CN115795082A - Distributed pose optimization method and system based on graph algorithm - Google Patents
Distributed pose optimization method and system based on graph algorithm Download PDFInfo
- Publication number
- CN115795082A CN115795082A CN202211373066.6A CN202211373066A CN115795082A CN 115795082 A CN115795082 A CN 115795082A CN 202211373066 A CN202211373066 A CN 202211373066A CN 115795082 A CN115795082 A CN 115795082A
- Authority
- CN
- China
- Prior art keywords
- tracks
- pose
- graph
- distributed
- pose optimization
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Navigation (AREA)
Abstract
The invention provides a distributed pose optimization method and a distributed pose optimization system based on a graph algorithm, wherein the method comprises the following steps: acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area; defining a connection vector between every two tracks according to whether a matching relation exists between every two tracks; constructing a connection graph between all tracks based on the connection vector between every two tracks; dividing the connection graph into a plurality of completely independent subgraphs by using a subgraph division algorithm in a graph theory; and performing pose optimization on each sub-graph to obtain an optimized pose estimation. According to the invention, the connection graph is constructed according to the matching relation among the tracks, the whole connection graph is divided according to the connection relation among the tracks to obtain a plurality of sub-graphs, and the pose optimization is carried out on the basis of each sub-graph to further obtain the global pose optimization, so that the distributed pose optimization can be realized, and the speed and the efficiency of the pose optimization are improved.
Description
Technical Field
The invention relates to the field of high-precision map production, in particular to a distributed pose optimization method and system based on a map algorithm.
Background
In the crowdsourcing composition system, crowdsourcing vehicles run on roads and collect information related to the roads, including current positions of the vehicles, ground elements, traffic signboards and the like, and then upload data required by composition to a cloud terminal for composition after certain processing. In order to fuse the data collected by multiple vehicles, the tracks need to be optimized to meet the consistency between them, which is the pose graph optimization in SLAM. The basic idea is to take the pose at each moment as a node in the pose graph, take the observation (constraint) between the poses as an edge between the poses, give a reasonable initial value for each pose node, and then optimize the constructed pose graph by adopting an iterative method until convergence. However, the pose graph optimization in the crowd-sourced scene has a problem that the data size is too large to solve in an acceptable time, so the optimization problem must be decomposed to perform distributed solution.
Disclosure of Invention
The invention provides a distributed pose optimization method and system based on a graph algorithm, aiming at the technical problems in the prior art, and the distributed pose optimization method and system can realize distributed pose optimization.
According to a first aspect of the invention, a distributed pose optimization method based on a graph algorithm is provided, and the method comprises the following steps:
acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area;
defining a connecting vector between every two tracks according to whether a matching relation exists between every two tracks;
constructing a connection graph among all tracks on the basis of connection vectors between every two tracks;
dividing the connection graph into a plurality of completely independent subgraphs by using a subgraph division algorithm in a graph theory;
and performing pose optimization on each sub-graph to obtain an optimized pose estimation.
On the basis of the technical scheme, the invention can be improved as follows.
Optionally, the defining a connection vector between every two tracks according to whether a matching relationship exists between every two tracks includes:
and judging whether the two tracks have the same line section, if so, setting the connection vector between the two tracks as 1, and if not, setting the connection vector between the two tracks as 0 if not, and otherwise, judging whether the two tracks have the same line section.
Optionally, the determining whether there is the same line segment on the two tracks, and if there is the same line segment on the two tracks, a matching relationship exists between the two tracks, including:
judging whether the two tracks have the same line section or not, if so, determining whether a matching relation exists between the two tracks according to the length of the same line section, and if the length of the same line section is greater than a set length threshold, determining that the matching relation exists between the two tracks; otherwise, there is no matching relationship between the two tracks.
Optionally, performing pose optimization on each sub-graph to obtain an optimized pose trajectory includes:
constructing pose optimization problem description based on each subgraph:
wherein, the mapping vehicle has N position and posture estimations in one acquisition, and the N position and posture estimations are P i ，i∈[1，2，…，N]In one trace, there are M GPS signals, denoted as g j ，j∈[1，2，…，M]And obtaining a pose measurement value between discontinuous poses through loop detection or matching, and recording the pose measurement value as L ij Abs (i-j) > 1, and the odometer measurement between successive poses is recorded as O ij ，i+
1=j, note G k Projection coordinates, P, for latitude and longitude j，loc Is a Cartesian coordinate component in pose, superscript l g ，lh，g、h∈[1，2，…，K]Distinguishing tracks of different laps, wherein I is a set of tracks of all laps;
and obtaining the optimized pose estimation by adopting an iteration method based on the pose optimization problem description.
Optionally, performing pose optimization on each sub-graph to obtain an optimized pose estimation includes:
and storing each sub-image information in a distributed optimizer, and performing pose optimization on each sub-image information based on the distributed optimizer to obtain an optimized pose estimation.
According to a second aspect of the invention, a distributed pose optimization system based on a graph algorithm is provided, which comprises:
the acquisition module is used for acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area;
the defining module is used for defining a connecting vector between every two tracks according to whether a matching relation exists between every two tracks;
the construction module is used for constructing a connection graph between all tracks based on the connection vector between every two tracks;
the partitioning module is used for partitioning the connection graph into a plurality of completely independent subgraphs by utilizing a subgraph partitioning algorithm in a graph theory;
and the optimization module is used for optimizing the pose of each sub-graph to obtain the optimized pose estimation.
Optionally, the optimization module is a distributed optimizer and configured to store each piece of sub-graph information in a distributed manner, and perform pose optimization on each piece of sub-graph information to obtain an optimized pose estimation.
According to a third aspect of the present invention, there is provided an electronic device, comprising a memory, and a processor, wherein the processor is configured to implement the steps of the distributed pose optimization method based on the graph algorithm when executing a computer management-like program stored in the memory.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer management-like program, which when executed by a processor, implements the steps of a distributed pose optimization method based on a graph algorithm.
According to the pose optimization method and system based on the graph algorithm, the connection graph is constructed according to the matching relation among the tracks, the whole connection graph is divided according to the connection relation among the tracks to obtain a plurality of sub-graphs, pose optimization is carried out on the basis of each sub-graph to further obtain global pose optimization, distributed pose optimization can be achieved, and the speed and the efficiency of the pose optimization are improved.
Drawings
FIG. 1 is a flow chart of a distributed pose optimization method based on a graph algorithm according to the present invention;
FIG. 2 is a schematic diagram of the connection between multiple traces;
FIG. 3 is a schematic diagram of pose optimization of a single pass trajectory;
FIG. 4 is a schematic diagram of pose optimization of a multi-pass trajectory;
FIG. 5 is a schematic structural diagram of a distributed pose optimization system based on a graph algorithm provided by the invention;
FIG. 6 is a schematic diagram of a hardware structure of a possible electronic device according to the present invention;
fig. 7 is a schematic diagram of a hardware structure of a possible computer-readable storage medium according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention. In addition, technical features of various embodiments or individual embodiments provided by the present invention may be arbitrarily combined with each other to form a feasible technical solution, and such combination is not limited by the sequence of steps and/or the structural composition mode, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, such a technical solution combination should not be considered to exist and is not within the protection scope of the present invention.
The pose graph optimization in a crowdsourcing scene has a large number of nodes and edges, the nodes and the edges form an intricate graph, and the conventional pose graph algorithm is usually to optimize and solve the whole network or to synchronize information among the nodes in an inter-process communication mode. The former limits optimization to be only calculated on a single computer, and cannot increase the speed in a mode of expanding computing resources; the latter requires a complex design and synchronization of information between servers takes a lot of time. Based on the problems and the particularity of crowdsourcing under open roads, the invention designs a distributed optimization method for pose graph optimization, and mainly focuses on the problem of pose optimization task division.
Fig. 1 is a flowchart of a distributed pose optimization method based on a graph algorithm, as shown in fig. 1, the method mainly includes the following steps:
s1, acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area.
And S2, defining a connection vector between every two tracks according to whether a matching relation exists between every two tracks.
Understandably, a set of N tracks T within a geographical area i ,i∈[1,2,…,N]We can define a connection quantity C according to whether there is a matching relationship between two tracks i,j If there is a matching relationship between the two tracks, the value of the connection amount is 1, otherwise, the value of the connection amount is 0.
As an embodiment, the defining a connection vector between every two tracks according to whether there is a matching relationship between every two tracks includes: and judging whether the two tracks have the same line section, if so, setting the connection vector between the two tracks as 1, and if not, setting the connection vector between the two tracks as 0 if not, and otherwise, judging whether the two tracks have the same line section.
Specifically, the method for determining whether there is a matching connection relationship between two tracks includes determining whether there is an overlap between the positions of the shape points on the two tracks, that is, whether there is a shape point at the same position, if there is an overlap, it is determined that there is a matching relationship between the two tracks, otherwise, there is no matching relationship between the two tracks.
And S3, constructing a connection graph between all tracks based on the connection vector between every two tracks.
And S4, dividing the connection graph into a plurality of completely independent subgraphs by using a subgraph division algorithm in the graph theory.
According to the connection relationship, a connection graph G can be constructed, the graph can be represented by a temporary matrix or a coefficient representation relationship, then the graph is divided into a plurality of completely independent subgraphs by using a subgraph division algorithm in graph theory, the subgraphs are the pose graphs which can be independently optimized, and a specific connection relationship schematic diagram can refer to FIG. 2.
Each circle in fig. 2 represents a complete track of crowdsourcing collection, and from the connection relationship, it can be seen that 1,2,3,4,5 have a matching relationship among several tracks, and have a communication relationship among them, and 6,7,8 also has a communication among the three tracks, but they are not reachable with several nodes in blue. Therefore, this trajectory pose optimization problem formed by the 8 passes of the trajectory can be divided into two parts: blue and green, without any constraint relation (residual terms) between the two parts, so that the optimization can be performed completely independently.
It should be noted that, if the matching connection graph in fig. 2 is a dense graph, that is, cannot be further divided into subgraphs, distributed pose optimization cannot be realized. As an embodiment, the determining whether the two tracks have the same line segment, and if so, the matching relationship between the two tracks includes: judging whether the two tracks have the same line section or not, if so, determining whether a matching relation exists between the two tracks according to the length of the same line section, and if the length of the same line section is greater than a set length threshold, determining that the matching relation exists between the two tracks; otherwise, there is no matching relationship between the two tracks.
It can be understood that, under the condition that the subgraph cannot be divided, a threshold value of the length of the overlapped line between the two tracks can be set, when the length of the overlapped line segment between the two tracks reaches the set threshold value of the length, the two tracks are considered to have a matching relationship, and if no overlapped line segment exists between the two tracks or the length of the overlapped line segment is smaller than the set threshold value of the length, no matching relationship exists between the two tracks. And finally, constructing a connection graph among the tracks according to the matching relation among the tracks, and dividing the whole connection graph. The subgraphs thus partitioned are not strictly independent, but are acceptable for use in approximate solution. Theoretically, the smaller this threshold, the closer the resulting solution is to the global solution.
And S5, performing pose optimization on each sub-graph to obtain optimized pose estimation.
Understandably, for each sub-graph after decomposition, each sub-graph can be pose optimized based on distributed resources. Wherein after being divided by the above matching network, the independent sub-graph information can be stored in the database and given an independent id, so that the distributed task division is completed. Next, a suitable optimizer can be created from the computing resources in the cluster, and the optimizer can consume tasks from the database, and finally solve the entire trajectory optimization problem.
For the pose optimization problem based on each subgraph, firstly, pose optimization is introduced, and a vehicle carrying a location mapping (SLAM) system usually acquires sensor information according to a certain frequency when running on the road, wherein the sensors include but are not limited to an Inertial Measurement Unit (IMU), a camera, a GPS receiver, wheel speed and the like. If the vehicle uses the information to construct a map, the sensor information needs to be fused for state estimation, and the constructed map has higher precision only if the vehicle pose estimation is accurate, because the positions of all map elements in the crowd-sourced mapping system are all based on the vehicle body pose. However, the estimation of the posture of the vehicle body cannot be made to a higher accuracy only by the vehicle-mounted sensor, which is caused by a large error or signal loss of the GPS, and an accumulated error. In order to increase the accuracy of pose estimation, loop detection is required and pose optimization is performed using the loop information and the relative pose relationship between the front and back poses.
After a complete acquisition is performed by the mapping vehicle, a relative track, a GPS track, traffic elements observed along the vehicle, a dynamic target object, and the like are usually obtained. The relative trajectory is complete and continuous, the position coordinates start from the origin, and it records the relative pose (odometer pose) between the front and back poses; the GPS track records GPS poses of a plurality of time points along the way, and records longitude and latitude and height information which are absolute coordinates; the observation records a plurality of traffic elements relative to the body coordinate system. With the relative trajectory and observation, the relative pose relationship between the partial poses can be obtained by using a matching algorithm. Together with the odometer pose and GPS global coordinate information in the previous relative trajectory, a pose optimization map can be constructed, as shown in fig. 3. In the diagram, triangles represent the poses at all times, circles represent GPS positions, real connecting lines between front triangles and rear triangles are front and rear odometer constraints, dotted line constraints between the triangles are loop constraints, the triangles represent the poses needing to be optimized, and the poses can be optimized through the pose graph optimization model.
The pose graph optimization problem is described formally below. As shown in FIG. 3, assume that the vehicle has N attitude estimates in one acquisition, P each i ，i∈[1，2，…，N]In addition, there are also GPS signals, whose sampling time point and pose estimation time point may be different, limited by the frequency of a single-point GPS, and it usually cannot correspond to the pose of the relative trajectory one-to-one, and it can be interpolated here, denoted as g j ，j∈[1，2，…，M]. In addition, through loop detection or matching, discontinuous poses (such as p in fig. 1) can be obtained 4 ，p 8 ) Measure the pose therebetween, and record as L ij Abs (i-j) > 1, and the odometer measurement between successive poses before and after is recorded as O ij I +1=j, and G k The plane projection coordinates (UTM coordinates) are latitude and longitude. Based on these symbols, the pose optimization problem can be represented as follows:
the first term in the above equation is the odometer error term, the second term is the loop error term, the third term is the GPS prior term, P in this term j，loc Is the cartesian coordinate component in the pose. And obtaining the optimized pose estimation by adopting an iteration method.
Fig. 3 is a pose graph optimization of a single-vehicle single-trip trajectory, in a crowdsourcing scene, a multi-vehicle multi-trip trajectory exists, odometer constraints exist between front and rear poses inside the trajectory, loop constraints exist inside the trajectory or between the trajectories, and in addition, GPS constraints are added to form a more complex pose graph, which can be referred to specifically as fig. 4.
Formalized description of the problem as in the above equation, unlike crowdsourcing, which has multiple passes, there is a loop constraint between the traces in addition to the odometry constraint and the loop constraint inside each trace. Therefore, the expression (1) above is also used, but a superscript l is added to each quantity, where the superscript l g ，l h ，g、h∈[1，2，…，K]To distinguish the traces of the different passes, I being the set of all pass traces. Therefore, the problem can be described as:
here, the first term and the third term are residual terms inside the trajectory, and the second term (loop term) may exist between different trajectories, which means that the optimization problem cannot be simply divided according to the runs of the trajectory. But need to take into account the loop-back (or matching) relationship between the trajectories.
For each piece of sub-image information after division, the pose optimization problem can be described as the formula (2), and the pose estimation after optimization can be obtained by adopting an iterative method based on the formula (2).
Referring to fig. 5, the distributed pose optimization system based on the graph algorithm provided by the present invention includes an obtaining module 501, a defining module 502, a constructing module 503, a dividing module 504, and an optimizing module 505, where:
the acquisition module 501 is used for acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area;
a defining module 502, configured to define a connection vector between every two tracks according to whether a matching relationship exists between every two tracks;
a constructing module 503, configured to construct a connection graph between all tracks based on a connection vector between every two tracks;
a dividing module 504, configured to divide the connection graph into multiple completely independent subgraphs by using a subgraph dividing algorithm in a graph theory;
and the optimizing module 505 is configured to perform pose optimization on each sub-graph to obtain an optimized pose estimation.
It can be understood that the distributed pose optimization system based on the graph algorithm provided by the present invention corresponds to the distributed pose optimization method based on the graph algorithm provided by each of the foregoing embodiments, and the relevant technical features of the distributed pose optimization system based on the graph algorithm may refer to the relevant technical features of the distributed pose optimization method based on the graph algorithm, and are not described herein again.
Referring to fig. 6, fig. 6 is a schematic view of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 6, an embodiment of the present invention provides an electronic device 600, which includes a memory 610, a processor 620, and a computer program 611 stored in the memory 610 and executable on the processor 620, and when the processor 620 executes the computer program 611, the steps of the distributed pose optimization method based on the graph algorithm are implemented.
Referring to fig. 7, a computer-readable storage medium according to an embodiment of the present invention is shown. As shown in fig. 7, the present embodiment provides a computer-readable storage medium 700, on which a computer program 711 is stored, which computer program 711, when executed by a processor, implements the steps of the distributed pose optimization method based on the graph algorithm.
According to the distributed pose optimization method and system based on the graph algorithm, the described pose graph optimization distributed solving method under the large-scale map construction scene can divide the optimization problem based on the matching (or loop) information, so that the solution equivalent to (or approximate to) global optimization can be obtained by fully utilizing computing resources.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A distributed pose optimization method based on a graph algorithm is characterized by comprising the following steps:
acquiring a plurality of tracks collected by vehicles with built-in maps in a geographic area;
defining a connection vector between every two tracks according to whether a matching relation exists between every two tracks;
constructing a connection graph between all tracks based on the connection vector between every two tracks;
dividing the connection graph into a plurality of completely independent subgraphs by using a subgraph division algorithm in a graph theory;
and performing pose optimization on each sub-graph to obtain an optimized pose estimation.
2. The distributed pose optimization method according to claim 1, wherein the defining a connection vector between every two tracks according to whether a matching relationship exists between every two tracks comprises:
and judging whether the two tracks have the same line section, if so, setting the connection vector between the two tracks as 1, and if not, setting the connection vector between the two tracks as 0 if not, and otherwise, judging whether the two tracks have the same line section.
3. The distributed pose optimization method according to claim 2, wherein the determining whether the two trajectories have the same line segment, and if so, the matching relationship between the two trajectories includes:
judging whether the two tracks have the same line section or not, if so, determining whether a matching relation exists between the two tracks according to the length of the same line section, and if the length of the same line section is greater than a set length threshold, determining that the matching relation exists between the two tracks; otherwise, there is no matching relationship between the two tracks.
4. The distributed pose optimization method of claim 1, wherein the pose optimization for each sub-graph to obtain an optimized pose trajectory comprises:
constructing pose optimization problem description based on each subgraph:
wherein, the mapping vehicle has N position and posture estimations in one acquisition, and the N position and posture estimations are P i ,i∈[1,2,…,N]In one pass there are M GPS signals, denoted as g j ,j∈[1,2,…,M]And obtaining a pose measurement value between discontinuous poses through loop detection or matching, and recording the pose measurement value as L ij ,abs(i-j)>1, front and rear successive positionsOdometer measurements between postures are marked as O ij I +1=j, G k Projection coordinates, P, for latitude and longitude j,loc Is a Cartesian coordinate component in pose, superscript l g ,l h ，g、h∈[1,2,…,K]To distinguish the tracks of different laps, l is the set of all laps;
and obtaining the optimized pose estimation by adopting an iteration method based on the pose optimization problem description.
5. The distributed pose optimization method of claim 1, wherein pose optimization for each sub-graph to obtain an optimized pose estimate comprises:
and storing each sub-image information in a distributed optimizer, and performing pose optimization on each sub-image information based on the distributed optimizer to obtain an optimized pose estimation.
6. A distributed pose optimization system based on a graph algorithm is characterized by comprising:
the acquisition module is used for acquiring a plurality of tracks acquired by vehicles with built-in maps in a geographic area;
the defining module is used for defining a connecting vector between every two tracks according to whether a matching relation exists between every two tracks;
the construction module is used for constructing a connection diagram among all tracks on the basis of the connection vector between every two tracks;
the partitioning module is used for partitioning the connection graph into a plurality of completely independent subgraphs by utilizing a subgraph partitioning algorithm in a graph theory;
and the optimization module is used for optimizing the pose of each sub-graph to obtain the optimized pose estimation.
7. The distributed pose optimization system of claim 6, wherein the optimization module is a distributed optimizer configured to store each sub-graph information in a distributed manner and perform pose optimization on each sub-graph information to obtain an optimized pose estimate.
8. An electronic device, comprising a memory, a processor for implementing the steps of the graph algorithm based distributed pose optimization method according to any one of claims 1-5 when executing a computer management class program stored in the memory.
9. A computer-readable storage medium, having stored thereon a computer management-like program which, when executed by a processor, performs the steps of the graph algorithm based distributed pose optimization method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211373066.6A CN115795082A (en) | 2022-11-03 | 2022-11-03 | Distributed pose optimization method and system based on graph algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211373066.6A CN115795082A (en) | 2022-11-03 | 2022-11-03 | Distributed pose optimization method and system based on graph algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115795082A true CN115795082A (en) | 2023-03-14 |
Family
ID=85435358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211373066.6A Pending CN115795082A (en) | 2022-11-03 | 2022-11-03 | Distributed pose optimization method and system based on graph algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115795082A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502589A (en) * | 2023-06-29 | 2023-07-28 | 苏州铂煜诺自动化设备科技有限公司 | Wiring method, device, equipment and storage medium of multilayer wiring package |
-
2022
- 2022-11-03 CN CN202211373066.6A patent/CN115795082A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502589A (en) * | 2023-06-29 | 2023-07-28 | 苏州铂煜诺自动化设备科技有限公司 | Wiring method, device, equipment and storage medium of multilayer wiring package |
| CN116502589B (en) * | 2023-06-29 | 2023-09-12 | 苏州铂煜诺自动化设备科技有限公司 | Wiring method, device, equipment and storage medium of multilayer wiring package |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106610294B (en) | Positioning method and device | |
| CN110160542B (en) | Method and device for positioning lane line, storage medium and electronic device | |
| JP5162849B2 (en) | Fixed point position recorder | |
| JP6595182B2 (en) | Systems and methods for mapping, locating, and attitude correction | |
| CN106153049A (en) | A kind of indoor orientation method and device | |
| AU2020356082B2 (en) | Vehicle and method for generating map corresponding to three-dimensional space | |
| JP4984659B2 (en) | Own vehicle position estimation device | |
| CN114323033B (en) | Positioning method and equipment based on lane lines and feature points and automatic driving vehicle | |
| CN115690338A (en) | Map construction method, map construction device, map construction equipment and storage medium | |
| CN112035591A (en) | Road network matching method, device, equipment and storage medium | |
| CN110069593A (en) | Image processing method and system, server, computer-readable medium | |
| CN106382931A (en) | An indoor positioning method and a device therefor | |
| Nguyen et al. | Mcd: Diverse large-scale multi-campus dataset for robot perception | |
| CN111183464B (en) | System and method for estimating saturation flow of signal intersection based on vehicle trajectory data | |
| CN115638787A (en) | Digital map generation method, computer readable storage medium and electronic device | |
| CN106255201A (en) | A kind of indoor orientation method and device | |
| CN114061611A (en) | Target object positioning method, apparatus, storage medium and computer program product | |
| CN115795082A (en) | Distributed pose optimization method and system based on graph algorithm | |
| Oran et al. | An HMM-based map matching method with cumulative proximity-weight formulation | |
| CN108759825A (en) | Towards the auto-adaptive estimate Kalman filter algorithm and system for having shortage of data INS/UWB pedestrian navigations | |
| Chiang et al. | Multifusion schemes of INS/GNSS/GCPs/V-SLAM applied using data from smartphone sensors for land vehicular navigation applications | |
| CN109307513B (en) | Real-time road matching method and system based on driving record | |
| CN114111817B (en) | Vehicle positioning method and system based on SLAM map and high-precision map matching | |
| CN117741717A (en) | Global positioning system bias detection and reduction | |
| CN113227713A (en) | Method and system for generating environment model for positioning |
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 |