CN112817026A - Method, device and equipment for determining pose of moving object and storage medium - Google Patents
Method, device and equipment for determining pose of moving object and storage medium Download PDFInfo
- Publication number
- CN112817026A CN112817026A CN202110127557.1A CN202110127557A CN112817026A CN 112817026 A CN112817026 A CN 112817026A CN 202110127557 A CN202110127557 A CN 202110127557A CN 112817026 A CN112817026 A CN 112817026A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- pose
- moving object
- determining
- map
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/53—Determining attitude
-
- 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- 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
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Navigation (AREA)
Abstract
The embodiment of the invention discloses a method, a device and equipment for determining the pose of a moving object and a storage medium. The method comprises the steps of firstly obtaining point cloud data of a moving object and a preset global point cloud map, then determining an initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then obtaining a local point cloud map comprising the initial pose in the preset global point cloud map, and finally determining a target pose of the moving object according to the point cloud data and the local point cloud map. The embodiment of the invention can initialize at any position of the global point cloud map, realizes the determination of the pose of the moving object, and solves the problem that the automatic driving vehicle can not determine the pose of the vehicle at any position in the map.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for determining a pose of a moving object.
Background
The autonomous vehicle needs to create a high-quality map in advance before going on the road. In practical use, a map created before is loaded, and then positioning is carried out based on the map, namely the current pose of the automatic driving vehicle in the map is obtained.
The traditional pose determination method requires that the automatic driving vehicle is located at a position near an original point during map building, and although the method can accurately determine the pose of the vehicle, the method cannot enable the automatic driving vehicle to determine the pose of the vehicle at any position in a map, so that great limitation is brought.
In practical use, the autonomous vehicle needs to have the capability of determining the vehicle pose at any position, so that in the current technical scheme, the problem that the autonomous vehicle cannot determine the vehicle pose at any position in a map exists.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for determining the pose of a moving object, which solve the problem that an automatic driving vehicle cannot determine the pose of the vehicle at any position in a map in the prior technical scheme, so that the automatic driving vehicle can determine the pose of the vehicle at any position in the map.
In order to solve the technical problems, the invention comprises the following steps:
in a first aspect, a pose determination method for a moving object is provided, and the method includes:
acquiring point cloud data of a moving object and a preset global point cloud map;
determining the initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to point cloud data and a global point cloud map;
acquiring a local point cloud map comprising an initial pose from a preset global point cloud map;
and determining the target pose of the moving object according to the point cloud data and the local point cloud map.
In some implementations of the first aspect, the global point cloud map includes a keyframe preset algorithm description sub-database, a keyframe point cloud database, and a keyframe point cloud pose database; determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, wherein the method comprises the following steps:
calculating a preset algorithm descriptor of the point cloud data;
and determining the initial pose of the moving object according to the preset algorithm descriptor, the preset algorithm descriptor sub-database, the key frame point cloud database and the key frame point cloud pose database.
In some implementations of the first aspect, determining the initial pose of the moving object according to the preset algorithm descriptor, the preset algorithm descriptor database, the key frame point cloud database, and the key frame point cloud pose database includes:
determining a target descriptor matched with a preset algorithm descriptor in a preset algorithm description sub-database;
determining target key frame point cloud data matched with the target descriptor in a key frame point cloud database;
and when the point cloud data and the target key frame point cloud data meet preset conditions, determining the initial pose of the moving object in a key frame point cloud pose database.
In some implementations of the first aspect, determining an initial pose of the moving object in the key frame point cloud pose database when the point cloud data and the target key frame point cloud data satisfy a preset condition includes:
when the similarity between the point cloud data and the target key frame point cloud data meets a preset threshold, determining a first target pose corresponding to the target key frame point cloud data in a key frame point cloud pose database;
and taking the first target pose as the initial pose of the moving object.
In some implementations of the first aspect, the preset algorithm includes a Scan Context algorithm.
In some implementations of the first aspect, determining the initial pose of the moving object from the satellite positioning system comprises:
acquiring the current position of a moving object and the position when a global point cloud map is created;
and determining the initial pose of the moving object according to the current position and the position when the global point cloud map is created.
In some implementations of the first aspect, determining an initial pose of the moving object from the current location and the location at the time the global point cloud map was created includes:
determining a second target pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map;
acquiring the current position of a moving object and the position when a global point cloud map is created;
determining an initial pose of the moving object according to the current position and the position when the global point cloud map is created;
and adjusting parameters of a preset algorithm according to the second target pose and the initial pose.
In some implementations of the first aspect, the second target pose includes a first position and a first deflection angle of the moving object; the first initial pose comprises an initial position and an initial deflection angle of the moving object; adjusting the parameters of the preset algorithm according to the second target pose and the initial pose, comprising:
calculating a first position difference between the first position and the initial position;
calculating a first angle difference value between a first deflection angle and an initial deflection angle;
determining a first difference value according to the first position difference value and the first angle difference value;
and when the first difference is larger than the preset threshold value, adjusting the parameters of the preset algorithm according to the first difference.
In a second aspect, there is provided a pose determination apparatus for a moving object, the apparatus including:
the acquisition module is used for acquiring point cloud data of a moving object and a preset global point cloud map;
the processing module is used for determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map;
the processing module is further used for acquiring a local point cloud map comprising an initial pose from a preset global point cloud map;
and the processing module is also used for determining the target pose of the moving object according to the point cloud data and the local point cloud map.
In a third aspect, an electronic device is provided, the device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the first aspect, and the pose determination method for a moving object in some implementations of the first aspect.
In a fourth aspect, a computer storage medium is provided, which is characterized by having stored thereon computer program instructions that, when executed by a processor, implement the first aspect and a pose determination method for a moving object in some implementations of the first aspect.
The embodiment of the invention provides a method, a device and equipment for determining the pose of a moving object and a storage medium. The method comprises the steps of firstly obtaining point cloud data of a moving object and a preset global point cloud map, then determining an initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then obtaining a local point cloud map comprising the initial pose in the preset global point cloud map, and finally determining a target pose of the moving object according to the point cloud data and the local point cloud map. The initial pose of the moving object is determined according to a satellite positioning system, or the initial pose of the moving object can be determined by using a preset algorithm according to point cloud data and a global point cloud map, then a local point cloud map is obtained in the global map according to the initial pose, and the target pose of the moving object is determined according to the local map and the point cloud data, so that the initialization can be carried out at any position of the global point cloud map, the pose of the moving object is determined, and the problem that the automatic driving vehicle cannot determine the vehicle pose at any position in the map is solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a pose determination method for a moving object according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of determining an initial pose of a moving object according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of determining an initial pose of a moving object by using a preset algorithm according to an embodiment of the present invention;
fig. 4 is a pose determination apparatus for a moving object according to an embodiment of the present invention;
fig. 5 is a block diagram of a computing device provided by an embodiment of the invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The high-precision map is necessary for automatic driving on an open road, and the point cloud map is a very important map layer of the high-precision map.
The autonomous vehicle needs to create a high-quality high-precision map in advance before getting on the road. In practical use, a map created before is loaded, and then positioning is carried out based on the map, namely the current pose of the automatic driving vehicle in the map is obtained.
The traditional pose determination method requires that the automatic driving vehicle is located at a position near an original point during map building, and although the method can accurately determine the pose of the vehicle, the method cannot enable the automatic driving vehicle to determine the pose of the vehicle at any position in a map, so that great limitation is brought.
In practical use, the autonomous vehicle needs to have the capability of determining the vehicle pose at any position, so that in the current technical scheme, the problem that the autonomous vehicle cannot determine the vehicle pose at any position in a map exists.
In order to solve the problem that the automatic driving vehicle cannot determine the vehicle pose at any position in a map in the existing technical scheme, the embodiment of the invention provides a pose determination method, a pose determination device and a storage medium of a moving object. The method comprises the steps of firstly obtaining point cloud data of a moving object and a preset global point cloud map, then determining an initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then obtaining a local point cloud map comprising the initial pose in the preset global point cloud map, and finally determining a target pose of the moving object according to the point cloud data and the local point cloud map. Because the initial pose of the moving object is determined according to the satellite positioning system, or the initial pose of the moving object can be determined according to the point cloud data and the global point cloud map by using a preset algorithm, the local point cloud map is obtained in the global map according to the initial pose, and the target pose of the moving object is determined according to the local map and the point cloud data, the initialization can be carried out at any position of the global point cloud map, the pose of the moving object is determined, and the problem that the automatic driving vehicle cannot determine the vehicle pose at any position in the map is solved.
The technical solutions provided by the embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a pose determination method for a moving object according to an embodiment of the present invention. The execution subject of the method may include a moving object, which is specifically a vehicle, a robot, or the like.
As shown in fig. 1, the pose determination method of a moving object may include:
s101: and acquiring point cloud data of the moving object and a preset global point cloud map.
In particular, the point cloud data may be data collected by a lidar, which may include three-dimensional coordinates of spatial points and the reflection intensity of an object.
The preset global point cloud map is a global point cloud map which is loaded in advance, and the global point cloud map comprises a preset algorithm description sub-database of a key frame, a key frame point cloud database and a key frame point cloud pose database.
In one embodiment, considering that the moving object may be located near the origin point during mapping, and thus the point cloud data is obtained, the initial pose of the moving object is obtained, before performing S102, it may be determined whether the moving object has the initial pose, if so, S102 is skipped, and S103 is performed directly, and if not, S102 is performed.
S102: and determining the initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map.
In one embodiment, the preset algorithm may include Scan Context algorithm, and other deep learning algorithms such as OverlapNet, etc.
Fig. 2 is a schematic flowchart of determining an initial pose of a moving object according to an embodiment of the present invention.
In the process of determining the initial pose of the moving object, as shown in fig. 2, it may be determined whether a Global Navigation Satellite System (GNSS) is available, and when the GNSS is unavailable, for example, when there is no GNSS device, or when the GNSS device is in a poor state and does not meet the condition, a preset algorithm may be used to determine the initial pose of the moving object.
Fig. 3 is a schematic flowchart of determining an initial pose of a moving object by using a preset algorithm according to an embodiment of the present invention.
When a preset algorithm is used for determining the initial pose of the moving object, the specific process is combined with the graph 3, and firstly, a preset algorithm descriptor of point cloud data can be calculated; then searching and determining a target descriptor matched with the preset algorithm descriptor in a preset algorithm description sub-database; then, finding target key frame point cloud data matched with the target descriptor in a key frame point cloud database; and finally, judging the similarity between the point cloud data and the target key frame point cloud data, determining a first target pose corresponding to the target key frame point cloud data in a key frame point cloud pose database when the similarity between the point cloud data and the target key frame point cloud data meets a preset threshold, and taking the first target pose as the initial pose of the moving object.
In one embodiment, determining the similarity between the Point cloud data and the target key frame Point cloud data may use an Iterative Closest Point (ICP) algorithm to register the acquired Point cloud data and the target key frame Point cloud data. If the two frames of point clouds can be matched through certain rotation and translation, the scene recognition result is correct, namely the similarity between the acquired point cloud data and the target key frame point cloud data meets a preset threshold; on the contrary, if the two frames of point clouds cannot be matched through certain rotation and translation, the scene recognition result is indicated to be wrong, namely, the similarity between the acquired point cloud data and the target key frame point cloud data does not meet the preset threshold value.
As shown in fig. 2, when the GNSS is available, the state of the GNSS device may be estimated by the number of satellites and the signal-to-noise ratio, and when the state of the GNSS device satisfies a preset use condition, the pose obtained by the GNSS device may be used as the initial pose.
In the process of taking the pose of the GNSS device as the initial pose, the current position of the moving object and the position when the global point cloud map is created may be specifically obtained, where the current position refers to a Universal Transverse Grid (UTM) coordinate of a current Universal ink-jet transit consumer Grid System (UTM), and the position when the global point cloud map is created refers to a UTM coordinate of a map creation start point stored when the global point cloud map is created by the integrated navigation device.
And then determining the initial pose of the moving object according to the current position and the position when the global point cloud map is created. When the initial pose is determined, the Euclidean distance between the current UTM coordinate and the UTM coordinate of the mapping starting point can be calculated, and then the pose of the moving object in the global point cloud map is determined according to the Euclidean distance, wherein the pose is the initial pose.
In addition, since the external environment is dynamically changed, such as season and weather, the appearance of the object is affected by the construction, which may challenge the preset algorithm for identification based on the appearance, and in severe cases may cause failure. Therefore, in order to improve the robustness of the initialization, the Global positioning characteristics of a Global Navigation Satellite System (GNSS) may be fused on the basis of the preset algorithm to adjust the parameters of the preset algorithm.
Or taking a Scan Context algorithm as an example, when a GNSS and a Scan Context are fused to adjust parameters of the Scan Context algorithm, firstly, a preset algorithm is used to determine a second target pose of a moving object according to point cloud data and a global point cloud map.
Then, parameters of a preset algorithm are adjusted according to the second pose and the initial pose determined by the GNSS device, where the second target pose includes a first position and a first deflection angle of the moving object, the initial pose includes an initial position and an initial deflection angle of the moving object, and the process of adjusting the parameters may specifically be to calculate a first position difference between the first position and the initial position, and then calculate a first angle difference between the first deflection angle and the initial deflection angle. And then determining a first difference value according to the first position difference value and the first angle difference value, and when the first difference value is greater than a preset threshold value, adjusting a parameter of a preset algorithm according to the first difference value, wherein the parameter refers to a parameter used for judging the similarity between the point cloud data and the target key frame point cloud data, such as a threshold value.
In the process of adjusting the parameters of the Scan Context algorithm, the parameters of the similarity of the Scan Context algorithm are dynamically adjusted according to the GNSS output result, so that scene changes caused by more dynamic objects, season and weather changes, construction and the like are avoided.
In the embodiment of the invention, by judging the state of the GNSS, when the state of the GNSS is good, the position of the GNSS is taken as the final initial position. And parameters of the Scan Context algorithm are adjusted by fusing the GNSS and the Scan Context algorithm to improve the accuracy of the Scan Context algorithm in determining the pose of the moving object. When the state of the GNSS is poor, the pose of the moving object can be determined by only calling a Scan Context algorithm, so that the robustness of pose determination is improved.
S103: and acquiring a local point cloud map including an initial pose from a preset global point cloud map.
In one embodiment, the process may refer to segmenting a local point cloud map, which may be a fixed-size point cloud map, in the vicinity of the initial pose in a preset global point cloud map.
After the local point cloud map is obtained, the local point cloud map may be matched with the acquired point cloud data to determine a target pose of the moving object, i.e., S104.
S104: and determining the target pose of the moving object according to the point cloud data and the local point cloud map.
Since the matching accuracy of one frame of point cloud and the local point cloud map is higher than that of one frame of point cloud and one frame of point cloud, the point cloud map is used in order to improve the matching accuracy. And the matching speed of the local map is higher than that of the global map, so that the local point cloud map is adopted in the process in consideration of the matching precision and the matching speed.
In addition, in an embodiment, the local point cloud map may be equivalent to a sliding window, and when the moving object moves continuously and the distance from the acquired point cloud data to the window boundary of the local point cloud map is lower than a threshold, a local point cloud map needs to be segmented again according to the point cloud data in the global point cloud map to update the local point cloud map, so that the moving object can dynamically determine the target pose.
In addition, in one embodiment, a semantic map can be created when the global point cloud map is created, initialization is performed by matching semantic information, and the pose is determined.
The embodiment of the invention provides a method for determining the pose of a moving object. The method comprises the steps of firstly obtaining point cloud data of a moving object and a preset global point cloud map, then determining an initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then obtaining a local point cloud map comprising the initial pose in the preset global point cloud map, and finally determining a target pose of the moving object according to the point cloud data and the local point cloud map. Because the initial pose of the moving object is determined according to the satellite positioning system, or the initial pose of the moving object can be determined according to the point cloud data and the global point cloud map by using a preset algorithm, the local point cloud map is obtained in the global map according to the initial pose, and the target pose of the moving object is determined according to the local map and the point cloud data, the initialization can be carried out at any position of the global point cloud map, the pose of the moving object is determined, and the problem that the automatic driving vehicle cannot determine the vehicle pose at any position in the map is solved.
Corresponding to the flow diagram of the method for determining the pose of the moving object in fig. 1, the embodiment of the invention also provides a device for determining the pose of the moving object.
Fig. 4 is a pose determination apparatus for a moving object according to an embodiment of the present invention. As shown in fig. 4, the apparatus includes:
an obtaining module 401, configured to obtain point cloud data of a moving object and a preset global point cloud map;
a processing module 402, which may be configured to determine an initial pose of the moving object according to a satellite positioning system, or determine an initial pose of the moving object using a preset algorithm according to the point cloud data and the global point cloud map;
the processing module 402 may further be configured to obtain a local point cloud map including an initial pose from a preset global point cloud map, and determine a target pose of the moving object according to the point cloud data and the local point cloud map.
In one embodiment, the global point cloud map may include a keyframe preset algorithm description sub-database, a keyframe point cloud database, and a keyframe point cloud pose database.
The processing module 402 may further be configured to calculate a preset algorithm descriptor of the point cloud data, and determine an initial pose of the moving object according to the preset algorithm descriptor, the preset algorithm descriptor database, the key frame point cloud database, and the key frame point cloud pose database.
The processing module 402 may further be configured to determine, in the preset algorithm description sub-database, a target descriptor matching the preset algorithm descriptor, then determine, in the key frame point cloud database, target key frame point cloud data matching the target descriptor, and determine, when the point cloud data and the target key frame point cloud data satisfy a preset condition, an initial pose of the moving object in the key frame point cloud pose database.
The processing module 402 may further be configured to determine, when the similarity between the point cloud data and the target key frame point cloud data satisfies a preset threshold, a first target pose corresponding to the target key frame point cloud data in the key frame point cloud pose database, and use the first target pose as an initial pose of the moving object.
In one embodiment, the preset algorithm may include a Scan Context algorithm.
The obtaining module 401 may further be configured to obtain a current position of the moving object and a position when the global point cloud map is created.
The processing module 402 may be further configured to determine an initial pose of the moving object according to the current position and the position when the global point cloud map is created.
The processing module 402 may be further configured to determine a second target pose of the moving object using a preset algorithm according to the point cloud data and the global point cloud map.
The obtaining module 401 may further be configured to obtain a current position of the moving object and a position when the global point cloud map is created.
The processing module 402 may further be configured to determine an initial pose of the moving object according to the current position and the position when the global point cloud map is created, and adjust a parameter of a preset algorithm according to the second target pose and the initial pose.
In one embodiment, the second target pose comprises a first position and a first deflection angle of the moving object; the initial pose includes an initial position and an initial deflection angle of the moving object.
The processing module 402 may be further configured to calculate a first position difference between the first position and the initial position, calculate a first angle difference between the first deflection angle and the initial deflection angle, determine a first difference according to the first position difference and the first angle difference, and adjust a parameter of a preset algorithm according to the first difference when the first difference is greater than a preset threshold.
The embodiment of the invention provides a pose determining device of a moving object. The acquisition module firstly acquires point cloud data of a moving object and a preset global point cloud map, then the processing module determines an initial pose of the moving object according to a satellite positioning system, or determines the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then acquires a local point cloud map comprising the initial pose in the preset global point cloud map, and finally determines a target pose of the moving object according to the point cloud data and the local point cloud map. The processing module determines the initial pose of the moving object according to the satellite positioning system, or determines the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, then acquires the local point cloud map in the global map according to the initial pose, and determines the target pose of the moving object according to the local map and the point cloud data, so that the initialization can be carried out at any position of the global point cloud map, the pose of the moving object can be determined, and the problem that the automatic driving vehicle cannot determine the vehicle pose at any position in the map is solved.
Fig. 5 is a block diagram of a hardware architecture of a computing device according to an embodiment of the present invention. As shown in fig. 5, computing device 500 includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are connected to each other through a bus 510, and the input device 501 and the output device 506 are connected to the bus 510 through the input interface 502 and the output interface 505, respectively, and further connected to other components of the computing device 500.
Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes input information based on computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; output device 506 outputs the output information outside of computing device 500 for use by a user.
That is, the computing device shown in fig. 5 may also be implemented as a pose determination device of a moving object, which may include: a processor and a memory storing computer executable instructions; the processor, when executing the computer-executable instructions, may implement the method for determining the pose of a moving object provided by the embodiments of the present invention.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement a pose determination method for a moving object provided by an embodiment of the invention.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, Erasable Read-Only memories (EROMs), floppy disks, Compact disk Read-Only memories (CD-ROMs), optical disks, hard disks, optical fiber media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations 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, 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, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (11)
1. A pose determination method for a moving object, the method comprising:
acquiring point cloud data of a moving object and a preset global point cloud map;
determining the initial pose of the moving object according to a satellite positioning system, or determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map;
acquiring a local point cloud map comprising the initial pose from a preset global point cloud map;
and determining the target pose of the moving object according to the point cloud data and the local point cloud map.
2. The method of claim 1, wherein the global point cloud map comprises a keyframe preset algorithm description sub-database, a keyframe point cloud database, and a keyframe point cloud pose database; determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map, wherein the method comprises the following steps:
calculating a preset algorithm descriptor of the point cloud data;
and determining the initial pose of the moving object according to the preset algorithm descriptor, the preset algorithm descriptor sub-database, the key frame point cloud database and the key frame point cloud pose database.
3. The method of claim 2, wherein determining the initial pose of the moving object according to the preset algorithm descriptor, the preset algorithm descriptor database, the key frame point cloud database, and the key frame point cloud pose database comprises:
determining a target descriptor matched with the preset algorithm descriptor in the preset algorithm description sub-database;
determining target keyframe point cloud data matched with the target descriptor in the keyframe point cloud database;
and when the point cloud data and the target key frame point cloud data meet preset conditions, determining the initial pose of the moving object in the key frame point cloud pose database.
4. The method of claim 3, wherein determining an initial pose of the moving object in the keyframe point cloud pose database when the point cloud data and the target keyframe point cloud data satisfy a preset condition comprises:
when the similarity between the point cloud data and the target key frame point cloud data meets a preset threshold, determining a first target pose corresponding to the target key frame point cloud data in the key frame point cloud pose database;
and taking the first target pose as an initial pose of the moving object.
5. The method of claim 1, wherein the pre-set algorithm comprises a Scan Context algorithm.
6. The method of claim 1, wherein said determining an initial pose of the moving object from a satellite positioning system comprises:
acquiring the current position of a moving object and the position when the global point cloud map is created;
and determining the initial pose of the moving object according to the current position and the position when the global point cloud map is created.
7. The method of claim 6, wherein the determining an initial pose of the moving object as a function of the current location and the location at the time the global point cloud map was created comprises:
determining a second target pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map;
acquiring the current position of a moving object and the position when the global point cloud map is created;
determining an initial pose of the moving object according to the current position and the position when the global point cloud map is created;
and adjusting parameters of the preset algorithm according to the second target pose and the initial pose.
8. The method of claim 7, wherein the second target pose comprises a first position and a first deflection angle of the moving object; the initial pose comprises an initial position and an initial deflection angle of the moving object; the adjusting the parameters of the preset algorithm according to the second target pose and the initial pose comprises:
calculating a first position difference between the first position and the initial position;
calculating a first angle difference value of the first deflection angle and the initial deflection angle;
determining a first difference value according to the first position difference value and the first angle difference value;
and when the first difference is larger than a preset threshold value, adjusting the parameter of the preset algorithm according to the first difference.
9. A pose determination apparatus of a moving object, the apparatus comprising:
the acquisition module is used for acquiring point cloud data of a moving object and a preset global point cloud map;
the processing module is used for determining the initial pose of the moving object by using a preset algorithm according to the point cloud data and the global point cloud map;
the processing module is further used for acquiring a local point cloud map comprising the initial pose from a preset global point cloud map;
the processing module is further used for determining the target pose of the moving object according to the point cloud data and the local point cloud map.
10. An electronic device, characterized in that the device comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of pose determination of a moving object as claimed in any one of claims 1 to 8.
11. A computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement a pose determination method of a moving object according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110127557.1A CN112817026A (en) | 2021-01-29 | 2021-01-29 | Method, device and equipment for determining pose of moving object and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110127557.1A CN112817026A (en) | 2021-01-29 | 2021-01-29 | Method, device and equipment for determining pose of moving object and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112817026A true CN112817026A (en) | 2021-05-18 |
Family
ID=75860290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110127557.1A Pending CN112817026A (en) | 2021-01-29 | 2021-01-29 | Method, device and equipment for determining pose of moving object and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112817026A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113587937A (en) * | 2021-06-29 | 2021-11-02 | 阿波罗智联(北京)科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN114236552A (en) * | 2021-11-12 | 2022-03-25 | 苏州玖物互通智能科技有限公司 | Repositioning method and system based on laser radar |
| CN114782528A (en) * | 2022-03-15 | 2022-07-22 | 美的集团(上海)有限公司 | Robot positioning initialization method, electronic device, and computer storage medium |
| CN114821363A (en) * | 2022-03-29 | 2022-07-29 | 群周科技(上海)有限公司 | Unmanned aerial vehicle positioning and mapping method and system based on semantic information matching |
| CN115248430A (en) * | 2021-09-23 | 2022-10-28 | 上海仙途智能科技有限公司 | Target object positioning method, device, terminal and medium |
| CN117705125A (en) * | 2024-02-05 | 2024-03-15 | 安徽蔚来智驾科技有限公司 | Positioning method, readable storage medium and intelligent device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006083297A2 (en) * | 2004-06-10 | 2006-08-10 | Sarnoff Corporation | Method and apparatus for aligning video to three-dimensional point clouds |
| CN110766716A (en) * | 2019-09-10 | 2020-02-07 | 中国科学院深圳先进技术研究院 | Method and system for acquiring information of space unknown moving target |
| CN110906924A (en) * | 2019-12-17 | 2020-03-24 | 杭州光珀智能科技有限公司 | Positioning initialization method and device, positioning method and device and mobile device |
| CN111311756A (en) * | 2020-02-11 | 2020-06-19 | Oppo广东移动通信有限公司 | Augmented reality AR display method and related device |
| CN111508021A (en) * | 2020-03-24 | 2020-08-07 | 广州视源电子科技股份有限公司 | Pose determination method and device, storage medium and electronic equipment |
| CN111862177A (en) * | 2020-07-29 | 2020-10-30 | 江南大学 | Three-dimensional point cloud registration method of workpiece based on direction histogram signature features |
| CN112014857A (en) * | 2020-08-31 | 2020-12-01 | 上海宇航系统工程研究所 | Three-dimensional laser radar positioning and navigation method for intelligent inspection and inspection robot |
-
2021
- 2021-01-29 CN CN202110127557.1A patent/CN112817026A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006083297A2 (en) * | 2004-06-10 | 2006-08-10 | Sarnoff Corporation | Method and apparatus for aligning video to three-dimensional point clouds |
| CN110766716A (en) * | 2019-09-10 | 2020-02-07 | 中国科学院深圳先进技术研究院 | Method and system for acquiring information of space unknown moving target |
| CN110906924A (en) * | 2019-12-17 | 2020-03-24 | 杭州光珀智能科技有限公司 | Positioning initialization method and device, positioning method and device and mobile device |
| CN111311756A (en) * | 2020-02-11 | 2020-06-19 | Oppo广东移动通信有限公司 | Augmented reality AR display method and related device |
| CN111508021A (en) * | 2020-03-24 | 2020-08-07 | 广州视源电子科技股份有限公司 | Pose determination method and device, storage medium and electronic equipment |
| CN111862177A (en) * | 2020-07-29 | 2020-10-30 | 江南大学 | Three-dimensional point cloud registration method of workpiece based on direction histogram signature features |
| CN112014857A (en) * | 2020-08-31 | 2020-12-01 | 上海宇航系统工程研究所 | Three-dimensional laser radar positioning and navigation method for intelligent inspection and inspection robot |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113587937A (en) * | 2021-06-29 | 2021-11-02 | 阿波罗智联(北京)科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN115248430A (en) * | 2021-09-23 | 2022-10-28 | 上海仙途智能科技有限公司 | Target object positioning method, device, terminal and medium |
| CN115248430B (en) * | 2021-09-23 | 2023-08-25 | 上海仙途智能科技有限公司 | Target object positioning method, device, terminal and medium |
| CN114236552A (en) * | 2021-11-12 | 2022-03-25 | 苏州玖物互通智能科技有限公司 | Repositioning method and system based on laser radar |
| CN114236552B (en) * | 2021-11-12 | 2024-05-31 | 苏州玖物智能科技股份有限公司 | Repositioning method and repositioning system based on laser radar |
| CN114782528A (en) * | 2022-03-15 | 2022-07-22 | 美的集团(上海)有限公司 | Robot positioning initialization method, electronic device, and computer storage medium |
| CN114821363A (en) * | 2022-03-29 | 2022-07-29 | 群周科技(上海)有限公司 | Unmanned aerial vehicle positioning and mapping method and system based on semantic information matching |
| CN117705125A (en) * | 2024-02-05 | 2024-03-15 | 安徽蔚来智驾科技有限公司 | Positioning method, readable storage medium and intelligent device |
| CN117705125B (en) * | 2024-02-05 | 2024-04-30 | 安徽蔚来智驾科技有限公司 | Positioning method, readable storage medium and intelligent device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112817026A (en) | Method, device and equipment for determining pose of moving object and storage medium | |
| CN109141437B (en) | Robot global repositioning method | |
| CN112113574B (en) | Method, apparatus, computing device and computer-readable storage medium for positioning | |
| JP6760114B2 (en) | Information processing equipment, data management equipment, data management systems, methods, and programs | |
| CN108332758B (en) | Corridor identification method and device for mobile robot | |
| CN112179330A (en) | Pose determination method and device of mobile equipment | |
| CN114111774B (en) | Vehicle positioning method, system, equipment and computer readable storage medium | |
| CN112767545A (en) | Point cloud map construction method, device, equipment and computer storage medium | |
| EP3819663A1 (en) | Method for determining a position of a vehicle | |
| US20160231432A1 (en) | Method for determining a current position of a motor vehicle in a geodetic coordinate system and motor vehicle | |
| CN114264301B (en) | Vehicle-mounted multi-sensor fusion positioning method, device, chip and terminal | |
| Dogramadzi et al. | Accelerated map matching for GPS trajectories | |
| JP2019207177A (en) | Self-position estimation apparatus | |
| CN116429084A (en) | Dynamic environment 3D synchronous positioning and mapping method | |
| CN112578781B (en) | Data processing method, device, chip system and medium | |
| CN113932799A (en) | Laser map updating method, system, electronic device, medium, and program product | |
| CN110986966A (en) | Automatic driving positioning method and system for long-distance tunnel | |
| Park et al. | Vehicle localization using an AVM camera for an automated urban driving | |
| CN115952248B (en) | Pose processing method, device, equipment, medium and product of terminal equipment | |
| JP6820762B2 (en) | Position estimator | |
| CN115993132A (en) | Visual inertial odometer initialization method and device and aerocar | |
| CN112393723B (en) | Positioning method, positioning device, medium and unmanned equipment | |
| KR102275695B1 (en) | Method And Apparatus for Real-Time Update of Three-Dimensional Distance Information for Use in 3D Map Building | |
| CN113297259B (en) | Robot and environment map construction method and device thereof | |
| Feng et al. | Block-Map-Based Localization in Large-Scale Environment |
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 |