Navigation method and device of mobile robot, electronic equipment and storage medium

Abstract

The invention provides a navigation method and device of a mobile robot, electronic equipment and a storage medium, and relates to the technical field of robotics.The method comprises the steps that a positioning score of the mobile robot is obtained; if it is determined that positioning of the mobile robot is lost according to the positioning score, controlling the head of the mobile robot to rotate to construct a local map; acquiring a global map of mobile robot navigation, and determining a navigation target point according to the global map; and determining a target terminal point in the local map according to the navigation target point, and generating a local navigation path by using the target terminal point for local navigation. By fusing the head motion control and the local planning navigation strategy, the robot can flexibly adjust the visual angle and actively obtain a wider visual field range and richer environment information in a narrow space or an environment with unstable positioning signals, the navigation precision and robustness of the robot in a complex and changeable scene are improved, and the navigation efficiency of the robot is improved. And challenges such as positioning drifting can be effectively handled.

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a navigation method, device, electronic equipment and storage medium of a mobile robot. Background Art

[0002] With the rapid advancement of science and technology, mobile robots have shown great application potential in many fields such as industrial production, home services, medical assistance, disaster relief, etc. In this process, the fluency of visual navigation technology is not only related to the efficiency of mobile robots, but also becomes one of the key indicators to measure their intelligence level, adaptability and user experience. As the core component of mobile robots' autonomous movement, traditional visual navigation systems mainly rely on the precise positioning information of mobile robots in the global map, and achieve accurate path planning and navigation by matching current visual input with map data.

[0003] The accuracy of global positioning information is crucial for traditional visual navigation systems, but in actual applications, positioning information is often affected by a variety of factors and produces deviations, such as signal interference, environmental changes, equipment failures, etc. Once the global positioning information is deviated, the mobile robot may mistakenly enter the obstacle area marked in the global map due to the inability to accurately determine its own position, resulting in mission failure. Especially when working in narrow spaces, the shortcomings of traditional visual navigation technology become more and more obvious. The susceptibility of positioning signals to interference leads to positioning drift, which seriously affects the navigation performance of mobile robots. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a navigation method, device, electronic device and storage medium for a mobile robot, which effectively solve the problem of positioning drift caused by the susceptibility of positioning signals of traditional visual navigation technology to interference.

[0005] In a first aspect, the present invention provides a navigation method for a mobile robot, wherein a visual module is provided on the head of the mobile robot, and the method comprises:

[0006] Obtaining a positioning score of the mobile robot, wherein the positioning score is determined based on the number of features of a key frame image of the mobile robot that successfully matches a map and a reprojected pixel distance;

[0007] If it is determined according to the positioning score that the positioning of the mobile robot is lost, controlling the head of the mobile robot to rotate to construct a local map;

[0008] Acquire a global map of the mobile robot's navigation, and determine a navigation target point according to the global map;

[0009] A target end point in the local map is determined according to the navigation target point, and a local navigation path is generated using the target end point to perform local navigation.

[0010] Further, controlling the head rotation of the mobile robot to construct a local map includes:

[0011] Controlling the head of the mobile robot to rotate and acquiring point cloud information through the visual module;

[0012] Determine the grid position and grid state of each grid according to the point cloud information;

[0013] Determine the confidence of the grid according to the number of point cloud observations to obtain the initial local map;

[0014] The confidence of the initial local map is updated according to the rotation angle of the head of the mobile robot to obtain the local map.

[0015] Further, the updating of the confidence of the initial local map according to the rotation angle of the head of the mobile robot to obtain the local map includes:

[0016] Controlling the rotation of the head of the mobile robot to obtain a map of the front semicircle area in the moving direction of the mobile robot;

[0017] Divide the front semicircular area map into at least one sector-shaped area, and calculate the confidence of each sector-shaped area;

[0018] If the confidence of the sector area is lower than the confidence threshold, the head of the mobile robot is controlled to rotate to update the confidence of the corresponding sector area map to obtain the local map.

[0019] Furthermore, the obtaining of the positioning score of the mobile robot includes:

[0020] Obtaining the number of features and reprojected pixel distances of the key frame image of the mobile robot that successfully matches the map;

[0021] If the number of features is greater than a number threshold and the reprojected pixel distance is less than a distance threshold, determining the positioning score to be an initial score;

[0022] Obtaining the moving distance of the mobile robot and re-obtaining the feature quantity;

[0023] If the number of features is less than the number threshold, the positioning score is re-determined according to the initial score and the moving distance.

[0024] Further, the re-determining the positioning score according to the moving distance includes:

[0025] Set the distance factor;

[0026] Multiplying the moving distance by the distance coefficient to obtain a fractional change value;

[0027] The score change value is subtracted from the initial score to obtain a new positioning score.

[0028] Further, determining that the mobile robot has lost its positioning according to the positioning score includes:

[0029] If the positioning score is greater than or equal to a first score threshold, it is determined that the positioning of the mobile robot is normal;

[0030] If the positioning score is less than the first score threshold and greater than or equal to the second score threshold, determining that the positioning of the mobile robot is unstable;

[0031] If the positioning score is less than the second score threshold or the time during which the positioning of the mobile robot is unstable exceeds a time threshold, it is determined that the positioning of the mobile robot is lost.

[0032] Further, determining the navigation target point according to the global map includes:

[0033] Roughly matching the local map with the global map to obtain a rough position of the local map in the global map;

[0034] A global path is planned in the global map according to the rough position, and an end of the global path is used as a navigation target point.

[0035] In a second aspect, the present invention further provides a navigation device for a mobile robot, wherein a visual module is provided on the head of the mobile robot, and the device comprises:

[0036] A data acquisition module, used to acquire a positioning score of the mobile robot, wherein the positioning score is determined based on the number of features of the key frame image of the mobile robot that successfully matches the map and the reprojection pixel distance;

[0037] A map construction module, configured to control the head of the mobile robot to rotate to construct a local map if it is determined according to the positioning score that the positioning of the mobile robot is lost;

[0038] A target determination module is used to obtain a global map of the mobile robot's navigation and determine a navigation target point according to the global map;

[0039] The local navigation module is used to determine the target end point in the local map according to the navigation target point, and generate a local navigation path using the target end point to perform local navigation.

[0040] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the navigation method of the mobile robot as described in the first aspect of the present invention.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the navigation method of the mobile robot as described in the first aspect of the present invention.

[0042] The navigation method, device, electronic device and storage medium of the mobile robot provided by the present invention, by integrating head motion control and local planning navigation strategy, can flexibly adjust the viewing angle in a narrow space or in an environment where the positioning signal is unstable, actively obtain a wider field of view and richer environmental information, improve the navigation accuracy and robustness of the robot in complex and changeable scenes, and effectively cope with challenges such as positioning drift. At the same time, the adaptability of the robot in various application scenarios is enhanced, and even when faced with complex navigation problems, smooth and reliable path planning and obstacle avoidance can be achieved, which greatly broadens the application scope of the robot and improves its work efficiency and user experience in various service scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 This is a first schematic diagram of the process of the navigation method of the mobile robot provided by an embodiment of the present invention;

[0045] Figure 2 is a second schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0046] Figure 3 is a third schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0047] Figure 4 is a fourth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0048] Figure 5 is a fifth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0049] Figure 6is a sixth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0050] Figure 7 is a seventh schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention;

[0051] Figure 8 is a schematic structural diagram of a navigation device for a mobile robot provided by an embodiment of the present invention;

[0052] Fig. 9 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention.

[0053] Description of main component symbols:

[0054] 800, navigation device of mobile robot; 810, data acquisition module; 820, map construction module; 830, target determination module; 840, local navigation module; 900, electronic device; 910, processor; 920, communication interface; 930, memory; 940, communication bus. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0056] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0058] Traditional visual navigation systems, as the core components of autonomous mobile robots, mainly rely on the precise positioning information of mobile robots in the global map, and achieve accurate path planning and navigation by matching the current visual input with map data. The accuracy of global positioning information is crucial for traditional visual navigation systems, but in practical applications, positioning information is often affected by a variety of factors and produces deviations, such as signal interference, environmental changes, equipment failures, etc. Once the global positioning information deviates, the mobile robot may mistakenly enter the obstacle area marked in the global map due to the inability to accurately judge its own position, resulting in mission failure. Especially when working in narrow spaces, the shortcomings of traditional visual navigation technology become more and more obvious. The susceptibility of positioning signals to interference leads to positioning drift, which seriously affects the navigation performance of mobile robots.

[0059] Example 1

[0060] The embodiment of the present invention provides a navigation method for a mobile robot, which effectively solves the problem that the positioning signal of the traditional visual navigation technology is susceptible to interference and causes positioning drift. In the embodiment of the present invention, the head of the mobile robot can rotate, and a visual module is set on the head, and the visual module includes but is not limited to devices such as a visual sensor and a depth camera. Figure 1 FIG. 1 is a first schematic diagram of a navigation method for a mobile robot provided by an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0061] S100, obtaining a positioning score of the mobile robot, where the positioning score is determined based on the number of features that successfully match the key frame image of the mobile robot with the map and the reprojection pixel distance.

[0062] Figure 2 is a second schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention, such as Figure 2 As shown, the acquisition of the positioning score specifically includes the following steps:

[0063] S110, obtaining the number of features and the reprojection pixel distance between the key frame image of the mobile robot and the map that are successfully matched.

[0064] The key frame image can be determined by comparing the matching degree of the image collected by the visual module with the map before the update, or based on the change of image features. In the visual positioning process, the more the number of feature points that successfully match the key frame image of the mobile robot with the pre-built map, the more similar the current position of the mobile robot is to a certain position in the map, thereby improving the accuracy and reliability of positioning.

[0065] The reprojection pixel distance refers to the pixel distance between the point in the three-dimensional space after projecting it onto the image plane and the actually observed image point. The smaller the reprojection pixel distance, the closer the positioning result is to the actual position, and the higher the positioning accuracy. The depth information of the environment is obtained through the visual module to generate three-dimensional point cloud data, and the three-dimensional point cloud data is projected onto the image plane of the visual module. The pixel distance between the projected image point and the actually observed image point is calculated to obtain the reprojection pixel distance.

[0066] S120: If the number of features is greater than the number threshold and the reprojected pixel distance is less than the distance threshold, determine that the positioning score is the initial score.

[0067] In the embodiment of the present invention, the quantity threshold and the distance threshold can be set according to the specific application scenario and the requirements of the positioning system, and the initial score can be set according to the actual situation. For example, the quantity threshold can be set to 100, the distance threshold can be set to 5, and the initial score can be set to 100 points, that is, if the number of features that successfully match the key frame image and the map is greater than 100, and the reprojection pixel distance is less than 5 pixels, the positioning score is determined to be 100 points.

[0068] S130, obtaining the moving distance of the mobile robot and re-obtaining the number of features.

[0069] Due to navigation tasks or changes in the environment, the mobile robot moves, and the distance between the current position and the position when the initial score was obtained last time is 0.2m. At this time, the number of features that successfully match the key frame image and the map may decrease, and the number of features that successfully match is determined based on the key frame image again.

[0070] S140: If the number of features is less than the number threshold, the positioning score is re-determined according to the initial score and the moving distance.

[0071] Exemplarily, if the number of features that successfully match the key frame image with the map drops to 15, and the number of features is less than the number threshold of 100, then the positioning is judged to be unsuccessful, and the positioning score is re-determined based on the initial score and the moving distance. Figure 3 is a third schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention, such as Figure 3 As shown, the redetermination of the positioning score specifically includes the following steps:

[0072] S141. Set the distance coefficient.

[0073] The distance coefficient can be set according to the initial score and actual conditions. In the embodiment of the present invention, the distance coefficient is set to 50.

[0074] S142, multiplying the moving distance by the distance coefficient to obtain a score change value;

[0075] In the embodiment of the present invention, the fractional change value calculated according to the moving distance and the distance coefficient is 10.

[0076] S143. Subtract the score change value from the initial score to obtain a new positioning score.

[0077] In the embodiment of the present invention, the mobile robot moves 0.2 m from the position where the initial score is obtained to the current position, and the new positioning score is 90 points.

[0078] S200: If it is determined according to the positioning score that the positioning of the mobile robot is lost, the head of the mobile robot is controlled to rotate to construct a local map.

[0079] Figure 4 4 is a fourth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention. Figure 4 As shown, judging whether the mobile robot positioning is lost according to the positioning score specifically includes the following steps:

[0080] S201: If the positioning score is greater than or equal to a first score threshold, it is determined that the positioning of the mobile robot is normal.

[0081] The first score threshold can be set according to actual conditions. In the embodiment of the present invention, the first score threshold can be set to 80 points. If it is determined that the positioning of the mobile robot is normal, the mobile control can be performed according to the normal navigation mode.

[0082] S202: If the positioning score is less than the first score threshold and greater than or equal to the second score threshold, it is determined that the positioning of the mobile robot is unstable.

[0083] The second score threshold can also be set according to actual conditions. In the embodiment of the present invention, the second score threshold is set to 40 points, and the positioning of the mobile robot is unstable, indicating that there is a large error between the map position and the actual position of the real environment.

[0084] S203: If the positioning score is less than a second score threshold or the time during which the positioning of the mobile robot is unstable exceeds a time threshold, it is determined that the positioning of the mobile robot is lost.

[0085] When the positioning score is less than 40, it means that the mobile robot is located in the obstacles on the map, and the mobile robot is determined to be lost. At the same time, if the mobile robot is in an unstable positioning state for a long time, and the time exceeds the set time threshold, it means that there are obstacles around the mobile robot for a long time, and the mobile robot is also determined to be lost.

[0086] When the mobile robot is in a state of lost positioning, the normal navigation mode cannot complete the navigation task. It is necessary to control the head rotation of the mobile robot to build a local map. Figure 55 is a fifth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention. Figure 5 As shown in FIG. 1 , the construction of the local map specifically includes the following steps:

[0087] S210, controlling the head of the mobile robot to rotate, and obtaining point cloud information through the visual module.

[0088] The depth information of the environment is obtained through the visual module to generate point cloud information. Since the field of view of the visual module is small and cannot cover all the environments around the mobile robot, it is necessary to control the head of the mobile robot to rotate and observe areas with low confidence, thereby improving the accuracy of the local map.

[0089] S220 . Determine the grid position and grid status of each grid according to the point cloud information.

[0090] In an embodiment of the present invention, the local map may be a grid map, and the pixel values ​​of the grid map include three states: idle, unknown, and occupied. Among them, idle means there are no obstacles, unknown means an area that is not sensed, and occupied means an obstacle occupies the current position. The distance of the obstacle in front of the mobile robot can be sensed through the point cloud distance information, and the position information of each grid in the map coordinate system can be marked. The grid state can be determined by the point cloud height. For example, if the height of the point cloud is 0m, the grid of the area is set to an idle state. If the height of the point cloud exceeds 0.1m, the grid of the area is set to an occupied state. For other point cloud heights, the grid of the area is set to an unknown state.

[0091] S230, determining the confidence of the grid according to the number of point cloud observations, and obtaining an initial local map.

[0092] The initial grid map confidence is set to 0, and the confidence is related to the number of times the grid area has been observed. For example, if a grid area has been observed 0 times by the point cloud, that is, it has not been observed, the confidence is set to 0; if the number of observations is less than or equal to 10 times, the confidence is set to 1; if the number of observations is n times, and n is greater than or equal to 10 times, the confidence is set to n / 10.

[0093] S240: Update the confidence of the initial local map according to the rotation angle of the head of the mobile robot to obtain a local map.

[0094] Figure 6 6 is a sixth schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention. Figure 6 As shown, the confidence update specifically includes the following steps:

[0095] S241. Control the head of the mobile robot to rotate, and obtain a map of the front semicircle area in the moving direction of the mobile robot.

[0096] Due to the viewing angle limitation of the visual module, the mobile robot cannot observe a large area through one image, so a map of the front semicircle area in the moving direction centered on the mobile robot is obtained.

[0097] S242: Divide the front semicircle area map into at least one sector-shaped area, and calculate the confidence level of each sector-shaped area.

[0098] In an embodiment of the present invention, the front semicircular area map is divided into four sector areas, and the confidence of each sector area is counted. Specifically, the confidence statistics are as follows: a ray is made clockwise from the center to the circle boundary, and if there is an obstacle on the ray, it is terminated, and the sum of the confidences from the starting point to the end point is counted, and if there is no obstacle, it is terminated at the circle boundary, until the confidence of the entire sector area is counted, and the total confidence of the sector area is obtained.

[0099] S243. If the confidence of the sector-shaped area is lower than the confidence threshold, the head of the mobile robot is controlled to rotate to update the confidence of the corresponding sector-shaped area map to obtain a local map.

[0100] Areas with confidence values ​​lower than the confidence threshold are counted in order, and the areas with confidence values ​​lower than the confidence threshold are updated in order by controlling the mobile robot to rotate its head until a map is constructed in which all areas meet the confidence threshold, i.e., a local map. In the embodiment of the present invention, the confidence threshold can be set according to actual conditions.

[0101] S300: Acquire a global map of the mobile robot's navigation, and determine a navigation target point according to the global map.

[0102] The mobile robot needs to know the location of the navigation target point in the local map in order to perform local navigation. In normal navigation mode, the navigation target point of the mobile robot is determined by the global planner planning the global path in the global map. The local map is only a small area of ​​the global map. In the absence of a global path, it is difficult to determine the navigation target point.

[0103] If the mobile robot performs local navigation in a narrow channel, it can be judged by constructing a local map. When an obvious channel area appears around the mobile robot, the middle of the end of the narrow channel is directly used as the navigation target point.

[0104] If the mobile robot performs local navigation in a narrow space, it needs to determine the navigation target point based on the global map. Figure 7 7 is a seventh schematic diagram of the navigation method flow of a mobile robot provided by an embodiment of the present invention. Figure 7 As shown, the determination of the navigation target point specifically includes the following steps:

[0105] S310: Roughly match the local map with the global map to obtain a rough position of the local map in the global map.

[0106] In an embodiment of the present invention, a narrow space is manifested as obstacles with more obvious features appearing in a local map. At this time, the local map and the global map are roughly matched to obtain a rough position of the current local map in the global map. The rough matching can adopt matching methods such as point-to-point matching, point-to-arc matching and feature matching.

[0107] S320: Plan a global path in the global map according to the rough position, and use the end of the global path as a navigation target point.

[0108] In the robot coordinate system, the global path can be planned directly using the global map according to the rough position, and the end of the global path can be used as the navigation target point.

[0109] If the mobile robot performs local navigation in an open space, it means that there are few obstacles when constructing the local map. In the robot coordinate system, the global path can be directly planned using the global map, and the end of the global path can be used as the navigation target point.

[0110] S400: Determine a target end point in the local map according to the navigation target point, and generate a local navigation path using the target end point to perform local navigation.

[0111] In the embodiment of the present invention, during the local navigation process, when the positioning state is restored from positioning loss to normal positioning, it is possible to switch to the normal navigation mode for navigation.

[0112] The navigation method of the mobile robot provided in the embodiment of the present invention integrates head motion control and local planning navigation strategy. The robot can flexibly adjust the viewing angle in a narrow space or an environment with unstable positioning signals, actively obtain a wider field of view and richer environmental information, improve the navigation accuracy and robustness of the robot in complex and changeable scenes, and effectively cope with challenges such as positioning drift.

[0113] Example 2

[0114] Based on the same technical concept as the above method embodiment 1, the embodiment of the present invention provides a navigation device for a mobile robot, Figure 8 FIG. 1 is a schematic diagram of the structure of a navigation device of a mobile robot provided by an embodiment of the present invention. Figure 8 As shown, the navigation device 800 of the mobile robot includes:

[0115] The data acquisition module 810 is used to obtain the positioning score of the mobile robot, and the positioning score is determined based on the number of features that successfully match the key frame image of the mobile robot with the map and the reprojection pixel distance.

[0116] The map construction module 820 is used to control the head of the mobile robot to rotate to construct a local map if it is determined that the positioning of the mobile robot is lost according to the positioning score.

[0117] The target determination module 830 is used to obtain a global map of the mobile robot's navigation and determine a navigation target point according to the global map.

[0118] The local navigation module 840 determines a target end point in the local map according to the navigation target point, and generates a local navigation path using the target end point to perform local navigation.

[0119] The navigation device for a mobile robot provided in an embodiment of the present invention enhances the adaptability of the robot in various application scenarios, and can achieve smooth and reliable path planning and obstacle avoidance even when faced with complex navigation problems, thereby greatly broadening the application scope of the robot and improving its work efficiency and user experience in various service scenarios.

[0120] It can be understood that the implementation method of the mobile robot navigation method described in the above embodiment 1 is also applicable to this embodiment and can achieve the same technical effect, so it will not be repeated here.

[0121] Example 3

[0122] Based on the same concept, an embodiment of the present invention further provides an electronic device, Fig. 9 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig. 9 As shown, the electronic device 900 may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute the steps of the mobile robot navigation method described in the above embodiments. For example, it includes:

[0123] S100, obtaining a positioning score of the mobile robot, where the positioning score is determined based on the number of features that successfully match the key frame image of the mobile robot with the map and the reprojection pixel distance;

[0124] S200: If it is determined according to the positioning score that the positioning of the mobile robot is lost, the head of the mobile robot is controlled to rotate to construct a local map;

[0125] S300, obtaining a global map of the mobile robot's navigation, and determining a navigation target point according to the global map;

[0126] S400: Determine a target end point in the local map according to the navigation target point, and generate a local navigation path using the target end point to perform local navigation.

[0127] The processor 910 may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0128] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0129] The memory 930 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] Example 4

[0131] Based on the same concept, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program includes at least one code segment, which can be executed by a main control device to control the main control device to implement the steps of the mobile robot navigation method described in the above embodiments. For example, it includes:

[0132] S100, obtaining a positioning score of the mobile robot, where the positioning score is determined based on the number of features that successfully match the key frame image of the mobile robot with the map and the reprojection pixel distance;

[0133] S200: If it is determined according to the positioning score that the positioning of the mobile robot is lost, the head of the mobile robot is controlled to rotate to construct a local map;

[0134] S300, obtaining a global map of the mobile robot's navigation, and determining a navigation target point according to the global map;

[0135] S400: Determine a target end point in the local map according to the navigation target point, and generate a local navigation path using the target end point to perform local navigation.

[0136] Based on the same technical concept, an embodiment of the present invention further provides a computer program, which is used to implement the above method embodiment when executed by a main control device.

[0137] The computer program may be stored in whole or in part on a computer-readable storage medium packaged with the processor, or may be stored in whole or in part on a memory not packaged with the processor.

[0138] Based on the same technical concept, an embodiment of the present invention further provides a processor, which is used to implement the above method embodiment. The above processor can be a chip.

[0139] In summary, the navigation method, device, electronic device and storage medium of the mobile robot provided by the present invention, by integrating head motion control and local planning navigation strategy, can flexibly adjust the viewing angle in a narrow space or an environment with unstable positioning signals, actively obtain a wider field of view and richer environmental information, improve the navigation accuracy and robustness of the robot in complex and changeable scenes, and effectively cope with challenges such as positioning drift. At the same time, the adaptability of the robot in various application scenarios is enhanced, and even when faced with complex navigation problems, smooth and reliable path planning and obstacle avoidance can be achieved, which greatly broadens the application scope of the robot and improves its work efficiency and user experience in various service scenarios.

[0140] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0141] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A navigation method for a mobile robot, characterized in that: The head of the mobile robot is provided with a visual module, and the method comprises: Obtaining a positioning score of the mobile robot, wherein the positioning score is determined based on the number of features of a key frame image of the mobile robot that successfully matches a map and a reprojected pixel distance; If it is determined according to the positioning score that the positioning of the mobile robot is lost, controlling the head of the mobile robot to rotate to construct a local map; Acquire a global map of the mobile robot's navigation, and determine a navigation target point according to the global map; A target end point in the local map is determined according to the navigation target point, and a local navigation path is generated using the target end point to perform local navigation.

2. The navigation method of a mobile robot according to claim 1, characterized in that: The controlling the head rotation of the mobile robot to construct a local map includes: Controlling the head of the mobile robot to rotate and acquiring point cloud information through the visual module; Determine the grid position and grid state of each grid according to the point cloud information; Determine the confidence of the grid according to the number of point cloud observations to obtain the initial local map; The confidence of the initial local map is updated according to the rotation angle of the head of the mobile robot to obtain the local map.

3. The navigation method of the mobile robot according to claim 2, characterized in that: The step of updating the confidence of the initial local map according to the rotation angle of the head of the mobile robot to obtain the local map comprises: Controlling the rotation of the head of the mobile robot to obtain a map of the front semicircle area in the moving direction of the mobile robot; Divide the front semicircular area map into at least one sector-shaped area, and calculate the confidence of each sector-shaped area; If the confidence of the sector area is lower than the confidence threshold, the head of the mobile robot is controlled to rotate to update the confidence of the corresponding sector area map to obtain the local map.

4. The navigation method of a mobile robot according to claim 1, characterized in that: The obtaining of the positioning score of the mobile robot comprises: Obtaining the number of features and reprojected pixel distances of the key frame image of the mobile robot that successfully matches the map; If the number of features is greater than a number threshold and the reprojected pixel distance is less than a distance threshold, determining the positioning score to be an initial score; Obtaining the moving distance of the mobile robot and re-obtaining the feature quantity; If the number of features is less than the number threshold, the positioning score is re-determined according to the initial score and the moving distance.

5. The navigation method of the mobile robot according to claim 4, characterized in that: The re-determining the positioning score according to the moving distance includes: Set the distance factor; Multiplying the moving distance by the distance coefficient to obtain a fractional change value; The score change value is subtracted from the initial score to obtain a new positioning score.

6. The navigation method of a mobile robot according to claim 1, characterized in that: The determining, according to the positioning score, that the mobile robot has lost its positioning includes: If the positioning score is greater than or equal to a first score threshold, it is determined that the positioning of the mobile robot is normal; If the positioning score is less than the first score threshold and greater than or equal to the second score threshold, determining that the positioning of the mobile robot is unstable; If the positioning score is less than the second score threshold or the time during which the positioning of the mobile robot is unstable exceeds a time threshold, it is determined that the positioning of the mobile robot is lost.

7. The navigation method of a mobile robot according to claim 1, characterized in that: Determining the navigation target point according to the global map includes: Roughly matching the local map with the global map to obtain a rough position of the local map in the global map; A global path is planned in the global map according to the rough position, and an end of the global path is used as a navigation target point.

8. A navigation device for a mobile robot, characterized in that: The head of the mobile robot is provided with a visual module, and the device comprises: A data acquisition module, used to acquire a positioning score of the mobile robot, wherein the positioning score is determined based on the number of features of the key frame image of the mobile robot that successfully matches the map and the reprojection pixel distance; A map construction module, configured to control the head of the mobile robot to rotate to construct a local map if it is determined according to the positioning score that the positioning of the mobile robot is lost; A target determination module is used to obtain a global map of the mobile robot's navigation and determine a navigation target point according to the global map; The local navigation module is used to determine the target end point in the local map according to the navigation target point, and generate a local navigation path using the target end point to perform local navigation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the computer program to implement the navigation method of the mobile robot according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the navigation method of the mobile robot according to any one of claims 1 to 7 is implemented.

Images