CN117289238A - Laser radar map construction optimization method, device, equipment and medium - Google Patents
Laser radar map construction optimization method, device, equipment and medium Download PDFInfo
- Publication number
- CN117289238A CN117289238A CN202311403393.6A CN202311403393A CN117289238A CN 117289238 A CN117289238 A CN 117289238A CN 202311403393 A CN202311403393 A CN 202311403393A CN 117289238 A CN117289238 A CN 117289238A
- Authority
- CN
- China
- Prior art keywords
- loop
- constraint
- detection result
- pose information
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000010276 construction Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 114
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 51
- 238000004590 computer program Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Abstract
The invention discloses a laser radar map construction optimization method, a device, equipment and a medium, wherein the laser radar map construction optimization method comprises the following steps: determining an initial radar odometer map according to the collected laser radar point cloud data of the vehicle; determining candidate frames of laser radar point cloud data in an initial radar odometer map, and performing loop detection based on pose information of the candidate frames to obtain a loop detection result; performing bidirectional loop constraint on the loop detection result, and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint; and under the condition that the loop detection result is accurate, performing first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map. By the technical scheme, the correctness of the loop detection result can be improved, and the consistency of the generated map is ensured.
Description
Technical Field
The present invention relates to the field of map construction technologies, and in particular, to a method, an apparatus, a device, and a medium for optimizing a laser radar map construction.
Background
In the vehicle autopilot technology, accurate structured map data provides necessary information assistance for vehicle driving positioning, perception, navigation, and regulation.
However, in the map data acquisition, an overlapping area inevitably appears, and due to the deviation of the sensor and the loss of algorithm precision, more double images and errors tend to appear in the overlapping area, so that the reliability of the map is reduced. Therefore, it is important to eliminate ghosts during the map building and updating process so that the newly acquired data can better fit the original data.
The existing mapping method relies on more exogenous positioning modes, such as combined inertial navigation, beacons and the like. For the loop part, only one-way constraint exists, error detection is easy to leak, and the problem of map consistency cannot be completely solved, even the result is deteriorated.
Disclosure of Invention
The invention provides a laser radar map construction optimization method, device, equipment and medium, which are used for ensuring the consistency of a map.
According to an aspect of the present invention, there is provided a laser radar map construction optimization method, including:
determining an initial radar odometer map according to the collected laser radar point cloud data of the vehicle;
determining a candidate frame of laser radar point cloud data in the initial radar odometer map, and performing loop detection based on pose information of the candidate frame to obtain a loop detection result; the loop detection result comprises at least one potential loop pair;
performing bidirectional loop constraint on the loop detection result, and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint;
and under the condition that the loop detection result is accurate, performing first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map.
According to another aspect of the present invention, there is provided a lidar mapping optimization apparatus, including:
the map determining module is used for determining an initial radar odometer map according to the acquired laser radar point cloud data of the vehicle;
the loop detection module is used for determining candidate frames of the laser radar point cloud data in the initial radar odometer map, and carrying out loop detection based on pose information of the candidate frames to obtain a loop detection result; the loop detection result comprises at least one potential loop pair; the loop detection result comprises at least one potential loop pair;
the result determining module is used for carrying out bidirectional loop constraint on the loop detection result and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint;
and the first optimization module is used for carrying out first graph optimization on the initial radar odometer map based on the bidirectional loop constraint under the condition that the loop detection result is accurate, so as to obtain an optimized radar odometer map.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the lidar mapping optimization method of any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the laser radar mapping optimization method according to any one of the embodiments of the present invention when executed.
According to the technical scheme, loop detection is carried out on the candidate frames in the initial radar odometer map, and bidirectional loop constraint is carried out on the loop detection result, so that the relative pose of the loop constraint is calculated from two directions, whether the loop detection result is accurate or not is determined, the accuracy of the loop detection result is further improved compared with the unidirectional loop constraint, the problem of missing error detection is avoided, and the consistency of the generated map is ensured.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a laser radar mapping optimization method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a laser radar map-building optimization method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a laser radar mapping optimization device according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing the laser radar map-building optimization method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a laser radar map construction optimization method according to an embodiment of the present invention, where the method may be performed by a laser radar map construction optimization device, and the laser radar map construction optimization device may be implemented in hardware and/or software, and may be configured in various general-purpose computing devices. As shown in fig. 1, the method includes:
s110, determining an initial radar odometer map according to the collected laser radar point cloud data of the vehicle.
The laser radar point cloud data can be obtained by acquiring the laser radar point cloud data through a laser radar sensor arranged on the vehicle within a preset acquisition time period and performing de-distortion processing on the laser radar point cloud data according to pose information of the vehicle within the preset acquisition time period. In the embodiment of the present invention, the preset acquisition duration may refer to an acquisition frequency of the radar sensor, that is, a time required for the laser radar sensor to acquire one frame of laser radar point cloud data; the pose information of the vehicle in the preset acquisition time period can be determined through an inertial navigation system arranged on the vehicle. Alternatively, the pose information may include heading angle information and position information; the de-orthodontic treatment process can be used for performing motion compensation on the laser radar point cloud data acquired in the preset acquisition time according to the pose information in the preset acquisition time. Alternatively, the placement position of the lidar sensor may be adaptively set according to those skilled in the art.
The initial radar odometer map may refer to a radar odometer map that has not been updated and optimized;
specifically, an initial radar odometer map may be constructed according to laser radar point cloud data acquired by a radar sensor disposed on the vehicle.
Optionally, determining the initial radar odometer map according to the collected laser radar point cloud data of the vehicle includes: performing feature extraction on the laser radar point cloud data according to the local curvature of the laser radar point cloud data; and performing point cloud feature matching on the laser radar point cloud data according to the extracted features of the laser radar point cloud data and the initial pose information of the vehicle, and generating an initial radar odometer point cloud map.
The initial pose information may be pose information of a vehicle start determined by the inertial navigation system, and may be determined according to the inertial navigation system; the extracted features of the lidar point cloud data may include angular features and face features.
Specifically, feature extraction can be performed on the laser radar point cloud data by calculating the local curvature of the collected laser radar point cloud data, point cloud feature matching is performed on the collected laser radar point cloud data according to the angle features and the plane features of the collected laser radar point cloud data and the initial pose information of the vehicle, global pose information of the laser radar point cloud data relative to the initial pose information is obtained, and an initial radar odometer point cloud map is generated according to the global pose information.
S120, determining candidate frames of laser radar point cloud data in the initial radar odometer map, and performing loop detection based on pose information of the candidate frames to obtain a loop detection result.
The candidate frame may refer to laser radar point cloud data meeting a preset detection condition in the initial radar odometer map. It should be noted that, the preset detection condition may be used to determine whether loop detection needs to be performed on the laser radar point cloud data of the current frame, so as to avoid ineffective loop detection. Alternatively, the preset detection conditions may be adaptively set according to those skilled in the art. Preferably, the loop is only possible to occur when the number of frames of the laser radar point cloud data reaches a certain number of frames threshold, and therefore, the preset detection condition can be determined by setting a preset number of frames threshold.
The loop detection result may include at least one potential loop pair, where the one potential loop pair includes one candidate frame and a loop frame corresponding to the candidate frame. It should be noted that, the loop frame may refer to laser radar point cloud data collected before the preset frame number of the candidate frame, that is, a history frame collected before the preset frame number of the candidate frame, so that a loop formed by a frame too close to the candidate frame is avoided, and the position information in the pose information of the candidate frame and the position information in the pose information of the history frame are smaller than a preset distance threshold, so as to prove that the distance between the candidate frame and the history frame is sufficiently close.
Specifically, a candidate frame of laser radar data in an initial radar odometer map can be determined, loop detection is performed on the candidate frame based on pose information of the candidate frame, and a loop frame corresponding to the candidate frame is determined as a loop detection result. Optionally, when there are multiple loop frames in the candidate frame, that is, there are multiple potential loop pairs in the loop detection result, only one potential loop pair may be reserved for the location information of the candidate frame in a downsampling manner, so as to reduce the calculation amount.
S130, carrying out bidirectional loop constraint on the loop detection result, and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint.
The bidirectional loop constraint can comprise forward constraint and reverse constraint, and the correctness of the loop detection result can be further checked through double constraint of the forward constraint and the reverse constraint so as to improve the consistency of the map.
Specifically, bidirectional loop constraint can be performed on the loop detection result, and whether the loop detection result is correct or not is determined according to the bidirectional loop constraint, namely whether the candidate frame in the potential loop pair and the loop frame corresponding to the candidate frame are credible or not is determined.
And S140, under the condition that the loop detection result is accurate, performing first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map.
Specifically, under the condition that the loop detection result is accurate, the relative pose between the candidate frame obtained through the bidirectional loop constraint and the corresponding loop frame can be used as the loop constraint to be added into graph optimization, and the first graph optimization is performed on the initial radar odometer map so as to obtain the optimized radar odometer map. Alternatively, the graph optimization algorithm may be any one of g2o, GTSAM, or Ceres. Optionally, in the case of an error in the loop detection result, the loop detection detects that the detected potential loop pair is incorrect, and the loop constraint of the potential loop pair is abandoned to be added to the graph optimization process.
Optionally, in an optional manner of the embodiment of the present invention, after performing the first map optimization on the initial radar odometer map based on the bidirectional loop constraint, the method further includes: if the difference between the pose information of the candidate frame after the first graph optimization and the pose information of the candidate frame before the first graph optimization is larger than a preset difference, the weight of the pose information in the graph optimization process is reduced, and the second graph optimization is carried out on the initial radar odometer map after the first graph optimization. It should be noted that, since many sensors are often involved in the autopilot system, the higher the accuracy of the sensor, the larger the weight coefficient of the optimization constraint of the corresponding sensor, so that the information matrix is used as the weight of the error term in the graph optimization algorithm to give different degrees of trust to different sensors, and therefore, the influence of the error value is reduced by reducing the weight of the corresponding pose information when the pose information error is larger.
According to the technical scheme, loop detection is carried out on the candidate frames in the initial radar odometer map, and bidirectional loop constraint is carried out on the loop detection result, so that the relative pose of the loop constraint is calculated from two directions, whether the loop detection result is accurate or not is determined, the accuracy of the loop detection result is further improved compared with the unidirectional loop constraint, the problem of missing error detection is avoided, and the consistency of the generated map is ensured.
Example two
Fig. 2 is a flowchart of a laser radar graph construction optimization method according to a second embodiment of the present invention, and based on this embodiment and the above embodiments and further details, specific steps of performing bidirectional loop constraint on a loop detection result, and determining whether the loop detection result is accurate based on the bidirectional loop constraint are provided. It should be noted that, in the embodiments of the present invention, the details of the description of other embodiments may be referred to, and will not be described herein. As shown in fig. 2, the method includes:
s210, determining an initial radar odometer map according to the collected laser radar point cloud data of the vehicle.
S220, determining candidate frames of laser radar point cloud data in the initial radar odometer map, and performing loop detection based on pose information of the candidate frames to obtain a loop detection result.
S230, forward constraint is carried out on the loop detection result according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame, reverse constraint is carried out on the loop detection result according to the pose information of the neighboring frame of the candidate frame and the pose information of the loop frame corresponding to the candidate frame, bidirectional loop constraint comprising the forward constraint and the reverse constraint is obtained, and whether the loop detection result is accurate is determined based on the bidirectional loop constraint.
Wherein, the adjacent frames may include self frames and frames adjacent to the self frames; alternatively, the number of adjacent frames may be adaptively set according to those skilled in the art, for example, for the candidate frame m and the loop frame n corresponding to the candidate frame, the adjacent frames of the loop frame n may include the own frame n, the adjacent frame n-2, the adjacent frame n-1, the adjacent frame n+1, and the adjacent frame n+2; accordingly, the neighboring frames of the candidate frame m may include the own frame m, the neighboring frame m-2, the neighboring frame m-1, the neighboring frame m+1, and the neighboring frame m+2.
Specifically, forward loop constraint can be performed on the loop detection result according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame, and reverse loop constraint can be performed on the loop detection result according to pose information of the neighboring frame of the candidate frame and pose information of the loop frame corresponding to the candidate frame, so that bidirectional loop constraint including forward loop constraint and reverse loop constraint is obtained, and further, whether the loop detection result is reliable or not can be determined according to the bidirectional loop constraint.
Optionally, forward constraint is performed on the loop detection result according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame, reverse constraint is performed on the loop detection result according to pose information of the neighboring frame of the candidate frame and pose information of the loop frame corresponding to the candidate frame, so as to obtain bidirectional loop constraint including forward constraint and reverse constraint, and whether the loop detection result is accurate is determined based on the bidirectional loop constraint, including: determining a first relative pose as a forward constraint according to pose information of the candidate frame and pose information of adjacent frames of the loop frame corresponding to the candidate frame; determining a second relative pose as a reverse constraint according to pose information of adjacent frames of the candidate frame and pose information of a loop frame corresponding to the candidate frame; if the difference value between the first relative pose and the inverted second relative pose is smaller than a preset credible threshold value, determining that the loop detection result is accurate.
The first relative pose may refer to a transformation pose between the candidate frame and a neighboring frame of the loop frame corresponding to the candidate frame. Optionally, the transformation pose between the candidate frame and at least one adjacent frame of the loop frame corresponding to the candidate frame may be sequentially obtained, the obtained transformation pose between the at least one candidate frame and the adjacent frame of the loop frame corresponding to the candidate frame is subjected to mean processing, and the result after mean processing is used as the first relative pose. The second relative pose may refer to a transformed pose between a neighboring frame of the candidate frame and a loop-back frame corresponding to the candidate frame. Similarly, the transformation pose between at least one adjacent frame of the candidate frames and the loop-back frame corresponding to the candidate frames can be sequentially obtained, the obtained transformation pose between the adjacent frame of the at least one candidate frame and the loop-back frame corresponding to the candidate frames is subjected to mean value processing, and the result after mean value processing is used as a first relative pose.
It should be noted that if the first and second relative poses are calculated to correctly reflect the constraint of the loop, then the first and second relative poses should be reciprocal, i.e
Wherein A represents a candidate frame, B' represents a neighboring frame of a loop frame corresponding to the candidate frame,representing a first relative pose->And representing a second relative pose, wherein A' represents a loop frame of the candidate frame, and B represents a loop frame corresponding to the candidate frame.
Specifically, the first relative pose can be determined according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame, and loop constraint can be performed on a loop detection result as forward constraint; determining a second relative pose according to pose information of adjacent frames of the candidate frame and pose information of loop frames corresponding to the candidate frame, and performing loop constraint on a loop detection result as reverse constraint; if the difference between the first relative pose and the second relative pose after the inversion processing is smaller than a preset credible threshold, the first relative pose and the second relative pose are determined to be capable of correctly reflecting the constraint of loop, namely the loop detection result is determined to be credible. The correctness of the loop detection result can be further improved through the bidirectional loop constraint checking, so that the correctness of the potential loop pair detected by the loop detection can be further improved, and the consistency of the map after optimization can be improved.
Optionally, after the loop detection result is subjected to bidirectional loop constraint, some potential loop pairs which do not pass the bidirectional loop constraint test exist, the potential loop pairs which do not pass the bidirectional loop constraint test can be subjected to bidirectional loop constraint test again, and a preset trusted threshold is properly expanded in the test process, so that more loop constraints are obtained, the optimization effect of graph optimization is improved, and the consistency of the optimized map is improved.
And S240, under the condition that the loop detection result is accurate, performing first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map.
According to the technical scheme, forward loop constraint and reverse loop constraint are carried out on the loop detection result according to the pose information of the candidate frame, the pose information of the loop frame corresponding to the candidate frame, the pose information of the adjacent frame of the candidate frame and the pose information of the adjacent frame of the loop frame corresponding to the candidate frame, the correctness of the loop detection result is determined based on the forward loop constraint and the reverse loop constraint, the correctness of the loop detection result is further improved, and the consistency of the generated map is ensured.
Example III
Fig. 3 is a schematic structural diagram of a laser radar mapping optimization device according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes:
a map determining module 310, configured to determine an initial radar odometer map according to the collected laser radar point cloud data of the vehicle;
the loop detection module 320 is configured to determine a candidate frame of laser radar point cloud data in the initial radar odometer map, and perform loop detection based on pose information of the candidate frame, so as to obtain a loop detection result; wherein the loop detection result comprises at least one potential loop pair;
the result determining module 330 is configured to perform bidirectional loop constraint on the loop detection result, and determine whether the loop detection result is accurate based on the bidirectional loop constraint.
The first optimization module 340 is configured to perform a first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map when the loop detection result is accurate.
According to the technical scheme, loop detection is carried out on the candidate frames in the initial radar odometer map, and bidirectional loop constraint is carried out on the loop detection result, so that the relative pose of the loop constraint is calculated from two directions, whether the loop detection result is accurate or not is determined, the accuracy of the loop detection result is further improved compared with the unidirectional loop constraint, the problem of missing error detection is avoided, and the consistency of the generated map is ensured.
Optionally, the result determining module 330 includes:
the bidirectional loop constraint unit is used for carrying out forward constraint on the loop detection result according to the pose information of the candidate frame and the pose information of the adjacent frame of the loop frame corresponding to the candidate frame, carrying out reverse constraint on the loop detection result according to the pose information of the adjacent frame of the candidate frame and the pose information of the loop frame corresponding to the candidate frame, obtaining bidirectional loop constraint comprising forward constraint and reverse constraint, and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint.
Optionally, the bidirectional loop restraint unit may be specifically configured to: determining a first relative pose as a forward constraint according to pose information of the candidate frame and pose information of adjacent frames of the loop frame corresponding to the candidate frame; determining a second relative pose as a reverse constraint according to pose information of adjacent frames of the candidate frame and pose information of a loop frame corresponding to the candidate frame; if the difference between the first relative pose and the second relative pose is smaller than a preset credible threshold, determining that the loop detection result is accurate.
Optionally, the device further includes:
and the second optimization module is used for reducing the weight of the pose information in the graph optimization process and performing second graph optimization on the initial radar odometer map after the first graph optimization if the difference between the pose information of the candidate frame after the first graph optimization and the pose information of the candidate frame before the first graph optimization is larger than a preset difference.
Optionally, the map determining module 310 further includes:
the feature extraction unit is used for extracting features of the laser radar point cloud data according to the local curvature of the laser radar point cloud data;
and the initial map generation unit is used for carrying out point cloud feature matching on the laser radar point cloud data according to the extracted features of the laser radar point cloud data and the initial pose information of the vehicle, and generating an initial radar odometer point cloud map.
Optionally, the laser radar point cloud data can be obtained by collecting the laser radar point cloud data through a laser radar sensor arranged on the vehicle within a preset collecting time period and performing de-distortion treatment on the laser radar point cloud data according to pose information of the vehicle within the preset collecting time period.
Alternatively, the pose information may be determined by an inertial navigation system provided on the vehicle.
The laser radar map construction optimizing device provided by the embodiment of the invention can execute the laser radar map construction optimizing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example IV
Fig. 4 shows a schematic diagram of an electronic device 410 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 410 includes at least one processor 411, and a memory, such as a Read Only Memory (ROM) 412, a Random Access Memory (RAM) 413, etc., communicatively connected to the at least one processor 411, wherein the memory stores computer programs executable by the at least one processor, and the processor 411 may perform various suitable actions and processes according to the computer programs stored in the Read Only Memory (ROM) 412 or the computer programs loaded from the storage unit 418 into the Random Access Memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 may also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input/output (I/O) interface 415 is also connected to bus 414.
Various components in the electronic device 410 are connected to the I/O interface 415, including: an input unit 416 such as a keyboard, a mouse, etc.; an output unit 417 such as various types of displays, speakers, and the like; a storage unit 418, such as a magnetic disk, optical disk, or the like; and a communication unit 419 such as a network card, modem, wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processor 411 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 411 performs the various methods and processes described above, such as a lidar mapping optimization method.
In some embodiments, the lidar mapping optimization method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 418. In some embodiments, some or all of the computer program may be loaded and/or installed onto the electronic device 410 via the ROM 412 and/or the communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the lidar mapping optimization method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to perform the lidar mapping optimization method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The laser radar map construction optimization method is characterized by comprising the following steps of:
determining an initial radar odometer map according to the collected laser radar point cloud data of the vehicle;
determining a candidate frame of laser radar point cloud data in the initial radar odometer map, and performing loop detection based on pose information of the candidate frame to obtain a loop detection result; the loop detection result comprises at least one potential loop pair;
performing bidirectional loop constraint on the loop detection result, and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint;
and under the condition that the loop detection result is accurate, performing first graph optimization on the initial radar odometer map based on the bidirectional loop constraint to obtain an optimized radar odometer map.
2. The method of claim 1, wherein performing a bi-directional loop-back constraint on the loop-back detection result and determining whether the loop-back detection result is accurate based on the bi-directional loop-back constraint comprises:
and forward constraint is carried out on a loop detection result according to the pose information of the candidate frame and the pose information of the adjacent frame of the loop frame corresponding to the candidate frame, reverse constraint is carried out on the loop detection result according to the pose information of the adjacent frame of the candidate frame and the pose information of the loop frame corresponding to the candidate frame, bidirectional loop constraint comprising the forward constraint and the reverse constraint is obtained, and whether the loop detection result is accurate or not is determined based on the bidirectional loop constraint.
3. The method according to claim 2, wherein forward constraining the loop detection result according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame, and backward constraining the loop detection result according to pose information of the neighboring frame of the candidate frame and pose information of the loop frame corresponding to the candidate frame, to obtain a bidirectional loop constraint including the forward constraint and the backward constraint, and determining whether the loop detection result is accurate based on the bidirectional loop constraint, comprises:
determining a first relative pose as a forward constraint according to pose information of the candidate frame and pose information of a neighboring frame of the loop frame corresponding to the candidate frame;
determining a second relative pose as a reverse constraint according to pose information of adjacent frames of the candidate frame and pose information of a loop frame corresponding to the candidate frame;
and if the difference value between the first relative pose and the inverted second relative pose is smaller than a preset credible threshold value, determining that the loop detection result is accurate.
4. The method of claim 1, further comprising, after first map optimization of the initial radar odometer map based on the bi-directional loop-back constraints:
if the difference between the pose information of the candidate frame after the first graph optimization and the pose information of the candidate frame before the first graph optimization is larger than a preset difference, the weight of the pose information in the graph optimization process is reduced, and the second graph optimization is carried out on the initial radar odometer map after the first graph optimization.
5. The method of claim 1, wherein determining an initial radar odometer map from the collected lidar point cloud data of the vehicle comprises:
extracting features of the laser radar point cloud data according to the local curvature of the laser radar point cloud data;
and performing point cloud feature matching on the laser radar point cloud data according to the extracted features of the laser radar point cloud data and the initial pose information of the vehicle, and generating an initial radar odometer point cloud map.
6. The method according to claim 1, wherein the laser radar point cloud data is obtained by collecting laser radar point cloud data through a laser radar sensor arranged on a vehicle within a preset collecting period, and performing de-distortion processing on the laser radar point cloud data according to pose information of the vehicle within the preset collecting period.
7. The method of any one of claims 1-6, wherein the pose information is determined by an inertial navigation system disposed on the vehicle.
8. A lidar mapping optimization device, comprising:
the map determining module is used for determining an initial radar odometer map according to the acquired laser radar point cloud data of the vehicle;
the loop detection module is used for determining candidate frames of the laser radar point cloud data in the initial radar odometer map, and carrying out loop detection based on pose information of the candidate frames to obtain a loop detection result; the loop detection result comprises at least one potential loop pair;
the result determining module is used for carrying out bidirectional loop constraint on the loop detection result and determining whether the loop detection result is accurate or not based on the bidirectional loop constraint;
and the first optimization module is used for carrying out first graph optimization on the initial radar odometer map based on the bidirectional loop constraint under the condition that the loop detection result is accurate, so as to obtain an optimized radar odometer map.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the lidar mapping optimization method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the lidar mapping optimization method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311403393.6A CN117289238A (en) | 2023-10-26 | 2023-10-26 | Laser radar map construction optimization method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311403393.6A CN117289238A (en) | 2023-10-26 | 2023-10-26 | Laser radar map construction optimization method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117289238A true CN117289238A (en) | 2023-12-26 |
Family
ID=89258662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311403393.6A Pending CN117289238A (en) | 2023-10-26 | 2023-10-26 | Laser radar map construction optimization method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117289238A (en) |
-
2023
- 2023-10-26 CN CN202311403393.6A patent/CN117289238A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969145B (en) | Remote sensing image matching optimization method and device, electronic equipment and storage medium | |
| EP3943964A2 (en) | Method and apparatus for determining positioning information of vehicle, electronic device, storage medium and program product | |
| CN113205041A (en) | Structured information extraction method, device, equipment and storage medium | |
| CN115457152A (en) | External parameter calibration method and device, electronic equipment and storage medium | |
| CN113177980A (en) | Target object speed determination method and device for automatic driving and electronic equipment | |
| CN113029136A (en) | Method, apparatus, storage medium, and program product for positioning information processing | |
| CN116881583A (en) | Method and device for calculating matching degree of sensing data and space model of Internet of things | |
| US20230123671A1 (en) | Localization and mapping | |
| CN115311624B (en) | Slope displacement monitoring method and device, electronic equipment and storage medium | |
| CN117289238A (en) | Laser radar map construction optimization method, device, equipment and medium | |
| CN114120252B (en) | Automatic driving vehicle state identification method and device, electronic equipment and vehicle | |
| CN115727871A (en) | Track quality detection method and device, electronic equipment and storage medium | |
| CN116295466A (en) | Map generation method, map generation device, electronic device, storage medium and vehicle | |
| CN115147561A (en) | Pose graph generation method, high-precision map generation method and device | |
| CN114049615B (en) | Traffic object fusion association method and device in driving environment and edge computing equipment | |
| CN116258769B (en) | Positioning verification method and device, electronic equipment and storage medium | |
| CN114694138B (en) | Road surface detection method, device and equipment applied to intelligent driving | |
| CN117589188B (en) | Driving path planning method, driving path planning device, electronic equipment and storage medium | |
| CN116380056B (en) | Inertial positioning method, inertial positioning device, electronic equipment and storage medium | |
| CN117739993B (en) | Robot positioning method and device, robot and storage medium | |
| CN116448105B (en) | Pose updating method and device, electronic equipment and storage medium | |
| CN117743617A (en) | Character interaction detection method, model training method and device | |
| CN115356129A (en) | Vehicle chassis parameter calibration method and device, electronic equipment and storage medium | |
| CN117434515A (en) | Vehicle positioning method, device, equipment and medium based on inertial odometer | |
| CN117953073A (en) | Calibration parameter determining method and device for depth camera and electronic equipment |
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 |