Navigation target point planning method based on dynamic area and chip

Abstract

The invention discloses a navigation target point planning method based on a dynamic region and a chip, and the navigation target point planning method comprises the steps: 1, judging whether a matching score in a relocation result is greater than a first preset score threshold value or not under the condition that the relocation result is verified to be failed, and if yes, entering a step 2; 2, performing weighted calculation according to the matching scores of the point cloud points falling into the corresponding area of the target map to obtain a target matching score; then entering the step 3; step 3, judging whether the target matching score is greater than a second preset score threshold, if so, successfully positioning, and otherwise, entering step 4; step 4, setting a search distance image based on the relation between the mask extracted from the reference map and the mask extracted from the depth dynamic area of the target map, and selecting a navigation target point in a preset positioning distance range based on the search distance image, and the positioning stability of the robot at the navigation position and the robustness of the robot in a dynamic environment are improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of navigation positioning, and in particular to a dynamic region-based navigation target point planning method and a chip. BACKGROUND

[0002] Currently, the working environment of a sweeping robot is a home environment. The home environment cannot be guaranteed to remain unchanged during the working time of the sweeping robot. The home environment will change in various ways due to the change in the distribution position of obstacles, forming a dynamic region. Some image segmentation algorithms (using a large number of image processing methods, such as image graying, binarization, threshold comparison, etc.) reduce the universality and calculation efficiency when the picture scene changes greatly.

[0003] Chinese patent CN202111314321.5 discloses a method for post-inspection of a relocation result. The method does not distinguish the types of dynamic regions and search for suitable navigation points based on the types of dynamic regions, but allows the robot to randomly sample during straight-line walking according to a path planning algorithm based on a rapidly expanding random tree, which is likely to cause incorrect judgment of the position of the robot, especially in a dynamic environment, thereby affecting the positioning stability of the robot in the dynamic region. SUMMARY

[0004] The application discloses a dynamic region-based navigation target point planning method for a robot. The specific technical solution comprises: The dynamic region-based navigation target point planning method comprises: obtaining a relocation result by using a relocation matching algorithm, and then inspecting the relocation result. The navigation target point planning method further comprises: step 1, in the case where the inspection of the relocation result fails, the robot determines whether the matching score in the relocation result is greater than a first preset score threshold. If yes, the method proceeds to step 2; step 2, the robot marks the point cloud matched by the relocation matching algorithm on a target map as a target matching point cloud; the matching score corresponding to the point cloud point falling on the target map in the target matching point cloud is weighted and calculated to obtain a target matching score; then the method proceeds to step 3; step 3, the robot determines whether the target matching score is greater than a second preset score threshold. If yes, it is determined that the positioning is successful, otherwise the method proceeds to step 4; wherein the second preset score threshold is greater than the first preset score threshold; step 4, the point cloud point corresponding to the target matching score is marked as a matching point, and the working map constructed by the robot when the point cloud is matched by using the relocation matching algorithm is marked as a reference map; a search distance image is set based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map, and a navigation target point is selected within a preset positioning distance range based on the search distance image starting from the matching point.

[0005] In summary, in the positioning of the map with dynamic areas, in the case of initial test failure, the application first compares with the score threshold, then does the weighted calculation based on the point cloud in the dynamic area or the non-dynamic area, and then compares with the higher score threshold, and constantly excludes the one-sided interference of the matching score. Then, based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic area of the target map, the search distance is set, the local map area and the contour of the marked obstacle are segmented for distance value analysis, and the position point matched with the search distance is selected as the navigation target point based on this. In the process of moving the robot from the current position point to the navigation target point, the robot is away from the depth dynamic area, so that the robot recognizes fewer depth dynamic areas at the navigation target point but does not deviate too far from the original position; improve the positioning stability of the robot at the navigation position and the robustness in the dynamic environment, and provide an important basis for subsequent navigation and positioning.

[0006] Further, in the step 4, based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map, a search distance image is set, and based on the search distance image, a navigation target point is selected within a preset positioning distance range from the matching point, and the method comprises: extracting a target mask according to the contour of the reference map; mapping a target distance image according to the dynamic region in the target map; wherein the point cloud points on the target map correspond to the distance values in the target distance image, so that the distance values in the target distance image are used to measure the distance information between the point cloud points on the target map and the dynamic region in the target map; mapping an obstacle distance image according to the obstacles marked in the reference map, and marking the distance values in the obstacle distance image as first distance values; wherein the point cloud points on the reference map correspond to the distance values in the obstacle distance image, so that the obstacle distance image is used to measure the distance information between the point cloud points on the reference map and the obstacles marked in the reference map; using the target mask to crop the target distance image and the obstacle distance image to obtain a positioning candidate region; and extracting a reference mask from the depth dynamic region of the target map, and then using the positioning candidate region to perform weighted calculation on the distance values corresponding to the reference mask to obtain second distance values; and setting the sum of the first distance values and the second distance values as a search distance, wherein the search distance corresponds to the search distance image, and the point cloud points on the distance image composed of the target distance image and the obstacle distance image correspond to the distance values in the search distance image; starting from the matching point, the point cloud point corresponding to the maximum search distance within the preset positioning distance range is selected as the navigation target point, so that the robot moves away from the depth dynamic region of the target map during the process of moving from the current position point to the navigation target point. In summary, by executing steps 44 to 46, the navigation target point can be set near the depth dynamic region, and the problem of low robustness of point cloud on the depth dynamic region to environmental changes can be solved.

[0007] Further, the method of extracting a target mask according to the contour of the reference map comprises: searching for a maximum map contour in the reference map, filling the maximum map contour, and setting the image region circled by the filled maximum map contour as the target mask. The boundary of the target mask is more continuous and smooth.

[0008] Further, the method of extracting a reference mask from the depth dynamic region of the target map comprises: selecting a position point as a center in the depth dynamic region of the target map, setting a sampling distance as a radius to form a circular domain, and setting the circular domain as the reference mask to segment a circular mask in the depth dynamic region of the target map.

[0009] Further, the method of using the distance values covered by the reference mask in the positioning candidate region for weighted calculation comprises: according to a pre-stored weight, respectively performing weighted calculation on each distance value corresponding to the positioning candidate region covered in the reference mask to obtain a second distance value of each point cloud point in the reference mask corresponding to the positioning candidate region; wherein each distance value corresponding to the positioning candidate region covered in the reference mask is a distance value of each point cloud point corresponding to the positioning candidate region in the point cloud on the reference mask; wherein each distance value corresponding to the positioning candidate region covered in the reference mask includes a minimum distance value between the point cloud point and the edge of the dynamic area in the reference mask or a minimum distance value between the point cloud point and the obstacle contour in the reference mask. The distance values after weighted calculation in the present application are all reduced, so that the search distance in subsequent calculation is reduced, and the navigation target point selected in the subsequent process is prevented from being set in a local area with a high coverage ratio of the deep dynamic area or a large number of deep dynamic areas, so that the robot moves away from the deep dynamic area during moving from the current position point to the navigation target point.

[0010] Further, for each point cloud point corresponding to the positioning candidate region in the reference mask, the sum of the first distance value corresponding to the same point cloud point and the second distance value corresponding to the same point cloud point is set as the search distance. The search distance image is mapped based on the search distance, so that the obstacle distance image and the reference mask are merged into the search distance image, and the distance information required for searching the navigation target point is extracted.

[0011] Further, in the step 2, the area where the target matching point cloud is distributed is a non-dynamic area, a reference dynamic area or a deep dynamic area; wherein the reference dynamic area and the deep dynamic area belong to dynamic areas; the non-dynamic area is used to represent an area where the environment of the robot has no change, and the matching score corresponding to the point cloud point falling on the matching position in the non-dynamic area is a first matching score; the reference dynamic area is used to represent an area where the environment of the robot changes, and the matching score corresponding to the point cloud point falling on the matching position in the reference dynamic area is a second matching score; the deep dynamic area is used to represent an area where the environment of the robot changes more frequently relative to the reference dynamic area, so that the probability of the point cloud point falling into the deep dynamic area is higher than the probability of the point cloud point falling into the reference dynamic area; the matching score corresponding to the point cloud point falling on the matching position in the deep dynamic area is a third matching score; wherein the third matching score is equal to the second preset score threshold, the third matching score is less than the second matching score, and the second matching score is less than the first matching score. Thus, the non-dynamic area, the reference dynamic area and the deep dynamic area are distinguished based on the matching score.

[0012] Further, within a preset test time, each time the repositioning matching algorithm matches a point cloud point on the dynamic area, the matching score corresponding to the point cloud point is accumulated; after the preset test time, the accumulated result is obtained, if the accumulated result is greater than a preset total score threshold, it is determined that the dynamic area is a depth dynamic area; if the accumulated result is less than or equal to the preset score threshold, it is determined that the dynamic area is a reference dynamic area; in the process of the repositioning matching algorithm, the robot matches the collected point cloud with the map, and each time a point cloud point in the point cloud is detected to fall into a corresponding type of area in the map, it is determined that a point cloud point is matched, and the corresponding matching score is obtained. Therefore, after the point cloud matched by the repositioning matching algorithm on the dynamic area of the target map is accumulated for the preset test time, the reference dynamic area and the non-dynamic area are distinguished from the dynamic area based on the accumulated value of the matching score.

[0013] Further, the method of weighting the matching score corresponding to the point cloud point falling on the target map in the target matching point cloud includes: first identifying the area where the target matching point cloud is distributed in the target map; based on the identified area, determining the matching score corresponding to the point cloud point falling on the target map in the target matching point cloud, and assigning a corresponding weight to the currently determined matching score; then using the assigned weight to control the weighted calculation of the matching score corresponding to the point cloud point falling on the target map in the target matching point cloud, and obtaining the target matching score. Therefore, the weighting calculation of the single matching score is performed according to the dynamic area or the non-dynamic area where the matched point cloud is located, and the matching score of the target matching point cloud on the same type of area is recalculated.

[0014] A chip for storing a program configured to perform the dynamic area-based navigation target point planning method. Compared with the prior art, the chip disclosed in the present application performs the navigation target point planning method, and does not exclude dynamic pixels in the map when the chip matches the point cloud with the map. Instead, a mask is set to correspond to the map with dynamic areas and subtracted between different maps to obtain a search distance image to set the navigation target point by directly extracting the search distance, so as to segment the positioning point within the map area corresponding to the mask, which is within a reasonable distance range from the obstacle and the dynamic area. Therefore, the adaptability of the positioning result finally determined by the positioning method to the dynamically changing environment is improved in different local map areas, so that a precise and stable map repositioning position point is planned in the dynamically changing environment. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of the dynamic area-based navigation target point planning method is disclosed for an embodiment of the present application.

[0016] Figure 2 As another embodiment of the present application, a flowchart of a dynamic region-based navigation target point planning method is disclosed. DETAILED DESCRIPTION

[0017] The specific embodiments of the present application will be further described below with reference to the accompanying drawings.

[0018] According to the relocation process disclosed in Chinese Patent CN202111314321.5, the robot selects the matching result corresponding to the position with the highest matching score as the relocation result, and then updates the map used for relocation calculation with the relocation result. Then the robot walks for a set time or a set distance and acquires point cloud data of the environment during the walking process. Then the robot matches the point cloud data acquired during the walking process with the updated map, and then determines whether the relocation is successful or failed according to the matching result (which is basically determined by the comparison result of the matching score and the score threshold). This method does not perform image region screening and matching point analysis at the image level of the map. The relocation failure or success result determined by the matching result is prone to cause mismatching in an environment where objects frequently change. In this case, if the robot uses the rapidly expanding random tree path planning algorithm to walk or go to the center of the point cloud, there is a phenomenon of walking a straight line at will or random walking, which will eventually affect the positioning accuracy of the mobile robot. In view of the foregoing technical defects, it is urgent to plan a navigation target point with strong adaptability.

[0019] As an embodiment, the present application discloses a dynamic region-based navigation target point planning method for searching for a navigation target point in a map with dynamic regions, thereby improving the scene adaptability of robot relocation.

[0020] As shown in Figure 1 The navigation target point planning method includes obtaining a relocation result by a relocation matching algorithm, then verifying the relocation result, and then performing step 1. During the verification process, the robot walks for a set time or a set distance and acquires point cloud of the environment during the walking process. The acquired point cloud is used to match with the global grid map previously constructed by the robot. The specific method for verifying the relocation result disclosed in the present application refers to a method for post-verification of the relocation result disclosed in Chinese Patent CN202111314321.5. Specifically, the case of judging relocation success in Chinese Patent CN202111314321.5 is identified as the case of verifying the success of the relocation result, and the case of judging relocation failure in Chinese Patent CN202111314321.5 is identified as the case of verifying the failure of the relocation result.

[0021] As Figure 1 shown, the navigation target point planning method disclosed in the present application further comprises: Step 1, in the case of failing to verify the repositioning result, the robot judges whether the matching score in the repositioning result is greater than a first preset score threshold, yes to enter step 2, otherwise it is determined that the robot positioning fails to end the execution of the navigation target point planning method. The matching score in the repositioning result is the percentage of the point cloud points on the pre-scanned point cloud map coinciding with the pre-marked obstacle position when the point cloud points fall on the corresponding matching position of the pre-constructed global grid map; the first preset score threshold is preferably 0.65, so that the robot continues to screen and judge from the repositioning result with a matching score higher than 0.65.

[0022] Step 2, the robot marks the point cloud matched by the repositioning matching algorithm on the target map as the target matching point cloud; then performs weighted calculation on the matching scores corresponding to the point cloud points falling on the target map in the target matching point cloud to obtain the target matching score; and then enters step 3. Wherein, the target map can reflect the point cloud and its matching situation on the dynamic area and the non-dynamic area around the robot, so the target map is classified as a dynamic map, and if the target map is obtained by image processing from a reference map, the reference map is classified as a dynamic map.

[0023] The target matching point cloud includes point cloud points on the non-dynamic area of the target map, point cloud points falling on the reference dynamic area of the target map, and / or point cloud points falling on the depth dynamic area of the target map, and the probability of point cloud points falling on the depth dynamic area is higher than the probability of point cloud points falling on the reference dynamic area. The weighted calculation in step 2 is to perform weighted calculation on the matching scores of the point cloud points on a single type of area after identifying the type of the area where the point cloud points are distributed, so as to obtain the target matching score.

[0024] Step 3, the robot judges whether the target matching score is greater than a second preset score threshold, yes to determine that the robot positioning is successful, otherwise enter step 4; wherein the second preset score threshold is greater than the first preset score threshold, the higher the set score threshold, the easier to determine the positioning success. The second preset score threshold and the first preset score threshold are both determined through a large number of data set tests, and can be set and modified according to the actual situation. Therefore, on the basis of checking the point cloud matching in the target map, steps 2 and 3 perform weighted calculation on the matched point cloud according to the type of the area where the point cloud is located, so as to determine whether the robot is positioned successfully through the matching score threshold comparison.

[0025] Step 4, mark the point cloud points corresponding to the target matching score as matching points, that is, mark the point cloud points with a target matching score less than or equal to a second preset score threshold as matching points; mark the working map constructed by the robot when performing point cloud matching using the repositioning matching algorithm as a reference map; it is worth noting that the matching map required for executing the repositioning matching algorithm is different from the reference map, and the reference map is a map constructed by the robot traversing the same working area at least once. Specifically, the robot constructs a working map in real time during the process of performing a work task in the working area, and at the same time, the robot performs point cloud matching using a target map. Therefore, when the point cloud matching is successful, the working map can be marked as the reference map, thereby updating the reference map. The point cloud data obtained by the robot during the execution of the repositioning matching algorithm can be loaded into the reference map, and the target map is updated so as to correspond to the reference map and adapt to the changing environment in which the robot is located.

[0026] For point cloud matching, three parameters such as matching score, matching area, and matching area rate can be used for threshold comparison, for example, it is determined that the matching positioning is successful when it is greater than or equal to the threshold value of the corresponding type.

[0027] It should be noted that the repositioning matching algorithm disclosed in the present application can be the repositioning calculation in Chinese patent CN202111314321.5 or any other repositioning matching algorithm related to point cloud matching disclosed in the prior art. Even if the corresponding repositioning matching algorithm is not robust to dynamic environments, it can be optimized by executing the positioning method disclosed in the present application.

[0028] Whenever the repositioning matching algorithm is completed, a result that the robot should be in which part of the map is obtained, which can also be said that a point cloud point is matched to the current position of the robot. After obtaining that the robot is in which part of the map, the robot coordinate position is set, and then the point cloud data obtained during the repositioning matching calculation of the robot is loaded into the global grid map for repositioning based on the robot coordinate position, the global grid map is updated, and then walking is performed on the global grid map.

[0029] The robot can be a sweeping robot, a mopping robot, a disinfection robot, a service robot, or other autonomous mobile robots. An accurate map is a prerequisite for the normal work of the robot. However, the home environment cannot be guaranteed to be unchanged during the working time of the sweeping robot, and various changes will always exist, for example, when the obstacle region distributed in the map changes, point cloud mismatching is easily caused, and the repositioning result verification fails.

[0030] In step 4, a search distance image is set based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map, and the relationship includes the relationship between covering and being covered; specifically, a target mask is extracted from the reference map, and a positioning candidate area (including distance information between point clouds on the target map (including matching points) and dynamic regions and obstacles) is cropped from the distance image corresponding to the target map and the distance image corresponding to the reference map based on the target mask; a reference mask is extracted from the depth dynamic region of the target map, and then a search distance image is set based on the weighted calculation result of the distance value corresponding to the reference mask of the positioning candidate area and the distance value (representing distance information between point clouds on the reference map and obstacles) associated with obstacle points in the distance image corresponding to the reference map, the search distance image covering distance information between point clouds on the target map and dynamic regions and distance information between point clouds on the reference map and obstacles; preferably, the search distance image, the distance image corresponding to the target map and the distance image corresponding to the reference map have the same scale and coordinates, so that the coordinates in the search distance image can be directly used on the reference map.

[0031] In step 4, a navigation target point is selected within a preset positioning distance range based on the search distance starting from the aforementioned matching point. Specifically, within the coordinate range covered by the distance image corresponding to the search distance, the coordinate point with the maximum search distance can be selected as the navigation target point within the preset positioning distance range, so that the robot moves from the current position point to the navigation target point and enters a local area (which can be part of the working area) with a reduced proportion of depth dynamic regions or a smaller number of depth dynamic regions, thereby searching for a navigation target point away from the depth dynamic region.

[0032] It should be noted that the depth dynamic region means that the environment where the robot is located is prone to change, and if the positioning algorithm is executed in the depth dynamic region, a large number of points cannot be matched to the map, so moving away from the depth dynamic region means that it is easier to successfully locate, and thus in the case where the target matching score is less than or equal to the second preset score threshold, after the search distance is set in step 4, a navigation target point is selected within a preset positioning distance range based on the search distance starting from the matching point, so as to find a position close to the matching point on the map with a shorter distance and fewer dynamic regions.

[0033] In summary, this application, for localization of maps with dynamic regions, first compares with a score threshold when the initial test fails. Then, it performs weighted calculations based on point clouds in both dynamic and non-dynamic regions, and compares with a higher score threshold, continuously eliminating interference from one-sided matching scores. Next, it sets a search distance based on the relationship between masks extracted from the reference map and masks extracted from the depth dynamic region of the target map. This allows for the segmentation of local map regions and the contours of marked obstacles for distance value analysis. Based on this, a location point matching the search distance is selected as the navigation target point. This ensures the robot moves away from the depth dynamic region as it moves from its current location to the navigation target point. Consequently, the robot identifies fewer depth dynamic regions at the navigation target point, but does not deviate too far from its original position. This improves the robot's localization stability at the navigation location and its robustness in dynamic environments, providing an important foundation for subsequent navigation and localization.

[0034] As one example, such as Figure 2 As shown, in step 4, a search distance image is set based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map. Starting from the matching point, the method for selecting the navigation target point within a preset positioning distance range based on this search distance image includes: Step 41: Extract the target mask based on the contour of the reference map; then proceed to step 42. Preferably, the method for extracting the target mask based on the contour of the reference map includes: searching for the largest map contour within the reference map; extracting the boundary of the reference map as the largest map contour using edge detection methods; filling the largest map contour to make the filled largest map contour more continuous and smooth; and then setting the image area enclosed by the filled largest map contour as the target mask, also known as the target mask image, to make the boundary of the target mask more continuous and smooth.

[0035] Step 42: Map the target distance image based on the dynamic regions in the target map; then proceed to step 43. Here, the point cloud points on the target map correspond to the distance values ​​in the target distance image. This can be understood as mapping the point cloud points on the target map to the distance values ​​in the target distance image, so that the distance values ​​in the target distance image are used to measure the distance information between the point cloud points on the target map and the dynamic regions in the target map. Therefore, the target distance image can be considered as a set of distance values ​​between each point cloud point on the target map and the dynamic regions in the target map. The dynamic regions in the target map have been identified before the weighted calculation in step 2. To ensure that the subsequently selected navigation target point is as far away as possible from the depth dynamic regions, the distance values ​​in the target distance image are preferably the minimum distance values ​​between the point cloud points on the target map and the edges of the dynamic regions.

[0036] Step 43, according to the marked obstacles in the reference map, a distance image of the obstacles is mapped, and the distance value in the distance image of the obstacles is marked as a first distance value; then step 44 is performed. Wherein, the point cloud points on the reference map correspond to the distance values in the distance image of the obstacles, so that the distance image of the obstacles is used to measure the distance information between the point cloud points on the reference map and the marked obstacles in the reference map, and then the distance image of the obstacles can be regarded as a collection of distance values between each point cloud point on the reference map and the marked obstacles in the reference map, so as to represent the distance information between the point cloud points on the reference map and the marked obstacles in the reference map. For example, in the case of ensuring obstacle avoidance effect, the distance value in the distance image of the obstacles is preferably the minimum distance value to the profile of the obstacle.

[0037] Step 44, the target distance image and the distance image of the obstacles are cropped by using the target mask to obtain a positioning candidate area, wherein the obtained point cloud points and their corresponding distance values are regarded as being in the positioning candidate area; if the target distance image and the distance image of the obstacles have overlapping parts, the target mask can also be used to crop the positioning candidate area from the overlapping parts to represent the same distance information in the target distance image and the distance image of the obstacles, that is, the distance information between the same point cloud points and the obstacles in or at the edge position of the dynamic area.

[0038] Step 44 uses the target mask to crop the positioning candidate area from the target distance image and the distance image of the obstacles, which is equivalent to extracting the positioning candidate area and obtaining its distance values in the target distance image and the distance image of the obstacles and the corresponding point cloud points. In some embodiments, the areas outside the positioning candidate area in the target distance image and the distance image of the obstacles can be deleted, so as to improve the calculation efficiency and reduce the data to be processed, and the subsequent work can be avoided.

[0039] In step 44, the reference mask is extracted from the depth dynamic area of the target map. Specifically, the method of extracting the reference mask from the depth dynamic area of the target map comprises: selecting a position point as the center of a circle in the depth dynamic area already identified in the target map, setting the sampling distance as the radius of the circle domain, and ensuring that the circle domain is located in the depth dynamic area; and then setting the circle domain as the reference mask to segment the circular mask in the depth dynamic area of the target map. Preferably, the sampling distance is preferably 1.5 m. The current position of the robot is taken as the center of the circle, and the sampling distance (which can be the walking distance of the robot) is taken as the radius of the circle domain.

[0040] Then, the distance values corresponding to the coverage of the positioning candidate region in the reference mask are weighted to obtain a second distance value, which is equivalent to weighting each distance value corresponding to the reference mask of the positioning candidate region in the target map, so as to convert each distance value into a corresponding second distance value. Specifically, the method of weighting the distance values corresponding to the coverage of the positioning candidate region in the reference mask includes: weighting each distance value corresponding to the coverage of the positioning candidate region in the reference mask according to the pre-stored weight to obtain the second distance value of each point cloud point corresponding to the positioning candidate region in the reference mask; the pre-stored weight is set according to the distance of the point cloud point on the depth dynamic region relative to the edge of the dynamic region (including the depth dynamic region and the reference dynamic region) and the distance value of the point cloud point relative to the obstacle contour, and preferably, the pre-stored weight is 0.5. The distance values after weighting are all reduced, so that the search distance in subsequent calculation is reduced, and the selected navigation target point is prevented from being set in a local area with a high coverage ratio of the depth dynamic region or a large number of depth dynamic regions, so that the robot moves away from the depth dynamic region during the movement from the current position point to the navigation target point.

[0041] It should be noted that each distance value corresponding to the coverage of the positioning candidate region in the reference mask is the distance value of each point cloud point corresponding to the positioning candidate region in the point cloud on the reference mask; each distance value corresponding to the coverage of the positioning candidate region in the reference mask includes the minimum distance value between the point cloud point and the edge of the dynamic region in the reference mask, or the minimum distance value between the point cloud point and the obstacle contour in the reference mask.

[0042] In step 4, whether the positioning candidate region is cropped from the target distance image and the obstacle distance image using the target mask or the positioning candidate region covers the region requiring weighting calculation in the reference mask, after creating the mask, the mask of the cropped image (corresponding to the aforementioned target mask) and the covered mask (corresponding to the aforementioned reference mask) correspond to the active region of the map region or the distance image, and the pixel points in the active region are assigned values, so that the active region is the same as the mask after assignment, so as to process the distance values corresponding to each point cloud point on the mask. The shape of the target mask is determined by the maximum contour of the reference map, and the maximum contour of the reference map outlines the region to be positioned in the form of a square, a circle, an ellipse, an irregular polygon, etc.

[0043] Step 45, set the sum value of the first distance value and the second distance value as the search distance, wherein the search distance corresponds to the search distance image, and the point cloud points on the distance image composed of the target distance image and the obstacle distance image correspond to the distance values in the search distance image; then execute step 46. Specifically, for each point cloud point on the position covered by the reference mask in the positioning candidate area, set the sum value between the first distance value corresponding to the mapping and the second distance value corresponding to the mapping as the search distance, and map the search distance image based on the search distance, and merge the obstacle distance image and the reference mask into the search distance image; wherein the search distance image can be regarded as a set of sum values between the distance values corresponding to each point cloud point on the position covered by the reference mask in the positioning candidate area and the distance values of the corresponding point cloud points of the obstacle distance image, to represent the distance information required for searching the navigation target point.

[0044] It should be noted that the positioning candidate area, the obstacle distance image and the search distance image all use the same coordinate scale. Therefore, the sum value between the distance between the point cloud and the obstacle in the integrated environment and the distance between the point cloud and the dynamic area is calculated to obtain the search distance, and is applicable to the reference map and the target map for positioning.

[0045] Step 46, from the matching point, select the point cloud point corresponding to the maximum search distance within a preset positioning distance range as the navigation target point, wherein the maximum distance value included in the preset positioning distance range is greater than the sampling distance; illustratively, within a range of 3 meters from the matching point, select the point cloud point with the maximum search distance or its projection point in the map plane as the navigation target point.

[0046] In summary, by executing steps 44 to 46, the navigation target point can be avoided to be set near the depth dynamic area, and the problem that the point cloud on the depth dynamic area is not robust to environmental changes is solved.

[0047] As an embodiment, in the step 2, the area where the target matching point cloud is distributed is a non-dynamic area, a reference dynamic area or a depth dynamic area; wherein the reference dynamic area and the depth dynamic area both belong to dynamic areas.

[0048] The non-dynamic area is used to represent an area in which the environment where the robot is located has no change, and correspondingly, the obstacles in the map have no displacement and change in contour size, that is, the obstacles in the surrounding environment of the robot are relatively fixed in distribution; the matching score corresponding to the point cloud point falling on the matching position of the non-dynamic area is a first matching score, the non-dynamic area is an area in which the robot preferentially navigates, and the first matching score can be set to be higher than or equal to 1, and is preferably 1.2, indicating that the matching part in the map is generally a stable wall or a relatively fixed obstacle, and the mapping of these areas only has some small differences, and the repositioning success rate in the non-dynamic area is relatively high.

[0049] The reference dynamic area is used to represent an area in which the environment where the robot is located changes, and the matching score corresponding to the point cloud point falling on the matching position of the reference dynamic area is a second matching score; the deep dynamic area is used to represent an area in which the environment where the robot is located changes more frequently relative to the reference dynamic area, so that the probability of the point cloud point falling into the deep dynamic area is higher than the probability of the point cloud point falling into the reference dynamic area; the matching score corresponding to the point cloud point falling on the matching position of the deep dynamic area is a third matching score; the second matching score is greater than the third matching score, that is, the matching success rate of the point cloud in the reference dynamic area is higher than the matching success rate in the deep dynamic area; for the non-dynamic area and different dynamic areas, the third matching score is equal to the second preset score threshold, and the second matching score is less than the first matching score; the first matching score, the second matching score, and the third matching score are all empirical values determined through a large number of point cloud matching tests, and can be set and modified according to actual environmental changes. Preferably, if the second matching score is 0.9, the third matching score is 0.7.

[0050] On the basis of distinguishing the dynamic area, the method for further distinguishing the reference dynamic area and the non-dynamic area comprises: every time the matching score corresponding to a point cloud point matched by the repositioning matching algorithm on the dynamic area changes within a preset test time, the matching score corresponding to the point cloud point is accumulated once, which is equivalent to performing an accumulation operation on the matching scores of each point cloud point in the target matching point cloud point by point within the preset test time. An accumulation result is obtained after the preset test time; if the accumulation result is greater than a preset total score threshold, it is determined that the dynamic area is a deep dynamic area; if the accumulation result is less than or equal to the preset score threshold, it is determined that the dynamic area is a reference dynamic area; so that the point cloud matched by the repositioning matching algorithm on the dynamic area of the target map is accumulated for the preset test time, and the reference dynamic area and the non-dynamic area are distinguished from the dynamic area based on the accumulation value of the matching score.

[0051] In order to improve the time robustness, the preset test time is preferably 10 days, and correspondingly, the preset total score threshold is preferably 5.

[0052] As an embodiment, in order to recalculate the matching score, the method of weighting the matching score corresponding to the point cloud points in the target matching point cloud falling on the target map includes: First, identify the area where the target matching point cloud is distributed in the target map, including distinguishing the non-dynamic area and the dynamic area in the target map, and distinguishing the reference dynamic area and the deep dynamic area from the dynamic area.

[0053] Specifically, if it is judged that the marked environmental information at the same coordinate position changes within a period of time, the coordinate position is a dynamic position point, and a plurality of adjacent or small-interval (for example, 1 to 3 grid points / coordinate position points) dynamic position points form the dynamic area; wherein, the marked environmental information includes information whether an obstacle occupies a position and information whether the same obstacle is displaced. If it is judged that the marked environmental information at the same coordinate position does not change within a period of time, the coordinate position is a non-dynamic position point, and a plurality of adjacent or small-interval (for example, 1 to 3 grid points / coordinate position points) non-dynamic position points form the non-dynamic area.

[0054] Based on the identified area, determine the matching score corresponding to the point cloud points in the target matching point cloud falling on the target map, and assign a corresponding weight to the currently determined matching score; in step 2, the weight assigned to the point cloud points on the non-dynamic area and the reference dynamic area (the weight assigned to the first matching score and the weight assigned to the second matching score) is higher than the weight assigned to the point cloud points on the deep dynamic area (the weight assigned to the third matching score), and the weight assigned to the point cloud points on the reference dynamic area is higher than the weight assigned to the point cloud points on the non-dynamic area; wherein, the weight assigned to the point cloud points on the non-dynamic area, the weight assigned to the point cloud points on the reference dynamic area, and the weight assigned to the point cloud points on the deep dynamic area are empirical values, which are determined through a large number of point cloud matching tests, and can be set and modified according to the actual environmental changes.

[0055] Then, using the assigned weight, control the weighted calculation of the matching score corresponding to the point cloud points in the target matching point cloud falling on the target map, to obtain the target matching score, specifically, separately perform weighted calculation for the aforementioned identified non-dynamic area, reference dynamic area or deep dynamic area, that is, multiply the matching score corresponding to the point cloud points on the identified area by the assigned weight, and the product is the target matching score corresponding to the matching successful point cloud points on the identified area, so as to make single matching score weighted calculation according to the dynamic area or non-dynamic area where the matched point cloud is located, and realize recalculating the matching score of the target matching point cloud on the same type of area.

[0056] As an embodiment, the method for constructing the target map in step 2 comprises: Step 21, extracting the obstacle area from the reference map and marking the extracted obstacle area as the first obstacle map area; extracting the obstacle area from the working map and marking the extracted obstacle area as the second obstacle map area; then performing step 22; wherein the obstacle area is composed of position points marked with obstacles, which can be understood as the area occupied by the obstacle in the map. In a dynamically changing environment, the area occupied by the obstacle in the map can change over time, forming a dynamic area, such as the movement of tables and chairs in a home environment, changes in pet activity areas, etc., which can be marked as obstacle map areas. The present application divides the obstacle map area into the first obstacle map area and the second obstacle map area due to the difference in map type or map construction time.

[0057] Specifically, the reference map is a map constructed by the robot when it first performs a work task in a preset working area. In some embodiments, the robot can quickly map the preset working area by scanning the point cloud of the surrounding environment with a sensor (which can be a one-time scan of the preset working area) or gradually advance the global cleaning work in the preset working area according to a certain unit area (e.g., a 4x4 grid area). When the robot finishes performing the work task, the reference map is saved, and the generation timestamp corresponding to the reference map is recorded.

[0058] After the robot first performs the work task, it can re-perform the work task as needed, wherein each time the work task is performed in the preset working area; each time the work task is performed, a global map is constructed in the preset working area. Each time the work task is performed, the preset working area is walked through once according to the preset planning path, and real-time position information is marked to the map.

[0059] The robot builds a map in the preset working area each time when performing a working task, saves the built map as the working map each time after performing a working task, and records the generation timestamp corresponding to the working map, wherein the working map built when performing the nth (n is an integer greater than 1) working task can be compared with the working map / reference map built when performing the working task at an earlier time in terms of the generation timestamp, so that the working map built subsequently is used to update the working map built previously, and in particular, in order to avoid that the environment scene changes too frequently in the same day, the date in the generation timestamp corresponding to the working map needs to be screened, and in the case where the generation timestamp corresponding to the reference map and the working map saved last time is in the same date, if it is judged that the generation timestamp corresponding to the working map saved currently and the generation timestamp corresponding to the working map saved last time are in the same date, the working map saved currently is abandoned, otherwise, the obstacle region can be extracted from the reference map and the working map saved currently by performing step 21.

[0060] Step 22, extract the overlapping region from the first obstacle map region and the second obstacle map region, and then control the second obstacle map region to subtract the overlapping region, and then mark the map region obtained by subtraction as a reference obstacle map; then perform step 23; specifically, the overlapping region is extracted from the first obstacle map region and the second obstacle map region, which is equivalent to performing an and operation on the first obstacle map region and the second obstacle map region to obtain the and result between the first obstacle map region and the second obstacle map region, and the and result is the overlapping region. Then the second obstacle map region is subtracted from the overlapping region, which can be understood that each pixel value in the overlapping region is subtracted by the pixel value at the corresponding position in the second obstacle map region, and the map region obtained by subtraction is the reference obstacle map, wherein the second obstacle map region can represent the obstacle information in the working map saved later with respect to the reference map, and contains the obstacle information that has appeared dynamic change; thus, the map region in the second obstacle map region is excluded from the influence of the obstacle factor in the reference map, which is beneficial to identify the dynamic region.

[0061] Step 23, identify the dynamic region and the non-dynamic region in the reference obstacle map; then perform step 24.

[0062] Specifically, in step 23, the method of identifying the dynamic region and the non-dynamic region in the reference obstacle map comprises: identifying the dynamic position point and the position point other than the dynamic position point in the reference obstacle map, respectively.

[0063] The pixel value of the dynamic position point in the reference obstacle map is set as a first pixel value; and the dynamic position point forms a dynamic region. It can be understood that a set or a region occupied by a plurality of dynamic position points is recorded as the dynamic region. Further, the method for dividing the reference dynamic region and the deep dynamic region in the dynamic region refers to the aforementioned associated embodiments. Preferably, according to the concept of image binarization, the first pixel value can be recorded as logic 1, so that the logic 1 can be used to identify the region with changes in the reference obstacle map.

[0064] The pixel value of the position point other than the dynamic position point in the reference obstacle map is set as a second pixel value; and the position point other than the dynamic position point forms a non-dynamic region. It can be understood that a region other than the dynamic region in the reference obstacle map is recorded as the non-dynamic region. Preferably, according to the concept of image binarization, the second pixel value can be recorded as logic 0, so that the logic 0 can be used to identify the region without changes in the reference obstacle map.

[0065] In step 23, the first pixel value and the second pixel value are not equal; when the first pixel value is 255 to represent a white pixel, the second pixel value is 0 to represent a black pixel, so as to realize the binarization processing of the reference obstacle map.

[0066] It should be noted that the dynamic position point is used to represent a position point with unchanged coordinate information but changed marked environment information. The marked environment information includes information about whether an obstacle occupies a position and information about whether the same obstacle is displaced. Whether the same obstacle is displaced and whether the occupied region is changed can be known by comparing the corresponding positions of the reference map in step 21 and the working map in step 21. The marked environment information can also be obtained by comparing the obstacle occupation information at the same position of the working map constructed in each execution of the working task.

[0067] Specifically, when the marked environment information of the same coordinate position point in the subsequently constructed working map is different from the marked environment information of the same coordinate position point in the previously constructed working map, or when the marked environment information of the same coordinate position point in the subsequently constructed working map is different from the marked environment information of the same coordinate position point in the reference map, it is determined that the same coordinate position point is a dynamic position point.

[0068] Step 24, the dynamic area in the reference obstacle map is dilated according to a preset size template; then step 25 is executed; the preset size template is 3 grids by 3 grids of grid area traversing the identified dynamic area in the reference obstacle map, and the current covered area in the reference obstacle map is dilated according to the preset size template once for each traversal, until the dynamic area in the reference obstacle map is traversed, the dynamic area of the reference obstacle map is denoised, and the positioning and recognition accuracy of the dynamic area is improved.

[0069] Step 25, the reference obstacle map where the dilated dynamic area is located is marked as the target map; or the dilated dynamic area is saved in the global map, and then the global map where the reference obstacle map is saved is marked as the target map; preferably, the global map can be a grid map / benchmark map / task map constructed by the robot in a preset working area for a working task; because the dilated dynamic area needs more redundant areas to accommodate, the reference obstacle map where the dilated dynamic area is located needs to be loaded into a larger map, so the aforementioned global map is additionally constructed, so that the global map where the reference obstacle map is saved is marked as the target map. Based on this, the target map is a map configured to execute the repositioning matching algorithm.

[0070] On the basis of the above-mentioned embodiments, at least on the basis of the constructed benchmark map, the robot starts to execute a working task for the second time and construct a map in a preset working area, and before the robot executes the step 21, the robot further includes: Step 201, judge whether the generation time stamp corresponding to the currently saved task map and the generation time stamp corresponding to the benchmark map are in the same date, if yes, execute step 202, otherwise execute step 204; wherein the initial map of the currently saved task map is the map constructed by the robot when executing the working task for the second time. In consideration of the date change factor, the generation time stamp corresponding to the currently saved task map is different from the generation time stamp corresponding to the benchmark map, and the generation time stamp corresponding to the currently saved task map required for each subsequent execution of step 201 is later than the generation time stamp corresponding to the currently saved task map required for the last execution of step 201.

[0071] Step 202, updating the current saved working map in step 201 to the last saved working map, and updating the generation timestamp corresponding to the current saved working map in step 201 to the generation timestamp corresponding to the last saved working map, to realize iterative updating of the working map required for judgment; meanwhile, performing the work task in the preset working area and constructing the map, i.e., relative to the constructed reference map or the last constructed working map (the last saved working map), starting to perform the work task in the preset working area and construct the map again, then updating the constructed map to the current saved working map and recording the generation timestamp corresponding to the constructed map; then performing step 203.

[0072] Step 203, judging whether the generation timestamp corresponding to the current saved working map in step 202 and the generation timestamp corresponding to the last saved working map in step 202 are in the same date, if yes, performing step 202 to reconstruct and save the new working map and the generation timestamp corresponding thereto, otherwise performing step 204.

[0073] Step 204, updating the current saved working map to the working map in step 201; then performing step 201, and this time the iterative execution of steps 201 to 203 is ended. If step 204 is executed by jumping from step 201, the current saved working map is the working map in step 201; if step 204 is executed by jumping from step 202, the current saved working map is the working map in step 202.

[0074] In some embodiments, when it is judged that the generation timestamp corresponding to the current saved working map and the generation timestamp corresponding to the last saved working map are in the same date, the last saved working map is deleted, and the current saved working map is updated to the last saved working map and the generation timestamp corresponding to the current saved working map is updated to the generation timestamp corresponding to the last saved working map by performing step 202, until it is judged that the generation timestamp corresponding to the current saved working map and the generation timestamp corresponding to the last saved working map are not in the same date, and then step 204 is executed.

[0075] From steps 201 to 204, it is first determined whether the generation time stamp corresponding to the currently saved working map and the generation time stamp corresponding to the reference map are the same date. If yes, the execution of the work task in the preset working area and the construction of the map are restarted. Otherwise, step 21 is executed. In the process of restarting the execution of the work task in the preset working area and the construction of the map, it is continuously determined whether the generation time stamp corresponding to the currently saved working map and the generation time stamp corresponding to the previously saved working map are the same date. If yes, the execution of the work task in the preset working area and the construction of the map are restarted. Otherwise, step 21 is executed. Thus, by adding date screening, the problem of too frequent scene changes in multiple frames of maps saved on the same day is prevented, the working map required for subsequent execution of step 21 more effectively reflects the latest environmental changes, and thus the target map saved in step 25 is more universal in a dynamically changing environment.

[0076] In addition, in combination with steps S1 to S3 in the method for post-inspection of the relocation result disclosed in Chinese Patent CN202111314321.5, the method for inspection of the relocation result by the robot in the present application includes: determining whether the matching score in the relocation result is greater than a first threshold and less than a second threshold. If yes, the map is updated through the relocation result. Then, walking for a set time or a set distance, and obtaining the point cloud of the environment in the walking process, and then matching the point cloud obtained in the walking process with the updated map, and then determining whether the robot positioning succeeds or fails according to the matching result. The first threshold is less than the second threshold. It should be noted that for the matching score, the corresponding first threshold and second threshold are set. If the matching score in the relocation result is less than or equal to the first threshold, the relocation is directly determined to fail. If the matching score in the relocation result is between the first threshold and the second threshold, the inspection step is entered, and the relocation result is post-inspected. If the matching score in the relocation result is greater than or equal to the second threshold, the relocation is directly determined to succeed. The first threshold is less than the second threshold, and the first threshold and the second threshold are empirical values determined through a large number of data set tests, and can be set and modified according to actual conditions.

[0077] The application also discloses a chip for storing a program configured to execute the dynamic area-based navigation target point planning method. Compared with the prior art, the chip disclosed by the application does not eliminate dynamic pixels in a map when the chip performs point cloud matching on the map, but sets a mask to correspond to a map with dynamic areas and subtracts and compares between different maps to obtain a search distance image to set a navigation target point by directly extracting a search distance, so as to segment out positioning points within a reasonable distance range from obstacles and dynamic areas in a map region corresponding to the mask, thereby improving the adaptability of a positioning method to a dynamic changing environment in different local map regions, and thus achieving the purpose of planning accurate and stable map repositioning points in a dynamic changing environment.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A navigation target point planning method based on dynamic regions, which includes: The relocation result is obtained through a relocation matching algorithm, and then the relocation result is verified. The method for planning navigation target points is characterized by further comprising: Step 1: If the relocation result fails, the robot determines whether the matching score in the relocation result is greater than a first preset score threshold. If so, proceed to Step 2. Step 2: The robot marks the point cloud matched by the relocation matching algorithm on the target map as the target matching point cloud; then it performs a weighted calculation on the matching scores of the point cloud points in the target matching point cloud that fall into the target map to obtain the target matching score; then proceeds to step 3. Step 3: The robot determines whether the target matching score is greater than the second preset score threshold. If yes, the positioning is successful; otherwise, proceed to step 4. The second preset score threshold is greater than the first preset score threshold. Step 4: Mark the point cloud points corresponding to the target matching score as matching points, and mark the working map constructed by the robot when performing point cloud matching using the relocalization matching algorithm as a reference map; set a search distance image based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map, and select the navigation target point within the preset positioning distance range based on the search distance image, starting from the matching point.

2. The navigation target point planning method according to claim 1, characterized in that, In step 4, a search distance image is set based on the relationship between the mask extracted from the reference map and the mask extracted from the depth dynamic region of the target map. Starting from the matching point, the method for selecting the navigation target point within a preset positioning distance range based on this search distance image includes: Extract the target mask based on the outline of the reference map; Based on the dynamic regions in the target map, a target distance image is mapped; wherein, the point cloud points on the target map correspond to the distance values ​​in the target distance image, so that the distance values ​​in the target distance image are used to measure the distance information between the point cloud points on the target map and the dynamic regions in the target map; Based on the obstacles marked in the reference map, an obstacle distance image is mapped, and the distance values ​​in the obstacle distance image are marked as the first distance value; wherein, the point cloud points on the reference map correspond to the distance values ​​in the obstacle distance image, so that the obstacle distance image is used to measure the distance information between the point cloud points on the reference map and the obstacles marked in the reference map; The target distance image and obstacle distance image are cropped using a target mask to obtain localization candidate regions; a reference mask is extracted from the depth dynamic region of the target map, and then the distance values ​​covered by the localization candidate regions within the reference mask are weighted and calculated to obtain the second distance value. The sum of the first distance value and the second distance value is set as the search distance, wherein the search distance corresponds to the search distance image, and the point cloud points on the distance image composed of the target distance image and the obstacle distance image correspond to the distance values ​​in the search distance image; Starting from the matching point, the point cloud point corresponding to the largest search distance within the preset positioning distance range is selected as the navigation target point, so that the robot moves away from the depth dynamic area of ​​the target map during the process of moving from the current position point to the navigation target point.

3. The navigation target point planning method according to claim 2, characterized in that, The method for extracting the target mask based on the contour of the reference map includes: The maximum map outline is searched within the reference map, then filled with the maximum map outline, and the image area enclosed by the filled maximum map outline is the target mask.

4. The navigation target point planning method according to claim 2, characterized in that, The method for extracting the reference mask from the depth dynamic region of the target map includes: Within the depth dynamic region of the target map, a location point is selected as the center, and the sampling distance is set as the radius to form a circular region. This circular region is then set as the reference mask to segment out a circular mask within the depth dynamic region of the target map.

5. The navigation target point planning method according to claim 4, characterized in that, The method of weighting the calculation using the distance values ​​covered by the reference mask within the positioning candidate area includes: According to the pre-stored weights, each distance value corresponding to the location candidate region covered by the reference mask is weighted and calculated to obtain the second distance value of each point cloud point in the reference mask corresponding to the location candidate region. Wherein, each distance value covered by the positioning candidate region within the reference mask is: the distance value of each point cloud point in the point cloud on the reference mask corresponding to the positioning candidate region; The distance values ​​that the candidate positioning region covers within the reference mask include: the minimum distance between the point cloud point and the edge of the dynamic region within the reference mask, or the minimum distance between the point cloud point and the outline of an obstacle within the reference mask.

6. The navigation target point planning method according to claim 2, characterized in that, For each point cloud point in the location candidate region corresponding to the reference mask, the sum of the first distance value calculated for the same point cloud point and the second distance value calculated for the same point cloud point is set as the search distance.

7. The navigation target point planning method according to claim 1, characterized in that, In step 2, the area where the target matching point cloud is distributed is a non-dynamic area, a reference dynamic area, or a deep dynamic area; among them, the reference dynamic area and the deep dynamic area are both dynamic areas. The non-dynamic region is used to represent the area where the robot's environment has not changed. The matching score of the point cloud point that falls into the non-dynamic region and matches the position is the first matching score. The reference dynamic region is used to represent the area where the robot's environment changes. The matching score of the point cloud point that falls into the reference dynamic region and matches the position is the second matching score. The depth dynamic region is used to represent the region where the robot's environment changes more frequently relative to the reference dynamic region, making the probability of a point cloud point falling into the depth dynamic region higher than the probability of a point cloud point falling into the reference dynamic region; the matching score corresponding to the point cloud point that falls into the depth dynamic region and matches the position is the third matching score. Wherein, the third matching score is equal to the second preset score threshold, the third matching score is less than the second matching score, and the second matching score is less than the first matching score.

8. The navigation target point planning method according to claim 7, characterized in that, Within a preset test time, whenever the matching score of a point cloud point matched by the relocation matching algorithm in the dynamic region changes, the matching score of the matched point cloud point is incremented once. After a preset test time, the accumulated result is obtained. If the accumulated result is greater than the preset total score threshold, the dynamic region is determined to be a deep dynamic region. If the accumulated result is less than or equal to the preset score threshold, then the dynamic region is determined to be a reference dynamic region; During the relocation matching algorithm, the robot matches the collected point cloud with the map. When a point cloud point is detected to fall into a corresponding type of area in the map, a point cloud point is determined to be matched, and the corresponding matching score is obtained.

9. The navigation target point planning method according to claim 7, characterized in that, The method for weighted calculation of the matching scores corresponding to point cloud points that fall into the target map in the target matching point cloud includes: First, identify the regions in the target map where the target matching point cloud is distributed; Based on the identified region, determine the matching score of the point cloud points in the target matching point cloud that fall on the target map, and assign corresponding weights to the currently determined matching scores; Then, using the assigned weights, the matching scores corresponding to the point cloud points in the target matching point cloud that fall onto the target map are weighted and calculated to obtain the target matching score.

10. A chip for storing a program, characterized in that, The program is configured to perform the navigation target point planning method based on any one of claims 1 to 9.

Images