CN115127538A - Map updating method, computer equipment and storage device - Google Patents
Map updating method, computer equipment and storage device Download PDFInfo
- Publication number
- CN115127538A CN115127538A CN202210531792.XA CN202210531792A CN115127538A CN 115127538 A CN115127538 A CN 115127538A CN 202210531792 A CN202210531792 A CN 202210531792A CN 115127538 A CN115127538 A CN 115127538A
- Authority
- CN
- China
- Prior art keywords
- pose
- map data
- key frame
- map
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Instructional Devices (AREA)
Abstract
The application discloses a map updating method, computer equipment and a storage device. The method comprises the following steps: screening out at least one key frame from sensing data of equipment to be positioned; determining at least one constraint factor by utilizing at least one key frame, wherein the constraint factor comprises a reference description relation between the key frame and reference map data, and the reference map data is used for positioning the equipment to be positioned; the reference map data is updated with at least one constraint factor. According to the scheme, the stability of map updating can be improved.
Description
Technical Field
The present application relates to the field of positioning technologies, and in particular, to a map updating method, a computer device, and a storage apparatus.
Background
Along with the development of science and technology and the continuous increase of people's requirement to quality of life, intelligent robot appears in people's daily life gradually, for example cleans robot, industrial robot, service robot, the robot of carrying goods in the warehouse etc.. The intelligent robot is usually positioned in real time according to a map in the operation process, and an environment map around the position of the intelligent robot needs to be acquired, so that the walking route and the position of the robot are acquired, and the intelligent robot can be stably positioned under the condition that the environment is stable and unchanged.
However, in the actual use process, due to the continuous change of the environment or the space, that is, if the environment changes significantly, the difference between the actual situation in the environment and the information in the map is too large, and the map cannot adapt to the scene of the changed environment, which may result in the inability to position or the positioning error.
Disclosure of Invention
The technical problem that this application mainly solved is to provide a map updating method, computer equipment and storage device, can improve the stability of map updating.
In order to solve the above problem, a first aspect of the present application provides a map updating method, including: screening out at least one key frame from sensing data of equipment to be positioned; determining at least one constraint factor by utilizing at least one key frame, wherein the constraint factor comprises a reference description relation between the key frame and reference map data, and the reference map data is used for positioning the equipment to be positioned; the reference map data is updated with at least one constraint factor.
In order to solve the above problem, a second aspect of the present application provides a computer device, which includes a memory and a processor coupled to each other, wherein the memory stores program data, and the processor is configured to execute the program data to implement any step of the above map updating method.
In order to solve the above problem, a third aspect of the present application provides a storage device storing program data executable by a processor, the program data being for implementing any one of the steps of the above map updating method.
According to the scheme, at least one key frame is screened out from the sensing data of the equipment to be positioned, then at least one constraint factor is determined by utilizing the reference description relationship between the at least one key frame and the reference map data, the reference map data is updated by utilizing the at least one constraint factor, the reference description relationship between the key frame and the reference map data is comprehensively considered, the updating stability of the reference map data can be improved, the updated reference map data is used for positioning, and the accuracy of positioning the equipment to be positioned can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the present application, the drawings required in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flowchart of an embodiment of a map updating method of the present application;
FIG. 2 is a schematic flowchart of a first embodiment of step S12 in FIG. 1 of the present application;
FIG. 3 is a schematic flow chart illustrating a second embodiment of step S12 in FIG. 1;
FIG. 4 is a schematic flow chart of a third embodiment of step S12 in FIG. 1 of the present application;
FIG. 5 is a flowchart illustrating an embodiment of step S13 of FIG. 1;
FIG. 6 is a schematic structural diagram of an embodiment of a pose factor graph model of the present application;
FIG. 7 is a schematic structural diagram of an embodiment of a map updating apparatus of the present application;
FIG. 8 is a schematic block diagram of an embodiment of a computer apparatus of the present application;
FIG. 9 is a schematic structural diagram of an embodiment of a memory device according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first" and "second" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.
The present application provides the following examples, each of which is specifically described below.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a map updating method according to an embodiment of the present application. The method may comprise the steps of:
s11: and screening out at least one key frame from the sensing data of the equipment to be positioned.
The map updating method can be used for map updating and positioning of devices to be positioned (such as movable devices), such as transport vehicles, automobiles and the like, but is not limited thereto. As an example, the map updating method of the present application may be applied to an Automated Guided Vehicle (AGV), which is a transport Vehicle equipped with an electromagnetic or optical automatic navigation device, capable of traveling along a predetermined navigation path, and having safety protection and various transfer functions. In the navigation process of the AGV trolley, the map can be updated, so that the AGV trolley can be positioned through the updated map.
The device to be positioned can gather sensing data through multiple sensor in the operation process, wherein, multiple sensor can set up on the device to be positioned, also can set up in can treating the other places that the positioning device was gathered and carry out data acquisition, and this application does not do the restriction to this.
In some embodiments, the acquired sensory data may include. The device to be positioned can be provided with sensors such as a laser radar, a speedometer and a camera, and in the operation process of the device to be positioned, the sensors such as a 2D laser radar, the speedometer and the camera can be adopted to continuously acquire laser point cloud data, speedometer data, camera images and the like. The laser point cloud data comprises sampling point coordinates and reflection intensity of scanning of the environment where the equipment to be positioned is located. The odometer data can be speed information, mileage information and the like of the equipment to be positioned recorded by the odometer, and the relative pose change of the equipment to be positioned can be calculated by integrating the speed information of the continuous multi-frame odometer. The camera image may be used to detect two-dimensional codes or textures in the environment in which the device to be positioned is located.
In some embodiments, the sensing data with the positioning device may be acquired at preset intervals or at a preset rate, each type of sensing data acquired by the sensor has a timestamp, the sensing data of each frame may be determined based on the acquired timestamp of the sensing data of the device to be positioned, and the like, that is, the sensing data of the same timestamp may be used as the sensing data of the same frame.
Because the processing of the laser point cloud data is more complex, each frame of laser point cloud is not processed, but a key frame is screened. When at least one frame of key frame is screened, the sensing data comprises point cloud data acquired at a plurality of moments respectively, the point cloud data acquired at each moment can be used as one frame, and the point cloud data acquired by the equipment to be positioned at the moment when the relative pose of the equipment to be positioned and the previous key frame meets the requirement is selected from the sensing data and used as a new key frame. The point cloud data of the first frame or the point cloud data of the first moment may be used as a previous key frame, and in one key frame, sensing data such as point cloud data, odometer data, camera image, and the like may be included.
Wherein, relative position appearance satisfies the requirement and includes: the relative pose is larger than a preset pose threshold value, and the relative pose comprises a relative distance or a relative angle. Specifically, the speed data of the odometer may be integrated from the key frame of the previous laser point cloud data, a relative distance of the device to be positioned with respect to the motion of the previous key frame and a relative angle of the device to be positioned with respect to the motion of the previous key frame are obtained, and when the relative distance is greater than a preset distance threshold or the relative angle is greater than a preset angle threshold, the laser point cloud data acquired at the current time may be regarded as the latest key frame. And if the relative pose does not meet the requirements, discarding the laser point cloud data acquired at the current moment.
S12: and determining at least one constraint factor by utilizing the at least one key frame, wherein the constraint factor comprises a reference description relation between the key frame and reference map data, and the reference map data is used for positioning the equipment to be positioned.
In some embodiments, before step S11, that is, before the device to be positioned is operated, reference map data may be constructed first, and reference map data of the device to be positioned may be obtained. The reference map data may comprise a priori map data and local map data, the a priori map data being a description of an initial state of the environment in which the device to be located is constructed.
In constructing the prior map data, the prior map data may include a contour map and a landmark map of the environment. The contour map may be in the form of an occupancy grid map, a point cloud map, an NDT (Normal distribution Transform) map, or the like (e.g., a form commonly used in the AGV field). The road sign map may contain information such as two-dimensional codes, ground textures, reflective columns, reflective plates, and the like. The form of the constructed prior map data and the road sign can be selected according to specific equipment to be positioned and an application scene, and the application is not limited to this.
In some embodiments, a laser SLAM (Simultaneous Localization And Mapping) algorithm may be used to construct prior map data of a device to be located, And when constructing a contour map of an environment of the prior map data, a recognizable landmark map may also be synchronously calibrated. The SLAM algorithm is not limited in this application, and may be, for example, Cartographer, Karto-SLAM, or the like.
Before the equipment to be positioned runs the positioning system, the current pose of the equipment to be positioned needs to be initialized. And acquiring an initial pose P (x, y, theta) of the equipment to be positioned at present on the prior map data, wherein the initial pose P represents a rectangular coordinate and a yaw angle of the equipment to be positioned under a map reference system respectively.
In some embodiments, when the current pose of the device to be positioned is obtained, a rough position range of the device to be positioned under a map reference system can be manually given, a search algorithm is executed to find the pose with the highest matching degree between the current frame laser point cloud data and the contour map, and the pose with the highest matching degree is taken as the initial pose of the device to be positioned.
In some embodiments, when the initial pose of the device to be positioned is obtained, landmarks, such as two-dimensional codes, textures, reflective columns, reflectors, and the like, are calibrated in advance in the environment, and the landmarks are provided with the pose of the landmarks in the prior map data. The method comprises the steps of detecting a landmark in an environment through a device to be positioned, and matching the landmark with a pre-calibrated landmark to calculate the initial pose of the device to be positioned under a map reference system.
After the initial pose of the equipment to be positioned is obtained, local map data can be constructed. The local map data and the contour map in the prior map data are kept consistent in form, that is, any form of an occupation grid map, a point cloud map, an NDT map and the like can be adopted.
When the local map data is constructed, the point cloud data used for the initialized initial pose can be used as a first key frame, and the key frame is inserted into the local map data to update the local map data. The updating method may be, for example, Cartographer, Karto-slam, or the like, which is not limited in this application.
In some embodiments, the a priori map data and the local map data may be used to locate a device to be located.
In some embodiments, a reference description relationship between at least one keyframe and reference map data may be utilized to derive at least one constraint factor. The at least one constraint factor may include an a priori map constraint factor between the key frame and the a priori map data, and a local map constraint factor between the key frame and the local map data. When the at least one key frame comprises a plurality of key frames, the constraint factor may further comprise an inter-frame constraint factor.
The prior map constraint factor can be obtained by utilizing the reference description relation between the key frame and the prior map data; obtaining a local map constraint factor by using a reference description relation between the key frame and the local map data; and obtaining an inter-frame constraint factor by using the reference description relation between the key frames. The process can be referred to in particular in the following examples.
S13: updating the reference map data with at least one constraint factor.
A pose factor graph model can be constructed based on at least one constraint factor, and the pose factor graph model comprises at least one constraint factor corresponding to at least one key frame, reference map data and pose variables to be solved of the key frame. And solving the pose factor graph model to obtain a solution of the pose variable to be solved of the key frame, so that the reference map data is updated by using the solution of the pose variable to be solved of the key frame. The prior map data can be updated, so that the equipment to be positioned can be positioned by utilizing the updated prior map data.
In the embodiment, at least one key frame is screened from the sensing data of the equipment to be positioned, at least one constraint factor is determined by utilizing the reference description relationship between the at least one key frame and the reference map data, the reference map data is updated by utilizing the at least one constraint factor, and the reference description relationship between the key frame and the reference map data is comprehensively considered, so that the updating stability of the reference map data can be improved, the updated reference map data is used for positioning, and the positioning accuracy of the equipment to be positioned can be improved.
In some embodiments, referring to fig. 2, in the step S12, the at least one key frame may include a plurality of key frames, and the inter-frame constraint factor between the key frames may be obtained. The process may include the steps of:
s1211: performing preset relationship processing on the mileage information between at least two key frames based on the sensing data corresponding to the plurality of key frames to obtain relationship mileage information; the sensing data is environmental data acquired by at least one sensor of the equipment to be positioned.
The environmental data acquired by at least one sensor of the equipment to be positioned is also acquired to obtain sensing data, and the sensor can comprise a laser radar, a speedometer, a camera and the like and can contain sensing data such as point cloud data, speedometer data, camera images and the like.
The preset relationship processing of the mileage information between the current key frame and the previous key frame, such as integral processing of the mileage information, may be obtained, and the obtained integral-calculated mileage information may be used as the relationship mileage information of the current key frame.
S1212: and taking the relation mileage information as an interframe constraint factor of the equipment to be positioned.
After obtaining the relationship mileage information corresponding to the current key frame, the relationship mileage information can be used as an interframe constraint factor of the equipment to be positioned in the current key frame, wherein the expression of the interframe constraint factor is f odo_i ＝[x odo_i y odo_i θ odo_i ] T ，x odo_i 、y odo_i 、θ odo_i Respectively, the rectangular coordinates and yaw angle in the map reference system.
In some embodiments, referring to fig. 3, in the step S12, the reference map data includes local map data, and a local map constraint factor between the key frame and the local map data may be obtained. The process may include the steps of:
s1221: the keyframes are registered with the local map data.
The point cloud data of the key frame and the local map data can be registered, a point cloud registration method can be adopted for registration, the essence of the point cloud registration is that the point cloud data measured in different coordinate systems are subjected to coordinate system transformation to obtain an integral data model, and a rotation matrix and a translation vector of the coordinate transformation are obtained through solving, so that the distance between the three-dimensional data measured in two visual angles is the minimum after the coordinate transformation.
Each key frame is used as a current key frame, and the method for registering the current key frame and the local map data is not limited in the application, for example, a scan matching method used in Cartographer, Karto-salm and the like can be adopted, and a registration result is obtained after registration, wherein the registration result includes a rotation matrix and a translation vector of a pose between the current key frame and the local map data.
S1222: and acquiring a relative pose transformation relation between the key frame and the local map data based on the registration result to serve as a local map constraint factor between the key frame and the local map data.
After the current key frame is registered with the local map data, the pose P of the current key frame is obtained i Pose P with local map data submap Relative pose transformation relation T between i ＝{x i ,y i ,θ i }. Therefore, the relative pose transformation relationship can be used as a local map constraint factor between the current key frame and the local map data, wherein the expression of the local map constraint factor can be expressed as: f. of submap_i ＝[x submap_i y submap_i θ submap_i ] T ，x submap_i 、y submap_i 、θ submap_i Respectively, the rectangular coordinates and yaw angle in the map reference system.
In some embodiments, the local map data of the device to be located may be updated by using the local map constraint factor, that is, the point cloud data of the current key frame may be inserted into the local map data, so as to update the local map data. The updating method includes, for example, a contour map updating method used in Cartographer and Karto-slam, and the updating method may be selected based on a form of local map data, which is not limited in this application.
In some embodiments, the range may be set on the size (or area) of the local map data, the number of frames of the key frame. When the size (or area) of the local map data exceeds the preset size (or area) and the number of the key frames exceeds the preset number of frames, the key frame which is added into the local map data first can be deleted from the local map data, or the point cloud data of the key frame in the local map data can be deleted according to the time sequence of the time stamp of the key frame.
In some embodiments, referring to fig. 4, in the step S12, the reference map data includes a priori map data, and a priori map constraint factor between the keyframe and the a priori map data may be obtained. The specific implementation process can comprise the following steps:
s1231: at least one marker is detected from the keyframes.
The method comprises the steps of setting a marker in advance in an operating environment of equipment to be positioned, and setting a calibration pose of the marker for the marker, wherein the pose can be a pose in a world coordinate system or a pose in a prior map coordinate system. When the equipment to be positioned operates, the sensor can collect sensing data to detect and identify the marker.
The marker comprises at least one of a two-dimensional code, a texture and a light-reflecting object (such as a light-reflecting plate and a light-reflecting column). For example, a camera may be used to detect a two-dimensional code from an image, a camera may be used to identify ground texture from an image, a laser may be used to detect reflective objects, and the like.
In some embodiments, the device to be positioned or another terminal may also be used to detect the markers for the keyframes acquired by the sensor, which is not limited herein.
If the presence of at least one marker is detected from the key frame, the following step S1232 is performed.
If it is detected from the key frame that the marker is not present, the following step S1233 is executed.
S1232: and if the marker is detected to exist, determining a prior map constraint factor based on the pose of the marker of the key frame in the prior map data.
If the marker is detected to exist, the relative marker pose of the equipment to be positioned and the marker can be obtained due to the fact that the marker is provided with the calibration pose. If the two-dimensional code is detected as the marker, the relative pose of the equipment to be positioned relative to the two-dimensional code can be calculated; if the texture of the marker is detected, the relative pose of the equipment to be positioned and the texture can be obtained; if the reflecting object exists in the marker, the relative pose of the equipment to be positioned and the reflecting object can be obtained through a triangulation positioning method. The relative pose obtained by each marker can be respectively used as the relative calibration pose of the device to be positioned and each marker, where the relative calibration pose with respect to the markers can be expressed as:
respectively, the rectangular coordinates and the yaw angle under the map reference system.
In the above process, after the relative marker pose of the device to be positioned relative to the marker is obtained, the relative marker pose can be obtained (i.e. the pose T in the prior map data is calibrated in advance) landmark ＝[x landmark y landmark θ landmark ] T ) And the calibration pose of the marker is obtained, and the prior pose of the equipment to be positioned in the prior map data or the prior pose of the equipment to be positioned in the world coordinate system is obtained, so that the prior pose can be used as a prior map constraint factor.
In some embodiments, the a priori map constraint factor may be expressed as:
wherein x is map_i 、y map_i 、θ map_i Individual watchRectangular coordinates and yaw angle shown in the map reference frame.
S1233: and if no marker is detected, determining a prior map constraint factor based on a response value of the equipment to be positioned registered between the prior map data.
If no marker is detected, the point cloud data of the key frame and the prior map data are registered, and the registration process may refer to the process of registering the key frame and the local map data, which is not described herein again. After registration, a pose transformation relation between a key frame of the equipment to be positioned and the prior map data can be obtained, so that a registration pose of the equipment to be positioned in the prior map data is obtained, and the registration pose can be expressed as follows: p i ＝[x map_i y map_i θ map_i ] T ，x map_i 、y map_i 、θ map_i Respectively, the rectangular coordinates and yaw angle in the map reference system.
The point cloud data of the key frame is projected to the prior map data by utilizing the registration pose, namely the point cloud data of the current key frame is projected to the reference (or the world reference system) of the prior map data to obtain the projection pose, so that the registration response value between the point cloud data of the key frame and the prior map data can be calculated. For example, the response value may be obtained by calculating the response value in Cartographer and Karto-slam, which is not limited in this application.
And if the response value is larger than a preset response threshold value, taking the registration pose as a prior map constraint factor.
In some embodiments, if no marker is detected in the key frame and the response value is not greater than the preset response value, the prior map constraint factor of the key frame is not obtained, that is, the prior map constraint factor of the key frame is not added.
In the embodiment, multiple markers are used as landmark information, and when one of the markers cannot be detected, the pose can be identified by detecting other markers, so that a key frame which is registered with the prior map data and has a high response value is used as a natural landmark, and the adaptability is high.
In some embodiments, referring to fig. 5, the updating the reference map data with at least one constraint factor in the step S13 may include the following steps:
s131: and establishing a pose factor graph model based on at least one constraint factor and reference map data, wherein the pose factor graph model comprises at least one constraint factor corresponding to a plurality of key frames, reference map data and pose variables to be solved of the key frames.
In some embodiments, the at least one key frame includes a plurality of key frames, and after the at least one key frame is screened out to obtain the at least one constraint factor, the pose factor graph model can be established based on information such as the constraint factor and reference map data.
Referring to fig. 6, the pose factor graph model includes pose variables to be solved for the keyframe, at least one constraint factor, and reference map data. Wherein, the pose variables to be solved of the key frame comprise local map pose variables P submap And keyframe pose variable { P i ,P i-1 ,…, i-N+1 }. The obtained constraint factors can be added into a pose factor graph model, and at least one constraint factor can comprise an inter-frame constraint factor { f ] between adjacent key frames odo_i ,f odo_i-1 ,…,f odo_i-N+2 A local map constraint factor { f) between the key frame and the local map data submap_i ,f submap_i-1 ,…,f submap_i-N+2 A priori map constraint factor { f) between keyframes and a priori map data map_1 ,f map_2 ,…,f map_k }。
In some embodiments, the number of keyframes in the pose factor map model may be controlled in a sliding window manner. When the number of key frames in the pose factor graph model exceeds a preset number of frames N (or the number of pose variables to be solved of the key frames exceeds a preset number of frames N, where N is a positive integer), the key frame added earliest in the pose factor graph model, that is, the key frame with the earliest timestamp, may be deleted. The number of key frames in the pose factor graph model does not exceed the preset frame number.
In some embodiments, the pose factor graph model may be initialized when the first keyframe is acquired. Adding local map data, a key frame pose variable corresponding to the first key frame, prior map data, a local map constraint factor between the first key frame and the local map data, and a prior map constraint factor between the first key frame and the prior map data into the pose factor map model.
In some embodiments, when a second key frame is obtained, a constraint factor and the like corresponding to the second key frame may be added to the pose factor graph model, and an inter-frame constraint factor between the first key frame and the second key frame may also be added this time.
In some embodiments, the pose factor graph model performs an optimization solution for each key frame added to the pose factor graph model, that is, performs the following step S132 for each key frame added to the pose factor graph model.
S132: and optimizing and solving the pose factor graph model to obtain key frame solving poses and local map poses corresponding to the plurality of key frames.
After the pose factor graph model is constructed, the pose factor graph model is optimized and solved to obtain a solution of pose variables to be solved of key frames in the pose factor graph model, namely, the pose of a local map and the pose solved by the key frames corresponding to each key frame.
In some embodiments, the pose factor graph model may be further represented by a function, and the process of optimizing the pose factor graph model may be represented as:
in the above formula, P i-N+1 ,…,P i Representing pose variables to be solved, P, of key frames in a pose factor graph model submap And representing the local map pose variables to be solved in the pose factor graph model. P k Representing the pose of the Kth key frame; p submap Representing local map data; p map Representing a priori map data;
representing an interframe constraint factor between the Kth key frame and the K-1 key frame; f. of submap_k Representing a local map constraint factor between the Kth key frame and the local map data; f. of map_k Representing a prior map constraint factor between the kth key frame and the prior map data.
Solving the formula to obtain a key frame solving pose { P) corresponding to each key frame (such as N key frames) i ,P i-1 ,…,P i-N+1 And the local map pose.
S133: and updating the reference map data based on the pose solving of the key frames corresponding to the plurality of key frames.
When updating the reference map data (such as the prior map data), it is necessary to determine whether a preset update condition for updating the prior map data is satisfied, and the prior map data is updated only when the preset update condition is satisfied.
Specifically, pose variables { P ] to be solved at a first preset number N of key frames can be determined i ,P i-1 ,…,P i-N+1 And judging whether the pose variables to be solved of at least a second preset number M of key frames exist and are connected with the prior map data by establishing factors, namely, M key frames exist in the pose factor map model and prior map data by establishing factor connection. Wherein M is a positive integer less than or equal to N.
If the key frame to-be-solved pose variables of the M key frames exist and are in factor connection with the prior map data, marking the key frame solving pose of the M key frames in factor connection as
And judging whether the solving poses of the key frames corresponding to the M key frames with the second preset number meet the preset updating condition. Wherein, the preset updating condition comprises: whether the residual error between the transformed value and the prior value is less than a preset updating threshold value or not; the conversion value is offSolving a pose transformation relation between the pose and the prior map data by using the key frames corresponding to the key frames; the prior value is a prior map constraint factor corresponding to the key frame.
Specifically, the pose transformation relation between the pose and the prior map data of key frames corresponding to M key frames is obtained, and transformation values are obtained
Using the prior map constraint factors corresponding to the M key frames as prior values { f } map_1 ,f map_2 ,…,f map_m }. Obtaining a residual between a transformed value and a prior value
Wherein the residual error comprises rectangular coordinates and yaw angle, i.e.
Determining residual error
If the difference is smaller than the preset update threshold, it is determined whether the rectangular coordinate and the yaw angle in each residual are smaller than the preset update threshold (ths) Δx 、ths Δy 、ths Δθ ) The method comprises the following steps:
and if the residual errors corresponding to the M key frames are all smaller than a preset updating threshold value and the key frame solving poses of the M key frames meet a preset updating condition, updating the prior map data by using the key frame solving poses corresponding to the N key frames of the first preset number.
The method of updating the prior map data may be determined based on a map form of the prior map data. For example, when the map form of the prior map data is the occupation grid map, the occupation probability of the grid can be updated by adopting a probability updating method; when the map form of the prior map data is a point cloud map, the key frame solving poses corresponding to the N key frames can be directly projected to a map reference system (such as a world reference system) and combined into the point cloud data of the prior map data; and when the map form of the prior map data is an NDT map, projecting the point cloud data of the N key frames to a map reference system and then updating the NDT value of the corresponding block.
The updated prior map data can be used for positioning the equipment to be positioned, and the map updating method in the step can be continuously executed until the equipment to be positioned does not have acquired sensing data or the positioning process is terminated.
In the embodiment, the local map constraint factors, the prior map constraint factors and the interframe constraint factors between adjacent key frames of the key frames are uniformly added into the pose factor graph model for optimization solution, so that the pose can be solved by utilizing the environment contour map in the area with little environment change, the pose can be solved by utilizing the markers of the artificial signposts in the area with obvious environment change, in addition, the pose can be accurately calculated by utilizing the local map information in the area with obvious environment change, the pose can be solved by utilizing the local map in the area with obvious environment change and no markers, and the environment adaptability is strong.
In addition, whether a priori map constraint factor is added or not is judged by utilizing the marker or key frame matching response value so as to judge whether the priori map data are updated or not. And when the matching response value of the marker or the key frame and the prior map data is high, the prior map constraint factor is added to update the prior map data, so that the prior map data is always correctly updated, the positioning precision of subsequent equipment to be positioned is improved, and the stability is ensured. In addition, when the key frame meets the preset updating condition, the prior map data is updated, so that the map can be always updated stably, and the map can be prevented from being updated mistakenly due to the fact that the position and posture of a certain key frame is calculated mistakenly.
With the above embodiments, the present application provides a map updating apparatus. Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a map updating apparatus according to the present application. The map updating apparatus 70 comprises a key frame module 71, a constraint factor module 72 and an update module 73.
The keyframe module 71 is configured to filter out at least one keyframe from the sensed data of the device to be located.
The constraint factor module 72 is configured to determine at least one constraint factor by using at least one key frame, where the constraint factor includes a reference description relationship between the key frame and reference map data, and the reference map data is used for locating a device to be located.
The updating module 73 is configured to update the reference map data with at least one constraint factor.
The specific implementation of this embodiment can refer to the implementation process of the above embodiment, and is not described herein again.
With reference to fig. 8, fig. 8 is a schematic structural diagram of an embodiment of a computer device according to the present application. The computer device 80 comprises a memory 81 and a processor 82, wherein the memory 81 and the processor 82 are coupled to each other, the memory 81 stores program data, and the processor 82 is configured to execute the program data to implement the steps of any of the above-described map updating methods.
In the present embodiment, the processor 82 may also be referred to as a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip having signal processing capabilities. The processor 82 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor 82 may be any conventional processor or the like.
The specific implementation of this embodiment can refer to the implementation process of the above embodiment, and is not described herein again.
For the method of the above embodiment, it can be implemented in the form of a computer program, so that the present application provides a storage device, please refer to fig. 9, where fig. 9 is a schematic structural diagram of an embodiment of the storage device of the present application. The storage device 90 stores therein program data 91 executable by a processor, the program data 91 being executable by the processor to implement the steps of any of the embodiments of the map updating method described above.
The specific implementation of this embodiment can refer to the implementation process of the above embodiment, and is not described herein again.
The storage device 90 of the present embodiment may be a medium that can store the program data 91, such as a usb disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the program data 91, and the server may transmit the stored program data 91 to another device for operation, or may operate the stored program data 91 by itself.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is only one type of logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a storage device, which is a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing an electronic device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (14)
1. A map updating method, the method comprising:
screening out at least one key frame from sensing data of equipment to be positioned;
determining at least one constraint factor by using the at least one key frame, wherein the constraint factor comprises a reference description relation between the key frame and reference map data, and the reference map data is used for positioning the equipment to be positioned;
updating the reference map data with the at least one constraint factor.
2. The method of claim 1, wherein the reference map data comprises local map data, and wherein determining at least one constraint factor using the at least one keyframe comprises:
registering the keyframe with the local map data;
and acquiring a relative pose transformation relation between the key frame and the local map data based on the registration result to serve as a local map constraint factor between the key frame and the local map data.
3. The method of claim 1, wherein the reference map data comprises a priori map data, and wherein determining at least one constraint factor using the at least one keyframe comprises:
detecting at least one marker from the keyframes;
if the marker exists, determining a priori map constraint factor based on the pose of the marker of the key frame in the priori map data;
and if the marker does not exist, determining a prior map constraint factor based on a response value of the equipment to be positioned in registration between the prior map data.
4. The method of claim 3, wherein determining an a priori map constraint factor based on poses of the markers of the keyframes on the a priori map data comprises:
acquiring a relative mark pose of the equipment to be positioned and the marker, wherein the marker is provided with a calibration pose;
and acquiring a prior pose of the equipment to be positioned in the prior map data by using the relative marker pose and the calibration pose of the marker, and taking the prior pose as the prior map constraint factor.
5. The method of claim 3, wherein determining a prior map constraint factor based on a response value of the device to be positioned registered between the prior map data comprises:
registering the key frame with the prior map data to obtain a registration pose of the equipment to be positioned in the prior map data;
projecting the keyframe to the prior map data with the registration pose to obtain a registered response value between the keyframe and the prior map data;
and if the response value is larger than a preset response threshold value, taking the registration pose as the prior map constraint factor.
6. The method of claim 3,
the marker includes: at least one of two-dimensional code, texture, and reflective object.
7. The method of claim 1, wherein the at least one key frame comprises a plurality of key frames; the obtaining at least one constraint factor by using the at least one key frame includes:
performing preset relationship processing on the mileage information between at least two key frames based on sensing data corresponding to the key frames to obtain relationship mileage information, wherein the sensing data is environmental data acquired by using at least one sensor of the equipment to be positioned;
and taking the relation mileage information as an interframe constraint factor of the equipment to be positioned.
8. The method of claim 1, wherein the at least one key frame comprises a plurality of key frames; the updating the reference map data with the at least one constraint factor includes:
establishing a pose factor graph model based on the at least one constraint factor and the reference map data, wherein the pose factor graph model comprises the at least one constraint factor corresponding to a plurality of key frames, the reference map data and pose variables to be solved of the key frames;
optimizing and solving the pose factor graph model to obtain key frame solving poses and local map poses corresponding to the key frames;
and updating the reference map data based on the pose solving of the key frames corresponding to the plurality of key frames.
9. The method of claim 8, wherein the updating the reference map data based on the keyframe solution poses corresponding to the plurality of keyframes comprises:
judging whether to-be-solved pose variables of key frames not less than a second preset number exist in to-be-solved pose variables of key frames of a first preset number and are connected with a priori map data establishment factor;
if yes, judging whether key frame solving poses corresponding to the key frames of the second preset number meet preset updating conditions;
and if the preset updating condition is met, solving the pose by using the key frames corresponding to the key frames with the first preset number, and updating the prior map data.
10. The method of claim 9,
the preset updating condition comprises the following steps: whether the residual error between the transformed value and the prior value is less than a preset updating threshold value or not;
wherein the transformation value is a pose transformation relation between a pose of a keyframe corresponding to the keyframe and the prior map data; and the prior value is a prior map constraint factor corresponding to the key frame.
11. The method of claim 1, wherein the at least one restriction factor comprises a local map restriction factor; the method further comprises the following steps:
and updating the local map data of the equipment to be positioned by using the local map constraint factor.
12. The method of claim 1, wherein the sensing data comprises point cloud data acquired at a plurality of respective times; screening out at least one key frame from the sensing data of the equipment to be positioned, wherein the screening out at least one key frame comprises the following steps:
and selecting the point cloud data acquired by the equipment to be positioned at the moment when the relative pose of the equipment to be positioned and the previous key frame meets the requirement from the sensing data as a new key frame.
13. A computer device comprising a memory and a processor coupled to each other, the memory having stored therein program data for execution by the processor to perform the steps of the method of any one of claims 1 to 12.
14. A storage device, characterized by program data stored therein which can be executed by a processor for carrying out the steps of the method according to any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531792.XA CN115127538A (en) | 2022-05-16 | 2022-05-16 | Map updating method, computer equipment and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531792.XA CN115127538A (en) | 2022-05-16 | 2022-05-16 | Map updating method, computer equipment and storage device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115127538A true CN115127538A (en) | 2022-09-30 |
Family
ID=83375988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210531792.XA Pending CN115127538A (en) | 2022-05-16 | 2022-05-16 | Map updating method, computer equipment and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115127538A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117451035A (en) * | 2023-12-25 | 2024-01-26 | 江苏中科重德智能科技有限公司 | Method and system for self-adaptively and automatically updating map by laser slam |
-
2022
- 2022-05-16 CN CN202210531792.XA patent/CN115127538A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117451035A (en) * | 2023-12-25 | 2024-01-26 | 江苏中科重德智能科技有限公司 | Method and system for self-adaptively and automatically updating map by laser slam |
| CN117451035B (en) * | 2023-12-25 | 2024-02-27 | 江苏中科重德智能科技有限公司 | Method and system for self-adaptively and automatically updating map by laser slam |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018142900A1 (en) | Information processing device, data management device, data management system, method, and program | |
| KR102399630B1 (en) | Method and apparatus for determining position and orientation of bucket of excavator | |
| CN111220993B (en) | Target scene positioning method and device, computer equipment and storage medium | |
| CN112734852B (en) | Robot mapping method and device and computing equipment | |
| WO2019175286A1 (en) | Image annotation | |
| WO2018125939A1 (en) | Visual odometry and pairwise alignment for high definition map creation | |
| Siegemund et al. | A temporal filter approach for detection and reconstruction of curbs and road surfaces based on conditional random fields | |
| CN110462343A (en) | The automated graphics for vehicle based on map mark | |
| CN112667837A (en) | Automatic image data labeling method and device | |
| CN108022264B (en) | Method and equipment for determining camera pose | |
| CN112197770A (en) | Robot positioning method and positioning device thereof | |
| CN108388244A (en) | Mobile-robot system, parking scheme based on artificial landmark and storage medium | |
| CN111324145B (en) | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium | |
| CN108332752B (en) | Indoor robot positioning method and device | |
| JP6593088B2 (en) | Vehicle position estimation apparatus and program | |
| KR102174729B1 (en) | Method and system for recognizing lane using landmark | |
| JP2018077162A (en) | Vehicle position detection device, vehicle position detection method and computer program for vehicle position detection | |
| CN112805766A (en) | Apparatus and method for updating detailed map | |
| CN114325634A (en) | Method for extracting passable area in high-robustness field environment based on laser radar | |
| CN115127538A (en) | Map updating method, computer equipment and storage device | |
| Krüger | Robust and efficient map-to-image registration with line segments | |
| CN116643291A (en) | SLAM method for removing dynamic targets by combining vision and laser radar | |
| CN112258391B (en) | Fragmented map splicing method based on road traffic marking | |
| CN115345944A (en) | Method and device for determining external parameter calibration parameters, computer equipment and storage medium | |
| CN112781591A (en) | Robot positioning method and device, computer readable storage medium and robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |