Indoor robot navigation positioning method and system, electronic equipment and storage medium
By integrating indoor point cloud data and image data, combining bottom and top map information, the service robot's navigation positioning accuracy and environmental adaptation are achieved, and the problem of low navigation accuracy caused by indoor environment changes is solved.
Patent Information
- Application Number
- CN202411516128.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-29
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-10-29
AI Technical Summary
Service robots have problems with low positioning errors and navigation accuracy due to items moving or environmental changes in indoor environments.
By integrating point cloud data at the bottom of the indoor and image data at the top, similarity comparison and optimization algorithms are used to adjust the robot's position estimation and map information to achieve real-time correction of the map, and navigation is combined with the bottom environment map and the top feature map.
It improves the robot's navigation and positioning accuracy and autonomy, enhances its ability to adapt to changes in the surrounding environment, and ensures more accurate environmental perception and map construction.
Smart Images

Figure CN119043339A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of robotics technology, and in particular to an indoor robot navigation and positioning method, system, electronic equipment and storage medium. Background Art
[0002] With the development of science and technology and the improvement of people's living standards, service robots have gradually integrated into people's daily lives, providing people with rich and humanized services. Compared with other types of robots, the working environment of service robots is usually more complex, which puts higher requirements on their positioning capabilities. Positioning is to determine the coordinates of the robot in the world coordinate system in its motion environment, which is crucial for service robots to perform various tasks. Accurate positioning information can help the robot understand its own position, surrounding environment and target location, so as to achieve precise navigation, obstacle avoidance and task completion.
[0003] When a service robot operates in an indoor environment, it mainly relies on the bottom lidar for positioning and navigation. The lidar calculates the distance between the object and the robot by emitting a laser beam and measuring the time it takes for it to reflect back. As one of the main sensors in the service robot, the lidar can continuously scan the surrounding environment, obtain high-precision distance information, and form initial point cloud data. This data is then used to build a map of the robot's environment. However, the movement of indoor objects or changes in the environment (such as rearranging furniture, the appearance of temporary obstacles, etc.) may cause the robot to be unable to accurately match the previously created map, resulting in positioning errors and "getting lost", which directly affects the navigation accuracy and operating efficiency of the service robot. Summary of the invention
[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides an indoor robot navigation and positioning method, system, electronic device and storage medium, which effectively solve the problems of low navigation accuracy and operation efficiency of service robots in indoor scenarios.
[0005] In a first aspect, the present invention provides an indoor robot navigation and positioning method, the method comprising: Obtain the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot; constructing a bottom environment map according to the initial point cloud data, and constructing a top feature map according to the image data; During the navigation movement of the robot according to the bottom environment map, real-time point cloud data is acquired, and similarity comparison is performed between the real-time point cloud data and the initial point cloud data to obtain a first similarity comparison value; According to the first similarity comparison value, selecting the bottom environment map and / or the top feature map for navigation to obtain navigation data; A navigation path is updated according to the navigation data and the real-time point cloud data, and the movement of the robot is controlled according to the navigation path.
[0006] Further, selecting the bottom environment map and / or the top feature map for navigation according to the first similarity comparison value to obtain navigation data includes: If the first similarity comparison value is greater than or equal to a first set threshold, the bottom environment map is used for navigation to obtain the navigation data; If the first similarity comparison value is less than the first set threshold value, and the first similarity comparison value is greater than the second set threshold value, the top feature map is used in combination with the bottom environment map for navigation to obtain the navigation data; If the first similarity comparison value is less than the second set threshold, the robot stops running and issues an alarm message.
[0007] Furthermore, after navigating by using the top feature map in combination with the bottom environment map, the method further includes: Performing a similarity comparison between the real-time point cloud data and the data of the top feature map to obtain a second similarity comparison value; If the second similarity comparison value is greater than or equal to a third set threshold, use the top feature map in combination with the bottom environment map to perform navigation to obtain the navigation data; If the second similarity comparison value is less than a third set threshold, the robot stops running and issues an alarm message.
[0008] Furthermore, the obtaining of the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot includes: Controlling the laser collection device of the robot to emit a laser beam, and receiving the laser reflected by the object at the bottom of the room, calculating the time difference from the emission to the reception of the laser beam, and constructing a global map; Recording the emission angle and distance information of the laser beam, and calculating the time difference from emission to reception of the laser beam to form initial point cloud data; The image acquisition device of the robot is controlled to acquire an indoor top image, and grayscale values are extracted according to the indoor top image to obtain the image data.
[0009] Furthermore, constructing a bottom environment map according to the initial point cloud data includes: Preprocessing the initial point cloud data of the current frame and the previous frame, and extracting feature points; Performing feature matching on the initial point cloud data of the current frame and the previous frame according to the feature points, and calculating the posture data of the robot from the previous frame to the current frame; The initial point cloud data is optimized according to the posture data, and the optimized initial point cloud data is integrated into the global map to construct the bottom environment map.
[0010] Furthermore, the optimized initial point cloud data is integrated into the global map to construct a bottom environment map, including: Registering the optimized initial point cloud data with the global map; Determine the overlapping area and non-overlapping area between the initial point cloud data and the global map by using the Euclidean distance method; Performing weighted fusion on the initial point cloud data of the overlapping area to obtain fused data, and performing segmentation and screening on the non-overlapping area by a clustering method to obtain environmental information; The bottom environment map is constructed according to the fused data and the environment information.
[0011] Further, constructing a top feature map according to the image data includes: Perform feature extraction based on the image data to obtain key feature information; Performing image segmentation on the image data to obtain a plurality of image region objects; Performing edge detection on a plurality of the image area objects to obtain edge feature information; The top feature map is constructed according to the key feature information and the edge feature information.
[0012] In a second aspect, the present invention provides an indoor robot navigation and positioning system, the system comprising: A data acquisition module is used to acquire the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot; A map construction module, used to construct a bottom environment map according to the initial point cloud data, and to construct a top feature map according to the image data; A data comparison module is used to obtain real-time point cloud data during the navigation movement of the robot according to the bottom environment map, and to compare the real-time point cloud data with the initial point cloud data to obtain a first similarity comparison value; A map selection module, configured to select the bottom environment map and / or the top feature map for navigation according to the first similarity comparison value, and obtain navigation data; A navigation and positioning module is used to update a navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
[0013] 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 indoor robot navigation and positioning method as described in the first aspect of the present invention.
[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the indoor robot navigation and positioning method as described in the first aspect of the present invention is implemented.
[0015] The indoor robot navigation and positioning method, system, electronic device and storage medium provided by the present invention integrate the point cloud data of the bottom of the room and the image data of the top of the room. When the point cloud data of the bottom is different, the robot will use the feature information of the top for comparison and fusion, and adjust the position estimation and map information of the robot through the optimization algorithm to achieve real-time correction of the map, so that the robot can more accurately perceive the changes in the surrounding environment, adapt to complex situations such as the movement of indoor objects or changes in the environment, and achieve more accurate environmental perception and map construction, thereby improving the navigation and positioning accuracy of the robot. At the same time, the corrected map not only provides a more reliable reference for future navigation tasks, but also enhances the autonomy and adaptability of the robot. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] 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.
[0017] Figure 1 This is a first schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 2 This is a second schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 3 This is a third schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 4 This is a fourth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 5 This is a fifth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 6 This is a sixth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 7This is the seventh schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention; Figure 8 It is a schematic diagram of the structure of an indoor robot navigation and positioning system provided by an embodiment of the present invention; Fig. 9 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention.
[0018] Description of main component symbols: 800, indoor robot navigation and positioning system; 810, data acquisition module; 820, map construction module; 830, data comparison module; 840, map selection module; 850, navigation and positioning module; 900, electronic device; 910, processor; 920, communication interface; 930, memory; 940, communication bus. DETAILED DESCRIPTION
[0019] 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.
[0020] 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.
[0021] 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.
[0022] When a service robot operates in an indoor environment, it mainly relies on the bottom lidar for positioning and navigation. The lidar calculates the distance between the object and the robot by emitting a laser beam and measuring the time it takes for it to reflect back. As one of the main sensors in the service robot, the lidar can continuously scan the surrounding environment, obtain high-precision distance information, and form initial point cloud data. This data is then used to build a map of the robot's environment. However, the movement of indoor objects or changes in the environment (such as rearranging furniture, the appearance of temporary obstacles, etc.) may cause the robot to be unable to accurately match the previously created map, resulting in positioning errors and "getting lost", which directly affects the navigation accuracy and operating efficiency of the service robot.
[0023] Example 1 In view of the above-mentioned deficiencies in the prior art, an embodiment of the present invention provides an indoor robot navigation and positioning method, which effectively solves the problems of low navigation accuracy and low operating efficiency of a service robot in indoor scenarios. Figure 1 FIG. 1 is a first schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: S100, obtaining initial point cloud data of the indoor bottom and image data of the indoor top collected by the robot; In an embodiment of the present invention, robots include but are not limited to indoor robots such as food delivery robots, household service robots, warehouse logistics robots and medical assistance robots. A laser acquisition device is set at the bottom of the robot to scan the indoor bottom environment and obtain the indoor bottom environmental data. An image acquisition device is set at the top of the robot to scan the indoor top environment and obtain top feature data.
[0024] Figure 2 : is a second schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention, such as Figure 2 As shown, step S100 specifically includes the following steps: S110, controlling the laser collection device of the robot to emit a laser beam, and receiving the laser reflected by the object at the bottom of the room, calculating the time difference from the emission to the reception of the laser beam, and constructing a global map.
[0025] In an embodiment of the present invention, the laser acquisition device may be a laser radar, which emits a laser beam at a certain frequency through a laser light source. The laser receiving module of the laser radar is responsible for receiving the laser reflected back by the object. The laser data processing module of the laser radar calculates the time difference or phase difference from the emission to the reception of the laser beam, and constructs a global map through the SLAM algorithm to calculate the position and orientation of the robot. This is a two-dimensional plane map containing information on obstacles and passable areas.
[0026] S120, recording the emission angle and distance information of the laser beam to form initial point cloud data; At the same time, the laser radar scans the surrounding environment by rotating and swinging. During the scanning process, the laser radar will continuously record the emission angle and corresponding distance information of each laser beam to form a series of initial point cloud data. These initial point cloud data contain information such as the position, shape, and size of obstacles in the environment.
[0027] S130, controlling the image acquisition device of the robot to acquire an indoor top image, extracting grayscale values according to the indoor top image, and obtaining image data.
[0028] In an embodiment of the present invention, the image acquisition device may be a camera, which is used to capture the features of the top of the room (such as ceiling structure, chandelier, etc.), and the optical lens of the camera focuses light onto the image sensor CMOS. This process converts the light signal into an analog electrical signal, and then converts the analog electrical signal into a digital signal through an analog-to-digital converter ADC. The digital signal represents the image in the form of pixels, and each pixel contains color information (red, green, blue, i.e., RGB), and a digital signal RGB image is obtained. The grayscale value is obtained by weighted averaging the RGB values in the digital signal RGB image through a floating-point algorithm. The calculation formula of the floating-point algorithm is as follows: Gray = R×0.3 + G×0.59 + B×0.11 In the above formula, Gray represents the grayscale value, R represents the red channel value, G represents the green channel value, and B represents the white channel value.
[0029] The grayscale value is an integer between 0 (black) and 255 (white), which represents the brightness of each pixel in the image. The captured images are usually in color, but when constructing the top feature map of the interior, only the brightness information of the image is extracted without the color information. The top feature map can be constructed through the grayscale value. At the same time, the amount of grayscale data is small, which can improve the subsequent data calculation and data comparison speed and reduce the probability of error.
[0030] S200, constructing a bottom environment map according to the initial point cloud data, and constructing a top feature map according to the image data.
[0031] Figure 3 is a third schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention, such as Figure 3 As shown, building the bottom environment map includes the following steps: S210 , preprocessing the initial point cloud data of the current frame and the previous frame, and extracting feature points.
[0032] Preprocessing operations such as filtering and denoising are performed on the initial point cloud data of the current frame and the previous frame or multiple frames, and then feature points are extracted from the preprocessed initial point cloud data.
[0033] S220, performing feature matching on the initial point cloud data of the current frame and the previous frame according to the feature points, and calculating the position and posture data of the robot from the previous frame to the current frame.
[0034] The brute force matching and fast nearest neighbor search library algorithms are used to perform feature matching on the initial point cloud data of the current frame with the initial point cloud data of the previous frame or multiple frames, and the preliminary pose transformation of the robot from the previous frame to the current frame is calculated based on the matched features.
[0035] S230, optimizing the initial point cloud data according to the posture data, integrating the optimized initial point cloud data into the global map, and constructing a bottom environment map.
[0036] Acquire multiple frames of initial point cloud data to optimize the pose and improve the accuracy, fuse the optimized initial point cloud data of the current frame into the global map, and construct the bottom environment map. Figure 4 4 is a fourth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention. Figure 4 As shown, step S230 specifically includes the following steps: S231, registering the optimized initial point cloud data with the global map.
[0037] In an embodiment of the present invention, the Super4pcs algorithm is used to align the optimized initial point cloud data with the global map to ensure their consistency in spatial position.
[0038] S232. Determine the overlapping area and non-overlapping area between the initial point cloud data and the global map by using the Euclidean distance method.
[0039] S233, performing weighted fusion on the initial point cloud data of the overlapping area to obtain fused data, and performing segmentation and screening on the non-overlapping area by using a clustering method to obtain environmental information.
[0040] The initial point cloud data in the overlapping area is weightedly fused to ensure a smooth transition of the fused data, and the non-overlapping area is segmented and screened by clustering method to retain useful environmental information.
[0041] S234. Construct a bottom environment map based on the fused data and environmental information.
[0042] Continuously obtain optimized initial point cloud data, repeat point cloud registration, fusion and optimization, and gradually build a complete bottom environment map.
[0043] Figure 55 is a fifth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention. Figure 5 As shown in Figure 1, constructing the top feature map specifically includes the following steps: S240: Extract features based on the image data to obtain key feature information.
[0044] Feature extraction is the process of identifying key information in an image that is useful for building a map. In grayscale images, these features may include texture, shape, color (brightness changes in grayscale images), etc.
[0045] S250: Segment the image data to obtain a plurality of image region objects.
[0046] Image segmentation is the process of dividing an image into multiple regions or objects that are visually or statistically similar. In an embodiment of the present invention, methods such as threshold segmentation, region growing algorithm, level set method and graph cut algorithm can be used to perform image segmentation.
[0047] S260: Perform edge detection on multiple image region objects to obtain edge feature information.
[0048] Edge detection is the process of identifying locations in an image where brightness changes significantly, which usually correspond to the boundaries of objects. In an embodiment of the present invention, a Canny edge detection algorithm or a Sobel edge detection algorithm is used for edge detection.
[0049] S270: Construct a top feature map according to the key feature information and the edge feature information.
[0050] Based on key feature information and edge feature information, geocoding, topological relationship analysis, vectorization and map rendering are used to construct the top feature map.
[0051] S300. When the robot is navigating and moving according to the bottom environment map, real-time point cloud data is acquired, and similarity comparison is performed between the real-time point cloud data and the initial point cloud data to obtain a first similarity comparison value.
[0052] When the robot is moving, it uses the bottom laser radar as the main navigation basis and uses the bottom environment map for real-time positioning and navigation. The similarity between the real-time point cloud data and the initial point cloud data of the bottom environment map is calculated to obtain a first similarity comparison value.
[0053] S400: According to the first similarity comparison value, select a bottom environment map and / or a top feature map for navigation to obtain navigation data.
[0054] First, the similarity switching threshold of the laser radar point cloud data is set as the first set threshold, the laser radar data similarity alarm threshold is set as the second set threshold, and the camera alarm threshold is set as the third set threshold, which is used to determine whether the navigation strategy and alarm strategy need to be switched.
[0055] Figure 6 6 is a sixth schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention. Figure 6 As shown, step S400 specifically includes the following steps: S410: If the first similarity comparison value is greater than or equal to a first set threshold, use the bottom environment map for navigation to obtain navigation data.
[0056] S420: If the first similarity comparison value is less than the first set threshold value, and the first similarity comparison value is greater than the second set threshold value, the top feature map is used in combination with the bottom environment map for navigation to obtain navigation data.
[0057] Specifically, stable visual features (such as corners, edges, textures, etc.) are extracted from the top feature map, and the extracted features are compared with the top features pre-stored in the map to find matching points. These matching points can be used as "anchor points" to correct map errors caused by environmental changes and help the robot locate more accurately on the bottom map of the environment. By combining the bottom point cloud data and the results of the top image feature matching, the robot's position estimation and map information are adjusted through the optimization algorithm, thereby achieving real-time correction of the map.
[0058] When the similarity of the point cloud data of the lidar data is restored to above the first set threshold, the lidar is switched back to the main navigation mode, and the bottom environment map is used for navigation.
[0059] S430: If the first similarity comparison value is less than the second set threshold, the robot stops running and issues an alarm message.
[0060] At this time, the robot may be running on an unfamiliar map and needs to re-scan the environment using lidar and cameras to create a corresponding map.
[0061] Figure 7 7 is a seventh schematic diagram of the process of the indoor robot navigation and positioning method provided by an embodiment of the present invention. Figure 7 As shown, step S400 also includes the following steps: S440: Perform a similarity comparison between the real-time point cloud data and the data of the top feature map to obtain a second similarity comparison value.
[0062] S450: If the second similarity comparison value is greater than or equal to a third set threshold, use the top feature map and the bottom environment map to perform navigation to obtain navigation data.
[0063] S460: If the second similarity comparison value is less than the third set threshold, the robot stops running and issues an alarm message.
[0064] Similarly, the robot may be running on an unfamiliar map at this time and needs to re-scan the environment using lidar and cameras to create a corresponding map.
[0065] S500: Update the navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
[0066] Based on the acquired navigation data and real-time point cloud data, the robot can make more accurate navigation decisions and update the navigation path, such as selecting the optimal path, avoiding obstacles, etc. The robot movement is controlled by forwarding the navigation path to the hardware control unit.
[0067] The indoor robot navigation and positioning method provided by the embodiment of the present invention integrates the point cloud data of the bottom of the room and the image data of the top of the room. When there is a difference in the point cloud data at the bottom, the robot will use the top feature information for comparison and fusion, and adjust the robot's position estimation and map information through the optimization algorithm to achieve real-time correction of the map, so that the robot can perceive changes in the surrounding environment more accurately and adapt to complex situations such as the movement of indoor objects or changes in the environment.
[0068] Example 2 Based on the same technical concept as the method embodiment of the above embodiment 1, the embodiment of the present invention provides an indoor robot navigation and positioning system. Figure 8 FIG. 1 is a schematic diagram of the structure of an indoor robot navigation and positioning system provided by an embodiment of the present invention. Figure 8 As shown, the indoor robot navigation and positioning system 800 includes: The data acquisition module 810 is used to acquire the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot; A map construction module 820, for constructing a bottom environment map based on the initial point cloud data, and a top feature map based on the image data; The data comparison module 830 is used to obtain real-time point cloud data during the navigation movement of the robot according to the bottom environment map, and to compare the real-time point cloud data with the initial point cloud data to obtain a first similarity comparison value; A map selection module 840, configured to select a bottom environment map and / or a top feature map for navigation according to the first similarity comparison value, and obtain navigation data; The navigation and positioning module 850 is used to update the navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
[0069] The indoor robot navigation and positioning system provided by the embodiment of the present invention can achieve more accurate environmental perception and map construction, and improve the navigation and positioning accuracy of the robot. At the same time, the corrected map not only provides a more reliable reference for future navigation tasks, but also enhances the autonomy and adaptability of the robot.
[0070] It can be understood that the implementation method of the indoor robot navigation and positioning method described in the above-mentioned embodiment 1 is also applicable to this embodiment and can achieve the same technical effect, so it will not be repeated here.
[0071] Example 3 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 indoor robot navigation and positioning method described in the above embodiments. For example, it includes: S100, obtaining initial point cloud data of the indoor bottom and image data of the indoor top collected by the robot; S200, constructing a bottom environment map according to the initial point cloud data, and constructing a top feature map according to the image data; S300, while the robot is navigating and moving according to the bottom environment map, acquiring real-time point cloud data, and performing a similarity comparison between the real-time point cloud data and the initial point cloud data to obtain a first similarity comparison value; S400: selecting a bottom environment map and / or a top feature map for navigation according to a first similarity comparison value, and acquiring navigation data; S500: Update the navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
[0072] 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.
[0073] 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 this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of 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 and other media that can store program codes.
[0074] 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.
[0075] Example 4 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 indoor robot navigation and positioning method described in the above embodiments. For example, it includes: S100, obtaining initial point cloud data of the indoor bottom and image data of the indoor top collected by the robot; S200, constructing a bottom environment map according to the initial point cloud data, and constructing a top feature map according to the image data; S300, while the robot is navigating and moving according to the bottom environment map, acquiring real-time point cloud data, and performing a similarity comparison between the real-time point cloud data and the initial point cloud data to obtain a first similarity comparison value; S400: selecting a bottom environment map and / or a top feature map for navigation according to a first similarity comparison value, and acquiring navigation data; S500: Update the navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
[0076] 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.
[0077] 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.
[0078] 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.
[0079] In summary, the indoor robot navigation and positioning method, system, electronic device and storage medium provided by the present invention integrates the point cloud data of the bottom of the room and the image data of the top of the room. When there is a difference in the point cloud data of the bottom, the robot will use the top feature information for comparison and fusion, and adjust the robot's position estimation and map information through the optimization algorithm to achieve real-time correction of the map, so that the robot can more accurately perceive changes in the surrounding environment, adapt to complex situations such as indoor object movement or environmental changes, achieve more accurate environmental perception and map construction, and improve the navigation and positioning accuracy of the robot. At the same time, the corrected map not only provides a more reliable reference for future navigation tasks, but also enhances the autonomy and adaptability of the robot. 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.
[0080] 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.
[0081] 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 method for indoor robot navigation and positioning, characterized in that: The method comprises: Obtain the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot; constructing a bottom environment map according to the initial point cloud data, and constructing a top feature map according to the image data; During the navigation movement of the robot according to the bottom environment map, real-time point cloud data is acquired, and similarity comparison is performed between the real-time point cloud data and the initial point cloud data to obtain a first similarity comparison value; According to the first similarity comparison value, selecting the bottom environment map and / or the top feature map for navigation to obtain navigation data; A navigation path is updated according to the navigation data and the real-time point cloud data, and the movement of the robot is controlled according to the navigation path.
2. The indoor robot navigation and positioning method according to claim 1, characterized in that: The step of selecting the bottom environment map and / or the top feature map for navigation according to the first similarity comparison value to obtain navigation data includes: If the first similarity comparison value is greater than or equal to a first set threshold, the bottom environment map is used for navigation to obtain the navigation data; If the first similarity comparison value is less than the first set threshold value, and the first similarity comparison value is greater than the second set threshold value, the top feature map is used in combination with the bottom environment map for navigation to obtain the navigation data; If the first similarity comparison value is less than the second set threshold, the robot stops running and issues an alarm message.
3. The indoor robot navigation and positioning method according to claim 2, characterized in that: After the top feature map is used in combination with the bottom environment map for navigation, the method further includes: Performing a similarity comparison between the real-time point cloud data and the data of the top feature map to obtain a second similarity comparison value; If the second similarity comparison value is greater than or equal to a third set threshold, use the top feature map in combination with the bottom environment map to perform navigation to obtain the navigation data; If the second similarity comparison value is less than a third set threshold, the robot stops running and issues an alarm message.
4. The indoor robot navigation and positioning method according to claim 1, characterized in that: The obtaining of the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot includes: Controlling the laser collection device of the robot to emit a laser beam, and receiving the laser reflected by the object at the bottom of the room, calculating the time difference from the emission to the reception of the laser beam, and constructing a global map; Recording the emission angle and distance information of the laser beam to form initial point cloud data; The image acquisition device of the robot is controlled to acquire an indoor top image, and grayscale values are extracted according to the indoor top image to obtain the image data.
5. The indoor robot navigation and positioning method according to claim 4, characterized in that: The step of constructing a bottom environment map according to the initial point cloud data comprises: Preprocessing the initial point cloud data of the current frame and the previous frame, and extracting feature points; Performing feature matching on the initial point cloud data of the current frame and the previous frame according to the feature points, and calculating the posture data of the robot from the previous frame to the current frame; The initial point cloud data is optimized according to the posture data, and the optimized initial point cloud data is integrated into the global map to construct the bottom environment map.
6. The indoor robot navigation and positioning method according to claim 5, characterized in that: The step of fusing the optimized initial point cloud data into the global map to construct a bottom environment map includes: Registering the optimized initial point cloud data with the global map; Determine the overlapping area and non-overlapping area between the initial point cloud data and the global map by using the Euclidean distance method; Performing weighted fusion on the initial point cloud data of the overlapping area to obtain fused data, and performing segmentation and screening on the non-overlapping area by a clustering method to obtain environmental information; The bottom environment map is constructed according to the fused data and the environment information.
7. The indoor robot navigation and positioning method according to claim 1, characterized in that: The step of constructing a top feature map according to the image data comprises: Perform feature extraction based on the image data to obtain key feature information; Performing image segmentation on the image data to obtain a plurality of image region objects; Performing edge detection on a plurality of the image area objects to obtain edge feature information; The top feature map is constructed according to the key feature information and the edge feature information.
8. An indoor robot navigation and positioning system, characterized in that: The system comprises: A data acquisition module is used to acquire the initial point cloud data of the indoor bottom and the image data of the indoor top collected by the robot; A map construction module, used to construct a bottom environment map according to the initial point cloud data, and to construct a top feature map according to the image data; A data comparison module is used to obtain real-time point cloud data during the navigation movement of the robot according to the bottom environment map, and to compare the real-time point cloud data with the initial point cloud data to obtain a first similarity comparison value; A map selection module, configured to select the bottom environment map and / or the top feature map for navigation according to the first similarity comparison value, and obtain navigation data; A navigation and positioning module is used to update a navigation path according to the navigation data and the real-time point cloud data, and control the movement of the robot according to the navigation path.
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 indoor robot navigation and positioning method 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 indoor robot navigation and positioning method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Indoor positioning method, indoor positioning system, AR indoor positioning navigation method and AR indoor positioning navigation system
CN115388902A
SLAM (Simultaneous Localization and Mapping)-based pose estimation method and system
CN116380035A
Vehicle positioning method and positioning model training method and device
CN117726786A
Indoor service robot positioning and mapping system and method
CN118129751A
Unmanned aerial vehicle indoor navigation system based on visual SLAM
CN118603103A
