WO2024093616A1 - 无人集卡对位方法、装置、设备及可读存储介质 - Google Patents

无人集卡对位方法、装置、设备及可读存储介质 Download PDF

Info

Publication number
WO2024093616A1
WO2024093616A1 PCT/CN2023/123470 CN2023123470W WO2024093616A1 WO 2024093616 A1 WO2024093616 A1 WO 2024093616A1 CN 2023123470 W CN2023123470 W CN 2023123470W WO 2024093616 A1 WO2024093616 A1 WO 2024093616A1
Authority
WO
WIPO (PCT)
Prior art keywords
container truck
unmanned container
alignment
unmanned
truck
Prior art date
Application number
PCT/CN2023/123470
Other languages
English (en)
French (fr)
Inventor
闫名慧
刘劲松
杨春
余文艳
孙权
Original Assignee
东风商用车有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东风商用车有限公司 filed Critical 东风商用车有限公司
Publication of WO2024093616A1 publication Critical patent/WO2024093616A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Definitions

  • the present invention relates to the field of unmanned container truck control in smart ports, and in particular to an unmanned container truck alignment method, device, equipment and readable storage medium.
  • ports mostly use manned container trucks to transport containers to complete ship loading operations.
  • the driver is required to manually park according to the manually placed parking rods under the port machinery, so that the subsequent port machinery can complete the container grabbing and releasing operations.
  • the above-mentioned method of using manned container trucks for parking is a safety hazard for the driver and the guide under the port machinery, and has low efficiency and high labor costs.
  • the main purpose of the present invention is to provide an unmanned container truck alignment method, device, equipment and readable storage medium, aiming to solve the technical problem in the prior art that when manned container trucks are parked, manual alignment is required, which is inefficient and has safety hazards.
  • the present invention provides an unmanned container truck alignment method, the unmanned container truck alignment method comprising the following steps:
  • the unmanned container truck is controlled to align.
  • a prompt message is output to prompt the port machinery equipment to load/unload the container;
  • the position of the unmanned container truck is adjusted based on the alignment information, and the process returns to the step of obtaining the alignment information of the unmanned container truck.
  • the method before the step of obtaining the alignment information of the unmanned container truck, the method includes:
  • the attitude angle value of the unmanned container truck relative to the target position is calculated based on the two target coordinates corresponding to the front of the unmanned container truck among the four target coordinates.
  • the method before the step of obtaining the alignment information of the unmanned container truck, the method includes:
  • test data is a plurality of sets of first test distance difference values and corresponding second test distance difference values between the unmanned container truck and the target position collected at a preset frequency
  • first test distance difference value is obtained by identifying the image of the unmanned container truck collected by a camera on the port machinery equipment
  • second test distance difference value is calculated based on the positioning information of the unmanned container truck and the target position
  • a second distance difference between the unmanned container truck and the target location is determined.
  • the step of constructing an error correction model based on test data includes:
  • a normal distribution curve is fitted, and an error correction model is constructed based on the normal distribution curve.
  • the step of adjusting the position of the unmanned container truck based on the alignment information includes:
  • the unmanned container truck is controlled to rotate along the target rotation direction by the target rotation angle, and to travel along the target driving direction by the target driving distance.
  • the method before the step of adjusting the position of the unmanned container truck based on the alignment information, the method further includes:
  • the unmanned truck will pause to adjust its position and wait or avoid obstacles.
  • the present invention further provides an unmanned container truck alignment device, the unmanned container truck alignment device comprising:
  • the alignment module is used to control the unmanned container truck to align based on the positioning information of the target position
  • An acquisition module is used to obtain the alignment information of the unmanned container truck
  • a determination module used to determine whether the unmanned container truck is successfully aligned based on the alignment information of the unmanned container truck;
  • a prompt module is used to output prompt information if the alignment is successful, so as to prompt the port machinery equipment to carry out container loading/unloading operations;
  • the adjustment module is used to adjust the position of the unmanned container truck based on the alignment information if the alignment is not successful, and return to the step of obtaining the alignment information of the unmanned container truck.
  • the unmanned container truck alignment device further includes a computing module, which is used to:
  • the attitude angle value of the unmanned container truck relative to the target position is calculated based on the two target coordinates corresponding to the front of the unmanned container truck among the four target coordinates.
  • the unmanned container truck alignment device further includes an error correction module, which is used to:
  • test data is a plurality of sets of first test distance difference values and corresponding second test distance difference values between the unmanned container truck and the target position collected at a preset frequency
  • first test distance difference value is obtained by identifying the image of the unmanned container truck collected by a camera on the port machinery equipment
  • second test distance difference value is calculated based on the positioning information of the unmanned container truck and the target position
  • a second distance difference between the unmanned container truck and the target location is determined.
  • the error correction module is further specifically used for:
  • the adjustment module is further specifically used for:
  • the unmanned container truck is controlled to rotate along the target rotation direction by the target rotation angle, and to travel along the target driving direction by the target driving distance.
  • the unmanned container truck alignment device further includes an obstacle warning module, which is used to:
  • the unmanned container truck will pause to adjust its position and wait or avoid obstacles on the spot.
  • the present invention also provides an unmanned container truck alignment device, which includes a processor, a memory, and an unmanned container truck alignment program stored in the memory and executable by the processor, wherein when the unmanned container truck alignment program is executed by the processor, the steps of the unmanned container truck alignment method described above are implemented.
  • the present invention further provides a readable storage medium, on which an unmanned container truck alignment program is stored, wherein when the unmanned container truck alignment program is executed by a processor, the steps of the unmanned container truck alignment method as described above are implemented.
  • the present invention provides an unmanned container truck alignment method, device, equipment and readable storage medium.
  • the unmanned container truck alignment method includes: controlling the unmanned container truck to align based on the positioning information of the target position; obtaining the alignment information of the unmanned container truck; determining whether the unmanned container truck is aligned successfully based on the alignment information of the unmanned container truck; if the alignment is successful, outputting prompt information to prompt the port machinery equipment to load/unload containers; if the alignment is not successful, adjusting the position of the unmanned container truck based on the alignment information, and returning to the step of obtaining the alignment information of the unmanned container truck.
  • the present invention can solve the problem that the manual parking of manned container trucks under port machinery equipment is inefficient and has potential safety hazards, and on this basis, ensure the alignment accuracy and safety reliability of the unmanned container truck, so that the overall interaction between the unmanned container truck and the port machinery equipment is safer and more efficient.
  • FIG1 is a schematic diagram of the hardware structure of an unmanned container truck alignment device involved in an embodiment of the present invention
  • FIG2 is a schematic diagram of a flow chart of an embodiment of an unmanned container truck alignment method according to the present invention.
  • FIG3 is a schematic flow chart of another embodiment of the unmanned container truck alignment method of the present invention.
  • FIG4 is a schematic flow chart of another embodiment of the unmanned container truck alignment method of the present invention.
  • FIG. 5 is a schematic diagram of functional modules of an embodiment of an unmanned container truck alignment device of the present invention.
  • an embodiment of the present invention provides an unmanned container truck alignment device.
  • FIG 1 is a schematic diagram of the hardware structure of the unmanned container truck alignment device involved in the embodiment of the present invention.
  • the unmanned container truck alignment device may include a processor 1001 (e.g., a central processing unit Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
  • processor 1001 e.g., a central processing unit Central Processing Unit, CPU
  • communication bus 1002 e.g., a central processing unit Central Processing Unit, CPU
  • user interface 1003 e.g., a user interface 1003, a network interface 1004, and a memory 1005.
  • the communication bus 1002 is used to realize the connection and communication between these components;
  • the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard);
  • the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as wireless fidelity WIreless-FIdelity, WI-FI interface);
  • the memory 1005 may be a high-speed random access memory (random access memory, RAM), or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
  • RAM random access memory
  • non-volatile memory such as a disk memory
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
  • FIG. 1 does not constitute a limitation on the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.
  • the memory 1005 as a computer storage medium in FIG. 1 may include an operating system, a network communication module, a user interface module, and an unmanned container truck alignment program.
  • the processor 1001 may call the unmanned container truck alignment program stored in the memory 1005 and execute the unmanned container truck alignment method provided in an embodiment of the present invention.
  • an embodiment of the present invention provides an unmanned container truck alignment method.
  • FIG. 2 is a schematic flow chart of an embodiment of an unmanned container truck alignment method according to the present invention.
  • the unmanned container truck alignment method comprises:
  • Step S10 based on the positioning information of the target position, controlling the unmanned container truck to align;
  • Step S20 obtaining the alignment information of the unmanned container truck
  • Step S30 determining whether the unmanned container truck is successfully aligned based on the alignment information of the unmanned container truck;
  • Step S40 if the alignment is successful, output a prompt message to prompt the port machinery to carry out container loading/unloading operations;
  • Step S50 If the alignment is not successful, the position of the unmanned container truck is adjusted based on the alignment information, and the process returns to the step of obtaining the alignment information of the unmanned container truck.
  • unmanned container trucks are used for automatic positioning to solve the problem that in the prior art, when manned container trucks are parked under port machinery equipment, manual positioning is required, which is inefficient and has safety hazards.
  • the target position corresponding to the high-precision positioning system and the positioning information of the unmanned container truck are first used for positioning.
  • there are problems such as positioning accuracy and safety reliability, which will lead to insufficient positioning success rate.
  • the positioning signal of the unmanned container truck under the bridge is floating, and the unmanned container truck may report an error and wait for the positioning signal to be restored on the spot;
  • the difference between the accuracy of the positioning signal and the longitude and latitude of the destination is greater than the preset difference (such as 5cm)
  • the unmanned container truck may need to re-circle and re-position. This repeated positioning will greatly affect the operating efficiency and may cause congestion;
  • the positioning signal is lost and no electronic fence is set in the map of the vehicle-side intelligent system, the vehicle is at risk of rushing into the sea at the quay bridge.
  • the alignment information of the unmanned container truck will be obtained in real time. Whether the unmanned container truck is successfully aligned is determined based on the judgment of the above alignment information. When it is determined that the alignment is successful, prompt information can be output, such as controlling the green light above the port machinery hoist, thereby indicating that the port machinery driver can carry out the grab/release operation of the box, that is, to prompt the port machinery equipment to load/unload containers. When it is determined that the unmanned container truck has not been successfully aligned, the position of the unmanned container truck can be adjusted based on the above alignment information.
  • the above-mentioned method of confirming the alignment result based on positioning information and alignment information can solve the problem of low efficiency and potential safety hazards in manual alignment parking of manned container trucks under port machinery equipment, and on this basis ensure the alignment accuracy and safety and reliability of unmanned container trucks.
  • step S20 the following steps are included:
  • Step S60 obtaining an image of the unmanned container truck captured by a camera on the port machinery equipment
  • Step S70 obtaining the front of the unmanned container truck and four sides of the position-limiting sub-frame based on the image recognition;
  • Step S80 marking the four vertex coordinates corresponding to the four sides of the limit subframe in the image coordinate system, and converting the four vertex coordinates into four corresponding target coordinates in the world coordinate system based on the SLAM algorithm;
  • Step S90 determining a first distance difference between the unmanned container truck and the target location based on the four target coordinates
  • Step S100 calculating the attitude angle value of the unmanned container truck relative to the target position based on the two target coordinates corresponding to the front of the unmanned container truck among the four target coordinates.
  • the unmanned container truck before the unmanned container truck obtains the alignment information, it is necessary to collect the alignment information based on the port intelligent alignment system iCPS, etc., and the iCPS collects the alignment information, and can establish a camera-specific image coordinate system based on the camera video information on the port machinery equipment hoist. Then, the image of the unmanned container truck is collected in real time based on the camera on the port machinery equipment hoist to capture and identify the boundary coordinates of the unmanned container truck in the collected image.
  • the unmanned container truck boundary that needs to be identified includes the front of the unmanned container truck and the four sides of the limit subframe.
  • the four vertex coordinates (X1, Y1), (X2, Y2), (X3, Y3), (X4, Y4) corresponding to the four sides of the limit subframe in the image coordinate system can be marked, and the four vertex coordinates can be converted into the corresponding four target coordinates (XG1, YG1), (XG2, YG2), (XG3, YG3), (XG4, YG4) in the world coordinate system based on the SLAM algorithm.
  • the first distance difference between the unmanned container truck and the target position can be determined.
  • the above first distance difference is the difference between the container truck and the precise operation center position, where a positive value represents the forward distance and a negative value represents the backward distance, and the unit is mm;
  • the attitude angle value ⁇ of the unmanned container truck relative to the target position can be calculated, where, The above-mentioned attitude angle value and the spreader attitude are in the same coordinate system, and the unit is 0.1 degree.
  • the above-mentioned first distance difference value and attitude angle value are both the positioning information of the unmanned container truck, and the above-mentioned positioning information will be pushed by iCPS to the VMS vehicle management platform, and the VMS vehicle management platform will push the above-mentioned positioning information to the corresponding unmanned container truck end OBU.
  • step S20 the following steps are included:
  • test data is a plurality of sets of first test distance difference values and corresponding second test distance difference values between the unmanned container truck and the target position collected at a preset frequency
  • first test distance difference value is obtained by identifying the image of the unmanned container truck collected by a camera on the port machinery equipment
  • second test distance difference value is calculated based on the positioning information of the unmanned container truck and the target position
  • a second distance difference between the unmanned container truck and the target location is determined.
  • the iCPS when the unmanned container truck approaches the loading and unloading point during the alignment process, the iCPS will report the distance L between the unmanned container truck and the target location at a fixed frequency, such as 1 Hz, and there will be a certain deviation between the values of L and the actual distance D between the unmanned container truck and the target location.
  • a fixed frequency such as 1 Hz
  • the alignment adjustment process of the unmanned container truck needs to ensure the accuracy of the alignment information, if the deviation is too large, the unmanned container truck will repeat the alignment adjustment until the alignment is successful, and its efficiency will be extremely low. Therefore, it is necessary to control this deviation within a certain allowable range to obtain more accurate alignment information, thereby improving the alignment efficiency.
  • the unmanned container trucks at the port are tested, and the test data L and D under each use case are collected at a frequency of seconds.
  • the collected test data are several groups of first test distance differences and corresponding second test distance differences between the unmanned container trucks and the target position collected at a preset frequency, wherein the first test distance difference is obtained by identifying the image of the unmanned container truck collected by the camera on the port machinery equipment, and the second test distance difference is calculated based on the positioning information of the unmanned container truck and the target position.
  • an error correction model can be constructed based on the test data.
  • the distance adjustment ratio can be determined based on the error correction model, and the distance adjustment ratio corresponds to the positive error between the two test distances L and D of the unmanned container truck relative to the target position.
  • the second distance difference between the unmanned container truck and the target position can be further determined based on the first distance difference and the distance adjustment ratio. For example, if the distance adjustment ratio is 0.5%-0.7%, and the first distance difference is L 0 , then the second distance difference can be further obtained as L 0 *(1+0.6%).
  • the second distance difference is the distance difference between the unmanned container truck and the target position that needs to be referred to when the unmanned container truck is adjusted in the alignment information.
  • the step of constructing an error correction model based on test data includes: include:
  • a normal distribution curve is fitted, and an error correction model is constructed based on the normal distribution curve.
  • the step of constructing an error correction model based on test data specifically includes: calculating the ratio of the above-mentioned several groups of first test distance difference values L 0 and the corresponding second test distance difference values D 0 to obtain several groups of ratios. Then, by determining how many groups (i.e., the number of groups) of ratios in different numerical ranges correspond to, the test data of all groups of ratios are integrated to obtain the following Table 1.
  • a normal distribution curve is obtained by curve algorithm fitting.
  • the error correction model can be constructed corresponding to the normal distribution curve obtained by fitting. Through the above error correction model, it can be determined how much the ratio of L0 / D0 is concentrated in a certain value range, such as concentrated between 100.5 and 100.7, that is, the actual distance between the unmanned container truck and the target position has a positive error of 0.5% to 0.7% relative to the distance monitored by the iCPS, that is, when the iCPS outputs the alignment information of the distance difference between the unmanned container truck and the target position, a correction value of 0.6% can be added.
  • the above-mentioned error correction model is based on simulation, and it can also be obtained by collecting more dimensional parameters, such as test data at various distances (within 10dm, 10-40dm, 40-80dm, 80-100dm, etc.) in various scenarios (rainy days, sunny days, snowy days, etc.) for group fitting to obtain a more accurate error adjustment model that adapts to more scenarios, thereby obtaining alignment information with higher prediction accuracy.
  • more dimensional parameters such as test data at various distances (within 10dm, 10-40dm, 40-80dm, 80-100dm, etc.) in various scenarios (rainy days, sunny days, snowy days, etc.) for group fitting to obtain a more accurate error adjustment model that adapts to more scenarios, thereby obtaining alignment information with higher prediction accuracy.
  • the step of adjusting the position of the unmanned truck based on the alignment information includes:
  • Step S501 determining a target driving direction and a target driving distance of the unmanned container truck based on the second distance difference
  • Step S502 determining a target rotation direction and a target rotation angle of the unmanned container truck based on the attitude angle value
  • Step S503 controlling the unmanned container truck to rotate along the target rotation direction by the target rotation angle, and to travel along the target driving direction by the target driving distance.
  • the position of the unmanned container truck can be adjusted based on the above relatively accurate alignment information.
  • the alignment information includes a second distance difference and a posture angle value.
  • the target driving direction and target driving distance of the unmanned container truck can be determined by the above second distance difference; the target rotation direction and target rotation angle of the unmanned container truck can be determined by the above posture angle value.
  • the unmanned container truck is controlled to rotate along the target rotation direction by the target rotation angle, and travel along the target driving direction by the target driving distance. Since the above alignment information is relatively accurate, the alignment adjustment can be completed efficiently and accurately at this time.
  • the step of adjusting the position of the unmanned container truck based on the alignment information further includes:
  • the unmanned container truck will pause to adjust its position and wait or avoid obstacles on the spot.
  • the automatic driving system of the unmanned container truck will usually directly execute the stepping command of the adjustment.
  • the vehicle-side laser radar of the unmanned container truck will continue to work synchronously, based on the reflection signal of the obstacle combined with the timestamp information, the scanning angle of the laser, the GPS position and the feature information. It is processed into high-precision three-dimensional coordinates, thus becoming a three-dimensional stereo signal with distance and spatial information, and then based on the fusion algorithm, a three-dimensional point cloud can be established.
  • the three-dimensional point cloud information of the obstacle will be obtained, and based on the adjustment trajectory of the unmanned container truck, it will be determined whether there is a risk of collision with the obstacle. If there is a risk of collision, even if the adjustment instruction requires the vehicle to move forward a certain distance at this time, the adjustment of the position of the unmanned container truck will be suspended, and the vehicle will wait or avoid obstacles on the spot, thereby ensuring the safety and efficiency of the operation of the unmanned container truck.
  • an unmanned container truck alignment method including: controlling the unmanned container truck to align based on the positioning information of the target position; obtaining the alignment information of the unmanned container truck; determining whether the unmanned container truck is aligned successfully based on the alignment information of the unmanned container truck; if the alignment is successful, outputting prompt information to prompt the port machinery equipment to load/unload containers; if the alignment is not successful, adjusting the position of the unmanned container truck based on the alignment information, and returning to the step of obtaining the alignment information of the unmanned container truck.
  • the present invention can solve the problem that the manual parking of manned container trucks under port machinery equipment is inefficient and has potential safety hazards, and on this basis, ensure the alignment accuracy and safety reliability of the unmanned container truck, so that the overall interaction between the unmanned container truck and the port machinery equipment is safer and more efficient.
  • an embodiment of the present invention further provides an unmanned container truck alignment device.
  • the unmanned container truck alignment device includes:
  • the alignment module 10 is used to control the unmanned container truck to align based on the positioning information of the target position;
  • An acquisition module 20 is used to acquire the alignment information of the unmanned container truck
  • a determination module 30, configured to determine whether the unmanned container truck is successfully aligned based on the alignment information of the unmanned container truck;
  • the prompt module 40 is used to output prompt information if the alignment is successful, so as to prompt the port machinery equipment to carry out the container loading/unloading operation;
  • the adjustment module 50 is used to adjust the position of the unmanned container truck based on the alignment information if the alignment is not successful, and return to the step of obtaining the alignment information of the unmanned container truck.
  • the unmanned container truck alignment device further includes a computing module for:
  • the attitude angle value of the unmanned container truck relative to the target position is calculated based on the two target coordinates corresponding to the front of the unmanned container truck among the four target coordinates.
  • the unmanned container truck alignment device further includes an error correction module, which is used to:
  • test data is a plurality of sets of first test distance difference values and corresponding second test distance difference values between the unmanned container truck and the target position collected at a preset frequency
  • first test distance difference value is obtained by identifying the image of the unmanned container truck collected by a camera on the port machinery equipment
  • second test distance difference value is calculated based on the positioning information of the unmanned container truck and the target position
  • a second distance difference between the unmanned container truck and the target location is determined.
  • the error correction module is further specifically used for:
  • a normal distribution curve is fitted, and an error correction model is constructed based on the normal distribution curve.
  • the adjustment module 50 is further specifically configured to:
  • the unmanned container truck is controlled to rotate along the target rotation direction by the target rotation angle, and to travel along the target driving direction by the target driving distance.
  • the unmanned container truck alignment device further includes an obstacle warning module, which is used to:
  • the unmanned container truck will pause to adjust its position and wait or avoid obstacles on the spot.
  • each module in the above-mentioned unmanned container truck alignment device corresponds to the various steps in the above-mentioned unmanned container truck alignment method embodiment, and its functions and implementation processes will not be repeated here one by one.
  • an embodiment of the present invention further provides a readable storage medium.
  • the readable storage medium of the present invention stores an unmanned container truck alignment program, wherein when the unmanned container truck alignment program is executed by a processor, the steps of the unmanned container truck alignment method described above are implemented.
  • the method implemented when the unmanned container truck alignment program is executed can refer to the various embodiments of the unmanned container truck alignment method of the present invention, and will not be repeated here.
  • the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present invention.
  • a storage medium such as ROM/RAM, magnetic disk, optical disk

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • Multimedia (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

本发明提供一种无人集卡对位方法、装置、设备及可读存储介质，无人集卡对位方法包括：基于目标位置的定位信息，控制无人集卡进行对位；获取无人集卡的对位信息；基于无人集卡的对位信息确定无人集卡是否对位成功；若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。通过本发明可以解决有人集卡采用人工在港机设备下进行对位停车效率低且存在安全隐患的问题，并在此基础上保障无人集卡的对位准确性以及安全可靠性，以使得整体无人集卡与港机设备交互作业更加的安全与高效。

Description

无人集卡对位方法、装置、设备及可读存储介质 技术领域
本发明涉及智慧港口无人集卡控制领域，尤其涉及一种无人集卡对位方法、装置、设备及可读存储介质。
背景技术
目前港口多采用有人集卡运输集装箱来完成装船作业，其中，在港机设备下或者堆场作业区需要精准对位停车时，均需要司机人为根据港机设备下人为放置的对位杆进行对位停车，以便于后续港口港机设备完成抓放集装箱作业。上述采用有人集卡来进行对位停车的方式，司机以及港机设备下引导人员会存在安全隐患，效率低且人工成本高。
发明内容
本发明的主要目的在于提供一种无人集卡对位方法、装置、设备及可读存储介质，旨在解决现有技术中有人集卡对位停车时，需要采用人工进行对位，效率低且存在安全隐患的技术问题。
第一方面，本发明提供一种无人集卡对位方法，所述无人集卡对位方法包括以下步骤：
基于目标位置的定位信息，控制无人集卡进行对位；
获取无人集卡的对位信息；
基于无人集卡的对位信息确定无人集卡是否对位成功；
若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
可选的，在所述获取无人集卡的对位信息的步骤之前包括：
获取港机设备上摄像头所采集的无人集卡的图像；
基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于 SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
可选的，在所述获取无人集卡的对位信息的步骤之前包括：
获取测试数据，并基于测试数据构建误差修正模型，所述测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得；
基于所述误差修正模型确定距离调整比；
基于所述第一距离差值与所述距离调整比，确定无人集卡与目标位置的第二距离差值。
可选的，所述基于测试数据构建误差修正模型的步骤包括：
计算得到若干组第一测试距离差值与对应的第二测试距离差值的比值；
确定处于不同数值范围的比值对应的组数；
基于所述不同数值范围的比值以及所述不同数值范围的比值对应的组数，拟合得到正态分布曲线，并基于正态分布曲线构建得到误差修正模型。
可选的，所述基于所述对位信息调整无人集卡的位置的步骤包括：
基于所述第二距离差值，确定无人集卡的目标行驶方向与目标行驶距离；
基于所述姿态角度值，确定无人集卡的目标转动方向与目标转动角度；
控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。
可选的，在所述基于所述对位信息调整无人集卡的位置的步骤之前还包括：
获取障碍物的三维点云信息；
基于无人集卡的调整轨迹与障碍物的三维点云信息确定无人集卡是否会与障碍物产生碰撞；
若会产生碰撞，则暂停调整无人集卡的位置，进行原地等待或避障。
第二方面，本发明还提供一种无人集卡对位装置，所述无人集卡对位装置包括：
对位模块，用于基于目标位置的定位信息，控制无人集卡进行对位；
获取模块，用于获取无人集卡的对位信息；
确定模块，用于基于无人集卡的对位信息确定无人集卡是否对位成功；
提示模块，用于若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
调整模块，用于若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
可选的，所述无人集卡对位装置还包括计算模块，用于：
获取港机设备上摄像头所采集的无人集卡的图像；
基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
可选的，所述无人集卡对位装置还包括误差修正模块，用于：
获取测试数据，并基于测试数据构建误差修正模型，所述测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得；
基于所述误差修正模型确定距离调整比；
基于所述第一距离差值与所述距离调整比，确定无人集卡与目标位置的第二距离差值。
可选的，所述误差修正模块，还具体用于：
计算得到若干组第一测试距离差值与对应的第二测试距离差值的比值；
确定处于不同数值范围的比值对应的组数；
基于所述不同数值范围的比值以及所述不同数值范围的比值对应的组 数，拟合得到正态分布曲线，并基于正态分布曲线构建得到误差修正模型。
可选的，所述调整模块，还具体用于：
基于所述第二距离差值，确定无人集卡的目标行驶方向与目标行驶距离；
基于所述姿态角度值，确定无人集卡的目标转动方向与目标转动角度；
控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。
可选的，所述无人集卡对位装置还包括障碍预警模块，用于：
获取障碍物的三维点云信息；
基于无人集卡的调整轨迹与障碍物的三维点云信息确定无人集卡是否会与障碍物产生碰撞；
若会产生碰撞，则暂停调整无人集卡的位置，进行原地等待或避障。
第三方面，本发明还提供一种无人集卡对位设备，所述无人集卡对位设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的无人集卡对位程序，其中所述无人集卡对位程序被所述处理器执行时，实现如上述所述的无人集卡对位方法的步骤。
第四方面，本发明还提供一种可读存储介质，所述可读存储介质上存储有无人集卡对位程序，其中所述无人集卡对位程序被处理器执行时，实现如上述所述的无人集卡对位方法的步骤。
本发明提供一种无人集卡对位方法、装置、设备及可读存储介质，无人集卡对位方法包括：基于目标位置的定位信息，控制无人集卡进行对位；获取无人集卡的对位信息；基于无人集卡的对位信息确定无人集卡是否对位成功；若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。通过本发明可以解决有人集卡采用人工在港机设备下进行对位停车效率低且存在安全隐患的问题，并在此基础上保障无人集卡的对位准确性以及安全可靠性，以使得整体无人集卡与港机设备交互作业更加的安全与高效。
附图说明
图1为本发明实施例方案中涉及的无人集卡对位设备的硬件结构示意图；
图2为本发明无人集卡对位方法一实施例的流程示意图；
图3为本发明无人集卡对位方法又一实施例的流程示意图；
图4为本发明无人集卡对位方法再一实施例的流程示意图；
图5为本发明无人集卡对位装置一实施例的功能模块示意图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
第一方面，本发明实施例提供一种无人集卡对位设备。
参照图1，图1为本发明实施例方案中涉及的无人集卡对位设备的硬件结构示意图。本发明实施例中，无人集卡对位设备可以包括处理器1001(例如中央处理器Central ProcessingUnit，CPU)，通信总线1002，用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信；用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard)；网络接口1004可选的可以包括标准的有线接口、无线接口(如无线保真WIreless-FIdelity，WI-FI接口)；存储器1005可以是高速随机存取存储器(random access memory，RAM)，也可以是稳定的存储器(non-volatile memory)，例如磁盘存储器，存储器1005可选的还可以是独立于前述处理器1001的存储装置。本领域技术人员可以理解，图1中示出的硬件结构并不构成对本发明的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
继续参照图1，图1中作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及无人集卡对位程序。其中，处理器1001可以调用存储器1005中存储的无人集卡对位程序，并执行本发明实施例提供的无人集卡对位方法。
第二方面，本发明实施例提供了一种无人集卡对位方法。
参照图2，图2为本发明无人集卡对位方法一实施例的流程示意图。
在本发明无人集卡对位方法一实施例中，无人集卡对位方法包括：
步骤S10，基于目标位置的定位信息，控制无人集卡进行对位；
步骤S20，获取无人集卡的对位信息；
步骤S30，基于无人集卡的对位信息确定无人集卡是否对位成功；
步骤S40，若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
步骤S50，若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
本实施例中，采用无人集卡进行自动驾驶对位，以解决现有技术中有人集卡在港口港机设备下对位停车时，需要采用人工进行对位，效率低且存在安全隐患的问题。其中，无人集卡进行自动驾驶对位过程中，首先会通过高精度定位系统对应的目标位置以及无人集卡的定位信息进行对位。而在无人集卡基于定位信息进行对位停车的实际运营过程中，存在对位准确性以及安全可靠性等问题，这些问题会导致对位成功率不足。如：(1)由于港机设备(桥吊、龙门吊、堆高机)等桥体的金属遮盖面积较大，桥下无人集卡的定位信号飘，无人集卡可能报错并原地等待定位信号恢复；(2)若定位信号的精度与目的地经纬度差值大于预设差值(如5cm)时，无人集卡可能需要重绕一圈再次定位，这种重复定位会大大影响运营效率，且可能造成拥堵；(3)在定位信号丢失，车端智能系统地图中未设置电子围栏的情况下，车辆在岸桥存在冲入海中的风险。
因此，本实施例方案中在通过高精度定位系统的定位信息进行对位的基础上，会实时获取无人集卡的对位信息。基于对上述对位信息的判断来确定无人集卡是否对位成功。当确定对位成功时，则可以输出提示信息，比如控制港机吊具上方绿灯，从而示意港机司机可以进行抓/放箱作业，即以提示港机设备进行装/卸集装箱的作业。当确定无人集卡尚未对位成功时，则此时可以基于上述对位信息调整无人集卡的位置。并在调整的同时或者调整完成之后再返回至获取无人集卡的对位信息的步骤，直至无人集卡对位成功。通过 上述基于定位信息以及基于对位信息确认对位结果的方式，可以解决有人集卡采用人工在港机设备下进行对位停车效率低且存在安全隐患的问题，并在此基础上保障无人集卡的对位准确性以及安全可靠性。
进一步，一实施例中，参照图3，在所述步骤S20之前包括：
步骤S60，获取港机设备上摄像头所采集的无人集卡的图像；
步骤S70，基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
步骤S80，标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
步骤S90，基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
步骤S100，基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
本实施例中，在无人集卡获取对位信息之前，需要基于港口智能对位系统iCPS等来采集得到对位信息，而iCPS采集得到对位信息，可以基于港机设备吊具上的摄像头视频信息，建立摄像头专用的图像坐标系。再基于港机设备吊具上的摄像头实时采集无人集卡的图像，来捕捉识别所采集图像中无人集卡的边界坐标。其中，需要识别得到的无人集卡边界包括无人集卡的车头以及限位副车架的四条边。此时可以标记标记图像坐标系下限位副车架的四条边对应的四个顶角坐标(X1,Y1)、(X2,Y2)、(X3,Y3)、(X4,Y4)，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标(XG1,YG1)、(XG2,YG2)、(XG3,YG3)、(XG4,YG4)。。
其中，基于上述四个目标坐标，可以确定无人集卡与目标位置的第一距离差值，上述第一距离差值为集卡距离抵达精准的作业中心位置的差值，其中正值表示前进距离，负值表示后退距离，单位为mm；基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标(XG1,YG1)、(XG2,YG2)，可以计算得到无人集卡相对于目标位置的姿态角度值θ，其中，其中上述姿态角度值与吊具姿态为同一坐标系，单位为0.1度。上述第一距离差值与姿态角度值均为无人集卡的对位信息，而上述对位信息会由iCPS推送至VMS车管平台，VMS车管平台再将上述定位信息推送至对应的无人集卡车端OBU。
进一步，一实施例中，在所述步骤S20之前包括：
获取测试数据，并基于测试数据构建误差修正模型，所述测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得；
基于所述误差修正模型确定距离调整比；
基于所述第一距离差值与所述距离调整比，确定无人集卡与目标位置的第二距离差值。
本实施例中，由于无人集卡在对位过程中靠近装卸货点时，iCPS会以固定频率如以1hz的频率上报无人集卡与目标位置的距离L，而L相对于无人集卡与目标位置的实际距离D，其数值之间会存在一定偏差。考虑到无人集卡的对位调整过程需要保障对位信息的准确性，若偏差过大会导致无人集卡重复执行对位调整直至对位成功，其效率将极其低下，因而需控制此偏差处于一定的允许范围内，以得到更为准确的对位信息，从而提高对位效率。
因此本实施例方案中，为了纠正上述偏差，对港口无人集卡进行测试，按照秒级频率收集各个用例下的测试数据L与D，所采集得到的测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得。
在收集得到测试数据后，再基于上述测试数据即可以构建得到误差修正模型。后续在实际运行中，可基于上述误差修正模型来确定距离调整比，上述距离调整比对应无人集卡相对于目标位置的两个测试距离L与D之间的正向误差。在得到上述距离调整比后，可以进一步基于上述第一距离差值与距离调整比，从而确定无人集卡与目标位置的第二距离差值。比如距离调整比为0.5％-0.7％，第一距离差值为L0，则可以进一步得到第二距离差值为L0*(1+0.6％)。以上述第二距离差值为对位信息中无人集卡在对位调整时，所需要参照的无人集卡与目标位置的距离差值。
更进一步，一实施例中，所述基于测试数据构建误差修正模型的步骤包 括：
计算得到若干组第一测试距离差值与对应的第二测试距离差值的比值；
确定处于不同数值范围的比值对应的组数；
基于所述不同数值范围的比值以及所述不同数值范围的比值对应的组数，拟合得到正态分布曲线，并基于正态分布曲线构建得到误差修正模型。
本实施例中，具体基于测试数据构建误差修正模型的步骤包括：将上述若干组第一测试距离差值L0与对应的第二测试距离差值D0进行比值计算，得到若干组比值。再通过确定处于不同数值范围的比值对应有多少组(即组数)来对所有组比值的测试数据进行整合得到如下表1。
表1

基于上述测试数据进行曲线算法拟合得到正态分布曲线，对应拟合所得的正态分布曲线可以构建得到误差修正模型，通过上述误差修正模型，可以确定L0/D0的比值有多少集中在某个数值范围内，如集中在100.5～100.7之间，即无人集卡与目标位置的实际距离相对于iCPS所监测的距离有0.5％～0.7％的正向误差，即在iCPS在输出无人集卡与目标位置的距离差值的对位信息时可增加0.6％的修正值。
其中，上述误差修正模型是基于模拟所得，也可以通过收集更多的维度参数，如各个场景下(雨天、晴天、雪天等)各个距离(10dm以内、10-40dm、40-80dm、80-100dm等)下的测试数据进行分组拟合得到更为精确适应更多场景的误差调整模型，从而得到预测精度更高的对位信息。
进一步，一实施例中，参照图4，所述基于所述对位信息调整无人集卡的位置的步骤包括：
步骤S501，基于所述第二距离差值，确定无人集卡的目标行驶方向与目标行驶距离；
步骤S502，基于所述姿态角度值，确定无人集卡的目标转动方向与目标转动角度；
步骤S503，控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。
本实施例中，在通过上述方式获取得到iCPS的对位信息之后，由于对位信息已经非常精确，此时可以基于上述较为精确的对位信息对无人集卡进行位置调整。具体地，对位信息包括第二距离差值与姿态角度值，通过上述第二距离差值可以确定无人集卡地目标行驶方向与目标行驶距离；通过上述姿态角度值，可以确定无人集卡地目标转动个方向与目标转动角度。在得到上述控制参数后，控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。由于上述对位信息较为准确，此时可以高效且精确的完成对位调整。
进一步，一实施例中，在所述基于所述对位信息调整无人集卡的位置的步骤之前还包括：
获取障碍物的三维点云信息；
基于无人集卡的调整轨迹与障碍物的三维点云信息确定无人集卡是否会与障碍物产生碰撞；
若会产生碰撞，则暂停调整无人集卡的位置，进行原地等待或避障。
本实施例中，由于无人集卡的对位调整属于遥控指令中的一种，通常此情况下下无人集卡的自动驾驶系统会直接执行调整的步进指令。而本方案在对位调整过程中，无人集卡的车端激光雷达会持续同步工作，基于障碍物的反射信号结合时间戳信息、激光的扫描角度、GPS位置与特征信息。将其处理为高精度的三维坐标，从而成为具有距离以及空间信息的三位立体信号，再基于融合算法，可建立三维点云。在基于对位信息调整无人集卡的位置之前会获取障碍物的三位点云信息，基于无人集卡的调整轨迹来确定是否存在与障碍物产生碰撞的风险。若存在存在产生碰撞的风险，则即使此时调整指令要求车辆前进一段距离，也会暂停调整无人集卡的位置，进行原地等待或避障，从而保障无人集卡的作业安全与高效。
本实施例中，提供一种无人集卡对位方法包括：基于目标位置的定位信息，控制无人集卡进行对位；获取无人集卡的对位信息；基于无人集卡的对位信息确定无人集卡是否对位成功；若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。通过本发明可以解决有人集卡采用人工在港机设备下进行对位停车效率低且存在安全隐患的问题，并在此基础上保障无人集卡的对位准确性以及安全可靠性，以使得整体无人集卡与港机设备交互作业更加的安全与高效。
第三方面，本发明实施例还提供一种无人集卡对位装置。
参照图5，无人集卡对位装置一实施例的功能模块示意图。
本实施例中，所述无人集卡对位装置包括：
对位模块10，用于基于目标位置的定位信息，控制无人集卡进行对位；
获取模块20，用于获取无人集卡的对位信息；
确定模块30，用于基于无人集卡的对位信息确定无人集卡是否对位成功；
提示模块40，用于若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
调整模块50，用于若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
进一步，一实施例中，所述无人集卡对位装置还包括计算模块，用于：
获取港机设备上摄像头所采集的无人集卡的图像；
基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
进一步，一实施例中，所述无人集卡对位装置还包括误差修正模块，用于：
获取测试数据，并基于测试数据构建误差修正模型，所述测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得；
基于所述误差修正模型确定距离调整比；
基于所述第一距离差值与所述距离调整比，确定无人集卡与目标位置的第二距离差值。
进一步，一实施例中，所述误差修正模块，还具体用于：
计算得到若干组第一测试距离差值与对应的第二测试距离差值的比值；
确定处于不同数值范围的比值对应的组数；
基于所述不同数值范围的比值以及所述不同数值范围的比值对应的组数，拟合得到正态分布曲线，并基于正态分布曲线构建得到误差修正模型。
进一步，一实施例中，所述调整模块50，还具体用于：
基于所述第二距离差值，确定无人集卡的目标行驶方向与目标行驶距离；
基于所述姿态角度值，确定无人集卡的目标转动方向与目标转动角度；
控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。
进一步，一实施例中，所述无人集卡对位装置还包括障碍预警模块，用于：
获取障碍物的三维点云信息；
基于无人集卡的调整轨迹与障碍物的三维点云信息确定无人集卡是否会与障碍物产生碰撞；
若会产生碰撞，则暂停调整无人集卡的位置，进行原地等待或避障。
其中，上述无人集卡对位装置中各个模块的功能实现与上述无人集卡对位方法实施例中各步骤相对应，其功能和实现过程在此处不再一一赘述。
第四方面，本发明实施例还提供一种可读存储介质。
本发明可读存储介质上存储有无人集卡对位程序，其中所述无人集卡对位程序被处理器执行时，实现如上述的无人集卡对位方法的步骤。
其中，无人集卡对位程序被执行时所实现的方法可参照本发明无人集卡对位方法的各个实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (10)

  1. 一种无人集卡对位方法，其特征在于，所述无人集卡对位方法包括：
    基于目标位置的定位信息，控制无人集卡进行对位；
    获取无人集卡的对位信息；
    基于无人集卡的对位信息确定无人集卡是否对位成功；
    若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
    若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
  2. 如权利要求1所述的无人集卡对位方法，其特征在于，在所述获取无人集卡的对位信息的步骤之前包括：
    获取港机设备上摄像头所采集的无人集卡的图像；
    基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
    标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
    基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
    基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
  3. 如权利要求2所述的无人集卡对位方法，其特征在于，在所述获取无人集卡的对位信息的步骤之前包括：
    获取测试数据，并基于测试数据构建误差修正模型，所述测试数据为若干组以预设频率采集的无人集卡与目标位置的第一测试距离差值与对应的第二测试距离差值，其中，第一测试距离差值基于港机设备上摄像头所采集的无人集卡的图像进行识别所得，第二测试距离差值基于无人集卡与目标位置的定位信息计算所得；
    基于所述误差修正模型确定距离调整比；
    基于所述第一距离差值与所述距离调整比，确定无人集卡与目标位置的第二距离差值。
  4. 如权利要求3所述的无人集卡对位方法，其特征在于，所述基于测试数据构建误差修正模型的步骤包括：
    计算得到若干组第一测试距离差值与对应的第二测试距离差值的比值；
    确定处于不同数值范围的比值对应的组数；
    基于所述不同数值范围的比值以及所述不同数值范围的比值对应的组数，拟合得到正态分布曲线，并基于正态分布曲线构建得到误差修正模型。
  5. 如权利要求3所述的无人集卡对位方法，其特征在于，所述基于所述对位信息调整无人集卡的位置的步骤包括：
    基于所述第二距离差值，确定无人集卡的目标行驶方向与目标行驶距离；
    基于所述姿态角度值，确定无人集卡的目标转动方向与目标转动角度；
    控制无人集卡沿着所述目标转动方向转动所述目标转动角度，并沿着所述目标行驶方向行进所述目标行驶距离。
  6. 如权利要求1所述的无人集卡对位方法，其特征在于，在所述基于所述对位信息调整无人集卡的位置的步骤之前还包括：
    获取障碍物的三维点云信息；
    基于无人集卡的调整轨迹与障碍物的三维点云信息确定无人集卡是否会与障碍物产生碰撞；
    若会产生碰撞，则暂停调整无人集卡的位置，进行原地等待或避障。
  7. 一种无人集卡对位装置，其特征在于，所述无人集卡对位装置包括：
    对位模块，用于基于目标位置的定位信息，控制无人集卡进行对位；
    获取模块，用于获取无人集卡的对位信息；
    确定模块，用于基于无人集卡的对位信息确定无人集卡是否对位成功；
    提示模块，用于若对位成功，则输出提示信息，以提示港机设备进行装/卸集装箱作业；
    调整模块，用于若未对位成功，则基于所述对位信息调整无人集卡的位置，并返回至获取无人集卡的对位信息的步骤。
  8. 如权利要求7所述的无人集卡对位装置，其特征在于，所述无人集卡对位装置还包括计算模块，用于：
    获取港机设备上摄像头所采集的无人集卡的图像；
    基于所述图像识别得到无人集卡的车头以及限位副车架的四条边；
    标记图像坐标系下限位副车架的四条边对应的四个顶角坐标，并基于SLAM算法将所述四个顶角坐标转换为世界坐标系下对应的四个目标坐标；
    基于所述四个目标坐标，确定无人集卡与目标位置的第一距离差值；
    基于所述四个目标坐标中无人集卡的车头对应的两个目标坐标计算得到无人集卡相对于目标位置的姿态角度值。
  9. 一种无人集卡对位设备，其特征在于，所述无人集卡对位设备包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的无人集卡对位程序，其中所述无人集卡对位程序被所述处理器执行时，实现如权利要求1至6中任一项所述的无人集卡对位方法的步骤。
  10. 一种可读存储介质，其特征在于，所述可读存储介质上存储有无人集卡对位程序，其中所述无人集卡对位程序被处理器执行时，实现如权利要求1至6中任一项所述的无人集卡对位方法的步骤。
PCT/CN2023/123470 2022-11-03 2023-10-09 无人集卡对位方法、装置、设备及可读存储介质 WO2024093616A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211372702.3A CN115773745A (zh) 2022-11-03 2022-11-03 无人集卡对位方法、装置、设备及可读存储介质
CN202211372702.3 2022-11-03

Publications (1)

Publication Number Publication Date
WO2024093616A1 true WO2024093616A1 (zh) 2024-05-10

Family

ID=85388733

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/123470 WO2024093616A1 (zh) 2022-11-03 2023-10-09 无人集卡对位方法、装置、设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN115773745A (zh)
WO (1) WO2024093616A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115773745A (zh) * 2022-11-03 2023-03-10 东风商用车有限公司 无人集卡对位方法、装置、设备及可读存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112150540A (zh) * 2020-08-26 2020-12-29 交通运输部水运科学研究所 场桥下集卡对位方法、装置、终端、存储介质及处理器
CN112528721A (zh) * 2020-04-10 2021-03-19 福建电子口岸股份有限公司 一种桥吊集卡安全定位方法和系统
CN114299146A (zh) * 2021-12-29 2022-04-08 北京万集科技股份有限公司 辅助停车方法、装置、计算机设备和计算机可读存储介质
WO2022133636A1 (zh) * 2020-12-21 2022-06-30 深圳元戎启行科技有限公司 无人集卡车调度方法、装置、计算机设备和存储介质
CN115180512A (zh) * 2022-09-09 2022-10-14 湖南洋马信息有限责任公司 基于机器视觉的集装箱卡车自动装卸方法及系统
CN115773745A (zh) * 2022-11-03 2023-03-10 东风商用车有限公司 无人集卡对位方法、装置、设备及可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112528721A (zh) * 2020-04-10 2021-03-19 福建电子口岸股份有限公司 一种桥吊集卡安全定位方法和系统
CN112150540A (zh) * 2020-08-26 2020-12-29 交通运输部水运科学研究所 场桥下集卡对位方法、装置、终端、存储介质及处理器
WO2022133636A1 (zh) * 2020-12-21 2022-06-30 深圳元戎启行科技有限公司 无人集卡车调度方法、装置、计算机设备和存储介质
CN114299146A (zh) * 2021-12-29 2022-04-08 北京万集科技股份有限公司 辅助停车方法、装置、计算机设备和计算机可读存储介质
CN115180512A (zh) * 2022-09-09 2022-10-14 湖南洋马信息有限责任公司 基于机器视觉的集装箱卡车自动装卸方法及系统
CN115773745A (zh) * 2022-11-03 2023-03-10 东风商用车有限公司 无人集卡对位方法、装置、设备及可读存储介质

Also Published As

Publication number Publication date
CN115773745A (zh) 2023-03-10

Similar Documents

Publication Publication Date Title
CN110969655B (zh) 用于检测车位的方法、装置、设备、存储介质以及车辆
EP4036870A1 (en) Parking spot detection method and parking spot detection system
WO2024093616A1 (zh) 无人集卡对位方法、装置、设备及可读存储介质
CN110837814B (zh) 车辆导航方法、装置及计算机可读存储介质
CN110082775B (zh) 基于激光装置的车辆定位方法和系统
CN110111603B (zh) 基于三维检测技术的停车辅助方法、装置及系统
CN112897345B (zh) 集装箱卡车与起重机的对位方法及相关设备
CN111624994A (zh) 一种基于5g通信的机器人巡检方法
CN115180512B (zh) 基于机器视觉的集装箱卡车自动装卸方法及系统
CN115123307A (zh) 基于障碍物意图的自动驾驶方法、装置及自动驾驶车辆
US11932518B2 (en) Systems and methods for calculating a path
CN113168189A (zh) 飞行作业方法、无人机及存储介质
CN114852064A (zh) 预防驾驶培训车辆横向碰撞的方法、装置及电子设备
US20220316909A1 (en) Method and Communication System for Supporting at Least Partially Automatic Vehicle Control
CN112102396B (zh) 桥吊下的车辆定位方法、装置、设备及存储介质
CN113665591A (zh) 无人驾驶控制方法、装置、设备及介质
CN115557432A (zh) 货物卸载方法、装置、电子设备及存储介质
CN115586552A (zh) 一种港口轮胎吊或桥吊下无人集卡精确二次定位方法
CN115410399A (zh) 一种货车停车方法、装置及电子设备
CN115963510A (zh) 一种基于激光点云的物流园区车辆精准停车方法和系统
CN115215221A (zh) 塔式起重机及其控制方法、控制装置和控制器
CN114407916B (zh) 车辆控制及模型训练方法、装置、车辆、设备和存储介质
US20230296399A1 (en) Method for releasing a digital map
CN117326490A (zh) 托盘的识别方法和叉起方法以及自主移动叉车
CN116242334A (zh) 一种面向港口锁站的车辆定位方法及系统