Vehicle alignment guiding method and related device

Abstract

The invention discloses a vehicle alignment guiding method and a related device, and relates to the technical field of vehicle-road cooperation, and the method comprises the steps: obtaining target point cloud data in a region of interest of a target lane, determining the minimum lane distance between a target vehicle and a multi-line laser radar according to the target point cloud data, and if the minimum lane distance is greater than a preset positioning reference threshold, determining that the target vehicle is aligned with the multi-line laser radar. If the minimum lane distance is smaller than or equal to a positioning reference threshold value, determining first point cloud data located on the front vertical surface of the container from the target point cloud data, determining alignment guide information of the target vehicle according to the first point cloud data, and if the minimum lane distance is smaller than or equal to the positioning reference threshold value, determining second point cloud data located on the top surface of the container from the target point cloud data, and determining alignment guide information according to the second point cloud data. According to the invention, the method achieves the simultaneous scanning of the point cloud through a plurality of laser beams based on the multi-line laser radar, determines the alignment guide information, improves the accuracy of the alignment guide information, saves the cost, and reduces the complexity of the vehicle alignment guide process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-road cooperation, in particular to a vehicle alignment guiding method and related device. BACKGROUND

[0002] In automatic freight transportation, accurate alignment between a vehicle and a spreader is required when loading and unloading containers. The alignment process is as follows: a single-line laser radar is used to obtain point cloud data in a radar detection area by carrying a rotating pan-tilt, and then target point cloud data in a region of interest near the working position is selected, and alignment guiding information of the vehicle is obtained according to the target point cloud data.

[0003] However, the single-line laser radar can only scan vertically once each time. After scanning is completed, the rotating pan-tilt needs to be rotated horizontally by a certain angle, and then the single-line laser radar is used for vertical scanning. In this way, all point cloud data in the radar detection area is obtained. Since the scanning of the single-line laser radar and the rotation of the rotating pan-tilt both take a certain amount of time, if the vehicle moves during scanning, distance errors will occur in points originally on the same plane, and thus the alignment guiding information of the vehicle will be inaccurate.

[0004] In order to reduce the time taken by the scanning of the single-line laser radar and the rotation of the rotating pan-tilt, multiple single-line laser radars can be used to carry multiple rotating pan-tilts. However, this approach increases costs, and the point cloud data scanned by multiple single-line laser radars needs to be synchronized and aggregated, which increases the complexity of the vehicle alignment guiding process. SUMMARY

[0005] In view of the above problems, the present application provides a vehicle alignment guiding method and related device to solve the problems of inaccurate alignment guiding information, high cost and high complexity in the prior art. The specific scheme is as follows:

[0006] The first aspect of the present application provides a vehicle alignment guiding method, comprising:

[0007] obtaining target point cloud data in a region of interest of a target lane, wherein the target point cloud data includes point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar;

[0008] determining a minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data;

[0009] in a case where the minimum lane distance is greater than a preset positioning reference threshold, determining first point cloud data located on a front vertical surface of the container from the target point cloud data, and determining alignment guiding information of the target vehicle according to the first point cloud data;

[0010] In a case where the minimum lane distance is less than or equal to the positioning reference threshold, second point cloud data located on a top surface of the container is determined from the target point cloud data, and the alignment guidance information is determined according to the second point cloud data.

[0011] In a possible implementation, the process of determining the positioning reference threshold comprises:

[0012] Obtaining position information of the multi-line laser radar;

[0013] Determining a point cloud occlusion ratio on the front vertical surface according to the position information of the multi-line laser radar and the target point cloud data;

[0014] Determining the positioning reference threshold according to the minimum lane distance in a case where the point cloud occlusion ratio is greater than a preset occlusion ratio threshold.

[0015] In a possible implementation, the target point cloud data comprises point cloud data corresponding to a plurality of laser beams of the multi-line laser radar respectively;

[0016] The determining of the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data comprises:

[0017] Determining minimum coordinate values of the point cloud data corresponding to the plurality of laser beams respectively in a lane direction as minimum coordinate values corresponding to the plurality of laser beams respectively;

[0018] Determining the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively;

[0019] In a possible implementation, the determining of the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively comprises:

[0020] Determining any value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance;

[0021] Or, determining a minimum value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance;

[0022] Or, calculating an average value of the minimum coordinate values corresponding to the plurality of laser beams respectively, and determining the average value as the minimum lane distance.

[0023] In a possible implementation, the determining of the first point cloud data located on the front vertical surface of the container from the target point cloud data comprises:

[0024] Projecting the point cloud data corresponding to the plurality of laser beams respectively onto a coordinate axis in the lane direction to obtain projected point cloud data;

[0025] screening vertical surface point cloud data from the projection point cloud data;

[0026] performing coordinate restoration processing on the vertical surface point cloud data to obtain target vertical surface point cloud data subjected to coordinate restoration;

[0027] performing clustering on the target vertical surface point cloud data to obtain a front vertical surface point cloud clustering cluster;

[0028] obtaining the first point cloud data according to the front vertical surface point cloud clustering cluster.

[0029] In a possible implementation, the obtaining the first point cloud data according to the front vertical surface point cloud clustering cluster comprises:

[0030] determining point cloud data in the front vertical surface point cloud clustering cluster as the first point cloud data;

[0031] or, removing, from the front vertical surface point cloud clustering cluster, point cloud data whose coordinate value in the lane direction is greater than a preset mean value threshold, and taking the remaining point cloud data as the first point cloud data.

[0032] In a possible implementation, the determining the alignment guide information of the target vehicle according to the first point cloud data comprises:

[0033] performing straight line fitting based on the first point cloud data to obtain a preset parameter value corresponding to a fitting straight line;

[0034] obtaining a distance between the front vertical surface and the multi-line laser radar and a heading angle deviation value according to the preset parameter value corresponding to the fitting straight line, wherein the heading angle deviation value refers to a difference between an actual heading angle of the container and a standard heading angle;

[0035] obtaining the alignment guide information according to the distance between the front vertical surface and the multi-line laser radar and the heading angle deviation value.

[0036] In a possible implementation, the determining second point cloud data located on a top surface of the container from the target point cloud data comprises:

[0037] for each laser beam in the plurality of laser beams:

[0038] sorting point cloud data corresponding to the laser beam in descending order of coordinate values in the lane direction to obtain a point cloud sorting result corresponding to the laser beam;

[0039] determining rear boundary point cloud data and front boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam;

[0040] to obtain the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser line beams;

[0041] According to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser line beams, the second point cloud data is obtained.

[0042] In a possible implementation, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser line beam are determined according to the point cloud sorting result corresponding to the laser line beam, including:

[0043] The point cloud data ranked first in the point cloud sorting result corresponding to the laser line beam is determined as the rear side boundary point cloud data corresponding to the laser line beam;

[0044] In the order from front to back according to the point cloud sorting result corresponding to the laser line beam, the coordinate difference of adjacent point cloud data in the lane direction is calculated in sequence to obtain target adjacent point cloud data that first makes the coordinate difference less than a preset difference threshold;

[0045] The previous point cloud data in the target adjacent point cloud data is determined as the front side boundary point cloud data corresponding to the laser line beam.

[0046] In a possible implementation, the second point cloud data is obtained according to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser line beams, including:

[0047] A first point cloud set is generated according to the front side boundary point cloud data corresponding to each of the plurality of laser line beams;

[0048] A second point cloud set is generated according to the rear side boundary point cloud data corresponding to each of the plurality of laser line beams;

[0049] The first point cloud set and the second point cloud set are taken as the second point cloud data;

[0050] The alignment guidance information is determined according to the second point cloud data, including:

[0051] The target vehicle and the container are positioned according to the first point cloud set and the second point cloud set, and a straight line fitting method or an extreme value removal and averaging method is used to obtain the alignment guidance information.

[0052] In a possible implementation, the method further includes:

[0053] Task information corresponding to the container is obtained;

[0054] A current work type is obtained from the task information;

[0055] The target lane is determined according to the current operation type, and a region of interest and a related parameter threshold of the target lane are determined, the related parameter threshold being used to assist in determining the alignment guidance information.

[0056] The second aspect of the present application provides a vehicle alignment guidance device, comprising:

[0057] A point cloud acquisition module is configured to acquire target point cloud data in a region of interest of a target lane, wherein the target point cloud data comprises point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar;

[0058] A distance determination module is configured to determine a minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data.

[0059] A first alignment module is configured to, when the minimum lane distance is greater than a preset alignment reference threshold, determine first point cloud data on a front vertical surface of the container from the target point cloud data, and determine alignment guidance information of the target vehicle according to the first point cloud data.

[0060] A second alignment module is configured to, when the minimum lane distance is less than or equal to the alignment reference threshold, determine second point cloud data on a top surface of the container from the target point cloud data, and determine the alignment guidance information according to the second point cloud data.

[0061] The third aspect of the present application provides a computer program product, comprising computer readable instructions, when the computer readable instructions are executed on an electronic device, the electronic device implements the vehicle alignment guidance method of the first aspect or any implementation manner of the first aspect.

[0062] The fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0063] The memory is configured to store a computer program;

[0064] The processor is configured to execute the computer program, so that the electronic device can implement the vehicle alignment guidance method of the first aspect or any implementation manner of the first aspect.

[0065] The fifth aspect of the present application provides a computer storage medium, the storage medium carries one or more computer programs, when the one or more computer programs are executed by an electronic device, the electronic device can implement the vehicle alignment guidance method of the first aspect or any implementation manner of the first aspect.

[0066] By the technical scheme, the vehicle alignment guiding method provided by the application acquires target point cloud data in a region of interest of a target lane, determines a minimum lane distance between a target vehicle and a multi-line laser radar according to the target point cloud data, in a case where the minimum lane distance is greater than a preset alignment reference threshold, determines first point cloud data located on a front vertical surface of a container from the target point cloud data, determines alignment guiding information of the target vehicle according to the first point cloud data, in a case where the minimum lane distance is less than or equal to the alignment reference threshold, determines second point cloud data located on a top surface of the container from the target point cloud data, and determines the alignment guiding information according to the second point cloud data. The application can simultaneously scan target point cloud data in the region of interest by the multi-line laser radar, and there is no time difference caused by scanning, so that even if the target vehicle moves, there is no distance error of points on the same plane, and the accuracy of the alignment guiding information is improved. Meanwhile, the multi-line laser radar can emit multiple laser beams from multiple angles, so the multi-line laser radar does not need to be equipped with a rotating holder, the cost is saved, and the multiple laser beams are synchronously emitted, and there is no need for additional synchronization and aggregation processing, and the complexity of the vehicle alignment guiding process is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0067] The above and other features, advantages, and aspects of the present disclosure will become more apparent by describing in detail the following specific embodiments in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale.

[0068] Figure 1 A system architecture schematic diagram is provided for the application;

[0069] Figure 2 An optional hardware structure schematic diagram of a terminal 100 provided for the application;

[0070] Figure 3 A structure schematic diagram of a server 200 provided for the application;

[0071] Figure 4 A flowchart of a vehicle alignment guiding method provided for the application;

[0072] Figure 5 A structure schematic diagram of a CPS accurate alignment system provided for the application;

[0073] Figure 6 A side view of a ROI region determined when the multi-line laser radar is installed on the overhead beam of the lane;

[0074] Figure 7 A front view of a ROI region determined when the multi-line laser radar is installed on the overhead beam of the lane;

[0075] Figure 8 A separation effect diagram of a front vertical surface point cloud cluster;

[0076] Figure 9 A structural schematic diagram of a vehicle alignment guiding device provided by the present application;

[0077] Figure 10 A structural schematic diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0078] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. The terms used in the embodiment part of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0079] The embodiments of the present application are described below in conjunction with the drawings. It is known to those skilled in the art that as technology develops and new scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0080] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, and this is only a way of distinguishing the objects with the same attributes in the description of the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products or devices containing a series of units do not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products or devices.

[0081] Reference is made to Figure 1 , Figure 1 A system architecture schematic diagram is shown. The system can include a terminal 100 and a server 200. The server 200 can include one or more servers (for example, one server is described as an example in the server 200), and the server 200 can provide the method provided by the embodiments of the present application for one or more terminals. Figure 1

[0082] The terminal 100 can be installed with an application program, and the above-mentioned application program and webpage can provide an interface. The terminal 100 can receive relevant parameters input by a user on the interface, and send the above-mentioned parameters to the server 200. The server 200 can obtain a processing result based on the received parameters, and return the processing result to the terminal 100.

[0083] ​It should be understood that, in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the cooperation of the server, and the embodiments of the present application are not limited thereto.

[0084] Next, the product form of the terminal 100 is described. Figure 1

[0085] The terminal 100 in the embodiments of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiments of the present application are not limited thereto.

[0086] Figure 2 An optional hardware structure schematic diagram of the terminal 100 is shown.

[0087] Referring to FIG. 1, Figure 2 As shown in FIG. 1, the terminal 100 can include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), a headphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190, and the like. Those skilled in the art can understand that the terminal 100 can include more or less components, or combine certain components, or different components, and the embodiments of the present application are not limited thereto. Figure 2 The terminal or multi-functional device is only an example and does not constitute a limitation on the terminal or multi-functional device, and can include more or less components, or combine certain components, or different components.

[0088] ​The input unit 130 can be used to receive inputted digital or character information, and to generate key signal inputs related to user settings of the portable multifunctional device and control of functions. Specifically, the input unit 130 can include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect touch operations of a user thereon or therearound (such as operations of the user using a finger, a knuckle, a stylus, or any suitable object on or near the touch screen), and drive corresponding connected devices according to pre-set programs. The touch screen can detect touch actions of the user on the touch screen, convert the touch actions into touch signals and send the touch signals to the processor 170, and can receive commands from the processor 170 and execute the commands; the touch signals at least include touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, the other input devices 132 can include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), trackballs, mice, joysticks, etc.

[0089] The input device 132 can receive inputted data, etc.

[0090] The display unit 140 can be used to display information inputted by the user or provided to the user, various menus of the terminal 100, interactive interfaces, file display, and / or playing of any kind of multimedia files.

[0091] The storage 120 can be used to store instructions and data. The storage 120 can mainly include a storage instruction area and a storage data area. The storage data area can store various data such as multimedia files, texts, etc.; the storage instruction area can store software units such as operating systems, applications, instructions required by at least one function, etc., or their subsets, expanded sets. It can also include a non-volatile random access memory; to provide the processor 170 with software and applications that include management of hardware, software, and data resources in the computing processing device, support control. It is also used for storage of multimedia files, and storage of running programs and applications.

[0092] The processor 170 is the control center of the terminal 100, connects each part of the whole terminal 100 by various interfaces and lines, executes various functions of the terminal 100 and processes data by running or executing instructions stored in the memory 120 and calling data stored in the memory 120, thereby performing overall control on the terminal device. Optionally, the processor 170 can include one or more processing units; preferably, the processor 170 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, the user interface and the application program, and the modem processor mainly processes the wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 170. In some embodiments, the processor, the memory, can be realized on a single chip, and in some embodiments, they can also be realized on independent chips respectively. The processor 170 can also be used to generate corresponding operation control signals to send to corresponding components of the computing processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein executes corresponding functions, thereby controlling corresponding components to act according to the requirements of the instructions.

[0093] The memory 120 can be used to store software codes related to the vehicle alignment guiding method, and the processor 170 can execute the steps of the vehicle alignment guiding method, or can also schedule other units (such as the above-mentioned input unit 130 and the display unit 140) to realize corresponding functions.

[0094] The RF unit 110 (optional) can be used to receive and send signals in the process of information or communication, for example, receiving the downlink information of the base station, and processing by the processor 170. In addition, the uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0095] In the embodiments of the present application, the RF unit 110 can send data to the server 200 and receive the processing result sent by the server 200.

[0096] It should be understood that the RF unit 110 is optional, which can be replaced by other communication interfaces, for example, a network interface.

[0097] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so as to realize the functions of managing charging, discharging, and power consumption management through the power management system.

[0098] The terminal 100 also includes an external interface 180, which can be a standard Micro USB interface or a multi-pin connector, and can be used to connect the terminal 100 and other devices for communication, or can be used to connect a charger to charge the terminal 100.

[0099] Although not shown, the terminal 100 can also include a flash, a Wireless Fidelity (WiFi) module, a Bluetooth module, different function sensors, etc., which will not be described here. Some or all of the methods described below can be applied in the terminal 100 as shown. Figure 2

[0100] ​Next, the product form of the server 200 is described. Figure 1 The product form of the server 200 is described.

[0101] Figure 3 A structural diagram of the server 200 is provided, as shown in the figure. Figure 3 The server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate through the bus 201.

[0102] The bus 201 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 In the figure, only one thick line is used, but it does not mean that there is only one bus or one type of bus.

[0103] The processor 202 can be any one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Micro Processor (MP), or a Digital Signal Processor (DSP), etc.

[0104] The memory 204 can include a volatile memory (Volatile Memory), such as a Random Access Memory (RAM). The memory 204 can also include a non-volatile memory (Non-Volatile Memory), such as a Read-Only Memory (ROM), a flash memory, a mechanical hard disk (Hard Disk Drive, HDD), or a solid state disk (Solid State Drive, SSD).

[0105] The memory 204 can be used to store software code related to the vehicle alignment guiding method, and the processor 202 can execute the steps of the vehicle alignment guiding method of the chip, or can schedule other units to realize the corresponding functions.

[0106] It should be understood that the terminal 100 and the server 200 described above can be centralized or distributed devices, and the processors (for example, the processor 170 and the processor 202) in the terminal 100 and the server 200 can be hardware circuits (for example, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a general-purpose processor, a DSP, a microprocessor, a microcontroller, or the like) or a combination of the hardware circuits, for example, the processor can be a hardware system with an instruction execution function, such as a CPU, a DSP, or the like, or a hardware system without an instruction execution function, such as an ASIC, an FPGA, or the like, or a combination of the hardware system without the instruction execution function and the hardware system with the instruction execution function.

[0107] The application provides a vehicle positioning guidance method.

[0108] The vehicle positioning guidance method of the application will be described in detail below with reference to the accompanying drawings.

[0109] Referring to Figure 4 , Figure 4 A flowchart of a vehicle positioning guidance method provided by the application is shown in FIG. 1. The method can include the following steps.

[0110] In step S401, target point cloud data in a region of interest of a target lane is acquired.

[0111] The target point cloud data includes point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar.

[0112] Referring to Figure 5 A structure diagram of a CPS precise positioning system provided by the application is shown in FIG. 2. Here, CPS refers to Chassis / Container-vehicle Positioning System, that is, a chassis / container vehicle positioning system. Figure 5 The application can collect original point cloud data in a scanning area of a multi-line laser radar, and the original point cloud data can be transmitted to a terminal device by using a User Datagram Protocol (UDP) through a local area network, and then the terminal device processes the original point cloud data to obtain target point cloud data in a region of interest (ROI) of a target lane.

[0113] The scanning area of ​​the aforementioned multi-line lidar covers the target lane. Optionally, the target lane includes at least one lane, meaning the scanning area of ​​the multi-line lidar covers at least one lane. Therefore, this embodiment can use the same multi-line lidar to simultaneously acquire target point cloud data within the regions of interest of multiple lanes, and perform subsequent processing separately for each lane.

[0114] Optionally, the aforementioned target point cloud data can be obtained by processing one or more frames of raw point cloud data acquired by a multi-line lidar.

[0115] Optionally, the raw point cloud data is data encapsulated into a data packet by the radar manufacturer according to its own supported format. Based on this, the process of processing the raw point cloud data includes: processing the raw point cloud data into readable point cloud data through the lidar driver, and filtering the readable point cloud data to remove point cloud data from areas of non-interest to prevent noise interference.

[0116] Optionally, this embodiment can obtain the task information corresponding to the container, obtain the current operation type from the task information, and determine the region of interest and relevant parameter thresholds of the target lane based on the current operation type. Here, the relevant parameter thresholds are used to assist in determining the following alignment guidance information.

[0117] For example, in this embodiment, the terminal device can also communicate with the cloud backend via a communication device (e.g., Figure 5 The system communicates with the communication antenna shown to obtain the task information corresponding to the container on the target vehicle from the cloud backend (the target point cloud data will be obtained according to step S401 only after the task information is obtained), and obtains the current operation type from the task information to determine the region of interest of the target lane and various subsequent parameter thresholds (including but not limited to the occlusion ratio threshold, preset filtering threshold, preset mean threshold and preset difference threshold mentioned below) based on the current operation type.

[0118] Optionally, the current operation type can be determined based on one or more of the following: number of containers, container model, and container location. Here, the number of containers refers to the number of containers loaded on the target vehicle; for example, the operation type can be divided into single-container type and multi-container type based on the number of containers. The container model refers to the size of the container; for example, the operation type can be divided into small-container type and large-container type based on the container model. The container location refers to the position of the container on the target vehicle.

[0119] It should be noted that the above-mentioned current job type is only an example. In addition, the current job type can be other types, and this application does not make specific limitations.

[0120] Optionally, the position of the region of interest is different for different types of work. Based on this, the process of dividing the region of interest can include: determining the loading and unloading area of the container on the target vehicle and the viewing angle range of the multi-line laser radar according to the current type of work, determining the initial region according to the viewing angle range of the multi-line laser radar and the loading and unloading area of the container on the target vehicle, and then performing secondary division on the initial region according to each lane to obtain the region of interest of each lane, that is, the region of interest of the target lane described above.

[0121] Referring to Figure 6 and Figure 7 , Figure 6 is a side view of the ROI region determined when the multi-line laser radar is installed on the overhead crossbeam of the lane, Figure 7 is a front view of the ROI region determined when the multi-line laser radar is installed on the overhead crossbeam of the lane.

[0122] When the target vehicle enters the scanning area of the multi-line laser radar, the side view of the ROI region shown by the triangular region of Figure 6 , and the front view of the ROI region shown by the triangular region of Figure 7 may be obtained when the target vehicle reaches the preset position. As shown in Figure 7 , the target lane includes lane 1 and lane 2, and then the ROI region determined by Figure 6 and Figure 7 includes the ROI region of lane 1 and the ROI region of lane 2.

[0123] Optionally, after obtaining the ROI region, the embodiment can take the position of the multi-line laser radar as the coordinate origin, the direction of the lane as the positive direction of the Y axis, the direction of the vehicle away from the lane as the negative direction of the Y axis (for example Figure 6 , the right side of the radar as the positive direction of the Y axis, and the left side of the radar as the negative direction of the Y axis), and the upward direction perpendicular to the ground as the positive direction of the Z axis, to obtain the positive direction of the X axis according to the right-hand screw rule.

[0124] Optionally, the ROI region is a cuboid region, and then the process of "performing point cloud screening on the readable point cloud data to remove the point cloud data in the non-region of interest" can include: performing straight-through filtering processing on the readable point cloud data to obtain target point cloud data in the cuboid region.

[0125] Step S402, determining the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data.

[0126] Here, the minimum lane distance refers to the minimum distance between the target vehicle and the multi-line laser radar in the Y axis.

[0127] It should be understood that as the target vehicle gradually approaches the multi-line laser radar, the area of the front vertical surface of the container on the target vehicle scanned by the laser beam in the multi-line laser radar gradually decreases due to the problem of head occlusion, so the number of point clouds on the front vertical surface gradually decreases, and the number of point clouds on the top surface of the container gradually increases. Here, the front vertical surface refers to the surface of the container closest to the multi-line laser radar and perpendicular to the ground, and the top surface refers to the uppermost surface of the container.

[0128] It should be understood that the more the number of point clouds, the higher the accuracy of the alignment guidance. Therefore, the present embodiment can determine the minimum lane distance of the target vehicle from the multi-line laser radar, so as to screen a proper number of point cloud data according to the minimum lane distance for subsequent alignment guidance.

[0129] Step S403, determine whether the minimum lane distance is greater than a preset positioning reference threshold, if yes, execute step S404, if no, execute step S405.

[0130] Step S404, determine first point cloud data located on the front vertical surface of the container from the target point cloud data, and determine alignment guidance information of the target vehicle according to the first point cloud data.

[0131] In the present embodiment, the positioning reference threshold is determined in advance. In the case where the minimum lane distance is greater than the preset positioning reference threshold, the distance between the target vehicle and the multi-line laser radar is far, at this time, the number of point clouds on the front vertical surface is greater than the number of point clouds on the top surface, then the present embodiment can screen the point cloud data on the front vertical surface of the container from the target point cloud data, for the convenience of the following description, the point cloud data on the front vertical surface is defined as the first point cloud data.

[0132] Further, the present embodiment can position the target vehicle and the container according to the first point cloud data to obtain alignment guidance information with higher accuracy.

[0133] Optionally, the alignment guidance information includes a deviation value of the center line of the container from the center line of the spreaders (claws).

[0134] Step S405, determine second point cloud data located on the top surface of the container from the target point cloud data, and determine alignment guidance information according to the second point cloud data.

[0135] In the case where the minimum lane distance is less than or equal to the positioning reference threshold, the distance between the target vehicle and the multi-line laser radar is very close, at this time, the number of point clouds on the front vertical surface is less than the number of point clouds on the top surface, then the present embodiment can screen the point cloud data on the top surface of the container from the target point cloud data, for the convenience of the following description, the point cloud data on the top surface is defined as the second point cloud data.

[0136] Further, the embodiment can position the target vehicle and the container according to the second point cloud data to obtain more accurate alignment guidance information.

[0137] Further, as Figure 5 After the terminal device obtains the alignment guidance information, the terminal device can send the alignment guidance information to the communication antenna, so as to send the alignment guidance information to the cloud background or the target vehicle through the communication antenna, and realize alignment guidance of the target vehicle. In this way, the target vehicle moves according to the alignment guidance information once each time the alignment guidance information is sent to the target vehicle, and then parks after the movement is completed, waits for the next alignment guidance to prevent position errors caused by communication time delay during movement, repeatedly guides until the gap meets the operation error requirement, and then the whole guidance process is completed, and the vehicle starts task operation. During the period, each lane can be independently guided for operation, and additional lane switching and other operations are not required.

[0138] The vehicle alignment guidance method provided in the application obtains target point cloud data in a region of interest of a target lane, determines a minimum lane distance between a target vehicle and a multi-line laser radar according to the target point cloud data, determines first point cloud data located on a front vertical surface of a container from the target point cloud data in a case where the minimum lane distance is greater than a preset positioning reference threshold, determines alignment guidance information of the target vehicle according to the first point cloud data, determines second point cloud data located on a top surface of the container from the target point cloud data in a case where the minimum lane distance is less than or equal to the positioning reference threshold, and determines the alignment guidance information according to the second point cloud data. The application can simultaneously scan target point cloud data in the region of interest through the multi-line laser radar, and there is no time difference caused by scanning, so that even if the target vehicle moves, there is no distance error of points on the same plane, and the accuracy of the alignment guidance information is improved. At the same time, the multi-line laser radar can emit multiple laser beams from multiple angles, so the multi-line laser radar does not need to be mounted on a rotating holder, the cost is saved, and the multiple laser beams are synchronously emitted, and there is no need for additional synchronization and summary processing, and the complexity of the vehicle alignment guidance process is reduced.

[0139] In some embodiments of the application, the determination process of the positioning reference threshold in the foregoing step S403 is introduced.

[0140] Optionally, the determination process of the positioning reference threshold can include: obtaining position information of the multi-line laser radar; determining a point cloud occlusion ratio on the front vertical surface according to the position information of the multi-line laser radar and the target point cloud data; and determining the positioning reference threshold according to the minimum lane distance when the point cloud occlusion ratio is greater than a preset occlusion ratio threshold.

[0141] Optionally, the position information of the multi-line laser radar comprises an installation position and an inclination angle of the multi-line laser radar, and the inclination angle can be used to obtain a scanning area of the multi-line laser radar.

[0142] In a specific implementation, the embodiment can obtain the target point cloud data according to the foregoing description during the process that the target vehicle gradually approaches the multi-line laser radar from a distance, and then determine the occlusion area on the front vertical surface according to the position information of the multi-line laser radar and the target point cloud data, divide the occlusion area by the total area of the front vertical surface to obtain the point cloud occlusion ratio on the front vertical surface. At the same time, the minimum lane distance corresponding to the target point cloud data can be obtained according to the foregoing description. When the target vehicle is located at different positions, different target point cloud data can be obtained, and then different point cloud occlusion ratios and minimum lane distances can be obtained.

[0143] It should be understood that the greater the point cloud occlusion ratio on the front vertical surface, that is, the greater the occlusion area, the fewer the point cloud on the front vertical surface, and the lower the accuracy and success rate of the alignment guidance based on the point cloud data on the front vertical surface. The embodiment can pre-set an occlusion ratio threshold value that makes the accuracy and success rate of the alignment guidance meet the requirements, and then compare the point cloud occlusion ratios obtained when the target vehicle is at different positions with the pre-set occlusion ratio threshold value. Here, if the point cloud occlusion ratio is greater than the occlusion ratio threshold value, it means that the number of point clouds on the front vertical surface is insufficient to obtain alignment guidance information with the required accuracy and success rate; otherwise, if the point cloud occlusion ratio is less than or equal to the occlusion ratio threshold value, it means that the number of point clouds on the front vertical surface is sufficient to obtain alignment guidance information with the required accuracy and success rate.

[0144] Optionally, the embodiment can determine the minimum lane distance when the point cloud occlusion ratio first exceeds the occlusion ratio threshold value during the process that the target vehicle gradually approaches the multi-line laser radar from a distance as the positioning reference threshold value.

[0145] For example, assuming that the target vehicle sequentially passes through position 1, position 2, position 3, position 4 and position 5 during the process that the target vehicle gradually approaches the multi-line laser radar from a distance, the point cloud occlusion ratio 1 and the minimum lane distance 1 are obtained according to the target point cloud data obtained at position 1, the point cloud occlusion ratio 2 and the minimum lane distance 2 are obtained according to the target point cloud data obtained at position 2, the point cloud occlusion ratio 3 and the minimum lane distance 3 are obtained according to the target point cloud data obtained at position 3, the point cloud occlusion ratio 4 and the minimum lane distance 4 are obtained according to the target point cloud data obtained at position 4, and the point cloud occlusion ratio 5 and the minimum lane distance 5 are obtained according to the target point cloud data obtained at position 5, assuming that the point cloud occlusion ratios 1, 2 and 3 are all less than the occlusion ratio threshold value, and the point cloud occlusion ratios 4 and 5 are both greater than the occlusion ratio threshold value, then the embodiment can determine the minimum lane distance 4 as the positioning reference threshold value.

[0146] Optionally, the specific value of the occlusion ratio threshold can be determined according to the job type obtained in the foregoing, for example, in a certain job type, when the occlusion ratio threshold is 50%, the positioning reference threshold is -3.0 meters.

[0147] In summary, the embodiment can accurately determine the positioning reference threshold through the point cloud occlusion ratio on the front vertical surface of the container, thereby improving the accuracy of the alignment guidance information.

[0148] As introduced in the foregoing, the embodiment uses multiple laser beam bundles of the multi-line laser radar to collect point cloud data, and the target point cloud data includes point cloud data corresponding to the multiple laser beam bundles of the multi-line laser radar, for example, the embodiment can label each target point cloud data with a label of the laser beam bundle to which the target point cloud data belongs, for distinction.

[0149] Further, the embodiment can determine minimum coordinate values Ymin of the point cloud data corresponding to the multiple laser beam bundles in the lane direction (i.e., the Y-axis direction) respectively, to obtain minimum coordinate values Ymin corresponding to the multiple laser beam bundles respectively, and determine the minimum lane distance according to the minimum coordinate values Ymin corresponding to the multiple laser beam bundles respectively.

[0150] As introduced in the foregoing, the positive direction of the Y-axis direction is the direction of the oncoming vehicle, and therefore, for each laser beam bundle, the point cloud with the minimum Y coordinate value in all the point clouds collected by the laser beam bundle is the edge point cloud of the target vehicle, i.e., the point cloud closest to the multi-line laser radar.

[0151] In a possible implementation, considering that generally, the target vehicle is straight in the lane direction, even if it is inclined, the inclination angle is not large, based on this, the embodiment can determine any one of the minimum coordinate values corresponding to the multiple laser beam bundles as the minimum lane distance (i.e., determine the minimum coordinate value corresponding to any one of the multiple laser beam bundles as the minimum lane distance between the target vehicle and the multi-line laser radar), or determine the minimum value of the minimum coordinate values Ymin corresponding to the multiple laser beam bundles as the minimum lane distance.

[0152] In a more preferred implementation, the embodiment can also calculate the average of the minimum coordinate values corresponding to the multiple laser beam bundles, and the average can be used as the minimum lane distance.

[0153] Of course, in addition to the above implementation, the process of "determining the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data" can also have other implementations, which are not limited by the present application.

[0154] As introduced above, when the minimum lane distance is greater than the positioning reference threshold, the alignment guidance can be performed based on the point cloud on the front vertical surface. Optionally, in this scenario, the vertical surface point cloud straight line fitting method can be used to obtain the alignment guidance information.

[0155] To this end, optionally, the process of "determining the first point cloud data on the front vertical surface of the container from the target point cloud data" can include: projecting the point cloud data corresponding to the plurality of laser beams respectively onto the coordinate axis in the lane direction to obtain the projected point cloud data, screening the vertical surface point cloud data from the projected point cloud data, performing coordinate restoration processing on the vertical surface point cloud data to obtain the coordinate-restored target vertical surface point cloud data, clustering the target vertical surface point cloud data to obtain the front vertical surface point cloud clustering cluster, and obtaining the first point cloud data according to the front vertical surface point cloud clustering cluster.

[0156] Specifically, the embodiment can project the point cloud data corresponding to the plurality of laser beams respectively onto the Y coordinate axis to obtain the projected point cloud data in the form of (0, Y, 0).

[0157] It should be understood that when the inclination angle of the target vehicle (container) is very small, the Y coordinate values of the point cloud data on the same vertical surface (the vertical surface in the present application refers to a surface perpendicular to the ground and approximately perpendicular to the lane direction, i.e., the Y coordinate axis, and the approximately perpendicular refers to a surface with an included angle of 45-90 degrees with the lane direction) differ very little. After being projected onto the Y coordinate axis, the point cloud data on the same vertical surface will be clustered together, and the point cloud data on the non-vertical surface will be relatively dispersed. Based on this, the embodiment can perform rough extraction of the vertical surface point cloud based on the projected point cloud data to obtain the vertical surface point cloud data, and then perform coordinate restoration and clustering processing on the vertical surface point cloud data, i.e., the front vertical surface point cloud clustering cluster can be obtained.

[0158] Optionally, the process of "screening the vertical surface point cloud data from the projected point cloud data, and performing coordinate restoration processing on the vertical surface point cloud data to obtain the coordinate-restored target vertical surface point cloud data" can include: removing the point cloud data at the non-vertical surface position from the projected point cloud data by using the radius filtering algorithm with a preset filtering threshold, and then performing coordinate restoration on the remaining point cloud data to obtain the target vertical surface point cloud data.

[0159] Optionally, the process of "clustering the target vertical surface point cloud data to obtain the front vertical surface point cloud clustering cluster" can include: separating the target vertical surface point cloud data and removing noise points by using the Euclidean clustering algorithm to obtain the point cloud clustering cluster of the vehicle head, the front vertical surface and other vertical surfaces, and then determining the front vertical surface point cloud clustering cluster from them.

[0160] Referring to FIG. 6, which is a separation effect diagram of the front vertical surface point cloud clustering cluster. As shown in FIG. 6, the point cloud data on the front vertical surface of the container is clustered together, and the point cloud data on the non-vertical surface is relatively dispersed. Figure 8 Figure 8 ​The uppermost horizontal line is the Y coordinate axis, the lowermost multiple line bundles are multiple point cloud data corresponding to multiple laser line bundles respectively, and the multiple white points in the middle dashed box are the front vertical surface point cloud clustering cluster. It can be seen that the Y coordinate values of the point cloud data in the front vertical surface point cloud clustering cluster are relatively close.

[0161] In an optional embodiment, the present embodiment can directly determine the point cloud data in the front vertical surface point cloud clustering cluster as the first point cloud data.

[0162] In another optional embodiment, considering that the previous clustering process may not be accurate enough, resulting in the possibility of including noise point cloud data not on the front vertical surface in the front vertical surface point cloud clustering cluster, in order to eliminate these noise point cloud data, the present embodiment can calculate the mean value of the Y coordinate values of all point cloud data in the front vertical surface point cloud clustering cluster as the lane direction mean value, and then eliminate the point cloud data with a difference greater than a preset mean value threshold from the front vertical surface point cloud clustering cluster. The remaining point cloud data is the first point cloud data.

[0163] The present embodiment can ensure that the first point cloud data is more accurate and aggregated through noise point cloud data elimination processing.

[0164] After obtaining the first point cloud data, optionally, the present embodiment can perform straight line fitting based on the first point cloud data to obtain a preset parameter value corresponding to the fitted straight line. Optionally, the preset parameter value includes: a projection coordinate value of any point on the fitted straight line on the X coordinate axis and a direction vector of the fitted straight line .

[0165] Optionally, the RANSAC algorithm can be used to perform straight line fitting on the first point cloud data. Here, the RANSAC (Random Sample Consensus) algorithm is a widely used iterative parameter estimation algorithm for fitting mathematical models from data containing noise and outliers. The advantage is that it has good robustness to data containing outliers and noise, and can estimate the accurate model in the data set containing outliers without requiring prior knowledge of the number of outliers.

[0166] The present embodiment uses the RANSAC algorithm for straight line fitting, which can effectively eliminate the influence of outliers in the first point cloud data and fit a more accurate straight line equation for positioning the target vehicle and container.

[0167] Further, the distance and heading angle deviation value of the front vertical surface and the multi-line laser radar can be obtained according to the preset parameter value corresponding to the fitted straight line. Here, the heading angle deviation value refers to the difference between the actual heading angle of the container and the standard heading angle.

[0168] Optionally, the following formula (1) can be used to obtain the distance from the coordinate origin, i.e., the position of the multi-line laser radar, to the fitted straight line The distance is also referred to as the distance from the front vertical surface to the multi-line laser radar.

[0169] Formula (1).

[0170] Optionally, the following formula (2) can be used to obtain the arctangent value of the slope of the fitted straight line The arctangent value is also referred to as the heading angle deviation value.

[0171] Formula (2).

[0172] Finally, the present embodiment can obtain the alignment guidance information according to the distance from the front vertical surface to the multi-line laser radar and the heading angle deviation value.

[0173] As introduced above, when the minimum lane distance is less than or equal to the positioning reference threshold, alignment guidance can be performed based on the point cloud on the top surface. Optionally, in this scenario, the top boundary point extraction method can be used to obtain the alignment guidance information.

[0174] To this end, for each laser beam of the plurality of laser beams, the present embodiment can sort the point cloud data corresponding to the laser beam in descending order of the coordinate value in the lane direction to obtain a point cloud sorting result corresponding to the laser beam, and then determine the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam. In this way, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams can be obtained. Finally, the present embodiment can obtain the second point cloud data according to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams.

[0175] That is, the present embodiment can sort each point cloud data corresponding to each laser beam in descending order of the Y coordinate value, i.e., in descending order of the distance from the point cloud data to the multi-line laser radar, to obtain a point cloud sorting result of each point cloud data corresponding to each laser beam.

[0176] Optionally, the process of "determining the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam" can include: determining the point cloud data ranked first in the point cloud sorting result corresponding to the laser beam as the rear side boundary point cloud data corresponding to the laser beam; and sequentially calculating the coordinate difference of adjacent point cloud data in the lane direction according to the sequence from front to back in the point cloud sorting result corresponding to the laser beam to obtain target adjacent point cloud data that first makes the coordinate difference less than a preset difference threshold, and determining the previous point cloud data in the target adjacent point cloud data as the front side boundary point cloud data corresponding to the laser beam.

[0177] Here, the rear side boundary point cloud data corresponding to a laser beam refers to the point cloud data on the top surface rear side boundary collected by the laser beam, and the rear side boundary refers to the side boundary of the top surface far from the multi-line laser radar beam; the front side boundary point cloud data corresponding to a laser beam refers to the point cloud data on the top surface front side boundary collected by the laser beam, and the front side boundary refers to the side boundary of the top surface close to the multi-line laser radar beam.

[0178] For example, the point cloud sorting result corresponding to a laser beam is point cloud data 1, point cloud data 2, point cloud data 3, …, and point cloud data n from front to back (i.e., the Y coordinate value from large to small), and the embodiment can determine the point cloud data 1 as the rear side boundary point cloud data corresponding to the laser beam.

[0179] Then the coordinate difference ΔY1 of the Y coordinate values of the point cloud data 2 and the point cloud data 1 can be calculated, and the size of ΔY1 and the preset difference threshold is compared, if ΔY1 is less than the preset difference threshold, the point cloud data 1 is determined as the front side boundary point cloud data corresponding to the laser beam.

[0180] If ΔY1 is greater than or equal to the preset difference threshold, the coordinate difference ΔY2 of the Y coordinate values of the point cloud data 3 and the point cloud data 2 is calculated, and the size of ΔY2 and the preset difference threshold is compared, if ΔY2 is less than the preset difference threshold, the point cloud data 2 is determined as the front side boundary point cloud data corresponding to the laser beam.

[0181] If ΔY2 is greater than or equal to the preset difference threshold, the coordinate difference ΔY3 of the Y coordinate values of the point cloud data 4 and the point cloud data 3 is calculated, and so on, until the front side boundary point cloud data corresponding to the laser beam is determined.

[0182] Optionally, the embodiment can only take the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams as the second point cloud data; optionally, the embodiment can also obtain all point cloud data on the top surface according to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams, and take all point cloud data as the second point cloud data.

[0183] As an example of taking only the back side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser line beams as the second point cloud data, the embodiment can optionally group the front side boundary point cloud data corresponding to each of the plurality of laser line beams into a first point cloud set, group the back side boundary point cloud data corresponding to each of the plurality of laser line beams into a second point cloud set, and then position the target vehicle and the container according to the first point cloud set and the second point cloud set by using a straight line fitting method or an extreme value removal and average calculation method, to obtain the alignment guide information.

[0184] Optionally, the process of positioning the target vehicle and the container according to the first point cloud set and the second point cloud set by using the straight line fitting method can include: performing straight line fitting on the first point cloud set and the second point cloud set respectively to obtain fitting straight lines corresponding to the first point cloud set and the second point cloud set respectively, and positioning the target vehicle and the container according to the fitting straight lines corresponding to the first point cloud set and the second point cloud set respectively to obtain the alignment guide information.

[0185] Optionally, the process of positioning the target vehicle and the container according to the first point cloud set and the second point cloud set by using the extreme value removal and average calculation method can include: removing extreme values and calculating averages in the non-lane direction (i.e., the X direction) for the first point cloud set and the second point cloud set respectively to obtain averages of the first point cloud set and the second point cloud set in the non-lane direction respectively, and positioning the target vehicle and the container according to the averages of the first point cloud set and the second point cloud set in the non-lane direction respectively to obtain the alignment guide information.

[0186] In summary, the embodiment of the present application divides two scenarios according to the minimum lane distance, can achieve the purpose of optimally utilizing point cloud data for multi-lane automatic precise alignment, and provides support for the needs of efficient container loading and unloading business of the target vehicle (such as an automatic driving container truck), and improves the success rate of alignment guide for container loading and unloading business.

[0187] It should be further noted that on the basis of the foregoing embodiments, the present application can also be improved as follows:

[0188] (1) Compared with a single-line laser radar, the scanning frequency of a multi-line laser radar when continuously covering multiple lanes can remain at a high level. Therefore, when obtaining the target point cloud data in the foregoing, multiple frames of target point cloud data (one frame of target point cloud data is obtained by one scanning of the multi-line laser radar through the plurality of laser line beams) can be obtained. Then, the multiple frames of target point cloud data can be summarized together, and the alignment guide information can be determined according to steps S402-S405; or each frame of target point cloud data can be determined according to steps S402-S405, and then the alignment guide information determined by the multiple frames of target point cloud data can be processed by weighted fusion (for example, a weighted average value is calculated), to obtain the final alignment guide information.

[0189] By collecting multiple frames of target point cloud data, the influence of occasional abnormal values on the guiding effect can be effectively reduced, and the stability and accuracy of the system output can be enhanced.

[0190] (2) In order to effectively utilize the advantages of the multi-line laser radar, the terminal device can select the algorithm complexity and the program structure according to the actual situation, control the calculation time of a single frame of target point cloud data, so that more frames of target point cloud data can be processed within the same time window, thereby achieving the purpose of optimizing the overall guiding effect by utilizing multiple frames of target point cloud data in the foregoing (1).

[0191] (3) The efficiency of the alignment guiding can be improved by optimizing the program structure, for example, the main program obtains each frame of raw point cloud data through laser radar driving, and then performs batch processing to obtain each frame of target point cloud data, and then a process instance is created for each lane to run the subsequent positioning algorithm, thereby optimizing the data processing efficiency of the program as much as possible.

[0192] (4) The algorithm complexity of the alignment guiding can be improved by the installation position of the multi-line laser radar. Preferably, the multi-line laser radar is installed at the front side of the working point, which needs to cover the position in the middle of the lane, which helps to better extract the point cloud of the straight edge part of the target vehicle from the target point cloud data. Of course, if the on-site conditions are not met, it can also be installed on the side of the working position, but the details of the foregoing embodiment may need to be adjusted, and the straight line fitting is performed on the side of the container or the vehicle head to calculate the guiding value solution, in addition, the installation angle of the multi-line laser radar needs to be calculated in combination with the lateral scanning angle of the multi-line laser radar, so as to correctly cover the target lane.

[0193] In addition to the above four possible improvements, the present application can have other improvements, which are not limited in the present application.

[0194] The above introduces a vehicle alignment guiding method provided by the embodiment of the present application, and the device for executing the above vehicle alignment guiding method will be introduced below.

[0195] Please refer to Figure 9 , Figure 9 The structure diagram of a vehicle alignment guiding device provided by the embodiment of the present application. As Figure 9 shown, the device can include:

[0196] The point cloud acquisition module 501 is configured to acquire target point cloud data in a region of interest of a target lane, wherein the target point cloud data includes point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar.

[0197] The distance determination module 502 is configured to determine the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data.

[0198] The first alignment module 503 is configured to determine, from the target point cloud data, first point cloud data located on a front vertical surface of the container when the minimum lane distance is greater than a preset alignment reference threshold, and determine alignment guide information of the target vehicle according to the first point cloud data.

[0199] The second alignment module 504 is configured to determine, from the target point cloud data, second point cloud data located on a top surface of the container when the minimum lane distance is less than or equal to the alignment reference threshold, and determine alignment guide information according to the second point cloud data.

[0200] In a possible implementation, the process of determining the alignment reference threshold in the first alignment module and the second alignment module can include:

[0201] obtaining position information of the multi-line laser radar;

[0202] determining a point cloud occlusion ratio on the front vertical surface according to the position information of the multi-line laser radar and the target point cloud data;

[0203] determining the alignment reference threshold according to the minimum lane distance when the point cloud occlusion ratio is greater than a preset occlusion ratio threshold.

[0204] In a possible implementation, the target point cloud data described above includes point cloud data corresponding to a plurality of laser beams of the multi-line laser radar respectively.

[0205] Therefore, the process of determining, by the distance determination module, the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data can include:

[0206] determining minimum coordinate values of the point cloud data corresponding to the plurality of laser beams respectively in the lane direction as minimum coordinate values corresponding to the plurality of laser beams respectively;

[0207] determining the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively.

[0208] In a possible implementation, the process of determining, by the distance determination module, the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively can include:

[0209] determining any value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance;

[0210] or, determining the minimum value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance;

[0211] or, calculating an average value of the minimum coordinate values corresponding to the plurality of laser beams respectively, and determining the average value as the minimum lane distance.

[0212] In a possible implementation, the process in which the first alignment module determines the first point cloud data located on the front vertical surface of the container from the target point cloud data can include:

[0213] projecting the point cloud data corresponding to the plurality of laser line beams respectively onto a coordinate axis in the lane direction to obtain projected point cloud data;

[0214] screening vertical surface point cloud data from the projected point cloud data;

[0215] performing coordinate restoration processing on the vertical surface point cloud data to obtain target vertical surface point cloud data subjected to coordinate restoration;

[0216] performing clustering on the target vertical surface point cloud data to obtain a front vertical surface point cloud clustering cluster;

[0217] obtaining the first point cloud data according to the front vertical surface point cloud clustering cluster.

[0218] In a possible implementation, the process in which the first alignment module obtains the first point cloud data according to the front vertical surface point cloud clustering cluster can include:

[0219] determining the point cloud data in the front vertical surface point cloud clustering cluster as the first point cloud data;

[0220] or, removing, from the front vertical surface point cloud clustering cluster, point cloud data whose difference between the coordinate value in the lane direction and the average value in the lane direction is greater than a preset average value threshold, and taking the remaining point cloud data as the first point cloud data.

[0221] In a possible implementation, the process in which the first alignment module determines the alignment guide information of the target vehicle according to the first point cloud data can include:

[0222] performing straight line fitting based on the first point cloud data to obtain a preset parameter value corresponding to a fitted straight line;

[0223] obtaining a distance between the front vertical surface and the multi-line laser radar and a heading angle deviation value according to the preset parameter value corresponding to the fitted straight line, wherein the heading angle deviation value refers to a difference between an actual heading angle of the container and a standard heading angle;

[0224] obtaining the alignment guide information according to the distance between the front vertical surface and the multi-line laser radar and the heading angle deviation value.

[0225] In a possible implementation, the process in which the second alignment module determines the second point cloud data located on the top surface of the container from the target point cloud data can include:

[0226] for each laser line beam in the plurality of laser line beams:

[0227] sorting the point cloud data corresponding to the laser line beam in descending order of the coordinate value in the lane direction to obtain a point cloud sorting result corresponding to the laser line beam;

[0228] According to the point cloud sorting result corresponding to the laser beam, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam are determined;

[0229] According to the point cloud sorting result corresponding to the laser beam, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam are determined;

[0230] According to the point cloud sorting result corresponding to the laser beam, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam are determined;

[0231] In a possible implementation, the process that the second alignment module determines the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam can include:

[0232] The point cloud data ranked first in the point cloud sorting result corresponding to the laser beam is determined as the rear side boundary point cloud data corresponding to the laser beam;

[0233] In a possible implementation, the process that the second alignment module determines the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam can include:

[0234] The point cloud data ranked first in the point cloud sorting result corresponding to the laser beam is determined as the rear side boundary point cloud data corresponding to the laser beam;

[0235] In a possible implementation, the process that the second alignment module determines the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam according to the point cloud sorting result corresponding to the laser beam can include:

[0236] According to the front side boundary point cloud data corresponding to the plurality of laser beams, a first point cloud set is generated;

[0237] According to the rear side boundary point cloud data corresponding to the plurality of laser beams, a second point cloud set is generated;

[0238] The first point cloud set and the second point cloud set are taken as the second point cloud data.

[0239] Correspondingly, the process that the second alignment module determines the alignment guide information according to the second point cloud data can include:

[0240] According to the first point cloud set and the second point cloud set, and using a straight line fitting method or an extreme value removal and averaging method, the target vehicle and the container are positioned to obtain the alignment guide information.

[0241] In a possible implementation, the vehicle alignment guide device provided by the embodiment of the application can further include a target information determination module.

[0242] The target information determination module is configured to obtain task information corresponding to the container, obtain a current work type from the task information, and determine a region of interest of the target lane and a related parameter threshold according to the current work type, the related parameter threshold being used to assist in determining the alignment guidance information.

[0243] The vehicle alignment guidance device provided by the embodiments of the present application corresponds to the vehicle alignment guidance method provided in the foregoing, and details can be referred to the foregoing, which will not be described herein again.

[0244] An electronic device is further provided in the embodiments of the present application. As shown in Figure 10 The electronic device in the embodiments of the present application can include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a desktop computer, and the like. Figure 10 The electronic device shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0245] As shown in Figure 10 The electronic device can include a processing device (for example, a central processing unit, a graphics processing unit, and the like) 601, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded from a storage device 608 to a random access memory (RAM) 603. In a state that the electronic device is powered on, various programs and data required for operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0246] Generally, the following devices can be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage device 608 including, for example, a memory card, a hard disk, and the like; and a communication device 609. The communication device 609 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 10 The electronic device with various devices is shown, but it should be understood that it is not required to implement or have all the shown devices. More or fewer devices can be alternatively implemented or provided.

[0247] The embodiment of the present application further provides a computer program product comprising computer readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the vehicle alignment guiding methods provided by the embodiments of the present application.

[0248] The embodiment of the present application further provides a computer readable storage medium, which carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement any of the vehicle alignment guiding methods provided by the embodiments of the present application.

[0249] In addition, it should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments. In addition, the connection relationship between the modules in the apparatus embodiments provided by the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0250] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course, it can also be realized by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. Generally, functions completed by computer programs can be easily realized by corresponding hardware, and the specific hardware structure for realizing the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better embodiment. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, training device, or network device, etc.) execute the methods described in various embodiments of the present application.

[0251] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, it can be realized in the form of a computer program product in whole or in part.

[0252] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, training device or data center to another website, computer, training device or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be stored by the computer or a data storage device such as a training device, a data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

Claims

1. A vehicle alignment guidance method characterized by, The method comprises: acquiring target point cloud data in a region of interest of a target lane, wherein the target point cloud data comprises point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar; determining a minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data; in a case where the minimum lane distance is greater than a preset positioning reference threshold, determining first point cloud data on a front vertical surface of the container from the target point cloud data, and determining alignment guide information of the target vehicle according to the first point cloud data; in a case where the minimum lane distance is less than or equal to the positioning reference threshold, determining second point cloud data on a top surface of the container from the target point cloud data, and determining the alignment guide information according to the second point cloud data.

2. The vehicle alignment guidance method according to claim 1, characterized by, The determination process of the positioning reference threshold comprises: acquiring position information of the multi-line laser radar; determining a point cloud occlusion ratio on the front vertical surface according to the position information of the multi-line laser radar and the target point cloud data; determining the positioning reference threshold according to the minimum lane distance when the point cloud occlusion ratio is greater than a preset occlusion ratio threshold.

3. The vehicle alignment guidance method according to claim 1 or 2, characterized by, The target point cloud data comprises point cloud data corresponding to a plurality of laser beams of the multi-line laser radar respectively; The determination of the minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data comprises: determining minimum coordinate values of the point cloud data corresponding to the plurality of laser beams respectively in a lane direction as minimum coordinate values corresponding to the plurality of laser beams respectively; determining the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively; The determination of the minimum lane distance according to the minimum coordinate values corresponding to the plurality of laser beams respectively comprises: determining any value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance; or, determining a minimum value in the minimum coordinate values corresponding to the plurality of laser beams respectively as the minimum lane distance; or, calculating an average value of the minimum coordinate values corresponding to the plurality of laser beams respectively, and determining the average value as the minimum lane distance.

4. The vehicle alignment guidance method according to claim 3, characterized by, The determination of the first point cloud data on the front vertical surface of the container from the target point cloud data comprises: projecting the point cloud data corresponding to the plurality of laser beams respectively onto a coordinate axis in the lane direction to obtain projected point cloud data; screening vertical surface point cloud data from the projected point cloud data; performing coordinate restoration processing on the vertical surface point cloud data to obtain target vertical surface point cloud data subjected to coordinate restoration; performing clustering on the target vertical surface point cloud data to obtain a front vertical surface point cloud clustering cluster; obtaining the first point cloud data according to the front vertical surface point cloud clustering cluster; The obtaining of the first point cloud data according to the front vertical surface point cloud clustering cluster comprises: determining point cloud data in the front vertical surface point cloud clustering cluster as the first point cloud data. Or, from the front vertical surface point cloud clustering cluster, the point cloud data whose coordinate value difference in the lane direction and the lane direction mean value is greater than the preset mean value threshold is eliminated, and the remaining point cloud data is taken as the first point cloud data.

5. The vehicle alignment guidance method according to claim 1, characterized by, The alignment guide information of the target vehicle is determined according to the first point cloud data, including: Based on the first point cloud data, a straight line fitting is performed to obtain a preset parameter value corresponding to the fitting straight line; According to the preset parameter value corresponding to the fitting straight line, a distance and a heading angle deviation value between the front vertical surface and the multi-line laser radar are obtained, wherein the heading angle deviation value refers to the difference between the actual heading angle of the container and the standard heading angle; According to the distance and the heading angle deviation value between the front vertical surface and the multi-line laser radar, the alignment guide information is obtained.

6. The vehicle alignment guidance method according to claim 1, characterized by, The second point cloud data located on the top surface of the container is determined from the target point cloud data, including: For each laser beam in the plurality of laser beams: The point cloud data corresponding to the laser beam is sorted in descending order according to the coordinate value in the lane direction to obtain a point cloud sorting result corresponding to the laser beam; According to the point cloud sorting result corresponding to the laser beam, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam are determined; The rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams are obtained; According to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams, the second point cloud data is obtained.

7. The vehicle alignment guidance method according to claim 6, characterized by, According to the point cloud sorting result corresponding to the laser beam, the rear side boundary point cloud data and the front side boundary point cloud data corresponding to the laser beam are determined, including: The point cloud data ranked first in the point cloud sorting result corresponding to the laser beam is determined as the rear side boundary point cloud data corresponding to the laser beam; According to the order from front to back of the point cloud sorting result corresponding to the laser beam, the coordinate difference in the lane direction of adjacent point cloud data is calculated in sequence to obtain target adjacent point cloud data that first makes the coordinate difference less than a preset difference threshold value; The previous point cloud data in the target adjacent point cloud data is determined as the front side boundary point cloud data corresponding to the laser beam.

8. The vehicle alignment guidance method according to claim 6, characterized by, According to the rear side boundary point cloud data and the front side boundary point cloud data corresponding to each of the plurality of laser beams, the second point cloud data is obtained, including: A first point cloud set is generated according to the front side boundary point cloud data corresponding to each of the plurality of laser beams; A second point cloud set is generated according to the rear side boundary point cloud data corresponding to each of the plurality of laser beams; The first point cloud set and the second point cloud set are taken as the second point cloud data; The alignment guide information is determined according to the second point cloud data, including: The target vehicle and the container are positioned by using a straight line fitting method or a method of removing extreme values and averaging the first point cloud set and the second point cloud set to obtain the alignment guide information.

9. The vehicle alignment guidance method according to claim 1, characterized by, Further comprising: Obtaining task information corresponding to the container; Obtaining a current work type from the task information; A region of interest and a related parameter threshold of the target lane are determined according to the current work type, and the related parameter threshold is used to assist in determining the alignment guidance information.

10. A vehicle alignment guidance device characterized by comprising: Comprise: a point cloud acquisition module, configured to acquire target point cloud data in a region of interest of a target lane, wherein the target point cloud data comprises point cloud data of a target vehicle and point cloud data of a container on the target vehicle collected by a multi-line laser radar; a distance determination module, configured to determine a minimum lane distance between the target vehicle and the multi-line laser radar according to the target point cloud data; a first alignment module, configured to, in a case where the minimum lane distance is greater than a preset alignment reference threshold, determine first point cloud data located on a front vertical surface of the container from the target point cloud data, and determine alignment guidance information of the target vehicle according to the first point cloud data; a second alignment module, configured to, in a case where the minimum lane distance is less than or equal to the alignment reference threshold, determine second point cloud data located on a top surface of the container from the target point cloud data, and determine the alignment guidance information according to the second point cloud data.

Images