Navigation method and system and computer readable storage medium
By matching local environmental point cloud information with the building model in the construction robot and updating the point cloud environmental map, the navigation accuracy problem caused by sensor environmental differences is solved, and high-precision navigation effect is achieved.
Patent Information
- Application Number
- CN202411058079.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-12
AI Technical Summary
When construction robots are performing tasks, the difference between the environment detected by the sensors and the prior map is large, resulting in low navigation accuracy. Existing technologies directly filter out dynamic information, leading to the loss of effective information.
By matching the local environmental point cloud information currently collected by the robot with the point cloud environmental map of the construction site, environmental change information is determined, and it is matched with the building model to determine the target environmental change information, the point cloud environmental map is updated, and environmental change information that is not caused by construction is filtered out.
It improves the accuracy and stability of robot navigation, effectively filters out interference from temporary dynamic objects, and ensures navigation accuracy.
Smart Images

Figure CN118936474A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automatic operation, and in particular to a navigation method, system and computer-readable storage medium. Background Art
[0002] When performing tasks, construction robots need to detect the surrounding environment through sensors, match it with the prior map, and navigate based on the matching results. However, the construction site environment will change over time, resulting in a large difference between the environment actually detected by the sensor and the prior map.
[0003] In related technologies, the dynamic change information in the environment is obtained by comparing the results of multiple frames of data collected by the robot sensor, and the dynamic change information is filtered out from the data collected by the sensor before navigation. However, directly filtering out all dynamic information will lead to the loss of effective information, such as components that have just been installed, laid, or painted, resulting in low robot navigation accuracy.
[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of the present invention is to provide a navigation method, a navigation system and a computer-readable storage medium, aiming to achieve the effect of improving the navigation accuracy of the robot.
[0006] To achieve the above object, the present invention provides a navigation method, which comprises:
[0007] According to the current position of the robot, the local environment point cloud information currently collected by the robot is matched with the point cloud environment map of the current construction site to determine the environment change information;
[0008] Matching the environmental change information with the building model of the construction site to determine target environmental change information;
[0009] The point cloud environment map is updated according to the target environment change information, and navigation is performed based on the updated environment map.
[0010] Optionally, the step of matching the environmental change information with the building model of the construction site to determine target environmental change information includes:
[0011] When the object region corresponding to the environment change information matches the object region corresponding to the building model, the environment change information corresponding to the object region is determined to be the target environment change information.
[0012] Optionally, before the step of matching the local environment point cloud information currently collected by the robot with the point cloud environment map of the current construction site according to the current position of the robot to determine the environment change information, the step further includes:
[0013] Detect whether the beacon is recognized;
[0014] When a beacon is identified, the current position is determined based on a beacon position associated with the beacon.
[0015] Optionally, before the step of detecting whether a beacon is identified, the step further includes:
[0016] Obtaining the building model and the initial point cloud environment map;
[0017] Determining a moving path of the robot according to the building model and the initial point cloud environment map;
[0018] A plurality of beacons are arranged on the moving path.
[0019] Optionally, the step of determining the movement path of the robot according to the building model and the initial point cloud environment map includes:
[0020] Determining the operation building model corresponding to the robot according to the building model;
[0021] Determining the operation plan of the robot according to the operation building model and the initial point cloud environment map;
[0022] The moving path is determined according to the operation plan.
[0023] Optionally, after the step of detecting whether a beacon is identified, the step further includes:
[0024] When no beacon can be identified, matching the point cloud environment map with the local point cloud environment information collected by the robot;
[0025] Navigate based on matching results.
[0026] Optionally, the step of navigating according to the matching result includes:
[0027] Acquire current posture information collected by the robot and mileage information of the robot;
[0028] Navigation is performed according to the current posture information, the mileage information and the matching result.
[0029] Optionally, after the step of updating the point cloud environment map according to the target environment change information and navigating based on the updated environment map, the method further includes:
[0030] When it is determined that the robot has arrived at the operating point, the lateral position of the robot is determined according to a matching result between the current point cloud environment map and the local environment point cloud information currently collected by the robot;
[0031] Obtaining the tilt angle posture collected by the inertial navigation unit of the robot;
[0032] Determine the position of the robot by using a camera disposed at the bottom of the robot;
[0033] The robot is adjusted to a working posture according to the lateral posture, the tilt angle posture and the facing posture.
[0034] In addition, to achieve the above objectives, the present invention also provides a navigation system, which includes a memory, a processor, and a navigation program stored in the memory and executable on the processor, and the navigation program implements the steps of the navigation method described above when executed by the processor.
[0035] In addition, to achieve the above-mentioned purpose, the present invention further provides a computer-readable storage medium, on which a navigation program is stored, and when the navigation program is executed by a processor, the steps of the navigation method described above are implemented.
[0036] The embodiment of the present invention proposes a navigation method, system and computer-readable storage medium, which matches the local environment point cloud information currently collected by the robot with the point cloud environment map of the current construction site according to the current position of the robot to determine the environment change information; matches the environment change information with the building model of the construction site to determine the target environment change information; updates the point cloud environment map according to the target environment change information, and performs navigation based on the updated environment map. In this way, when the point cloud environment map is updated by the environment change information, the environment change information caused by non-construction reasons in the environment change information can be effectively filtered out by the building model of the construction site, and the environment change information is updated according to the target environment change, thereby improving the navigation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention;
[0038] Figure 2 A flowchart of an embodiment of a navigation method of the present invention is shown;
[0039] Figure 3 A flowchart of another embodiment of the navigation method of the present invention is shown;
[0040] Figure 4 The figure is a schematic diagram of the robot structure involved in the embodiment of the present invention.
[0041] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0042] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0043] Because in the related technology, directly filtering out all dynamic information will lead to the loss of effective information, such as components that have just been installed, built, or painted, resulting in low robot navigation accuracy.
[0044] In order to improve the navigation accuracy of the robot, an embodiment of the present invention provides a navigation method, system and computer-readable storage medium, wherein the main steps of the method include:
[0045] Determine the robot's current position;
[0046] Matching the local environment point cloud information currently collected by the robot with the point cloud environment map of the current construction site according to the current position to determine the environment change information;
[0047] Matching the environmental change information with the building model of the construction site to determine target environmental change information;
[0048] The point cloud environment map is updated according to the target environment change information, and navigation is performed based on the updated environment map.
[0049] In this way, when the point cloud environment map is updated through environmental change information, the environmental change information caused by non-construction reasons can be effectively filtered out through the building model of the construction site, and the environmental change information is updated according to the target environmental changes, thereby improving navigation accuracy.
[0050] The content to be protected by the claims of the present invention will be described in detail below with reference to the accompanying drawings.
[0051] like Figure 1 As shown, Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention.
[0052] The terminal in the embodiment of the present invention may be a navigation system.
[0053] like Figure 1As shown, the terminal may include: a processor 1001, such as a CPU, a memory 1003, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between these components. The memory 1003 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1003 may also be a storage device independent of the aforementioned processor 1001.
[0054] Those skilled in the art will understand that Figure 1 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0055] like Figure 1 As shown, the memory 1003 as a computer storage medium may include an operating system and a navigation program.
[0056] exist Figure 1 In the terminal shown, the processor 1001 can be used to call the navigation program stored in the memory 1003 and perform the following operations:
[0057] According to the current position of the robot, the local environment point cloud information currently collected by the robot is matched with the point cloud environment map of the current construction site to determine the environment change information;
[0058] Matching the environmental change information with the building model of the construction site to determine target environmental change information;
[0059] The point cloud environment map is updated according to the target environment change information, and navigation is performed based on the updated environment map.
[0060] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0061] When the object region corresponding to the environment change information matches the object region corresponding to the building model, the environment change information corresponding to the object region is determined to be the target environment change information.
[0062] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0063] Detect whether the beacon is recognized;
[0064] When a beacon is identified, the current position is determined based on a beacon position associated with the beacon.
[0065] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0066] Obtaining the building model and the initial point cloud environment map;
[0067] Determining a moving path of the robot according to the building model and the initial point cloud environment map;
[0068] A plurality of beacons are arranged on the moving path.
[0069] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0070] Determining the operation building model corresponding to the robot according to the building model;
[0071] Determining the operation plan of the robot according to the operation building model and the initial point cloud environment map;
[0072] The moving path is determined according to the operation plan.
[0073] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0074] When no beacon can be identified, matching the point cloud environment map with the local point cloud environment information collected by the robot;
[0075] Navigate based on matching results.
[0076] Optionally, the step of navigating according to the matching result includes:
[0077] Acquire current posture information collected by the robot and mileage information of the robot;
[0078] Navigation is performed according to the current posture information, the mileage information and the matching result.
[0079] Further, the processor 1001 may call the navigation program stored in the memory 1003, and further perform the following operations:
[0080] When it is determined that the robot has arrived at the operating point, the lateral position of the robot is determined according to a matching result between the current point cloud environment map and the local environment point cloud information currently collected by the robot;
[0081] Obtaining the tilt angle posture collected by the inertial navigation unit of the robot;
[0082] Determine the position of the robot by using a camera disposed at the bottom of the robot;
[0083] The robot is adjusted to a working posture according to the lateral posture, the tilt angle posture and the facing posture.
[0084] The following is an explanation of the content claimed in the claims of the present invention through specific exemplary schemes, so that those skilled in the art can better understand the scope of protection of the claims of the present invention. It is understood that the following exemplary schemes do not limit the scope of protection of the present invention, but are only used to explain the present invention.
[0085] For example, refer to Figure 2 In one embodiment of the navigation method of the present invention, the navigation method comprises the following steps:
[0086] Step S10: matching the local environment point cloud information currently collected by the robot with the point cloud environment map of the current construction site according to the current position of the robot to determine the environment change information;
[0087] In this embodiment, the subject executing the navigation method may be a navigation system, and a construction robot refers to a robot that provides construction operations. Since the navigation of a construction robot faces challenges such as large environmental changes, high precision requirements, and a wide range of operations in a construction environment, the construction robot requires sufficiently high navigation precision. A navigation system using the navigation method provided in this embodiment can provide a high navigation precision for a construction robot, etc.
[0088] The navigation system can be mounted on a robot that provides construction work, or on a central control device that controls one or more robots, and the central control device is used to control or guide the movement and operation of the robot. In this embodiment, taking the robot equipped with the navigation system as an example, when the robot itself is equipped with the navigation system, the autonomy of the robot can be improved.
[0089] During the navigation process, the robot keeps moving, and when the preset conditions corresponding to the current position can be determined, the current position of the robot is determined. It should be noted that there are many ways to determine the current position of the robot, such as determining the current position of the robot through GPS positioning, inertial navigation unit positioning, etc. However, there may be certain requirements for the accuracy of the determined current position of the robot, and the accuracy needs to be greater than the accuracy of the position determined when the robot navigates through the current point cloud environment map.
[0090] The robot is also provided with a sensor, which may be a radar sensor, a laser sensor, or a multi-source sensor of a plurality of sensor sets. The sensor is used to obtain the local environment point cloud information of the current robot. The local environment point cloud information is the environment point cloud information in the robot's surrounding environment that can be collected by the sensor.
[0091] The point cloud environment map of the construction site includes the environmental point cloud information of objects in all areas within the construction site. The point cloud environment map is a three-dimensional point cloud map. Before the robot operation begins, the initial environment map of the construction site can be surveyed and drawn by the robot or other equipment. Since the environment of the construction site will change, the environment map also needs to be updated to ensure the accuracy of the map.
[0092] After the current position of the robot is determined, the environmental point cloud information of the area corresponding to the local environmental point cloud information in the point cloud environment map can be found in the point cloud environment map of the currently used construction site according to the current position.
[0093] The environmental point cloud information of the area corresponding to the local environmental point cloud information in the point cloud environmental map is then compared and matched with the local environmental point cloud information collected by the robot in real time to determine the difference between the two. The difference between the two is the environmental change information, which can characterize the changes between the real environment in the area near the current robot and the environment corresponding to the last updated point cloud environmental map.
[0094] Step S20, matching the environmental change information with the building model of the construction site to determine target environmental change information;
[0095] Environmental change information includes long-term environmental change information, that is, environmental change information caused by construction, such as newly built walls, and temporary environmental change information, such as temporary mobile equipment, vehicles, personnel, materials, etc. caused by construction. In the point cloud environment map, it is not necessary to retain the environmental point cloud information corresponding to the temporary environmental change information, so it is necessary to filter out these temporary environmental change information, leaving the target environmental change information caused by construction, and the environmental change information caused by construction will match the construction model, because the building model is the design model corresponding to the building that needs to be built on the construction site. During the construction operation, it is necessary to build according to the building model, thereby causing environmental changes. Therefore, the environmental change information is matched with the building model to determine the target environmental change information caused by construction, and the target environmental change information is the environmental change information that can be updated to the point cloud environment map.
[0096] Step S30: updating the point cloud environment map according to the target environment change information, and performing navigation based on the updated environment map.
[0097] The target environment change is the change of the environmental point cloud information corresponding to the objects in the environment, including increased environmental point cloud information and reduced environmental point cloud information. The environmental point cloud information in the point cloud environment map is increased or reduced according to the target environment change, thereby updating the point cloud environment map so that the environmental point cloud information of the updated point cloud environment map matches the current real environment. The robot continues to navigate based on the updated environmental map, thereby improving navigation accuracy.
[0098] In this embodiment, the local environment point cloud information currently collected by the robot is matched with the point cloud environment map of the current construction site according to the current position of the robot to determine the environment change information; the environment change information is matched with the building model of the construction site to determine the target environment change information; the point cloud environment map is updated according to the target environment change information, and navigation is performed based on the updated environment map. In this way, when the point cloud environment map is updated by the environment change information, the environment change information caused by non-construction reasons in the environment change information can be effectively filtered out by the building model of the construction site, and the environment change information is updated by the target environment change, which solves the problem of unstructured scene mapping and navigation at the construction site, and filters out the interference of temporary dynamic objects, thereby improving navigation accuracy and stability.
[0099] Furthermore, the step of matching the environmental change information with the building model of the construction site to determine the target environmental change information includes:
[0100] When the object region corresponding to the environment change information matches the object region corresponding to the building model, the environment change information corresponding to the object region is determined to be the target environment change information.
[0101] In the construction scene, construction brings about the improvement of buildings, so most of the environmental change information is a new process. In addition, the environmental change information also includes reduced environmental point cloud information. The environmental point cloud information includes the target environmental point cloud information caused by the building and the temporary environmental point cloud information. If it is caused by the building, the newly added or reduced objects will correspond to the building model, and the environmental point cloud information identified or not identified based on these objects is the target environmental point cloud information. Determine the newly added or reduced object area corresponding to the environmental point cloud information of the environmental change information. When the object area matches the object area corresponding to the building model, determine that the environmental change information corresponding to the object area is the target environmental change information. When the object area does not match the object area corresponding to the building model, determine that the environmental change information corresponding to the object area is not the target environmental change information, but the temporary environmental change information, which should be filtered out. In this way, the target environmental change information can be quickly and accurately screened out, and the efficiency and accuracy of updating the map can be improved, thereby improving the navigation accuracy and efficiency.
[0102] Furthermore, after the step of updating the point cloud environment map according to the target environment change information and navigating based on the updated environment map, the method further includes:
[0103] When it is determined that the robot has arrived at the operating point, the lateral position of the robot is determined according to a matching result between the current point cloud environment map and the local environment point cloud information currently collected by the robot;
[0104] Obtaining the tilt angle posture collected by the inertial navigation unit of the robot;
[0105] Determine the position of the robot by using a camera disposed at the bottom of the robot;
[0106] The robot is adjusted to a working posture according to the lateral posture, the tilt angle posture and the facing posture.
[0107] Reference Figure 4 The navigation system includes a sensor installed on the robot to collect local environmental point cloud information, an inertial navigation unit, the inertial navigation unit includes an odometer, and a camera installed at the bottom of the robot. Among them, the sensor can be a radar or laser sensor, the inertial navigation unit can determine the tilt angle posture of the robot, and combined with the odometer, it can also navigate the robot. The bottom camera can shoot the ground to determine the robot's relative posture. The robot can also include a wireless communication device for receiving a building model or a point cloud environment map sent by the central control device. The focus of the robot's navigation includes the robot's operating point. When the robot arrives at the operating point, the robot's lateral posture is determined by matching the local environmental point cloud information currently collected by the sensor with the current point cloud environment map (the latest updated point cloud environment map), the tilt angle posture collected by the robot's inertial navigation unit is obtained, and the ground image is obtained by the camera set at the bottom of the robot. The relative posture can be determined based on the ground image. Optionally, a beacon is placed at the operating point, and the relative posture is determined based on the image position and shape of the captured beacon in the ground image to improve the accuracy of the relative posture. Then, the robot is determined to be in the working posture from three perspectives: side block posture, tilt angle posture and facing posture. If not, it is adjusted to the working posture according to the above postures to improve the robot's operating accuracy and efficiency.
[0108] Optionally, refer to Figure 3 Based on any of the above embodiments, in another embodiment of the navigation method of the present invention, before step S10, it also includes:
[0109] Step S40, detecting whether a beacon is recognized;
[0110] Step S50: When a beacon is identified, the current position is determined according to the beacon position associated with the beacon.
[0111] In this embodiment, one or more beacons may be set in the construction site, and the position of the beacon is generally fixed. When the robot recognizes the beacon, it indicates that the robot is at the beacon position or near the beacon. The beacon and the beacon position may be pre-associated and saved, and the beacon position is the position of the beacon in the construction site.
[0112] Since a plurality of beacons may be set up at a construction site, it is necessary to distinguish each beacon. Optionally, the beacon may also be a mark such as an RFID or a magnetic nail that can determine and distinguish the information of each beacon in the construction site, and the beacon may also include an image mark that can distinguish the beacon.
[0113] Optionally, an environmental image is collected based on a camera of the robot; when it is recognized that the environmental image includes a beacon, the current position is determined according to the beacon.
[0114] If the beacon includes an image mark that can distinguish the beacon, then the robot is correspondingly provided with a camera, and the camera can obtain an image of the robot's surrounding environment. When the beacon is identified in the environment image collected by the robot's camera, the beacon position associated with the beacon is determined, and the current position of the robot is determined according to the beacon position.
[0115] Optionally, the beacon is an image mark including a QR code for distinguishing the beacon. After the camera captures the beacon, the QR code of the beacon can be scanned according to the beacon image to determine the beacon number information or other information for distinguishing each beacon in the construction site, thereby determining the beacon position associated with the beacon according to the above information. Alternatively, the beacon is an image mark of different colors and / or shapes, and the beacon can be determined according to the appearance of the beacon, and the associated beacon position can be determined according to the appearance of the beacon.
[0116] Optionally, the camera can be installed at the bottom of the robot, and the beacon can be placed on the ground at the construction site. The environment image captured by the robot's camera is a ground image. When the camera can capture the beacon image on the ground, the beacon position is the current position of the robot. In this way, the beacon position saved by the beacon association can be directly used as the current position of the robot.
[0117] Optionally, the image position of the beacon in the beacon image can be identified based on the environment image, the relative position of the beacon and the robot can be determined based on the image position, and the current position of the robot can be determined based on the relative position and the beacon position pre-associated with the beacon.
[0118] In the technical solution disclosed in this embodiment, the camera of the robot collects environmental images; when it is recognized that the environmental images include beacons, the current position is determined according to the beacons. In this way, by deploying navigation beacons at the construction site and updating the navigation map according to the current position determined by the beacons, a definite reference position is provided when updating the map, thereby improving navigation accuracy.
[0119] Furthermore, before step S40, the method further includes:
[0120] Obtaining the building model and the initial point cloud environment map;
[0121] Determining a moving path of the robot according to the building model and the initial point cloud environment map;
[0122] A plurality of beacons are arranged on the moving path.
[0123] In this embodiment, beacons need to be placed at the construction site. In order to improve the utilization rate of beacons, beacons can be placed on the moving path of the robot. The robot's moving path can be determined by the central control device or the robot. The central control device can obtain the building model and the initial point cloud environment map before the operation begins, and the robot can also receive the building model and the initial point cloud environment map sent by the central control device. Then, the robot's moving path is determined according to the building model and the initial point cloud environment map, and other devices such as robots place beacons along the moving path in sequence, and the number of beacons or the interval distance can be determined. This improves the utilization rate of beacons, and can also ensure that the robot can identify beacons in time when moving, determine the reference position, update the map in time, and improve navigation accuracy.
[0124] Furthermore, the step of determining the movement path of the robot according to the building model and the initial point cloud environment map includes:
[0125] Determining the operation building model corresponding to the robot according to the building model;
[0126] Determining the operation plan of the robot according to the operation building model and the initial point cloud environment map;
[0127] The moving path is determined according to the operation plan.
[0128] In the construction scene, there can be multiple operation processes. Different industries have different corresponding processes, and the moving paths of the robots that perform the operation processes are also different. In order to improve the accuracy of planning the moving paths, the moving paths are determined for robots with different operation processes. The operation building models corresponding to multiple operation processes are split out from the building model, and the operation building model corresponding to the robot is determined from them. Then, the operation planning of the robot is completed according to the operation building model corresponding to the robot and the initial point cloud environment map. The operation planning includes multiple operation points, moving paths, and material information required for the operation of the robot. The robot can determine the moving path according to the operation planning, and thus can complete the operation according to the moving path determined according to the operation planning. In this way, a more accurate moving path can be determined based on the robot's operation building model, thereby improving the operation efficiency and the accuracy of beacon layout, and improving navigation accuracy.
[0129] Furthermore, after step S40, the method further includes:
[0130] When no beacon can be identified, matching the point cloud environment map with the environment information collected by the robot;
[0131] Navigate based on matching results.
[0132] When the beacon cannot be identified in the environmental image, it is determined that the robot is not at the beacon position or near the beacon, so it is impossible to obtain the reference position for updating the map based on the beacon, and the map cannot be accurately updated. The robot navigates based on the current point cloud environment map, matches the current point cloud environment map with the local point cloud environment information collected by the robot, and determines the current position of the robot based on the matching result. When the matching degree corresponding to the matching result is lower than the preset value, or the current position determined in this way cannot be used as a reference position, the current position determined based on the matching result cannot become the reference position for updating the map. Therefore, navigation is performed based on the current position determined by the matching result and the current point cloud environment map. On the one hand, the robot is further moved to improve navigation efficiency, and on the other hand, the robot is moved to find the next beacon to update the map and improve navigation accuracy.
[0133] Furthermore, the step of navigating according to the matching results includes:
[0134] Acquire the current posture information collected by the robot and the mileage information of the robot;
[0135] Navigation is performed according to the current position information, the mileage information and the matching result.
[0136] The robot also includes an inertial navigation unit, which can be used to collect the robot's current posture information and mileage information. The robot can also be positioned based on the current posture information and mileage information. The current posture information, mileage information and the above matching results are combined from multiple sources to obtain more accurate positioning information, which can improve navigation accuracy.
[0137] In addition, an embodiment of the present invention further proposes a navigation system, which includes a memory, a processor, and a navigation program stored in the memory and executable on the processor, wherein the navigation program implements the steps of the navigation method described in the above embodiments when executed by the processor.
[0138] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which a navigation program is stored. When the navigation program is executed by a processor, the steps of the navigation method described in the above embodiments are implemented.
[0139] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0140] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for the navigation system to execute the methods described in each embodiment of the present invention.
[0142] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A navigation method, It is characterized in that The navigation method comprises: According to the current position of the robot, the local environment point cloud information currently collected by the robot is matched with the point cloud environment map of the current construction site to determine the environment change information; Matching the environmental change information with the building model of the construction site to determine target environmental change information; The point cloud environment map is updated according to the target environment change information, and navigation is performed based on the updated environment map.
2. The navigation method according to claim 1, It is characterized in that The step of matching the environmental change information with the building model of the construction site to determine the target environmental change information comprises: When the object region corresponding to the environment change information matches the object region corresponding to the building model, the environment change information corresponding to the object region is determined to be the target environment change information.
3. The navigation method according to claim 1, It is characterized in that Before the step of matching the local environment point cloud information currently collected by the robot with the point cloud environment map of the current construction site according to the current position of the robot to determine the environment change information, the step further includes: Detect whether the beacon is recognized; When a beacon is identified, the current position is determined based on a beacon position associated with the beacon.
4. The navigation method according to claim 3, It is characterized in that Before the step of detecting whether a beacon is identified, the method further includes: Obtaining the building model and the initial point cloud environment map; Determining a moving path of the robot according to the building model and the initial point cloud environment map; A plurality of beacons are arranged on the moving path.
5. The navigation method according to claim 4, It is characterized in that The step of determining the movement path of the robot according to the building model and the initial point cloud environment map comprises: Determining the operation building model corresponding to the robot according to the building model; Determining the operation plan of the robot according to the operation building model and the initial point cloud environment map; The moving path is determined according to the operation plan.
6. The navigation method according to claim 3, It is characterized in that After the step of detecting whether the beacon is recognized, the method further includes: When no beacon can be identified, matching the point cloud environment map with the local point cloud environment information collected by the robot; Navigate based on matching results.
7. The navigation method according to claim 6, It is characterized in that The step of navigating according to the matching results comprises: Acquire current posture information collected by the robot and mileage information of the robot; Navigation is performed according to the current posture information, the mileage information and the matching result.
8. The navigation method according to claim 1, It is characterized in that After the step of updating the point cloud environment map according to the target environment change information and navigating based on the updated environment map, the method further includes: When it is determined that the robot has arrived at the operating point, the lateral position of the robot is determined according to a matching result between the current point cloud environment map and the local environment point cloud information currently collected by the robot; Obtaining the tilt angle posture collected by the inertial navigation unit of the robot; Determine the position of the robot by using a camera disposed at the bottom of the robot; The robot is adjusted to a working posture according to the lateral posture, the tilt angle posture and the facing posture.
9. A navigation system, It is characterized in that The navigation system comprises: a memory, a processor and a navigation program stored in the memory and executable on the processor, wherein the navigation program implements the steps of the navigation method according to any one of claims 1 to 8 when executed by the processor.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a navigation program, and when the navigation program is executed by a processor, the steps of the navigation method according to any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Unmanned aerial vehicle control method and system, unmanned aerial vehicle equipment and remote control equipment
CN111984021A
Method for creating environment map for use in autonomous navigation of mobile robot
CN113841101A
High-precision map construction processing method and system
CN115049792A
Real-time accurate map construction method based on BIM (Building Information Modeling), terminal and storage medium
CN115290097A
Autonomous navigation map updating method and device for indoor robot and storage medium
CN115406434A
