local contour's projection onto the horizontal plane and the virtual driving path, namely the first intersection point and the second intersection point. The first intersection point represents the intersection of the projection of the head of the local sub-contour onto the horizontal plane and the virtual driving path, which is closer to the target intelligent vehicle. The second intersection point represents the intersection of the projection of the tail of the local sub-contour onto the horizontal plane and the virtual driving path, which is farther from the target intelligent vehicle. Therefore, the two local sub-contours are also the parts that each of the left and right bypass paths detours. The process of analyzing the integrity of the local sub-contours is also the process of analyzing the reliability of the bypass paths.

[0089] Local contours and global contours are in one-to-one correspondence at the same pose. Similarly, local sub-contours on each side of the virtual driving path are also in one-to-one correspondence with global sub-contours.

[0090] Step S103-3: In the three-dimensional electronic map, the reliability of the two local sub-contours is scored based on the two global sub-contours to obtain the reliability values ​​of the two local sub-contours respectively.

[0091] This specific embodiment determines the reliability of the two local sub-contours by scoring their reliability using two global sub-contours, which in turn determines the reliability of the two detour routes.

[0092] In some specific embodiments, the step of scoring the reliability of the two local sub-contours based on the two global sub-contours in the three-dimensional electronic map to obtain the reliability values ​​of the two local sub-contours respectively includes:

[0093] Step S103-21: In the preset three-dimensional coordinate system where the three-dimensional electronic map is located, determine the target plane based on the virtual driving path.

[0094] The target plane includes the vertical axis in the preset three-dimensional coordinate system.

[0095] In some specific embodiments, in order to reduce data centralization, determining the target plane based on the virtual driving path in the preset three-dimensional coordinate system where the three-dimensional electronic map is located includes:

[0096] Step S103-211: Determine the path segment in the virtual driving path that divides the two global sub-contours.

[0097] Determine the path segments in the virtual driving path that divide the two global sub-contours.

[0098] The path segment is the section in the horizontal projection of the virtual driving path that intersects with the horizontal projection of the global contour.

[0099] Steps S103-212: Project the path segment onto the two candidate planes respectively to obtain two projected line segments.

[0100] The two candidate planes are formed by the two coordinate axes in the preset three-dimensional coordinate system where the three-dimensional electronic map is located, and both candidate planes include the vertical axis in the preset three-dimensional coordinate system.

[0101] Step S103-213: Determine the candidate plane containing the longest projected line segment as the target plane.

[0102] In this specific embodiment, the target plane is determined based on the direction of the path segment to reduce data concentration and improve data identification. The target plane includes a vertical axis in a preset three-dimensional coordinate system to enable the analysis of lateral information of static obstacles.

[0103] Step S103-22: Project each global sub-contour and its corresponding local sub-contour onto the target plane to obtain the global connected region of each global sub-contour and the at least one local connected region of the corresponding local sub-contour.

[0104] The global connected region refers to the connected region of the global sub-contour.

[0105] The locally connected region refers to the connected region of a local sub-contour.

[0106] The connected region refers to a region in an image that consists of pixels with the same pixel value and adjacent positions.

[0107] Steps S103-23: Obtain the reliability value of the corresponding local sub-contour based on the global connected region of each global sub-contour and the at least one local connected region of the corresponding local sub-contour.

[0108] By transforming 3D information onto a target plane including the vertical axis of a preset 3D coordinate system, the 3D information is converted into 2D information, simplifying the complexity of the analysis and improving its reliability. Furthermore, each local sub-contour on each side of the path segment has a global sub-contour as the basis for the analysis, making the analysis results objective, effective, and reliable.

[0109] In some specific embodiments, obtaining the reliability value of the corresponding local sub-contour based on the globally connected region of each global sub-contour and the at least one locally connected region of the corresponding local sub-contour includes:

[0110] Steps S103-291: Based on the area of ​​each of the at least one locally connected regions of each local sub-contour, obtain the first total area of ​​the corresponding local sub-contour, and calculate the second total area of ​​each global sub-contour.

[0111] For example, the areas of each of the at least one locally connected regions of each local sub-contour are added together to obtain a first total area of ​​the corresponding local sub-contour; the areas of each global sub-contour are added together to obtain a second total area.

[0112] Step S103-292: Calculate the ratio of the first total area of ​​each local sub-contour to the second total area of ​​the corresponding global sub-contour, and obtain the effective area ratio of the corresponding local sub-contour.

[0113] The effective area percentage represents the completeness of a local sub-contour relative to its corresponding global sub-contour. A higher effective area percentage indicates higher completeness and a higher reliability.

[0114] Steps S103-293: Based on the ratio of the number of at least one locally connected region of each local sub-contour to the total number of all locally connected regions of all local sub-contours, obtain the effective quantity ratio of each local sub-contour.

[0115] The effective quantity percentage represents the degree of fragmentation of locally connected regions within a local sub-contour. A higher effective quantity percentage indicates a higher degree of fragmentation and a lower reliability value.

[0116] Steps S103-294: Based on the first sum of the shortest neighbor distances between adjacent local connected regions of each local sub-contour and the second sum of all shortest neighbor distances of all local sub-contours, calculate the ratio of the first sum to the second sum to obtain the effective distance percentage of each local sub-contour.

[0117] The effective distance percentage represents the concentration of locally connected regions within a local sub-contour. A higher effective distance percentage indicates a lower concentration of locally connected regions within the local sub-contour, resulting in a lower reliability value.

[0118] Steps S103-295: Based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value of the effective area ratio, the preset effective quantity weight value of the effective quantity ratio, and the preset effective distance weight value of the effective distance ratio, obtain the reliability value of the corresponding local sub-contour.

[0119] In this specific embodiment, steps S103-292, S103-293 and S103-294 are not distinguished by the order of execution. The three steps can be executed simultaneously or in stages. This embodiment of the application is not limited to this.

[0120] This specific embodiment comprehensively scores the reliability of each local sub-contour by considering the area, number, and adjacent distance of locally connected regions, thus transforming the contour information of the local sub-contour into quantifiable information. The reliability rate value characterizes the completeness of information within the local sub-contour, thereby determining the objectivity, effectiveness, and reliability of the generated detour path and improving the scientific rigor of the generated detour path.

[0121] In some specific embodiments, the reliability value of the corresponding local sub-contour is obtained based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value of the effective area ratio, the preset effective quantity weight value of the effective quantity ratio, and the preset effective distance weight value of the effective distance ratio, including the following formula:

[0122] R = c1 x P s xc2x(1-P) n )ⅹc3ⅹ(1-P d );

[0123] Where R represents the reliability value of the local sub-profile, and P s P represents the effective area percentage of the local sub-contour. n P represents the effective quantity percentage of the local sub-contours. d c1 represents the effective distance percentage of the local sub-contour, c2 represents the preset effective area weight value of the effective area percentage, c3 represents the preset effective quantity weight value of the effective quantity percentage, and c3 represents the preset effective distance weight value of the effective distance percentage.

[0124] In this specific embodiment, the effective area ratio of a local sub-contour is positively correlated with the reliability rate; the effective quantity ratio of a local sub-contour is negatively correlated with the reliability rate; and the effective distance ratio of a local sub-contour is positively correlated with the reliability rate. That is, the larger the effective area ratio, the higher the reliability rate; the smaller the effective quantity ratio, the higher the reliability rate; and the higher the effective distance ratio, the lower the reliability rate.

[0125] Step S103-4: Determine the obstacle avoidance detour path of the target intelligent vehicle based on the outer region of the local sub-contour with the largest reliability value among the two local sub-contours.

[0126] In some specific embodiments, determining the obstacle avoidance detour path of the target intelligent vehicle based on the outer region of the local sub-contour with the highest reliability value among the two local sub-contours includes:

[0127] Step S103-41: Determine the maximum reliability value among the reliability values ​​of the two local sub-contours.

[0128] Step S103-42: When the maximum reliability value is greater than or equal to the preset reliability threshold, the obstacle avoidance detour path of the target intelligent vehicle is determined based on the outer region where the local sub-contour corresponding to the maximum reliability value is located.

[0129] This specific embodiment limits the maximum reliability value by setting a preset reliability rate threshold. Even at the maximum reliability rate, if the value is too small, a candidate path cannot be determined in the outer region where the local sub-contour corresponding to the maximum reliability rate value is located. This avoids blindly detouring around the outer region where static obstacle information is incomplete, which introduces unpredictability, ensures the success rate of detouring, and improves the operating efficiency of the target intelligent vehicle.

[0130] In some specific embodiments, before obtaining the reliability value of the corresponding local sub-contour based on the globally connected region of each global sub-contour and the at least one locally connected region of the corresponding local sub-contour, the method further includes:

[0131] Step S103-28-1: When any local sub-contour includes only two local connected regions in at least one local connected region, determine the shortest adjacent distance value and the interval region between the two local connected regions.

[0132] Step S103-28-2: When the shortest adjacent distance value is less than or equal to a preset adjacent distance threshold, and the interval area is biased towards the target intelligent vehicle, the adjustment position of the target intelligent vehicle is determined.

[0133] Step S103-28-3: When the target intelligent vehicle obtains the third perception information fed back at the adjusted position, repair any local sub-contour based on the third perception information.

[0134] Step S103-28-4: Project the repaired local sub-contour onto the target plane to obtain at least one locally connected region of the local sub-contour.

[0135] In this specific embodiment, if the local sub-contour includes only two locally connected regions, and the gap between the two locally connected regions is closer to the target intelligent vehicle, for example, the two locally connected regions are projected onto the target axis (excluding the vertical axis) in the target plane to obtain a first projection line segment and a second projection line segment. The first position value closest to the origin and the second position value farthest from the origin are determined in the first and second projection line segments, and a first intermediate value between the first and second position values ​​is calculated. The gap is projected onto the target axis to obtain a third projection line segment. A second intermediate value is determined at the midpoint of the third projection line segment. When the second intermediate value is closer to the projection position of the target intelligent vehicle on the target axis than the first intermediate value, the gap between the two locally connected regions is closer to the target intelligent vehicle. By adjusting the observation position of the target intelligent vehicle—for example, by moving the target intelligent vehicle laterally a certain distance away from the driving path to the adjusted position—and observing and perceiving the target intelligent vehicle from a different angle, third-party perception information is obtained. Furthermore, information is supplemented to the local sub-contour on the observed side. For instance, the target intelligent vehicle collects point clouds of the surrounding environment at the adjusted position, including new point clouds of static obstacles. These new point clouds of static obstacles are then fused with the original local contour to generate a new local sub-contour. This further improves the integrity rate of the local sub-contour, thereby increasing the reliability of the local sub-contour on that side.

[0136] This application embodiment responds to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and acquires second perception information of the static obstacles acquired by at least one intelligent vehicle passing by; based on the first perception information and the second perception information of each of the at least one intelligent vehicle, a three-dimensional local contour of the static obstacle is generated in a three-dimensional electronic map; based on the local contour in the three-dimensional electronic map, a detour path for obstacle avoidance of the target intelligent vehicle is determined. This results in a highly reliable detour path, improves the success rate of detours, and enhances the operating efficiency of the target intelligent vehicle.

[0137] This application also provides an apparatus embodiment that follows the above embodiments, used to implement the method steps described in the above embodiments. The interpretation of the same names is the same as that in the above embodiments, and the same technical effects are achieved. Therefore, it will not be repeated here.

[0138] like Figure 2 As shown, this application provides a device 200 for determining the detour path of an intelligent vehicle, comprising:

[0139] The response unit 201 is configured to respond to acquiring first perception information of static obstacles in front of the target intelligent vehicle's driving path, and to acquiring second perception information of the static obstacles acquired by at least one intelligent vehicle passing by.

[0140] The contour generation unit 202 is used to generate a three-dimensional local contour of the static obstacle in a three-dimensional electronic map based on the first perception information and the second perception information.

[0141] The path determination unit 203 is used to determine the obstacle avoidance detour path of the target intelligent vehicle based on the local contour in the three-dimensional electronic map.

[0142] This application embodiment responds to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and acquires second perception information of the static obstacles acquired by at least one intelligent vehicle passing by; based on the first perception information and the second perception information of each of the at least one intelligent vehicle, a three-dimensional local contour of the static obstacle is generated in a three-dimensional electronic map; based on the local contour in the three-dimensional electronic map, a detour path for obstacle avoidance of the target intelligent vehicle is determined. This results in a highly reliable detour path, improves the success rate of detours, and enhances the operating efficiency of the target intelligent vehicle.

[0143] Example 3

[0144] This embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method steps described in the above embodiment.

[0145] Example 4

[0146] This application provides a non-volatile computer storage medium storing computer-executable instructions that can perform the steps described in the above embodiments.

[0147] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0148] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining a detour path of an intelligent vehicle, characterized in that, The method comprises: obtaining first perception information of a static obstacle in front of a target intelligent vehicle on a driving path, and obtaining second perception information of the static obstacle obtained by at least one intelligent vehicle passing by; generating a three-dimensional local profile of the static obstacle in a three-dimensional electronic map based on the first perception information and the second perception information; determining a detour path for the target intelligent vehicle to avoid the static obstacle based on the three-dimensional local profile in the three-dimensional electronic map.

2. The method of claim 1, wherein, The method of determining the detour path for the target intelligent vehicle to avoid the static obstacle based on the three-dimensional local profile in the three-dimensional electronic map comprises: matching the local profile with a global profile of each digital model in a digital library of material equipment to obtain a target digital model with the highest matching degree value; when the matching degree value of the target digital model is greater than or equal to a preset matching degree threshold, vertically dividing the local profile and the global profile into two local sub-profiles and global sub-profiles corresponding to the local sub-profiles based on a virtual driving path of the target intelligent vehicle in the three-dimensional electronic map; in the three-dimensional electronic map, scoring the reliability of the two global sub-profiles and the corresponding local sub-profiles respectively to obtain a reliability value of each of the two local sub-profiles; determining the detour path for the target intelligent vehicle to avoid the static obstacle based on an outer region where the local sub-profile with the maximum reliability value in the two local sub-profiles is located.

3. The method of claim 2, wherein, The method of scoring the reliability of the two global sub-profiles and the corresponding local sub-profiles respectively in the three-dimensional electronic map to obtain a reliability value of each of the two local sub-profiles comprises: determining a target plane in a preset three-dimensional coordinate system based on the virtual driving path; projecting each global sub-profile and the corresponding local sub-profile onto the target plane to obtain a global connected region of each global sub-profile and the at least one local connected region of the corresponding local sub-profile; obtaining a reliability value of the corresponding local sub-profile based on the global connected region of each global sub-profile and the at least one local connected region of the corresponding local sub-profile.

4. The method of claim 3, wherein, The method of determining a target plane in a preset three-dimensional coordinate system based on the virtual driving path comprises: determining a path segment in the virtual driving path that divides the two global sub-profiles; projecting the path segment onto two candidate planes respectively to obtain two projection line segments, wherein the two candidate planes are respectively planes formed by two coordinate axes in the preset three-dimensional coordinate system, and the two candidate planes both include a vertical axis in the preset three-dimensional coordinate system; determining a candidate plane where the longest projection line segment is located as the target plane.

5. The method of claim 3, wherein, The method of obtaining a reliability value of the corresponding local sub-profile based on the global connected region of each global sub-profile and the at least one local connected region of the corresponding local sub-profile comprises: obtaining a first total area of the corresponding local sub-profile based on the area of the at least one local connected region of each local sub-profile, and calculating a second total area of each global sub-profile; Calculate the ratio of the first total area of ​​each local sub-contour to the second total area of ​​the corresponding global sub-contour to obtain the effective area ratio of the corresponding local sub-contour; Based on the ratio of the number of at least one locally connected region of each local sub-contour to the total number of all locally connected regions of all local sub-contours, the effective quantity ratio of each local sub-contour is obtained. Based on the first sum of the shortest neighbor distances between adjacent local connected regions of each local sub-contour and the second sum of the shortest neighbor distances of all local sub-contours, the ratio of the first sum to the second sum is calculated to obtain the effective distance percentage of each local sub-contour. Based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value, the preset effective quantity weight value, and the preset effective distance weight value of the effective distance ratio, the reliability value of the corresponding local sub-contour is obtained.

6. The method of claim 5, wherein, The reliability value of the corresponding local sub-contour is obtained based on the effective area ratio, effective quantity ratio, and effective distance ratio of each local sub-contour, as well as the preset effective area weight value, the preset effective quantity weight value, and the preset effective distance weight value of the effective distance ratio, including the following formula: R = c1 x P s x c2 x (1 - P n ) x c3 x (1 - P d ); wherein R represents a reliability value of a local sub-profile, P s represents an effective area ratio value of the local sub-profile, P n represents an effective quantity ratio value of the local sub-profile, P d represents an effective distance ratio value of the local sub-profile, c1 represents a preset effective area weight value of the effective area ratio value, c2 represents a preset effective quantity weight value of the effective quantity ratio value, and c3 represents a preset effective distance weight value of the effective distance ratio value.

7. The method of claim 3, wherein, Before obtaining the reliability value of the corresponding local sub-contour based on the global connected region of each global sub-contour and the at least one local connected region of the corresponding local sub-contour, the method further includes: When any local sub-contour includes only two local connected regions in at least one local connected region, determine the shortest adjacent distance value and the interval region between the two local connected regions. When the shortest adjacent distance value is less than or equal to a preset adjacent distance threshold, and the interval area is biased towards one side of the target intelligent vehicle, the adjustment position of the target intelligent vehicle is determined; When the target intelligent vehicle obtains the third perception information fed back at the adjusted position, the any local sub-contour is repaired based on the third perception information. The repaired local sub-contour is projected onto the target plane to obtain at least one locally connected region of the local sub-contour.

8. The method of claim 2, wherein, The step of determining the obstacle avoidance detour path of the target intelligent vehicle based on the outer region of the local sub-contour with the highest reliability value among the two local sub-contours includes: Determine the maximum reliability value among the reliability values ​​of the two local sub-profiles; When the maximum reliability value is greater than or equal to the preset reliability threshold, the obstacle avoidance detour path of the target intelligent vehicle is determined based on the outer region where the local sub-contour corresponding to the maximum reliability value is located.

9. A device for determining a detour path of an intelligent vehicle, characterized in that include: The response unit is configured to respond to acquiring first perception information of static obstacles ahead of the target intelligent vehicle's driving path, and to acquire second perception information of the static obstacles acquired by at least one intelligent vehicle passing by. a contour generation unit configured to generate a local contour of the static obstacle in three dimensions in a three-dimensional electronic map based on the first perception information and the second perception information; a path determination unit configured to determine a detour path for the target intelligent vehicle to avoid the static obstacle based on the local contour in the three-dimensional electronic map.

10. An electronic device, comprising: comprise: one or more processors; a memory device for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1 to 7.

Images