Navigation method, system and equipment of freight robot for container and storage medium

Through lidar, point cloud data is collected and fitted lines are extracted, and target point cloud data is screened, which solves the problem of inaccurate positioning of freight robots in the container, achieving higher mobility accuracy.

CN119085658APending Publication Date: 2024-12-06SOUTH CHINA UNIV OF TECH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411307457.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The inaccurate positioning of the freight robot in the container leads to inaccurate movement, mainly because the wavy shape of the container box wall affects the lidar positioning results.

Method used

Point cloud data is collected through lidar, fitted lines facing the container wall, filter target point cloud data, determine the positioning data of the freight robot, and adjust the navigation data based on the positioning data to improve movement accuracy.

Benefits of technology

The accuracy of the movement of the freight robot in the container is improved, and by screening and adjusting the navigation data, the positioning distance between the freight robot and the container wall is more accurate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085658A_ABST
    Figure CN119085658A_ABST
Patent Text Reader

Abstract

The invention discloses a navigation method, system and equipment of a freight robot for a container and a storage medium, and belongs to the technical field of transportation robots. The navigation method comprises the following steps that a laser radar is arranged, and the navigation method of the freight robot for the container comprises the following steps that the laser radar is controlled to collect first point cloud data of the current position, and a first fitting straight line of the wall face orientation of the container is extracted according to the first point cloud data; controlling the freight robot to move to a target position, and acquiring second point cloud data at the target position; screening target point cloud data from the second point cloud data according to the first fitting straight line, and determining positioning data of the freight robot according to the target point cloud data; and adjusting the navigation data of the freight robot according to the positioning data. The moving accuracy of the freight robot is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of transport robots, and in particular to a navigation method, system, equipment and storage medium for a freight robot for a container. Background Art

[0002] With the development of industrial intelligence, freight robots need to load and unload goods in containers. At present, freight robots are often positioned based on lidar, and the Naruto robot is navigated according to the positioning results. However, since the wall of the container is in a wavy state, it will affect the positioning of the freight robot in the container, resulting in inaccurate movement of the freight robot.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a navigation method, system, device and storage medium for a freight robot for a container, aiming to improve the accuracy of the movement of the freight robot.

[0005] To achieve the above object, the present invention provides a navigation method for a freight robot for a container, which is applied to the freight robot. The freight robot is provided with a laser radar. The navigation method for the freight robot for a container comprises the following steps:

[0006] Controlling the laser radar to collect first point cloud data of the current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data;

[0007] Controlling the freight robot to move toward a target location and acquiring second point cloud data at the target location;

[0008] Filtering target point cloud data in the second point cloud data according to the first fitting straight line, and determining positioning data of the freight robot according to the target point cloud data;

[0009] The navigation data of the freight robot is adjusted according to the positioning data.

[0010] Optionally, the step of screening target point cloud data in the second point cloud data according to the first fitting straight line includes:

[0011] Calculate two predicted position coordinates according to the first fitting straight line, the two predicted position coordinates including a first predicted coordinate and a second predicted coordinate;

[0012] Calculate a second distance between each data point in the second point cloud data and the first predicted coordinate and the second predicted coordinate respectively, and determine the third point cloud data corresponding to the first predicted coordinate and the fourth point cloud data corresponding to the second predicted coordinate according to the second distance;

[0013] The third point cloud data and the fourth point cloud data are used as the target point cloud data.

[0014] Optionally, the step of determining the positioning data of the freight robot according to the target point cloud data includes:

[0015] respectively calculating a third average coordinate of the third point cloud data and a fourth average coordinate of the fourth point cloud data;

[0016] Determine a second fitting straight line according to the third average coordinate and the fourth average coordinate;

[0017] The positioning distances between the freight robot and each wall of the container are determined according to the second fitting straight line, and the positioning data are determined according to a plurality of the positioning distances.

[0018] Optionally, the second point cloud data is stored in a KD tree structure, and after the step of calculating two predicted position coordinates according to the first fitting straight line, wherein the two predicted position coordinates include a first predicted coordinate and a second predicted coordinate, the step further includes:

[0019] Determine a query range according to the first predicted coordinates and the second predicted coordinates;

[0020] The root node of the KD tree selects a corresponding subtree for traversal according to the first predicted coordinates, the second predicted coordinates and the query range;

[0021] When the distance between the point of the KD tree and the first predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the third point cloud data; when the distance between the point of the KD tree and the second predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the fourth point cloud data;

[0022] The step of using the third point cloud data and the fourth point cloud data as the target point cloud data is performed.

[0023] Optionally, the step of extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data includes:

[0024] Determine target first sub-point cloud data according to the first point cloud data;

[0025] The first fitting straight line is determined according to a random consistency algorithm and the target first sub-point cloud data.

[0026] Optionally, the step of determining target first sub-point cloud data according to the first point cloud data includes:

[0027] Segmenting the first point cloud data to obtain a plurality of first sub-point cloud data;

[0028] and calculating a first distance between each first sub-point cloud data and the center point of the chassis of the freight robot to obtain a plurality of first distances;

[0029] Target first sub-point cloud data are determined from a plurality of first sub-point cloud data according to the plurality of first distances.

[0030] Optionally, three single-line laser radars are arranged on the chassis of the freight robot and are distributed at different positions of the robot. After the step of controlling the laser radar to collect the first point cloud data of the current position, the step further includes:

[0031] Controlling the three single-line laser radars to collect point cloud data respectively to obtain a plurality of point cloud data;

[0032] Converting the plurality of point cloud data into standard point cloud data based on the center coordinates of the robot respectively to obtain the plurality of standard point cloud data;

[0033] The first point cloud data is obtained by superimposing a plurality of the standard point cloud data.

[0034] In addition, to achieve the above-mentioned purpose, the present invention further provides a navigation system for a freight robot for a container, which is applied to the freight robot. The freight robot is provided with a laser radar, and the navigation system for the freight robot for a container includes:

[0035] an acquisition module, used for controlling the laser radar to acquire first point cloud data of a current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data;

[0036] A control module, used to control the freight robot to move to a target position and obtain second point cloud data at the target position;

[0037] a calculation module, configured to filter target point cloud data in the second point cloud data according to the first fitting straight line, and determine positioning data of the freight robot according to the target point cloud data;

[0038] An adjustment module is used to adjust the navigation data of the freight robot according to the positioning data.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides a navigation device for a container freight robot, the navigation device for a container freight robot comprising: a memory, a processor, and a navigation program for a container freight robot stored in the memory and executable on the processor, the navigation program for a container freight robot being configured to implement the steps of the navigation method for a container freight robot described in any one of the above-mentioned items.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a navigation program of a container freight robot is stored. When the navigation program of the container freight robot is executed by a processor, the steps of the navigation method of the container freight robot described in any one of the above items are implemented.

[0041] The present invention proposes a navigation method for a freight robot for a container, which controls the laser radar to collect first point cloud data of the current position, controls the freight robot to move to the target position, and obtains second point cloud data at the target position; filters the target point cloud data in the second point cloud data according to the first fitting straight line, and determines the positioning data of the freight robot according to the target point cloud data. Since the first fitting straight line filters the target point cloud data in the second point cloud data, the target point cloud data is accurately filtered out, thereby improving the positioning data determined based on the target point cloud data, and adjusting the navigation data of the freight robot according to the positioning data, thereby making the movement of the freight robot more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a structural schematic diagram of a navigation device of a container freight robot in a hardware operating environment involved in an embodiment of the present invention;

[0043] Figure 2 This is a flow chart of a first embodiment of a navigation method for a freight robot for a container according to the present invention;

[0044] Figure 3 This is an example of a cargo robot in a container from a bird's-eye view;

[0045] Figure 4 This is a flow chart of a second embodiment of the navigation method of a freight robot for a container according to the present invention;

[0046] Figure 5 It is a flowchart of a third embodiment of the navigation method of a freight robot for a container according to the present invention.

[0047] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0049] Reference Figure 1 , Figure 1 The schematic diagram of the navigation device structure of the container freight robot in the hardware operating environment involved in the embodiment of the present invention is shown in FIG. The navigation device of the container freight robot here may be a freight robot, and the freight robot may include a lifting device, a traction device, and a grabbing device, so as to move the goods in the container.

[0050] like Figure 1 As shown, the navigation device of the container freight robot may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The interactive device 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional interactive device 1003 may also be connected to the communication bus through a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0051] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the navigation device of the freight robot for containers, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0052] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a navigation program for a container freight robot.

[0053] exist Figure 1In the navigation device of the container freight robot shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the navigation device of the container freight robot of the present invention can be set in the navigation device of the container freight robot, and the navigation device of the container freight robot calls the navigation program of the container freight robot stored in the memory 1005 through the processor 1001, and executes the navigation method of the container freight robot provided in the embodiment of the present invention.

[0054] The embodiment of the present invention provides a navigation method for a freight robot for a container, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a navigation method for a freight robot for a container according to the present invention.

[0055] In this embodiment, the navigation method of the container freight robot includes:

[0056] Step S1, controlling the laser radar to collect first point cloud data of the current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data;

[0057] In this embodiment, the laser radar is controlled to emit laser and receive the returned laser reflection, and the first point cloud data is determined according to the laser reflection. Of course, in this embodiment, the number of laser radars and the type of laser radars are not limited. Preferably, three single-line laser radars are used. In other embodiments, multi-line laser radars can also be used. Preferably, the first fitting straight line of the wall orientation of the container is extracted according to the first point cloud data. Specifically, a random sample consensus algorithm (RANSAC) can be used to determine the first fitting straight line of the wall orientation of the container. It should be noted that containers usually follow international standard dimensions, so after determining the orientation of one wall of the container, the orientation of other walls of the container can be directly determined. In addition, the direction of the first fitting straight line fitted here is perpendicular to the direction of gravity, that is, the tilt of the wall of the container is not considered. Specifically, in the random consistency algorithm, since the direction of the first fitting straight line is required to be perpendicular to the direction of gravity by default, the selection equation model can be:

[0058] y=ax+b

[0059] A small number of points are randomly selected from the first point cloud data, usually at least two points are needed to determine the direction of the fitted line. The process is repeated multiple times to achieve iteration, and the fitted line with the best consistent data is selected from all the iteration results as the first fitted line.

[0060] Step S2, controlling the freight robot to move to a target position and acquiring second point cloud data at the target position;

[0061] Optionally, refer to Figure 3 , Figure 3 This is a top view of the freight robot in the container of this embodiment. In this embodiment, the target position here can be the farthest end from the container door. It can also be the position that the robot passes through when moving from the current position to the farthest end from the container door. The method of obtaining the second point cloud data here needs to be the same as the method of obtaining the first point cloud data.

[0062] Step S3, screening target point cloud data in the second point cloud data according to the first fitting straight line, and determining the positioning data of the freight robot according to the target point cloud data;

[0063] It should be noted that the second point cloud data will include point cloud data of all walls except the container. The point cloud data corresponding to different walls will affect the positioning data of the freight robot. Therefore, the first fitting straight line is required to filter the target point cloud data in the second point cloud data. In this embodiment, the target point cloud data used to determine the positioning data is filtered according to the first fitting straight line, so as to avoid the accuracy of the positioning data being affected by the target point cloud data. An accurate and effective second fitting straight line is determined according to the target point cloud data, the distance between the freight robot and the container wall is determined according to the second fitting straight line, and the positioning data is determined according to the distance between the freight robot and the container wall;

[0064] Step S4: adjusting the navigation data of the freight robot according to the positioning data.

[0065] Specifically, in this embodiment, optionally, the freight robot needs to be controlled to be 10 cm away from the wall of the container and to move parallel to the wall of the container. When the positioning data can determine that the robot is 15 cm away from the wall of the container, the travel data of the freight robot is adjusted so that the freight robot is 10 cm away from the wall of the container. Further, the freight robot is controlled according to the navigation data, and the step of controlling the laser radar to collect the first point cloud data of the current position is returned.

[0066] In this embodiment, the laser radar is controlled to collect the first point cloud data of the current position, the freight robot is controlled to move to the target position, and the second point cloud data at the target position is obtained; the target point cloud data is filtered in the second point cloud data according to the first fitting straight line, and the positioning data of the freight robot is determined according to the target point cloud data. Since the first fitting straight line filters the target point cloud data in the second point cloud data, the target point cloud data is accurately filtered out, thereby improving the positioning data determined based on the target point cloud data, and adjusting the navigation data of the freight robot according to the positioning data, thereby making the freight robot move more accurately.

[0067] Further, based on the first embodiment, a second embodiment of the navigation method of the container freight robot of the present invention is proposed. In this embodiment, referring to Figure 4 The step of screening target point cloud data in the second point cloud data according to the first fitting straight line comprises:

[0068] Step S31, calculating two predicted position coordinates according to the first fitting straight line, the two predicted position coordinates including a first predicted coordinate and a second predicted coordinate;

[0069] Step S32, calculating a second distance between each data point in the second point cloud data and the first predicted coordinates and the second predicted coordinates, and determining third point cloud data corresponding to the first predicted coordinates and fourth point cloud data corresponding to the second predicted coordinates according to the second distance;

[0070] Step S33: taking the third point cloud data and the fourth point cloud data as the target point cloud data.

[0071] In this embodiment, two predicted position coordinates are determined specifically by the analytical equation of the first fitting line. In other embodiments, there may be more than two predicted position coordinates. The first predicted coordinate is (x1, y1) and the second predicted coordinate is (x2, y2). Preferably, the numerical difference between x1 and x2 is greater than the preset numerical difference, so that two similar predicted coordinates can be avoided, thereby preventing the third point cloud data and the fourth point cloud data from having the same point.

[0072] In this embodiment, two predicted position coordinates are calculated, and the second distance is calculated between each data point of the second point cloud data and the first predicted coordinate and the second predicted coordinate, and the third point cloud data corresponding to the first predicted coordinate and the fourth point cloud data corresponding to the second predicted coordinate are determined according to the second distance. Since the second point cloud data here is the point cloud data after the freight robot moves, the two predicted position coordinates are the screening of the second point cloud data. In addition, the third point cloud data and the fourth point cloud data are used as the target point cloud data, which is essentially to correct the error of the first fitting straight line through the third point cloud data and the fourth point cloud data.

[0073] Furthermore, the step of determining the positioning data of the freight robot according to the target point cloud data includes:

[0074] respectively calculating a third average coordinate of the third point cloud data and a fourth average coordinate of the fourth point cloud data;

[0075] Determine a second fitting straight line according to the third average coordinate and the fourth average coordinate;

[0076] The positioning distances between the freight robot and each wall of the container are determined according to the second fitting straight line, and the positioning data are determined according to a plurality of the positioning distances.

[0077] In this embodiment, the third point cloud data here may include multiple points, and the average value of the coordinates of each point of the third point cloud data is calculated as the third average coordinate; the fourth point cloud data here may include multiple points, and the average value of the coordinates of each point of the fourth point cloud data is calculated as the fourth average coordinate. That is, the parameters a and b of the second fitting straight line are determined according to the third average coordinate and the fourth average coordinate. Thus, the second fitting straight line is obtained. Optionally, the position of the wall of the container is determined according to the second fitting straight line, so as to calculate the vertical distance from the freight robot to the two side walls of the vehicle body, and determine the straight-line distance from the freight robot to the entrance and exit of the container. According to the vertical distance and the straight-line distance, the positioning data is determined.

[0078] In this embodiment, the third average coordinates of the third point cloud data and the fourth average coordinates of the fourth point cloud data are calculated respectively; the second fitting straight line is determined according to the third average coordinates and the fourth average coordinates, which actually corrects the first fitting straight line, thereby improving the accuracy of the positioning data.

[0079] Furthermore, the second point cloud data is stored in a KD tree structure, and after the step of calculating two predicted position coordinates according to the first fitting straight line, wherein the two predicted position coordinates include the first predicted coordinates and the second predicted coordinates, the method further includes:

[0080] Determine a query range according to the first predicted coordinates and the second predicted coordinates;

[0081] The root node of the KD tree selects a corresponding subtree for traversal according to the first predicted coordinates, the second predicted coordinates and the query range;

[0082] When the distance between the point of the KD tree and the first predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the third point cloud data; when the distance between the point of the KD tree and the second predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the fourth point cloud data;

[0083] The step of using the third point cloud data and the fourth point cloud data as the target point cloud data is performed.

[0084] In this embodiment, it should be noted that before using the KD tree to determine the third point cloud data and the fourth point cloud data, it is necessary to construct a KD tree, including selecting the dimensions of the data. In this embodiment, the dimensions of the data include the coordinates of the point in the X direction and the coordinates of the Y direction. In addition, it is necessary to select the segmentation value of the current node. In other embodiments, the third point cloud data and the fourth point cloud data can also be determined by a clustering method.

[0085] In this embodiment, the third point cloud data and the fourth point cloud data are determined by using the KD tree, which can effectively reduce the amount of calculation and improve the operating efficiency of the freight robot.

[0086] Further, based on any of the above embodiments, a third embodiment of the navigation method of the container freight robot of the present invention is proposed. In this embodiment, referring to Figure 5 The step of extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data comprises:

[0087] Step S21, determining target first sub-point cloud data according to the first point cloud data;

[0088] Step S22: determining the first fitting straight line according to a random consistency algorithm and the target first sub-point cloud data.

[0089] Furthermore, the step of determining target first sub-point cloud data according to the first point cloud data includes:

[0090] Segmenting the first point cloud data to obtain a plurality of first sub-point cloud data;

[0091] and calculating a first distance between each first sub-point cloud data and the center point of the chassis of the freight robot to obtain a plurality of first distances;

[0092] The target first sub-point cloud data is determined in the multiple first sub-point cloud data according to the multiple first distances. In this embodiment, by extracting the left wall data, the right wall data and the front wall data and determining the target first sub-point cloud data, in some embodiments, the left wall data can be selected as the target first sub-point cloud data, where the left side of the opening of the container is the left wall, and the right side of the opening of the container is the right wall. It should be noted that the first fitting straight line calculated by the random consistency algorithm here will have a certain angle error, but the random consistency algorithm has a high computational efficiency, can comprehensively judge the situation of each point in the target first sub-point cloud data, and can effectively avoid the generation of an erroneous first fitting straight line.

[0093] Further, based on any of the above embodiments, a fourth embodiment of the navigation method of the container freight robot of the present invention is proposed. In this embodiment, three single-line laser radars are arranged on the chassis of the freight robot, which are distributed at different positions of the robot. After the step of controlling the laser radar to collect the first point cloud data of the current position, the method further includes:

[0094] Controlling the three single-line laser radars to collect point cloud data respectively to obtain a plurality of point cloud data;

[0095] Converting the plurality of point cloud data into standard point cloud data based on the center coordinates of the robot respectively to obtain the plurality of standard point cloud data;

[0096] The first point cloud data is obtained by superimposing a plurality of the standard point cloud data.

[0097] Preferably, three single-line laser radars are installed on the mobile chassis of the freight robot, and according to installation and position restrictions, the field of view of the radars is limited to 170°, so that a complete environmental perception data can be obtained by splicing the data of the three radars. And before executing the step of controlling the laser radar to collect the first point cloud data of the current position, the three radars need to be calibrated to avoid errors caused by installation.

[0098] In this embodiment, the three single-line laser radars are controlled separately to collect point cloud data to obtain multiple point cloud data; the multiple point cloud data are converted into standard point cloud data based on the center coordinates of the robot to obtain multiple standard point cloud data; the multiple standard point cloud data are superimposed to obtain the first point cloud data, which can improve the accuracy of the first point cloud data.

[0099] In addition, an embodiment of the present invention further provides a navigation system for a freight robot for a container, which is applied to the freight robot. The freight robot is provided with a laser radar. The navigation system for the freight robot for a container includes:

[0100] an acquisition module, used for controlling the laser radar to acquire first point cloud data of a current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data;

[0101] A control module, used to control the freight robot to move to a target position and obtain second point cloud data at the target position;

[0102] a calculation module, configured to filter target point cloud data in the second point cloud data according to the first fitting straight line, and determine positioning data of the freight robot according to the target point cloud data;

[0103] An adjustment module is used to adjust the navigation data of the freight robot according to the positioning data.

[0104] In addition, an embodiment of the present invention also proposes a navigation device of a container freight robot, the navigation device of the container freight robot comprising: a memory, a processor, and a navigation program of the container freight robot stored in the memory and executable on the processor, the navigation program of the container freight robot being configured to implement the steps of an embodiment of the navigation method of the container freight robot described in any one of the above items.

[0105] In addition, an embodiment of the present invention further proposes a storage medium, on which a navigation program of a freight robot for a container is stored. When the navigation program of the freight robot for a container is executed by a processor, the steps of an embodiment of the navigation method of the freight robot for a container described in any one of the above items are implemented.

[0106] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0107] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, 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 (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0109] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A navigation method for a container freight robot, characterized in that: Applied to a freight robot, the freight robot is provided with a laser radar, and the navigation method of the container freight robot comprises the following steps: Controlling the laser radar to collect first point cloud data of the current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data; Controlling the freight robot to move toward a target location and acquiring second point cloud data at the target location; Filtering target point cloud data in the second point cloud data according to the first fitting straight line, and determining positioning data of the freight robot according to the target point cloud data; The navigation data of the freight robot is adjusted according to the positioning data.

2. The navigation method of the container freight robot according to claim 1, characterized in that: The step of screening target point cloud data in the second point cloud data according to the first fitting straight line comprises: Calculate two predicted position coordinates according to the first fitting straight line, the two predicted position coordinates including a first predicted coordinate and a second predicted coordinate; Calculate a second distance between each data point in the second point cloud data and the first predicted coordinate and the second predicted coordinate respectively, and determine the third point cloud data corresponding to the first predicted coordinate and the fourth point cloud data corresponding to the second predicted coordinate according to the second distance; The third point cloud data and the fourth point cloud data are used as the target point cloud data.

3. The navigation method of the container freight robot according to claim 2, characterized in that: The step of determining the positioning data of the freight robot according to the target point cloud data comprises: respectively calculating a third average coordinate of the third point cloud data and a fourth average coordinate of the fourth point cloud data; Determine a second fitting straight line according to the third average coordinate and the fourth average coordinate; The positioning distances between the freight robot and each wall of the container are determined according to the second fitting straight line, and the positioning data are determined according to a plurality of the positioning distances.

4. The navigation method of the container freight robot according to claim 2, characterized in that: The second point cloud data is stored in a KD tree structure, and after the step of calculating two predicted position coordinates according to the first fitting straight line, wherein the two predicted position coordinates include a first predicted coordinate and a second predicted coordinate, the step further includes: Determine a query range according to the first predicted coordinates and the second predicted coordinates; The root node of the KD tree selects a corresponding subtree for traversal according to the first predicted coordinates, the second predicted coordinates and the query range; When the distance between the point of the KD tree and the first predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the third point cloud data; when the distance between the point of the KD tree and the second predicted coordinate is less than or equal to the preset distance, it is determined that the point of the KD tree belongs to the fourth point cloud data; The step of using the third point cloud data and the fourth point cloud data as the target point cloud data is performed.

5. The navigation method of the container freight robot according to claim 1, characterized in that: The step of extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data comprises: Determine target first sub-point cloud data according to the first point cloud data; The first fitting straight line is determined according to a random consistency algorithm and the target first sub-point cloud data.

6. The navigation method of the container freight robot according to claim 5, characterized in that: The step of determining target first sub-point cloud data according to the first point cloud data comprises: Segmenting the first point cloud data to obtain a plurality of first sub-point cloud data; and calculating a first distance between each first sub-point cloud data and the center point of the chassis of the freight robot to obtain a plurality of first distances; Target first sub-point cloud data are determined from a plurality of first sub-point cloud data according to the plurality of first distances.

7. The navigation method of a container freight robot according to any one of claims 1 to 6, characterized in that: The chassis of the freight robot is provided with three single-line laser radars distributed at different positions of the robot. After the step of controlling the laser radars to collect the first point cloud data of the current position, the method further includes: Controlling the three single-line laser radars to collect point cloud data respectively to obtain a plurality of point cloud data; Converting the plurality of point cloud data into standard point cloud data based on the center coordinates of the robot respectively to obtain the plurality of standard point cloud data; The first point cloud data is obtained by superimposing a plurality of the standard point cloud data.

8. A navigation system for a container freight robot, characterized in that: Applied to a freight robot, the freight robot is provided with a laser radar, and the navigation system of the container freight robot includes: an acquisition module, used for controlling the laser radar to acquire first point cloud data of a current position, and extracting a first fitting straight line of the wall orientation of the container according to the first point cloud data; A control module, used to control the freight robot to move to a target position and obtain second point cloud data at the target position; a calculation module, configured to filter target point cloud data in the second point cloud data according to the first fitting straight line, and determine positioning data of the freight robot according to the target point cloud data; An adjustment module is used to adjust the navigation data of the freight robot according to the positioning data.

9. A navigation device for a container freight robot, characterized in that: The navigation device of the container freight robot includes: a memory, a processor, and a navigation program of the container freight robot stored in the memory and executable on the processor. The navigation program of the container freight robot is configured to implement the steps of the navigation method of the container freight robot as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a navigation program of the container freight robot, and when the navigation program of the container freight robot is executed by the processor, the steps of the navigation method of the container freight robot according to any one of claims 1 to 7 are implemented.