Garage navigation system based on slam navigation map and cad building plan

Abstract

The application relates to the field of computer mapping positioning, in particular to a garage navigation system based on a SLAM navigation map and a CAD building map, the system comprising a memory which stores a target SLAM navigation map of a target garage, and the target SLAM navigation map is marked with the IDs corresponding to each parking area; the system further comprises a processor and a storage medium which stores a computer program, and when the computer program is executed by the processor, the following steps are realized: S100, acquiring an ID input by a user; S200, acquiring the coordinates of a parking area in the target SLAM navigation map which matches the ID input by the user; and S300, taking the coordinates as a target point to perform path planning. The application realizes automatic marking of the IDs corresponding to each parking area on the SLAM navigation map, and solves the problem that manual marking is prone to marking errors.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer mapping positioning, in particular to a garage navigation system based on SLAM navigation map and CAD building map. BACKGROUND

[0002] The mobile charging robot can charge the vehicle specified by the user in the garage. The existing implementation process is as follows: after the user inputs the parking space number, manually mark the position corresponding to the parking space number in the SLAM navigation map of the mobile charging robot, and the mobile charging robot plans the path to the target point and charges the vehicle after reaching the target point. The existing implementation process relies on manual marking of the position corresponding to the parking space number in the SLAM navigation map, which brings a large workload to the manual work, and manual marking is prone to marking errors, resulting in positioning deviation of the mobile charging robot when searching for the charging vehicle. SUMMARY

[0003] The present application aims to provide a garage navigation system based on SLAM navigation map and CAD building map, which solves the problem of large manual workload and manual marking errors in the existing method of relying on manual marking of the position corresponding to the parking space number in the SLAM navigation map, and improves the positioning accuracy of the mobile charging robot when searching for the charging vehicle.

[0004] According to the present application, a garage navigation system based on SLAM navigation map and CAD building map is provided, comprising a memory, the memory stores a target SLAM navigation map of a target garage, the target SLAM navigation map is marked with the ID corresponding to each parking area, and the acquisition method of the target SLAM navigation map comprises:

[0005] S001, acquiring a first SLAM navigation map of a target garage.

[0006] S002, adjusting the resolution of the first SLAM navigation map to the resolution of the CAD building map of the target garage to obtain a second SLAM navigation map with the same resolution as the CAD building map; the CAD building map is marked with the ID corresponding to each parking area.

[0007] S003, performing feature matching between the second SLAM navigation map and the CAD building map to obtain the coordinate conversion relationship when the CAD building map is mapped to the second SLAM navigation map.

[0008] S004, mapping IDs of each parking area marked in the CAD building drawing to the second SLAM navigation map according to the coordinate conversion relationship, to obtain a third SLAM navigation map marked with IDs of each parking area.

[0009] S005, adjusting the resolution of the third SLAM navigation map to the resolution of the first SLAM navigation map, to obtain the target SLAM navigation map with the same resolution as the first SLAM navigation map.

[0010] The system further comprises a processor and a storage medium storing a computer program, when the computer program is executed by the processor, the following steps are realized:

[0011] S100, obtaining an ID input by a user.

[0012] S200, obtaining coordinates of a parking area matching the ID input by the user in the target SLAM navigation map.

[0013] S300, performing path planning with the coordinates as target points.

[0014] The present application has obvious beneficial effects compared with the prior art. By the above technical solution, the garage navigation system based on the SLAM navigation map and the CAD building drawing provided by the present application can achieve considerable technical progress and practicality, and has wide industrial utilization value. It at least has the following beneficial effects:

[0015] The present application performs multi-step processing on the first SLAM navigation map of the target garage based on the CAD building drawing with IDs of each parking area of the target garage, and finally obtains the target SLAM navigation map marked with IDs of each parking area. The present application realizes automatic marking of IDs of each parking area on the SLAM navigation map. On this basis, the mobile charging robot no longer needs to be manually marked for charging position when executing the charging instruction issued by the user, solving the problem of large manual workload and easy marking errors in the prior art method of manually marking positions corresponding to parking numbers (i.e. IDs of parking areas) in the SLAM navigation map, and improving the positioning accuracy of the mobile charging robot when charging. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 A flowchart of a method for obtaining a target SLAM navigation map is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person skilled in the art without creative work fall within the scope of protection of the present application.

[0019] According to the present application, a garage navigation system based on a SLAM navigation map and a CAD building map is provided, comprising a memory storing a target SLAM navigation map of a target garage, wherein the target SLAM navigation map is marked with IDs corresponding to each parking area; the system further comprises a processor and a storage medium storing a computer program, when the computer program is executed by the processor, the following steps are implemented:

[0020] S100, obtaining an ID input by a user.

[0021] It should be understood that when the user parks the car in a certain parking area of the target garage, if the user has the demand to charge the car, the user can operate through the related APP, and the operation at least includes inputting the ID (i.e. the parking space number) of the user's car in the target garage; thus, the APP can send a charging instruction to the mobile charging robot for the car in the parking area corresponding to the ID in the target garage.

[0022] S200, obtaining the coordinates of the parking area matching the ID input by the user in the target SLAM navigation map.

[0023] According to the present application, the target SLAM navigation map is marked with IDs corresponding to each parking area, thus the mobile charging robot can know the parking area where the user's car is located by matching the ID input by the user with the IDs corresponding to each parking area in the target SLAM navigation map; for the mobile charging robot, the coordinates of each position in the target SLAM navigation map are known, thus the mobile charging robot can also obtain the coordinates of the parking area matching the ID input by the user. Optionally, the coordinates of the parking area are one of the coordinates of the four vertices corresponding to the parking area, or the coordinates of the center point of the parking area (which can be obtained according to the coordinates of the four vertices corresponding to the parking area).

[0024] S300, taking the coordinates as a target point for path planning.

[0025] According to the application, the current position of the mobile charging robot is taken as a starting point, and the coordinates of the parking area matched with the ID input by the user are taken as a target point. After the starting point and the target point are determined, the mobile charging robot can plan a path and reach the target point based on the planned path to perform a charging task. Those skilled in the art understand that any path planning method in the prior art falls within the protection scope of the application, and thus will not be described here.

[0026] As shown in Figure 1 the target SLAM navigation map acquisition method comprises the following steps:

[0027] S001, a first SLAM navigation map of a target garage is acquired.

[0028] Optionally, the first SLAM navigation map of the target garage is acquired by a laser radar, and the map is a 2D map. Those skilled in the art understand that any method for acquiring a SLAM navigation map based on a laser radar in the prior art falls within the protection scope of the application.

[0029] S002, the resolution of the first SLAM navigation map is adjusted to the resolution of a CAD building drawing of the target garage to obtain a second SLAM navigation map with the same resolution as the CAD building drawing; the CAD building drawing is marked with the IDs corresponding to the parking areas.

[0030] It should be understood that the resolution of the first SLAM navigation map and the resolution of the CAD building drawing of the target garage can be different. The application adjusts the resolution of the first SLAM navigation map to the resolution of the CAD building drawing of the target garage, so as to facilitate the feature matching between the second SLAM navigation map and the CAD building drawing in S003. In order to facilitate the distinction, the first SLAM navigation map after the resolution adjustment is recorded as the second SLAM navigation map. The process of adjusting the resolution is the prior art, and thus will not be described here. Those skilled in the art understand that any method for adjusting the resolution in the prior art falls within the protection scope of the application.

[0031] S003, the second SLAM navigation map is matched with the CAD building drawing to acquire the coordinate conversion relationship when the CAD building drawing is mapped to the second SLAM navigation map.

[0032] According to the application, the SLAM navigation map and the CAD building drawing corresponding to the target garage have many straight line features, such as wall surfaces (represented as straight lines in the SLAM navigation map and the CAD building drawing) and support columns (which can be divided into straight lines); preferably, the second SLAM navigation map is matched with the CAD building drawing to acquire the coordinate conversion relationship when the CAD building drawing is mapped to the second SLAM navigation map, which comprises:

[0033] S0031, extracting straight lines in the second SLAM navigation map.

[0034] The skilled in the art know that any method for extracting straight lines in a SLAM navigation map in the prior art falls within the protection scope of the present application. As one method for extracting straight lines in a SLAM navigation map in the prior art, it mainly includes: obtaining contours in the SLAM navigation map by using an edge detection algorithm; and extracting straight lines in the contours by using a Hough transform.

[0035] S0032, extracting straight lines in the CAD building drawing.

[0036] Optionally, the CAD building drawing is a 2D image, and any method for extracting straight lines in an image in the prior art can be applied to extract straight lines in the CAD building drawing.

[0037] S0033, obtaining a matching relationship between the straight lines in the second SLAM navigation map and the straight lines in the CAD building drawing.

[0038] It should be understood that matching means that a straight line in the second SLAM navigation map corresponds to a straight line in the CAD building drawing, which corresponds to the same object in the target garage, such as the same wall surface.

[0039] According to the present application, the second SLAM navigation map of the target garage and the CAD building drawing have the same resolution, so the length of the straight line corresponding to the same object in the target garage in the second SLAM navigation map is the same as that in the CAD building drawing. Therefore, the present application can perform straight line matching based on the length of each straight line in the second SLAM navigation map and the length of each straight line in the CAD building drawing.

[0040] If the length of a straight line in the second SLAM navigation map is equal to the length of a plurality of straight lines in the CAD building drawing, it is further determined whether the distance of the plurality of straight lines from a preset position is equal to the distance of the straight line in the second SLAM navigation map from the corresponding preset position, and the straight line with equal distance is selected as the matched straight line. The preset position in the CAD building drawing and the preset position in the second SLAM navigation map in the determination process of the present application are the same position in the target garage, for example, both are the center position of the garage or the entrance position of the garage. If the number of straight lines with equal distance is still greater than 1, another preset position is selected for determination again, and so on, until the straight line in the CAD building drawing that uniquely matches the straight line in the second SLAM navigation map is selected.

[0041] The skilled in the art know that any method for determining the matching of straight lines in two images in the prior art falls within the protection scope of the present application.

[0042] S0034, obtaining a coordinate conversion relationship when the CAD architectural drawing is mapped to the second SLAM navigation map according to the matching relationship.

[0043] According to the application, the coordinate conversion relationship when the CAD architectural drawing is mapped to the second SLAM navigation map according to the matching relationship comprises:

[0044] S00341, obtaining a coordinate v i of a midpoint of the i-th straight line l i,1 in the CAD architectural drawing.

[0045] S00342, obtaining a coordinate v i of a midpoint of a straight line matched with l i,2 in the second SLAM navigation map.

[0046] Optionally, the straight line matched with l i in the second SLAM navigation map is obtained according to a length difference of each straight line with l i in the second SLAM navigation map and a relative position relationship of each straight line with a target garage center position in the second SLAM navigation map.

[0047] According to the application, the straight line matched with l i in the second SLAM navigation map has a same length as l i , so the length difference of the straight line matched with l i in the second SLAM navigation map with l i is close to 0, and a distance of the straight line matched with l i in the second SLAM navigation map from the target garage center position in the second SLAM navigation map is equal to a distance of the i-th straight line in the CAD architectural drawing from the target garage center position in the CAD architectural drawing.

[0048] S00343, obtaining an i-th coordinate conversion relationship when v i,1 is mapped to v i,2 .

[0049] It should be understood that after v i,1 and v i,2 are obtained, a homogeneous transformation matrix when v i,1 is converted to v i,2 is obtained, and the homogeneous transformation matrix is the i-th coordinate conversion relationship when v i,1 is mapped to v i,2 . The method for obtaining the homogeneous transformation matrix is prior art, which is not described herein.

[0050] Those skilled in the art will understand that any method for obtaining coordinate transformation relationships in the prior art falls within the protection scope of this invention.

[0051] S00344, Obtain the coordinate transformation relationship when mapping the CAD architectural drawing to the second SLAM navigation map according to the i-th coordinate transformation relationship.

[0052] Preferably, the coordinate transformation relationship when mapping the CAD architectural drawing to the second SLAM navigation map is the i-th coordinate transformation relationship and the coordinate transformation relationship in the CAD architectural drawing excluding l. i The average coordinate transformation relationship of the coordinate transformation relationships corresponding to all lines other than the CAD architectural drawing is calculated (i.e., the average of the coordinate transformation relationships corresponding to all lines). Therefore, the calculated coordinate transformation relationship when mapping the CAD architectural drawing to the second SLAM navigation map references the coordinate transformation relationships corresponding to all lines, making it more accurate and avoiding the potential inaccuracies that may occur when relying on a single line to obtain the coordinate transformation relationship.

[0053] S004, based on the coordinate transformation relationship, map the IDs corresponding to each parking area marked in the CAD architectural drawing to the second SLAM navigation map to obtain a third SLAM navigation map marked with the IDs corresponding to each parking area.

[0054] According to the present invention, mapping the IDs corresponding to each parking area marked on the CAD architectural drawing to the second SLAM navigation map according to the coordinate transformation relationship includes:

[0055] S0041, Obtain the set A = (A1, A2, ..., A...) of parking areas in the CAD architectural drawing. N ), A n A represents the nth parking area in the CAD architectural drawing, where n ranges from 1 to N; n =(A n,1 A n,2 A n,3 A n,4 ), A n,1 A n,2 A n,3 and A n,4 A respectively n The coordinates of the first, second, third, and fourth vertices.

[0056] It should be understood that the target garage includes N parking areas, each parking area (usually a quadrilateral) has 4 vertices, and the corresponding parking area can be determined based on the coordinates of the 4 vertices.

[0057] S0042, Traverse A, and use the aforementioned coordinate transformation relationship to transform A. nA' is obtained by conversion n =(A' n,1 ,A' n,2 ,A' n,3 ,A' n,4 ), A' is obtained by conversion n,1 ,A' n,2 ,A' n,3 and A' n,4 are coordinates of A n,1 ,A n,2 ,A n,3 and A n,4 respectively after conversion by using the coordinate conversion relationship.

[0058] S0043, the ID of the area a n in the second SLAM navigation map is set to the ID of A n , a n =(a n,1 ,a n,2 ,a n,3 ,a n,4 ), a n,1 , a n,2 , a n,3 and a n,4 are coordinates of the first, second, third and fourth vertices of a n respectively, a n,1 =A' n,1 , a n,2 =A' n,2 , a n,3 =A' n,3 , a n,4 =A' n,4 .

[0059] It should be understood that the target garage does not include the corresponding identification of each parking area in the second SLAM navigation map, and accordingly, the corresponding coordinates of each parking area in the target garage in the second SLAM navigation map are unknown. The S0043 of the application determines the coordinates of the four vertices of each parking area of the target garage in the second SLAM navigation map, that is, determines each parking area of the target garage in the second SLAM navigation map, and also matches the ID of each parking area in the second SLAM navigation map (for the sake of distinction, the second SLAM navigation map after marking the corresponding ID of each parking area is referred to as the third SLAM navigation map), which provides the possibility for the mobile charging robot to automatically find the corresponding charging area according to the ID input by the user.

[0060] S005, the resolution of the third SLAM navigation map is adjusted to the resolution of the first SLAM navigation map, and the target SLAM navigation map with the same resolution as the first SLAM navigation map is obtained.

[0061] It should be understood that the first SLAM navigation map of the application is constructed by the mobile charging robot, and is a map on which the existing mobile charging robot performs a charging task; and the target SLAM navigation map is only marked with the IDs of the parking areas compared with the first SLAM navigation map, the coordinate systems of the two navigation maps are the same, and the coordinates of the same objects in the two navigation maps are also the same, so the target SLAM navigation map can be used as a map on which the subsequent mobile charging robot performs a charging task.

[0062] The application realizes automatic marking of the IDs of the parking areas on the SLAM navigation map, and on this basis, the mobile charging robot does not need to be marked with the charging position by manual operation when performing the charging instruction issued by the user, thereby solving the problems of large manual workload and easy marking error in the prior art method of marking the positions corresponding to the parking space numbers (i.e. the IDs of the parking areas) in the SLAM navigation map by manual operation, and improving the positioning accuracy of the mobile charging robot during charging.

[0063] Although some specific embodiments of the application have been described in detail through examples, those skilled in the art should understand that the above examples are only for illustration, but not for limiting the scope of the application. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the application. The scope of the application is defined by the appended claims.

Claims

1. A garage navigation system based on SLAM navigation map and CAD building plan, characterized by, The system comprises a memory storing a target SLAM navigation map of a target garage, the target SLAM navigation map being marked with IDs of respective parking areas, and a method for obtaining the target SLAM navigation map comprises: S001, obtaining a first SLAM navigation map of a target garage; S002, adjusting a resolution of the first SLAM navigation map to a resolution of a CAD building map of the target garage to obtain a second SLAM navigation map with the same resolution as the CAD building map, the CAD building map being marked with IDs of respective parking areas; S003, performing feature matching between the second SLAM navigation map and the CAD building map to obtain a coordinate conversion relationship when the CAD building map is mapped to the second SLAM navigation map; S004, mapping the IDs of respective parking areas marked in the CAD building map to the second SLAM navigation map according to the coordinate conversion relationship to obtain a third SLAM navigation map marked with IDs of respective parking areas; S005, adjusting a resolution of the third SLAM navigation map to a resolution of the first SLAM navigation map to obtain the target SLAM navigation map with the same resolution as the first SLAM navigation map; The system further comprises a processor and a storage medium storing a computer program, when the computer program is executed by the processor, the following steps are implemented: S100, obtaining an ID input by a user; S200, obtaining coordinates of a parking area matching the ID input by the user in the target SLAM navigation map; S300, taking the coordinates as a target point to perform path planning; S003 comprises: S0031, extracting straight lines in the second SLAM navigation map; S0032, extracting straight lines in the CAD building map; S0033, obtaining a matching relationship between the straight lines in the second SLAM navigation map and the straight lines in the CAD building map; S0034, obtaining a coordinate conversion relationship when the CAD building map is mapped to the second SLAM navigation map according to the matching relationship; S0034 comprises: S00341, acquiring the coordinate v of the midpoint of the i-th straight line in the CAD building drawing l i ; S00342, acquiring the coordinate w of the midpoint of the (i+1)-th straight line in the CAD building drawing i,1 ; S00342, obtaining coordinates v of a midpoint of the matched straight line in the second SLAM navigation map l i coordinates v of a midpoint of the matched straight line i,2 ; S00343, get v i,1 to v i,2 i-th coordinate conversion relationship when mapping; S00344, obtaining a coordinate conversion relationship when the CAD building map is mapped to the second SLAM navigation map according to the i-th coordinate conversion relationship.

2. The system of claim 1, wherein, In S004, the IDs of respective parking areas marked in the CAD building map are mapped to the second SLAM navigation map according to the coordinate conversion relationship, comprising: S0041, obtaining a set A=(A1, A2, …, A N ), A n is the nth parking area in the CAD building drawing, n is in the range of 1 to N; A n =(A n,1 ,A n,2 ,A n,3 ,A n,4 ), A n,1 , A n,2 , A n,3 and A n,4 are the coordinates of the first, second, third and fourth vertices of A n , respectively S0042, traversing A, using the coordinate conversion relationship on A n to obtain A' n = (A' n,1 , A' n,2 , A' n,3 , A' n,4 ), A' n,1 , A' n,2 , A' n,3 and A' n,4 are coordinates obtained by using the coordinate conversion relationship on A n,1 , A n,2 , A n,3 and A n,4 , respectively. S0043, set the ID of the region a n in the second SLAM navigation map to A n , set the ID of the region a n = (a n,1 , a n,2 , a n,3 , a n,4 ), a n,1 , a n,2 , a n,3 and a n,4 are respectively the coordinates of the first, second, third and fourth vertices corresponding to a n , a n,1 = A' n,1 , a n,2 = A' n,2 , a n,3 = A' n,3 , a n,4 = A' n,4 .

3. The system of claim 1, wherein, In S00342, the second SLAM navigation map is matched with l i The matched straight lines are obtained according to the length difference of each straight line in the second SLAM navigation map and the relative position relationship of each straight line in the second SLAM navigation map relative to the target garage center position. l i The matched straight lines are obtained according to the length difference of each straight line in the second SLAM navigation map and the relative position relationship of each straight line in the second SLAM navigation map relative to the target garage center position.

4. The system of claim 1, wherein, In S00344, the coordinate conversion relationship when the CAD building drawing is mapped to the second SLAM navigation map is an average coordinate conversion relationship of the i-th coordinate conversion relationship and a coordinate conversion relationship corresponding to other straight lines in the CAD building drawing except l i the i-th coordinate conversion relationship.

5. The system of claim 1, wherein, In S001, the first SLAM navigation map of the target garage is obtained by a laser radar.

Images