Vehicle positioning method, device, equipment, storage medium and program product

Abstract

The embodiment of the invention relates to a vehicle positioning method and device, equipment, a storage medium and a program product. The method comprises the following steps: determining a conversion pose of a front vehicle under a physical coordinate system of a rear vehicle according to a first global pose of the front vehicle and a second global pose of the rear vehicle; acquiring vehicle data sensed by a rear vehicle, detecting the vehicle data according to the conversion pose, and determining a hanging box of the front vehicle and a detection pose of the hanging box in the vehicle data; according to the detection pose and the geometric position relation between the head of the front vehicle and the hanging box, the head global pose of the head is determined; and determining a target global pose of the front vehicle according to the vehicle head global pose. The method can reduce the vehicle positioning cost.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of vehicle tracking technology, and in particular, to a vehicle positioning method, device, equipment, storage medium and program product. Background Art

[0002] Vehicle formation autonomous driving refers to a dynamic formation of a convoy for autonomous driving, where multiple vehicles are arranged longitudinally and a certain distance is maintained between each adjacent vehicle. The vehicle closer to the front of each adjacent vehicle can be called the front vehicle, and the other vehicle can be called the rear vehicle. Generally, during the process of vehicle formation autonomous driving, a high degree of positioning consistency is required between the front vehicle and the rear vehicle, so that the rear vehicle can accurately follow the front vehicle for autonomous driving.

[0003] In the related art, in order to ensure the consistency of positioning between the front vehicle and the rear vehicle, a global positioning system, a map navigation system and various environmental sensors (such as lidar, cameras, etc.) are usually installed on both the front vehicle and the rear vehicle to locate the front vehicle and the rear vehicle to ensure the consistency of positioning between the front vehicle and the rear vehicle.

[0004] However, the above technology may cause the problem of high positioning cost. Summary of the invention

[0005] The embodiments of the present disclosure provide a vehicle positioning method, apparatus, device, storage medium and program product, which can be used to reduce the cost of vehicle positioning.

[0006] In a first aspect, an embodiment of the present disclosure provides a vehicle positioning method, the method comprising:

[0007] Determine a transformed posture of the front vehicle in a physical coordinate system of the rear vehicle according to a first global posture of the front vehicle and a second global posture of the rear vehicle;

[0008] The vehicle data sensed by the rear vehicle is detected and processed according to the converted posture, and the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data are determined;

[0009] Determine the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box;

[0010] The target global pose of the leading vehicle is determined based on the global pose of the front vehicle.

[0011] In a second aspect, an embodiment of the present disclosure provides a vehicle positioning device, the device comprising:

[0012] A first determination module is used to determine a transformed posture of the front vehicle in a physical coordinate system of the rear vehicle according to a first global posture of the front vehicle and a second global posture of the rear vehicle;

[0013] A detection module is used to detect and process the vehicle data sensed by the rear vehicle according to the converted posture, and determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data;

[0014] The second determination module is used to determine the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box;

[0015] The positioning module is used to determine the target global posture of the preceding vehicle based on the global posture of the vehicle head.

[0016] In a third aspect, an embodiment of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method of the first aspect is implemented when the processor executes the computer program.

[0017] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method of the first aspect described above is implemented.

[0018] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which implements the method of the first aspect when executed by a processor.

[0019] The vehicle positioning method, device, equipment, storage medium and program product provided by the embodiments of the present disclosure determine the conversion posture of the front vehicle in the physical coordinate system of the rear vehicle according to the first global posture of the front vehicle and the second global posture of the rear vehicle, and detect and process the vehicle data sensed by the rear vehicle according to the conversion posture to determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data, and then determine the head global posture of the front vehicle according to the detection posture of the hanging box and the geometric position relationship between the front vehicle and the hanging box, and determine the target posture of the front vehicle based on the head global posture. In this method, since the front vehicle only needs to send its own global posture detected to the rear vehicle, the rear vehicle can comprehensively calculate the global posture of the front vehicle based on this combined with its own perception data to achieve consistency in positioning the front and rear vehicles, so that the front vehicle itself does not need to use multiple types of sensors for perception to achieve front and rear vehicle positioning, so that the front vehicle can remove some sensors, so that a part of the positioning cost can be saved in the front and rear vehicle positioning process. At the same time, since the rear vehicle can calculate the global pose of the front vehicle's front end through the front vehicle's perceived data, and comprehensively solve the global pose of the front vehicle based on the global pose detected by the front vehicle itself, the considered data is relatively large and rich, so the global pose of the front vehicle obtained by the rear vehicle is more accurate, so that the rear vehicle can accurately follow the front vehicle, thereby improving the consistency of the positioning of the front and rear vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0021] Figure 2 A schematic diagram of a vehicle positioning method according to an embodiment;

[0022] Figure 3 A schematic flow chart of a vehicle positioning method in another embodiment;

[0023] Figure 4 A schematic flow chart of a vehicle positioning method in another embodiment;

[0024] Figure 5 This is an example diagram of detecting the front vehicle box angle in another embodiment;

[0025] Figure 6 is a flowchart of a vehicle positioning method in another embodiment;

[0026] Figure 7 is a detailed flow chart of a vehicle positioning method in another embodiment;

[0027] Figure 8 FIG. 4 is a structural block diagram of a vehicle positioning device in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure more clear, the embodiments of the present disclosure are further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present disclosure and are not used to limit the embodiments of the present disclosure.

[0029] First, before specifically introducing the technical solution of the embodiment of the present disclosure, the technical background or technical evolution context based on the embodiment of the present disclosure is introduced. Generally, in the field of vehicle formation automatic driving, there are two current technical backgrounds: one is that the front and rear vehicles do not communicate, and the rear vehicle directly detects and tracks the front vehicle and calculates the running trajectory of the front vehicle; in this method, since the rear vehicle cannot obtain the positioning or motion information of the front vehicle, it can only rely on the observation information of the vehicle to calculate the running trajectory of the front vehicle, which will cause a lot of noise in the front vehicle trajectory calculation; on the other hand, during the driving of the truck convoy, the rear vehicle can basically only see the front vehicle trailer, and purely relying on observation cannot accurately calculate the overall truck model of the front vehicle, resulting in errors in the front vehicle trajectory calculation. The other is that the global positioning system, map navigation system and various environmental sensors are installed on the front and rear vehicles, and then the front and rear vehicles are respectively positioned in the global coordinate system or the map coordinate system, and then the positioning results are communicated to each other; in this method, since there are high requirements for the positioning accuracy of the front and rear vehicles, the positioning relying only on the satellite navigation system cannot meet the requirements, and the front and rear vehicles are required to be equipped with environmental sensors such as laser radar or camera, and high-precision maps are pre-established for positioning. This increases the cost of sensors on the one hand, and on the other hand requires the establishment of high-precision maps in advance for all sections of the road to be traveled, which is difficult to implement on a large scale. It can be seen that the current technologies all have certain problems. Based on this, the embodiments of the present disclosure provide a vehicle positioning method, device, equipment, storage medium and program product that can solve the above technical problems. In addition, it should be noted that the applicant has put in a lot of creative work in determining the problems existing in the above-mentioned different technologies and the technical solutions introduced in the following embodiments.

[0030] The technical solutions involved in the embodiments of the present disclosure are introduced below in combination with the scenarios to which the embodiments of the present disclosure are applied.

[0031] The vehicle positioning method provided by the embodiment of the present disclosure can be applied to a computer device, which can be a terminal. The internal structure diagram thereof can be as follows: Figure 1As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a vehicle positioning method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0032] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0033] In one embodiment, Figure 2 As shown, a vehicle positioning method is provided, which is applied to Figure 1 Taking the computer device in the example as an example, the method may include the following steps:

[0034] S202: Determine a transformed posture of the front vehicle in a physical coordinate system of the rear vehicle according to the first global posture of the front vehicle and the second global posture of the rear vehicle.

[0035] Among them, a global positioning system can be set on both the front vehicle and the rear vehicle, and the global positioning system can be used to collect the real-time global position and posture of the corresponding vehicle in real time. The global positioning system here can be, for example, a satellite navigation system, or a positioning system based on high-precision map matching, etc.

[0036] In this step, after the front and rear vehicles are powered on, initialization processing can be performed first, specifically including: the front vehicle can collect its own global posture in real time through the global positioning system installed on the front vehicle, for example, the global posture obtained at the current moment can be recorded as the first global posture, and then the first global posture can be sent to the communication module on the rear vehicle through the communication module on the front vehicle, so that the rear vehicle can receive the first global posture of the front vehicle for initialization processing. After the rear vehicle obtains the first global posture of the front vehicle, it can also collect its own global posture in real time through the global positioning system installed on the rear vehicle, for example, the global posture obtained at the current moment can be recorded as the second global posture.

[0037] It should be noted that the global poses collected by the front and rear vehicles can be, for example, poses in the global coordinate system. Usually, the global coordinate system and the physical coordinate system of the vehicle itself can be converted, for example, the global poses of each vehicle can be converted to their respective physical coordinate systems. Here, the physical coordinate system of each vehicle can be set according to actual conditions, for example, it can be a coordinate system established with the center of the vehicle as the origin and the length, width and height of the vehicle body as the three coordinate system directions.

[0038] Since the physical coordinate system where the front vehicle is located is different from the physical coordinate system where the rear vehicle is located, in order to facilitate the positioning consistency of the front and rear vehicles, the rear vehicle can convert the first global pose of the front vehicle to the physical coordinate system where the rear vehicle is located. In the specific conversion, for example, the front vehicle can also send the relevant parameters of its physical coordinate system to the rear vehicle, and the rear vehicle first converts the first global pose of the front vehicle to the physical coordinate system of the front vehicle, and at the same time converts the second global pose of the rear vehicle to the physical coordinate system of the rear vehicle, and then uses the conversion relationship between the physical coordinate systems of the front and rear vehicles to convert the pose of the front vehicle to its physical coordinate system and then to the physical coordinate system of the rear vehicle; for another example, assuming that the first global pose of the front vehicle and the second global pose of the rear vehicle can carry the relevant information of their respective global coordinate systems and physical coordinate systems, then the first global pose of the front vehicle and the second global pose of the rear vehicle can also be directly mathematically operated, such as multiplying the inverse transformation matrix of the second global pose by the first global pose, so as to convert the first global pose of the front vehicle to the physical coordinate system of the rear vehicle.

[0039] In addition, the first global pose and the second global pose can be represented by a multi-dimensional vector, for example, a global pose composed of a position and a multi-dimensional angle. For example, the second global pose is represented by T0, specifically: T0 = (x0, y0, z0, roll0, pith0, yaw0); the first global pose is represented by T1, specifically: T1 = (x1, y1, z1, roll1, pith1, yaw1). Among them, (x, y, z) represents the coordinates of the vehicle, roll represents the pitch angle, pitch represents the roll angle, and yaw represents the heading angle.

[0040] S204, detecting and processing the vehicle data sensed by the rear vehicle according to the converted posture, and determining the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data.

[0041] In which, taking the case where the front vehicle and the rear vehicle are trucks, a truck is generally composed of a flexible connection between a front vehicle and a hanging box, that is, the front vehicle and the rear vehicle can each have their own front vehicle and hanging box. Then, for the first global posture of the front vehicle and the second global posture of the rear vehicle, both can be the global posture of their respective front vehicles and / or the global posture of the hanging box.

[0042] In this step, the rear vehicle may be equipped with various sensors such as laser radar and camera. After the rear vehicle is powered on, these sensors may be used to sense the surrounding environmental data, that is, the surrounding environmental data may be collected. The environmental data may include vehicle data around the rear vehicle. Generally, the vehicle data may include the front vehicle, and of course, other vehicles may also be included, such as the rear vehicle corresponding to the rear vehicle itself, etc. At the same time, the vehicle data may be point cloud data, RGB image data, etc.

[0043] Since the above vehicle data is sensed by the rear vehicle, that is, the vehicle data is collected in the physical coordinate system of the rear vehicle, the rear vehicle can detect the front vehicle data in the vehicle data with the help of the conversion posture of the front vehicle to the physical coordinate system of the rear vehicle. For example, image recognition or image detection can be used to identify or detect point cloud data and RGB images, so as to detect the hanging box of the front vehicle and the posture of the hanging box of the front vehicle from the point cloud data and RGB images. Here, the posture of the hanging box detected from the vehicle data can be recorded as the detection posture of the hanging box.

[0044] It should be noted that, generally, the vehicles in the vehicle data perceived by the rear vehicle are all vehicles around the rear vehicle, which may include the front vehicle. Generally, the rear vehicle cannot see the front vehicle's front vehicle's front end and can only see the front vehicle's box. Therefore, the vehicle data perceived by the rear vehicle usually includes the data of the front vehicle's box. Therefore, the vehicle data detected by the rear vehicle here also obtains the detection posture of the front vehicle's box.

[0045] Similarly, the detection posture of the front vehicle hanging box can also be represented by a multi-dimensional vector, for example, a global posture composed of position and multi-dimensional angle can be used. For example, the detection posture of the front vehicle hanging box is represented by T 0→1 Indicates, specifically: T 0→1 =(x,y,z,roll,pith,yaw).

[0046] S206, determining the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box.

[0047] Among them, let's continue to take the example that the front car and the rear car are trucks. For example, when the front car turns, the front car's front head may have turned, but the trajectory of the front car's trailer may not have turned yet. In this case, if the rear car follows or tracks based on the posture of the front car's trailer, it is very likely that it will not turn. Obviously, such following will result in following errors. Therefore, generally the rear car needs to follow based on the front car's front head, that is, it needs to calculate the posture of the front car.

[0048] Based on this, after the rear vehicle obtains the detected posture of the hanging box of the front vehicle, it can calculate the posture of the front vehicle's head based on the detected posture of the hanging box of the front vehicle. In the specific calculation, the front vehicle can detect the geometric position relationship between its head and the hanging box in real time, and then send the geometric position relationship to the communication module of the rear vehicle through its own sending module, so that the rear vehicle can obtain the real-time geometric position relationship of the front vehicle. Here, the geometric position relationship between the front vehicle's head and the hanging box can be, for example, the distance between the front vehicle's head and the hanging box, the angle between the front vehicle and the hanging box, etc.

[0049] After the rear vehicle obtains the geometric position relationship between the front vehicle and the hanging box, the geometric position relationship can be used to combine the detection posture of the hanging box to perform mathematical calculations on the posture of the front vehicle to obtain the posture of the front vehicle. It should be noted that since the detection posture of the hanging box of the front vehicle is obtained by detection in the vehicle data, the detection posture of the hanging box is generally a posture in the image coordinate system or physical coordinates of the rear vehicle, and the corresponding posture of the front vehicle obtained directly through the geometric position relationship combined with the detection posture of the hanging box is also a posture in the image coordinate system or physical coordinates of the rear vehicle; and generally, when the rear vehicle follows the front vehicle, it needs to follow based on the global posture, so here the calculated posture of the front vehicle can be converted to the global coordinate system to obtain the posture of the front vehicle in the global coordinate system, which is recorded as the global posture of the front vehicle.

[0050] Alternatively, the above may also be to first convert the detected posture of the hanging box into the global coordinate system, and then directly calculate the global posture of the front vehicle head in the global coordinate system in combination with the geometric position relationship between the front vehicle head and the hanging box. In addition, it should be noted that generally the front vehicle and the rear vehicle are in the same global coordinate system, that is, the global coordinate systems corresponding to the front vehicle and the rear vehicle are the same global coordinate system.

[0051] Similarly, the global posture of the front of the vehicle can also be represented by a multi-dimensional vector, such as a global posture composed of position and multi-dimensional angles. For example, the global posture of the front of the vehicle is represented by T3, which is specifically expressed as: T3 = (x3, y3, z3, roll3, pith3, yaw3).

[0052] S208, determining a target global posture of the preceding vehicle according to the global posture of the vehicle head.

[0053] In this step, after obtaining the global posture of the front of the front vehicle, the rear vehicle can directly use the global posture of the front of the front vehicle as the final target global posture of the front vehicle. Alternatively, the rear vehicle can combine the global posture of the front of the front vehicle with the position information related to other front and rear vehicles to comprehensively obtain the final target global posture of the front vehicle. Alternatively, there can be other ways to determine the target global posture of the front vehicle through the global posture of the front of the front vehicle. In short, the target global posture of the front vehicle can be determined.

[0054] After the following vehicle determines the final target global posture of the leading vehicle, the following vehicle can adjust its following position according to the target global posture and follow the leading vehicle to ensure the positioning consistency of the leading and trailing vehicles and achieve accurate vehicle following.

[0055] Furthermore, it should be noted that although only one set of following implementation process between the front vehicle and the rear vehicle is provided in this embodiment, for the vehicle formation automatic driving scene including more than two vehicles, the vehicle formation automatic driving refers to two or more vehicles driving in formation, the front and rear vehicles keep a short distance (within 10 meters), the front vehicle can be manually driven, and the rear vehicle is automatic driving. In this vehicle formation automatic driving scene, each two adjacent vehicles can include a front vehicle and a rear vehicle, and the rear vehicle can follow its corresponding front vehicle in the manner of this embodiment, so as to achieve the following of the entire vehicle fleet.

[0056] In addition, from the above description, it can be seen that in this embodiment, if the first vehicle in the vehicle formation uses manual driving, then the first vehicle does not need sensors such as lidar and cameras. These sensors can be removed and only the satellite positioning system is retained, thereby saving the cost of the entire vehicle formation in the positioning process.

[0057] At the same time, through the above-mentioned steps of associated calculation, it can be known that the front vehicle only needs to send its relatively simple global pose to the rear vehicle, and the rear vehicle can accurately calculate the global pose of the front vehicle head based on the vehicle data perceived by itself. Therefore, while realizing the joint positioning of the front and rear vehicles, the front and rear vehicles can reduce the dependence of the front and rear vehicles on the global positioning accuracy and improve the consistency of the positioning of the front and rear vehicles. It can also be seen that the method of this embodiment can maintain the consistency of the positioning of the front and rear vehicles even when the satellite signal (i.e., the signal of the global positioning system) is poor in bridge tunnels, toll stations, tunnels, etc.

[0058] Similarly, the target global pose of the preceding vehicle may also be represented by a multi-dimensional vector, such as a global pose composed of position and multi-dimensional angles. For example, the target global pose of the preceding vehicle may be represented by T4, specifically: T4 = (x4, y4, z4, roll4, pith4, yaw4).

[0059] In the above vehicle positioning method, the conversion posture of the front vehicle in the physical coordinate system of the rear vehicle is determined according to the first global posture of the front vehicle and the second global posture of the rear vehicle, and the vehicle data sensed by the rear vehicle is detected and processed according to the conversion posture to determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data, and then the head global posture of the front vehicle can be determined according to the detection posture of the hanging box and the geometric position relationship between the front vehicle and the hanging box, and the target posture of the front vehicle is determined based on the head global posture. In this method, since the front vehicle only needs to send its own global posture detected to the rear vehicle, the rear vehicle can combine its own perception data to comprehensively calculate the global posture of the front vehicle to achieve the consistency of positioning of the front and rear vehicles. In this way, there is no need for the front vehicle itself to use multiple types of sensors for perception to achieve front and rear vehicle positioning, so that the front vehicle can remove some sensors, so that part of the positioning cost can be saved in the front and rear vehicle positioning process. At the same time, since the rear vehicle can calculate the global pose of the front vehicle's front end through the front vehicle's perceived data, and comprehensively solve the global pose of the front vehicle based on the global pose detected by the front vehicle itself, the considered data is relatively large and rich, so the global pose of the front vehicle obtained by the rear vehicle is more accurate, so that the rear vehicle can accurately follow the front vehicle, thereby improving the consistency of the positioning of the front and rear vehicles.

[0060] The above embodiment mentioned that the sensed vehicle data of the rear vehicle can be detected and processed based on the conversion posture of the front vehicle to obtain the detection posture of the front vehicle's hanging box. The following embodiment describes a possible real-time method for calculating the detection posture of the front vehicle's hanging box through the sensed vehicle data.

[0061] In another embodiment, another vehicle positioning method is provided. Based on the above embodiment, Figure 3 As shown, the above S204 may include the following steps:

[0062] S302, detecting and processing the vehicle data to determine candidate vehicles in the vehicle data and candidate positions and postures of the candidate vehicles.

[0063] In this step, after obtaining the perceived vehicle data, the following vehicle can use algorithms such as target recognition algorithms or target detection algorithms to identify the vehicles included in the vehicle data to obtain the identified candidate vehicles. Generally, after identifying or detecting each candidate vehicle, the color, size, model, posture and other information of each candidate vehicle can also be obtained accordingly. The posture of each candidate vehicle obtained here can be recorded as a candidate posture.

[0064] S304, selecting a target posture that matches the converted posture from the candidate postures, and determining the candidate vehicle corresponding to the target posture as the leading vehicle.

[0065] In this step, after the rear vehicle obtains the candidate postures of each candidate vehicle, the posture of the front vehicle detected by the rear vehicle and the posture of the front vehicle transmitted by the front vehicle should theoretically be consistent or relatively close. Therefore, here each candidate posture can be matched with the transformed posture of the front vehicle respectively, and the candidate posture that matches the transformed posture of the front vehicle can be found from each candidate posture and used as the target posture. At the same time, the candidate vehicle corresponding to the target posture can be found, and this candidate vehicle is the front vehicle.

[0066] When performing posture matching here, for example, the transformed posture of the front vehicle and each candidate posture are transformed into the same coordinate system, and then the distance between each candidate posture and the transformed posture is calculated to obtain multiple distance values, and the candidate posture with the smallest distance value is selected from them. The candidate posture with the smallest distance value is the posture closest to the transformed posture, that is, the two may be the posture of the same vehicle, so it can be used as the target posture.

[0067] S306, determining the hanging box of the preceding vehicle and the detection posture of the hanging box according to the target posture.

[0068] In this step, after the rear vehicle selects the front vehicle from the candidate vehicles, it can also obtain the target position of the front vehicle. The target posture of the front vehicle can include the posture of the hanging box of the front vehicle. Therefore, the hanging box of the front vehicle can be found from the target posture of the front vehicle, and then the posture of the hanging box of the front vehicle can be obtained from it, which is recorded as the detected posture of the hanging box.

[0069] In this embodiment, the rear vehicle detects the perceived vehicle data to obtain candidate vehicles and candidate postures, and screens out the target posture that matches the conversion posture of the front vehicle, and then obtains the detection posture of the front vehicle's hanging box. In this way, by detecting the perceived data and matching it with the conversion posture of the front vehicle, the process of determining the detection posture of the front vehicle's hanging box is refined, so that the final detection posture of the front vehicle's hanging box is more accurate, and the efficiency of determining the detection posture of the front vehicle's hanging box can also be improved.

[0070] The above embodiment mentioned that the global posture of the front vehicle's front end can be determined based on the detected posture of the front vehicle's trailer and the geometric position relationship between the front vehicle's trailer and the front end. The following embodiment describes a possible real-time method for specifically determining the global posture of the front vehicle's front end.

[0071] In another embodiment, another vehicle positioning method is provided. Based on the above embodiment, Figure 4 As shown, the above S206 may include the following steps:

[0072] S402, determining the global posture of the hanging box in the global coordinate system according to the detected posture and the second global posture.

[0073] In this step, after the rear vehicle obtains the detected posture of the front vehicle's box, since the detected posture of the front vehicle's box may be the posture in the image coordinate system or physical coordinate system of the rear vehicle, and it is necessary to calculate the posture of the front vehicle's front in the global coordinate system to achieve following, the detected posture of the front vehicle's box needs to be converted to the global coordinate system.

[0074] During the specific conversion, since the second global posture of the rear vehicle is the posture in the global coordinate system, the relevant information of the global coordinate system can be obtained through the second global posture of the rear vehicle, and then the detected posture of the hanging box of the front vehicle is converted to the global coordinate system through the relevant information to obtain the posture of the hanging box in the global coordinate system, which is recorded as the global posture of the hanging box.

[0075] For example, one way of conversion here may be to directly perform mathematical operations on the detected posture of the front vehicle's box and the second global posture of the rear vehicle, such as multiplying the transformation matrix of the second global posture by the detected posture of the front vehicle's box, so as to convert the detected posture of the front vehicle's box to the global coordinate system.

[0076] Similarly, the global pose of the above-mentioned hanging box can also be represented by a multi-dimensional vector, for example, a global pose composed of position and multi-dimensional angle. For example, the global pose of the hanging box is represented by T2, which is specifically expressed as: T2 = (x2, y2, z2, roll2, pith2, yaw2).

[0077] S404, determining the global posture of the front of the vehicle according to the global posture of the hanging box and the geometric position relationship between the front of the vehicle and the hanging box.

[0078] In this step, after obtaining the global pose of the hanging box, the rear vehicle can calculate the pose of the front vehicle's front in the global coordinate system according to its geometric position relationship with the front vehicle's front.

[0079] As an optional embodiment, the geometric position relationship may include, for example, a box angle between the front of the vehicle and the box, that is, an angle between the front of the vehicle and the box, which will form a relatively obvious box angle when turning. Figure 5 The process shown is for detecting the posture and angle of the box hanging on the front vehicle, where the box hanging angle can be recorded as θ.

[0080] After obtaining the angle between the front of the front vehicle and the box, the length of the box can also be obtained; then the length, angle and global pose of the box are mathematically calculated to determine the global pose of the front of the vehicle. For example, the length, angle and global pose of the box can be mathematically calculated using trigonometric functions and the law of sine. Of course, other auxiliary parameters can also be combined for calculation, as long as the global pose of the front of the vehicle can be calculated in the end. The global pose of the front of the vehicle calculated here is recorded as the global pose of the front of the vehicle. In addition, the length of the box of the front vehicle can also be transmitted from the front vehicle to the rear vehicle, or it can be calculated by the rear vehicle based on the vehicle data of the front vehicle sensed.

[0081] In this embodiment, after the detected posture of the front vehicle's hanging box is converted to the global coordinate system, the global posture of the front vehicle's front can be calculated by combining the geometric position relationship between the front vehicle's front and the hanging box. This method of calculating through coordinate conversion and geometric position relationship is relatively simple and intuitive, so the efficiency and accuracy of calculating the global posture of the front vehicle's front can be improved, and the timeliness and accuracy of the following vehicle can be guaranteed. In addition, the global posture of the front vehicle's front is calculated by the length of the hanging box, the hanging box angle and the global posture of the hanging box. This process is relatively clear and simple, and the factors considered are further increased, so the efficiency and accuracy of calculating the global posture of the front vehicle's front can be further improved, and the timeliness and accuracy of the following vehicle can be further guaranteed.

[0082] The above embodiment mentioned that the global posture of the front of the front vehicle calculated by the rear vehicle can be combined with other position information to obtain the final global posture of the front vehicle. The following embodiment describes an implementation method of this process.

[0083] In another embodiment, another vehicle positioning method is provided. Based on the above embodiment, the above S208 may include the following steps:

[0084] The global pose of the vehicle head and the first global pose are fused to determine the target global pose of the leading vehicle.

[0085] In this step, after the rear vehicle calculates and obtains the front vehicle's global posture, in order to further improve the accuracy of the front vehicle positioning, the final global posture of the front vehicle can be determined in combination with the first global posture obtained by the front vehicle's own positioning. Specifically, the first global posture of the front vehicle and the front global posture are input into the Kalman filter for optimal solution to obtain the optimal global posture of the front vehicle, which is the target global posture of the front vehicle. Here, the target global posture of the front vehicle can be the global posture of the front vehicle, or it can be considered as the global posture of the entire front vehicle.

[0086] In this embodiment, the target global pose of the leading vehicle is obtained by fusing the global pose transmitted by the leading vehicle and the calculated global pose of the leading vehicle's front. This can further improve the accuracy of the determined global pose of the leading vehicle, effectively ensure the consistency of the positioning of the leading and trailing vehicles, and enable the trailing vehicle to accurately follow the leading vehicle.

[0087] The following embodiment illustrates an implementation method for the following vehicle to obtain the first global posture and geometric position relationship of the leading vehicle.

[0088] In another embodiment, another vehicle positioning method is provided. Based on the above embodiment, the above method may further include the following steps:

[0089] Receive communication data sent by the preceding vehicle; the communication data includes a first global position and / or a geometric position relationship between the front end of the preceding vehicle and the hanging box.

[0090] In this step, as mentioned above, the front vehicle can obtain its own global posture in real time, and can also detect the geometric position relationship between the front vehicle and the hanging box in real time through relevant sensors for detecting geometric positions (such as angle sensors, etc.), and send its own global posture detected in real time and the geometric position relationship detected in real time to the rear vehicle simultaneously or in batches.

[0091] Of course, the leading vehicle can also measure its own length, the length of the hanging box, the length of the front of the vehicle and other data through infrared sensors, and send them to the trailing vehicle; of course, the leading vehicle can also send other types of data to the trailing vehicle.

[0092] In this embodiment, the rear vehicle receives communication data sent by the front vehicle, including the first global posture and the geometric position relationship between the front vehicle's front end and the hanging box. This allows the rear vehicle to have sufficient data to calculate the detected posture of the hanging box of the front vehicle, thereby ensuring the efficiency and accuracy of the calculation, and further ensuring the consistency of the positioning of the front and rear vehicles.

[0093] A detailed embodiment is given below to illustrate the vehicle positioning method of the embodiment of the present disclosure. Figure 6 The simple flow chart shown and Figure 7 The detailed process example diagram shown in the figure, the method may include the following steps:

[0094] S1, the following vehicle receives its first global posture sent by the leading vehicle;

[0095] S2, the rear vehicle obtains its own second global posture, and calculates the transformed posture of the front vehicle in the physical coordinate system of the rear vehicle according to the first global posture and the second global posture;

[0096] S3, the following vehicle obtains vehicle data sensed by its own sensors;

[0097] S4, the following vehicle detects and processes the vehicle data to determine candidate vehicles in the vehicle data and candidate positions and postures of the candidate vehicles;

[0098] S5, the following vehicle selects a target posture matching the converted posture from the candidate postures, and determines the candidate vehicle corresponding to the target posture as the leading vehicle;

[0099] S6, the following vehicle selects the detection posture of the hanging box of the front vehicle from the target posture;

[0100] S7, the rear vehicle calculates the global posture of the hanging box in the global coordinate system according to the detected posture of the hanging box and the second global posture;

[0101] S8, the rear vehicle receives the angle between its own vehicle head and the hanging box, and the length of the hanging box sent by the front vehicle;

[0102] S9, the rear vehicle performs mathematical calculations on the length, angle and global position of the hanging box to obtain the global position of the front of the front vehicle;

[0103] S10, the rear vehicle fuses the front global pose of the front vehicle and the first global pose of the front vehicle to obtain a target global pose of the front vehicle;

[0104] S11, the rear vehicle follows the front vehicle based on its target global posture.

[0105] It should be understood that, although the various steps in the above flow chart are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above figure may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0106] In one embodiment, Figure 8 As shown, a vehicle positioning device is provided, comprising: a first determination module, a detection module, a second determination module and a positioning module, wherein:

[0107] A first determination module is used to determine a transformed posture of the front vehicle in a physical coordinate system of the rear vehicle according to a first global posture of the front vehicle and a second global posture of the rear vehicle;

[0108] A detection module is used to detect and process the vehicle data sensed by the rear vehicle according to the converted posture, and determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data;

[0109] The second determination module is used to determine the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box;

[0110] The positioning module is used to determine the target global posture of the preceding vehicle based on the global posture of the vehicle head.

[0111] In another embodiment, another vehicle positioning device is provided. Based on the above embodiment, the above detection module may include:

[0112] A detection unit, used to detect and process the vehicle data, and determine candidate vehicles in the vehicle data and candidate positions and postures of the candidate vehicles;

[0113] A screening unit, used to screen out a target posture matching the converted posture from the candidate postures, and determine the candidate vehicle corresponding to the target posture as the leading vehicle;

[0114] The posture determination unit is used to determine the hanging box of the preceding vehicle and the detection posture of the hanging box according to the target posture.

[0115] In another embodiment, another vehicle positioning device is provided. Based on the above embodiment, the second determination module may include:

[0116] A hanging box posture determination unit, used for determining the hanging box global posture of the hanging box in the global coordinate system according to the detected posture and the second global posture;

[0117] The vehicle head posture determination unit is used to determine the vehicle head global posture of the vehicle head according to the global posture of the hanging box and the geometric position relationship between the vehicle head of the preceding vehicle and the hanging box.

[0118] Optionally, the above-mentioned geometric position relationship includes the box angle between the locomotive head and the box, and the above-mentioned locomotive head posture determination unit is specifically used to obtain the length of the box; perform mathematical calculations on the length of the box, the box angle and the global posture of the box to determine the global posture of the locomotive head.

[0119] In another embodiment, another vehicle positioning device is provided. Based on the above embodiment, the above positioning module is specifically used to fuse the global posture of the front of the vehicle and the first global posture to determine the target global posture of the leading vehicle.

[0120] In another embodiment, another vehicle positioning device is provided. Based on the above embodiment, the above device may further include:

[0121] The receiving module is used to receive the communication data sent by the preceding vehicle; the communication data includes the first global posture and / or the geometric position relationship between the front end of the preceding vehicle and the hanging box.

[0122] The specific definition of the vehicle positioning device can be found in the definition of the vehicle positioning method above, which will not be repeated here. Each module in the above-mentioned vehicle positioning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0123] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0124] According to the first global posture of the front vehicle and the second global posture of the rear vehicle, the transformation posture of the front vehicle in the physical coordinate system of the rear vehicle is determined; according to the transformation posture, the vehicle data sensed by the rear vehicle are detected and processed to determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data; according to the detection posture and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined; according to the global posture of the front of the vehicle, the target global posture of the front vehicle is determined.

[0125] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0126] The vehicle data is detected and processed to determine candidate vehicles and candidate postures of the candidate vehicles in the vehicle data; a target posture matching the conversion posture is screened out from the candidate postures, and the candidate vehicle corresponding to the target posture is determined as the front vehicle; the hanging box of the front vehicle and the detection posture of the hanging box are determined according to the target posture.

[0127] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0128] According to the detected posture and the second global posture, the global posture of the hanging box in the global coordinate system is determined; according to the global posture of the hanging box and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined.

[0129] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0130] Obtain the length of the hanging box; perform mathematical calculations on the length of the hanging box, the hanging box angle, and the global posture of the hanging box to determine the global posture of the front of the vehicle.

[0131] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0132] The global pose of the vehicle head and the first global pose are fused to determine the target global pose of the leading vehicle.

[0133] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0134] Receive communication data sent by the preceding vehicle; the communication data includes a first global position and / or a geometric position relationship between the front end of the preceding vehicle and the hanging box.

[0135] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0136] According to the first global posture of the front vehicle and the second global posture of the rear vehicle, the transformation posture of the front vehicle in the physical coordinate system of the rear vehicle is determined; according to the transformation posture, the vehicle data sensed by the rear vehicle are detected and processed to determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data; according to the detection posture and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined; according to the global posture of the front of the vehicle, the target global posture of the front vehicle is determined.

[0137] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0138] The vehicle data is detected and processed to determine candidate vehicles and candidate postures of the candidate vehicles in the vehicle data; a target posture matching the conversion posture is screened out from the candidate postures, and the candidate vehicle corresponding to the target posture is determined as the front vehicle; the hanging box of the front vehicle and the detection posture of the hanging box are determined according to the target posture.

[0139] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0140] According to the detected posture and the second global posture, the global posture of the hanging box in the global coordinate system is determined; according to the global posture of the hanging box and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined.

[0141] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0142] Obtain the length of the hanging box; perform mathematical calculations on the length of the hanging box, the hanging box angle, and the global posture of the hanging box to determine the global posture of the front of the vehicle.

[0143] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0144] The global pose of the vehicle head and the first global pose are fused to determine the target global pose of the leading vehicle.

[0145] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0146] Receive communication data sent by the preceding vehicle; the communication data includes a first global position and / or a geometric position relationship between the front end of the preceding vehicle and the hanging box.

[0147] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0148] According to the first global posture of the front vehicle and the second global posture of the rear vehicle, the transformation posture of the front vehicle in the physical coordinate system of the rear vehicle is determined; according to the transformation posture, the vehicle data sensed by the rear vehicle are detected and processed to determine the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data; according to the detection posture and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined; according to the global posture of the front of the vehicle, the target global posture of the front vehicle is determined.

[0149] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0150] The vehicle data is detected and processed to determine candidate vehicles and candidate postures of the candidate vehicles in the vehicle data; a target posture matching the conversion posture is screened out from the candidate postures, and the candidate vehicle corresponding to the target posture is determined as the front vehicle; the hanging box of the front vehicle and the detection posture of the hanging box are determined according to the target posture.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0152] According to the detected posture and the second global posture, the global posture of the hanging box in the global coordinate system is determined; according to the global posture of the hanging box and the geometric position relationship between the front of the front vehicle and the hanging box, the global posture of the front of the vehicle is determined.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0154] Obtain the length of the hanging box; perform mathematical calculations on the length of the hanging box, the hanging box angle, and the global posture of the hanging box to determine the global posture of the front of the vehicle.

[0155] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0156] The global pose of the vehicle head and the first global pose are fused to determine the target global pose of the leading vehicle.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0158] Receive communication data sent by the preceding vehicle; the communication data includes a first global position and / or a geometric position relationship between the front end of the preceding vehicle and the hanging box.

[0159] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all data fully authorized by all parties.

[0160] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the embodiments of the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0161] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The above-described embodiments only express several implementation methods of the embodiments of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the embodiments of the present disclosure, and these all belong to the protection scope of the embodiments of the present disclosure. Therefore, the protection scope of the patent of the embodiments of the present disclosure shall be subject to the attached claims.

Claims

1. A vehicle positioning method, characterized in that: The method comprises: Determining a transformed posture of the front vehicle in a physical coordinate system of the rear vehicle according to a first global posture of the front vehicle and a second global posture of the rear vehicle; Detecting and processing the vehicle data sensed by the rear vehicle according to the converted posture, and determining the hanging box of the front vehicle and the detection posture of the hanging box in the vehicle data; Determining the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box; The target global posture of the preceding vehicle is determined according to the global posture of the vehicle head.

2. The method according to claim 1, characterized in that The detecting and processing the vehicle data sensed by the rear vehicle according to the converted posture to determine the hanging box of the front vehicle and the detected posture of the hanging box in the vehicle data includes: Performing detection processing on the vehicle data to determine candidate vehicles in the vehicle data and candidate positions and postures of the candidate vehicles; Selecting a target posture matching the converted posture from the candidate postures, and determining the candidate vehicle corresponding to the target posture as the leading vehicle; The hanging box of the preceding vehicle and the detection posture of the hanging box are determined according to the target posture.

3. The method according to claim 1, characterized in that The determining of the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box comprises: Determining the global posture of the hanging box in the global coordinate system according to the detected posture and the second global posture; The global posture of the front of the vehicle is determined according to the global posture of the hanging box and the geometric position relationship between the front of the vehicle and the hanging box.

4. The method according to claim 3, characterized in that The geometric position relationship includes a box angle between the vehicle head and the box, and determining the vehicle head global position of the vehicle head according to the box global position and the geometric position relationship between the vehicle head and the box of the preceding vehicle includes: Obtaining the length of the hanging box; Mathematical calculations are performed on the length of the hanging box, the hanging box angle, and the hanging box global posture to determine the head global posture of the vehicle head.

5. The method according to any one of claims 1 to 4, characterized in that: Determining the target global pose of the preceding vehicle according to the vehicle head global pose comprises: The vehicle head global pose and the first global pose are fused to determine the target global pose of the leading vehicle.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Receive communication data sent by the preceding vehicle; the communication data includes the first global posture, and / or the geometric position relationship between the front of the preceding vehicle and the hanging box.

7. A vehicle positioning device, characterized in that: The device comprises: A first determination module is used to determine a transformed posture of the leading vehicle in a physical coordinate system of the following vehicle according to a first global posture of the leading vehicle and a second global posture of the following vehicle; A detection module, used for detecting and processing the vehicle data sensed by the following vehicle according to the converted posture, and determining the hanging box of the leading vehicle and the detection posture of the hanging box in the vehicle data; A second determination module is used to determine the global posture of the front of the vehicle according to the detected posture and the geometric position relationship between the front of the vehicle and the hanging box; A positioning module is used to determine the target global posture of the preceding vehicle according to the global posture of the vehicle head.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images