CN112327312A - Vehicle pose determining method and device, vehicle and storage medium - Google Patents
Vehicle pose determining method and device, vehicle and storage medium Download PDFInfo
- Publication number
- CN112327312A CN112327312A CN202011176628.9A CN202011176628A CN112327312A CN 112327312 A CN112327312 A CN 112327312A CN 202011176628 A CN202011176628 A CN 202011176628A CN 112327312 A CN112327312 A CN 112327312A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- determining
- coordinate system
- local
- 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 48
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 230000006870 function Effects 0.000 claims description 46
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 239000013078 crystal Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
-
- 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)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a vehicle pose determining method, a vehicle pose determining device, a vehicle and a storage medium, wherein the method comprises the steps of determining correctly matched local reflecting data according to the local reflecting data and global reflecting data; constructing a residual error item e according to the correctly matched reflective data1(ii) a Constructing an optimization function from at least one residual term, wherein the at least one residual term comprises e1(ii) a And determining the vehicle pose according to the optimization function. By the scheme, optimization can be performed by using the matching constraint of the light reflecting part in the special scene of the tunnel, and the pose variable of the vehicle can be obtained with higher accuracy.
Description
Technical Field
The embodiment of the application relates to the field of automatic driving, in particular to a vehicle pose determining method and device, a vehicle and a storage medium.
Background
The laser radar sensor can be applied to the aspects of mapping, positioning, environment perception and the like in the field of automatic driving, but under some under-constrained scenes (such as open scenes and tunnel scenes), all pose variables of a vehicle cannot be obtained by singly using the laser radar sensor, so that multi-sensor fusion is required. Currently, laser radar, Global Positioning System (GPS), vehicle speed, and the like are widely used in the field of vehicle automatic driving. The GPS can solve the problem of the vehicle in an open scene, but because the GPS signal is not arranged in the tunnel, the technology cannot provide additional constraint for the vehicle. The vehicle speed has accumulated errors, and when the vehicle runs in the tunnel for a long time, the pose calculated based on the vehicle speed has larger errors.
Disclosure of Invention
The embodiment of the application provides a vehicle pose determining method and device, a vehicle and a storage medium, which can realize optimization by using matching constraint of a light reflecting part in a special scene of a tunnel, and obtain a pose variable of the vehicle with higher accuracy.
In a first aspect, an embodiment of the present application provides a vehicle pose determination method, where the method includes:
determining correctly matched local light reflection data according to the local light reflection data and the global light reflection data;
constructing a residual error item e according to the correctly matched reflective data1；
Constructing an optimization function from at least one residual term, wherein the at least one residual term comprises e1；
And determining the vehicle pose according to the optimization function.
Optionally, the determining, according to the local reflection data and the global reflection data, correct matching local reflection data includes:
acquiring correctly identified local light reflection data;
determining a distance difference between the correctly identified local reflection data and the global reflection data;
and if the distance difference meets a preset threshold value, determining the correctly identified local reflective data as the correctly matched local reflective data.
By adopting the implementation mode, the correctly matched local reflective data can be determined by taking the global reflective data as a reference.
Optionally, the acquiring correctly identified partial reflection data includes:
acquiring the number of candidate reflecting part points under a laser radar coordinate system;
calculating theoretical laser points according to laser radar scanning parameters;
if the absolute value of the difference value between the number of the candidate light reflecting parts and the theoretical laser point is within the threshold range, converting the position data of the candidate light reflecting parts from the laser radar coordinate system to the vehicle coordinate system;
and taking the converted position data as correct local reflection data for identification.
By designing the implementation mode, correct local reflection data can be determined and identified according to scanning parameters of the laser radar under a laser radar coordinate system.
Optionally, before determining the distance difference between the correctly identified local reflection data and the global reflection data, the method further comprises:
and converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system.
By adopting the technical means in the embodiment, the correctly identified reflective data can be converted into the coordinate system which is the same as the global reflective data, so that whether the correctly identified reflective data is correctly matched or not can be judged.
Optionally, the converting the correctly identified reflection data from the vehicle coordinate system to the world coordinate system includes:
converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system through a conversion function;
the transfer function is used for mapping the three-dimensional coordinate parameters into two-dimensional coordinate parameters.
The correctly identified reflection data can be translated from the vehicle coordinate system to the same world coordinate system as the global reflection data by the implementation process described above in this embodiment.
Optionally, the said according toThe correctly matched reflective data construct residual error item e1The method comprises the following steps:
determining a difference between the global reflectance data and the correctly matched reflectance data;
determining the difference as the residual term e1。
Through the designed implementation mode, the residual error item corresponding to the correctly matched reflective data can be obtained.
Optionally, constructing an optimization function according to at least one residual term includes:
an optimization function is constructed from the sum of the absolute values of at least one residual term.
By the implementation mode, the optimization function can be obtained to optimize the vehicle pose.
In a second aspect, an embodiment of the present application further provides a vehicle pose determination apparatus, including:
the determining module is used for determining correctly matched local reflecting data according to the local reflecting data and the global reflecting data;
a construction module for constructing a residual error item e according to the correctly matched reflective data1；
A construction module further configured to construct an optimization function according to at least one residual term, wherein the at least one residual term includes the e1；
And the determining module is also used for determining the vehicle pose according to the optimization function.
Optionally, the determining module is configured to obtain correctly identified local reflective data;
determining a distance difference between the correctly identified local reflection data and the global reflection data;
and if the distance difference meets a preset threshold value, determining that the correctly identified local reflective data is the correctly matched local reflective data.
Optionally, the determining module is configured to obtain the number of candidate light reflecting part points in a laser radar coordinate system;
calculating theoretical laser points according to laser radar scanning parameters;
if the absolute value of the difference value between the number of the candidate light reflecting parts and the theoretical laser point is within the threshold range, converting the position data of the candidate light reflecting parts from the laser radar coordinate system to the vehicle coordinate system;
and using the converted position data as correct local reflection data for identification.
Optionally, the apparatus may further include a conversion module;
and the conversion module is used for converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system.
Optionally, the conversion module is configured to convert the correctly identified reflection data from the vehicle coordinate system to the world coordinate system through a conversion function;
wherein the transfer function is used to map the three-dimensional coordinate parameters to two-dimensional coordinate parameters.
Optionally, the determining module is further configured to determine a difference between the global reflection data and the reflection data that is correctly matched;
and determining the difference as the residual term e1。
Optionally, the building module is configured to build an optimization function according to a sum of absolute values of the at least one residual term.
In a third aspect, embodiments of the present application further provide a vehicle, where the vehicle includes a memory, a controller, and a computer program stored on the memory and executable on the controller, and the controller, when executing the computer program, implements the vehicle pose determination method provided in the embodiments of the present application.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a controller, the vehicle pose determination method provided by the present application is implemented.
The embodiment of the application provides a vehicle pose determining method, a vehicle pose determining device, a vehicle and a storage medium, wherein the method comprises the step of determining the number of local reflections according toDetermining correctly matched local reflective data according to the global reflective data; constructing a residual error item e according to the correctly matched reflective data1(ii) a Constructing an optimization function from at least one residual term, wherein the at least one residual term comprises e1(ii) a And determining the vehicle pose according to the optimization function. By the scheme, optimization can be performed by using the matching constraint of the light reflecting part in the special scene of the tunnel, and the pose variable of the vehicle can be obtained with higher accuracy.
Drawings
FIG. 1 is a schematic view of a vehicle pose in a world coordinate system;
FIG. 2 is a schematic diagram of the conversion between the world coordinate system, the vehicle coordinate system and the lidar coordinate system;
FIG. 3 is a schematic view of a tunnel interior with a light reflecting component affixed thereto;
fig. 4 is a flowchart of a vehicle pose determination method in an embodiment of the present application;
FIG. 5 is a flow chart of a method of determining matching correct localized reflectance data in an embodiment of the present application;
FIG. 6 is a flowchart of a method for obtaining correctly identified partially reflective data in an embodiment of the present application;
FIG. 7 is a schematic view of a vehicle position determining apparatus in an embodiment of the present application;
fig. 8 is a schematic structural view of a vehicle in the embodiment of the present application;
fig. 9 is a block diagram of a computer-readable storage medium in an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
In addition, in the embodiments of the present application, the words "optionally" or "exemplarily" are used for indicating as examples, illustrations or explanations. Any embodiment or design described herein as "optionally" or "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "optionally" or "exemplarily" etc. is intended to present the relevant concepts in a concrete fashion.
In order to facilitate a clearer understanding of the methods provided in the embodiments of the present application, the related concepts related to the embodiments of the present application are explained herein, specifically as follows:
as shown in FIG. 1, the pose of the vehicle in the world coordinate system includes three parameters, x, y, and yaw, where x and y are the positions of the vehicle in the horizontal direction and the vertical direction, and yaw is the included angle between the vehicle direction and the horizontal direction. Assuming that the vehicle pose is expressed in a world coordinate system, and the vehicle coordinate system, the lidar coordinate system, and the world coordinate system can be transformed with each other through a calibrated algorithm, a transformation diagram between the three coordinate systems can be shown in fig. 2.
In a tunnel scene, because no fixed obstacle exists in front of the laser radar, the driving distance of the vehicle along the tunnel direction cannot be calculated according to the observation of the laser radar, and the driving distance can only be calculated through the speed of the vehicle. However, due to the accumulated error of the vehicle speed, the obtained distance of the vehicle running along the tunnel direction is not accurate. Based on the defect, the scheme provided by the application can obtain accurate driving distance in the tunnel direction and enhance the restriction in the transverse direction of the tunnel by adding the restriction by adhering the light reflecting parts (such as the light reflecting plates) on the two sides of the tunnel.
For example, as shown in fig. 3, reflectors with a height of 1 meter and a width of 0.1 meter may be adhered to both sides of the tunnel, and the distance between the reflectors on the same side is 5 meters. When the vehicle reaches the tunnel region, the laser radar can identify the reflector.
Based on the above concept, the embodiment of the present application provides a vehicle pose determination method, which may be applied in a tunnel scene, and a flowchart thereof is shown in fig. 4, where the method may include, but is not limited to, the following steps:
s401, determining correctly matched local reflective data according to the local reflective data and the global reflective data.
The partial reflection data in the embodiment of the present application may be understood as position data of the reflection member in the vehicle coordinate system. Illustratively, the position parameters may include coordinate positions x and y and an angular position yaw, i.e., the position data of the light reflecting member may be three-dimensional data. The global reflection data may be understood as position data of the light reflecting component in the world coordinate system, that is, the step may be understood as determining the correctly matched local reflection data according to the global reflection data and the local reflection data belonging to different coordinate systems.
S402, constructing a residual error item e according to the correctly matched reflective data1。
For example, in this embodiment of the application, the implementation manner of the residual error item constructed according to the correct-matching reflection data may be to determine a difference value between the global reflection data and the correct-matching reflection data, and determine the difference value as the residual error item e1. The implementation process can be expressed by the following formula
e1＝Wj-Proj(T*Li) (1)
Wherein L isiFor the ith matching of the correct reflection data, i.e. the position of the ith reflector in the vehicle coordinate system, WjThe jth global reflective data, namely the position of the jth reflective part in the world coordinate system, and T is the actual position of the vehicle.
It will be appreciated that i and j may be the same numerical value, i.e. representing the same retroreflective element in different coordinate systems.
And S403, constructing an optimization function according to the at least one residual error item.
Illustratively, this step may be to construct an optimization function from the sum of the absolute values of at least one residual term, for example:
(x，y，yaw)＝argmin∑|ei| (2)
wherein x, y and yaw are vehicle poses, eiTo the constructed residual terms.
Further, the at least one residual term may include the e1I.e. an optimization function is constructed at least on the basis of matching the correct light-reflecting components.
Optionally, in this embodiment of the application, the optimization function may be further constructed by combining a residual term of the laser matching result and a residual term constructed by the vehicle speed, that is, i in the above formula (2) is 3, and then the above formula (2) is also an optimization function constructed by respectively matching the correct reflective component, the laser matching result, and the vehicle speed according to the residual terms in three dimensions.
For example, the residual term constructed according to the laser matching result may be e2The residual term constructed from vehicle speed may be e3。
Wherein e is3＝P-Plast (3)
The above P may represent the pose of the vehicle at the present time estimated based on the vehicle speed, PlastThe vehicle pose obtained after the last time optimization can be represented.
Of course, a person skilled in the art may also construct a residual term based on reference factors of other aspects to establish the above-mentioned optimization function, so as to determine the vehicle pose, which is not limited in the embodiment of the present application.
And S404, determining the vehicle pose according to the optimization function.
After the optimization function in the above formula (2) is established, the pose of the vehicle at the current time, i.e., x, y, and yaw in the above formula (2), can be solved by using an optimization library, such as google ceres.
The embodiment of the application provides a vehicle pose determining method, which comprises the steps of determining correctly matched local reflection data according to the local reflection data and global reflection data; constructing a residual error item e according to the correctly matched reflective data1(ii) a Constructing an optimization function from at least one residual term, wherein the at least one residual term comprises e1(ii) a And determining the vehicle pose according to the optimization function. By the scheme, optimization can be performed by using the matching constraint of the light reflecting part in the special scene of the tunnel, and the pose variable of the vehicle can be obtained with higher accuracy.
As shown in fig. 5, in an example, the implementation manner of determining that the correct partial reflection data is matched in step S401 may include, but is not limited to, the following steps:
s501, correctly identified local light reflection data is obtained.
The local light reflection data correctly identified in the step can be understood as scanning the light reflection part inside the tunnel through the laser radar, and if the scanning result of the light reflection part meets a certain condition, the data of the light reflection part is the local light reflection data correctly identified through the laser radar.
It should be noted that when the vehicle primarily identifies the local reflective parts, a plurality of local reflective parts can be identified, and then the reflective data identified in the laser radar coordinate system can be converted into the world coordinate system, and the identified reflective parts are marked and indexed according to the identification sequence, and the corresponding reflective data is added into the global reflective data.
S502, determining the distance difference between the correctly identified local reflective data and the global reflective data.
Since the local reflective data is the position data of the reflective part in the vehicle coordinate system, and the global reflective data is the data in the world coordinate system, the correctly identified reflective data can be converted from the vehicle coordinate system to the world coordinate system before the step is executed, and then the distance difference between the two can be determined in the same coordinate system.
For example, the distance difference between the two can be determined by equation (4), which is as follows:
wherein x in the above formula (4)i、yiPosition data of the ith partial reflector in the world coordinate system, xj、yjThe position data of the jth global reflector in the world coordinate system is shown. Similarly, i and j may represent the same retroreflective element, i.e., may be the same value, except that xi、yiThe reflected light data represented is the reflected light data converted from the vehicle coordinate system to the world coordinate system.
And S503, if the distance difference meets a preset threshold, determining that the correctly identified local reflective data is correctly matched local reflective data.
Calculating by the formula (4), if the obtained distance difference meets a preset threshold, for example, is smaller than the preset threshold, it is determined that the correctly identified local light reflecting component is successfully matched, and accordingly, the correctly identified local light reflecting data is correctly matched local light reflecting data; on the contrary, if the distance difference is larger than or equal to the preset threshold, the correctly identified local reflector fails to be matched, and the correctly identified local reflector is used as a new reflector.
Optionally, the new retroreflective element data may be added to the global retroreflective data for reference in a subsequent matching process.
As shown in fig. 6, in an example, the implementation manner of obtaining the correctly identified partial reflection data in step S501 may include, but is not limited to, the following implementation manners, for example,
s601, acquiring the number of the candidate reflecting part points in a laser radar coordinate system.
For example, raw data of the lidar, such as values in different directions x, y, and z, and the intensity of the lidar, etc. are acquired in the lidar coordinate system. And selecting laser points with the reflection intensity exceeding the threshold value from the intensity threshold values, determining the selected laser points as candidate reflecting part points, and further determining the number of the candidate reflecting part points.
Wherein, the threshold value can be determined according to the type of the laser, the type of the light reflecting component and the actual scanning distance of the laser spot. Of course, those skilled in the art can determine other thresholds according to actual needs, and determine the number of candidate light reflecting part points according to the thresholds.
And S602, calculating the theoretical laser point number according to the laser radar scanning parameters.
Illustratively, a theoretical laser spot number, which can be understood as a laser spot number that the light reflecting member should theoretically have, can be calculated from the angular resolution of the laser radar, the width of the light reflecting member, the actual scanning distance and angle of the laser spot.
And S603, if the absolute value of the difference value between the point number of the candidate light reflecting part and the theoretical laser point number is in the threshold range, converting the position data of the candidate light reflecting part from the laser radar coordinate system to the vehicle coordinate system.
If the absolute value of the difference between the actually acquired number of the candidate light reflecting part and the calculated theoretical laser number is within the threshold range, which indicates that the actually acquired number of the light reflecting part is not much different from the theoretically calculated number, the candidate light reflecting part can be determined as the correctly identified light reflecting part. For the correctly identified light-reflecting component, the position data can be converted from the laser coordinate system to the vehicle coordinate system.
And if the absolute value of the difference value between the actually acquired candidate reflecting part point number and the calculated theoretical laser point number is not in the threshold range, namely the actually acquired reflecting part point number is greatly different from the theoretically calculated point number, determining the candidate reflecting part as the reflecting part with the identification error.
And S604, taking the converted position data as correct local light reflection data.
And storing the converted position data serving as correct local reflection data in the local reflection data.
In one example, the step S502 mentioned above, the implementation of converting the correctly identified reflection data from the vehicle coordinate system to the world coordinate system may include converting the correctly identified reflection data from the vehicle coordinate system to the world coordinate system through a conversion function. For example, this is achieved by the following formula:
Wi＝Proj(T*Li) (5)
wherein, WiFor correctly identified reflection data in the world coordinate system, LiFor correctly identified reflection data in a vehicle coordinate system, the Proj function represents a conversion function, which can be used to map a three-dimensional coordinate parameter to a two-dimensional coordinate parameter, and T can be calculated based on the vehicle pose, for example, according to the following formula (6) and the vehicle pose.
The above x, y, yaw represent the vehicle pose.
It should be noted that, when the correctly identified reflection data is converted from the vehicle coordinate system to the world coordinate system by the first formula and the vehicle pose, since the vehicle pose is not yet optimized, there may be a problem of low accuracy, when the new reflection data is added to the global reflection data in step S503, the data in the vehicle coordinate system corresponding to the new reflection data may be converted to the world coordinate system by the optimized vehicle pose, and the index thereof is marked, and then the data is added to the global reflection data, thereby improving the accuracy of subsequent data matching.
Fig. 7 is a vehicle position determining apparatus provided in an embodiment of the present application, which may be used to determine the pose of a vehicle with high accuracy in a contracted beam scene such as a tunnel, as shown in fig. 7, and the apparatus includes: a determining module 701 and a constructing module 702;
the determining module is used for determining correctly matched local reflecting data according to the local reflecting data and the global reflecting data;
a construction module for constructing a residual error item e according to the correctly matched reflective data1；
The construction module is further used for constructing an optimization function according to at least one residual error item, wherein the at least one residual error item comprises e1, namely the optimization function is constructed at least according to the residual error item matched with the correct reflective data;
and the determining module is also used for determining the vehicle pose according to the optimization function.
Illustratively, the optimization function may include
(x，y，yaw)＝argmin∑|ei|，
Wherein x, y and yaw are vehicle poses, eiTo the constructed residual terms.
In one example, the determining module may include an obtaining unit and a determining unit;
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring correctly identified local light reflection data;
a determining unit for determining a distance difference between the correctly identified local reflection data and the global reflection data;
further, if the distance difference satisfies a preset threshold, the determining unit is configured to determine that the correctly identified local reflective data is correctly matched local reflective data.
In an example, the obtaining unit is configured to obtain the number of candidate light reflecting part points in a laser radar coordinate system; calculating theoretical laser points according to the scanning parameters of the laser radar; if the absolute value of the difference value between the number of the candidate light reflecting parts and the theoretical laser point is within the threshold range, the position data of the candidate light reflecting parts are converted from the laser radar coordinate system to the vehicle coordinate system by the acquisition unit, and the converted position data is used as the correct local light reflecting data.
In one example, the apparatus may further include a conversion module 703;
and the conversion module is used for converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system.
Illustratively, the conversion module is configured to convert the correctly identified reflection data from the vehicle coordinate system to the world coordinate system through a conversion function, wherein the conversion function is as shown in the above equation (5).
Optionally, the determining module is further configured to determine a difference between the global reflection data and the reflection data with a correct match, and determine the difference as a residual term e1。
Optionally, the building module is configured to build an optimization function according to a sum of absolute values of the at least one residual term.
The vehicle pose determination device can execute the vehicle pose determination method provided by the figures 4 to 6, and has corresponding devices and beneficial effects in the method.
Fig. 8 is a schematic structural diagram of a vehicle according to embodiment 8 of the present invention, and as shown in fig. 8, the vehicle includes a controller 801, a memory 802, an input device 803, and an output device 804; the number of the controllers 801 in the vehicle may be one or more, and one controller 801 is illustrated in fig. 8; the controller 801, the memory 802, the input device 803, and the output device 804 in the vehicle may be connected by a bus or other means, and fig. 8 illustrates an example of connection by a bus.
The memory 802 is a computer-readable storage medium that can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (e.g., the determining module 701, the constructing module 702 in the vehicle pose determining apparatus) corresponding to the vehicle pose determining method in the embodiments of fig. 4 to 6. The controller 801 executes various functional applications and data processing of the crystal plane machine by running software programs, instructions, and modules stored in the memory 802, so as to implement the vehicle pose determination method described above.
The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 802 may further include memory located remotely from the controller 801, which may be connected to a terminal/server through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
As shown in fig. 9, embodiments of the present application also provide a storage medium 901 containing computer executable instructions, which when executed by a computer processor 902, are used to perform a vehicle pose determination method, which includes the steps shown in fig. 4 to 6.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to implement the methods or functions described in the embodiments of the present application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. A vehicle pose determination method, characterized by comprising:
determining correctly matched local light reflection data according to the local light reflection data and the global light reflection data;
constructing a residual error item e according to the correctly matched reflective data1；
Constructing an optimization function from at least one residual term, wherein the at least one residual term includes the e1；
And determining the vehicle pose according to the optimization function.
2. The method of claim 1, wherein determining from the local reflection data and the global reflection data that matches correct local reflection data comprises:
acquiring correctly identified local light reflection data;
determining a distance difference between the correctly identified local reflection data and the global reflection data;
and if the distance difference meets a preset threshold value, determining the correctly identified local reflective data as the correctly matched local reflective data.
3. The method of claim 2, wherein said obtaining correctly identified partial reflectance data comprises:
acquiring the number of candidate reflecting part points under a laser radar coordinate system;
calculating theoretical laser points according to laser radar scanning parameters;
if the absolute value of the difference value between the number of the candidate light reflecting parts and the theoretical laser point is within the threshold range, converting the position data of the candidate light reflecting parts from the laser radar coordinate system to the vehicle coordinate system;
and taking the converted position data as correctly identified local light reflection data.
4. The method of claim 2, wherein prior to determining the distance difference between the correctly identified local reflection data and the global reflection data, the method further comprises:
and converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system.
5. The method of claim 4, wherein said converting said correctly identified glint data from a vehicle coordinate system to a world coordinate system comprises:
converting the correctly identified reflective data from the vehicle coordinate system to the world coordinate system through a conversion function;
wherein the transfer function is used to map the three-dimensional coordinate parameters to two-dimensional coordinate parameters.
6. The method of claim 1, wherein said constructing a residual term e from said matching correct glint data1The method comprises the following steps:
determining a difference between the global reflectance data and the correctly matched reflectance data;
determining the difference as the residual term e1。
7. The method of claim 1, wherein constructing an optimization function from at least one residual term comprises:
an optimization function is constructed from the sum of the absolute values of at least one residual term.
8. A vehicle pose determination apparatus characterized by comprising:
the determining module is used for determining correctly matched local reflecting data according to the local reflecting data and the global reflecting data;
a construction module for constructing a residual error item e according to the correctly matched reflective data1；
The constructing module is further configured to construct an optimization function according to at least one residual term, wherein the at least one residual term includes the e1；
The determining module is further configured to determine a vehicle pose according to the optimization function.
9. A vehicle characterized by comprising a memory, a controller, and a computer program stored on the memory and executable on the controller, the controller implementing the vehicle pose determination method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the vehicle pose determination method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176628.9A CN112327312A (en) | 2020-10-28 | 2020-10-28 | Vehicle pose determining method and device, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176628.9A CN112327312A (en) | 2020-10-28 | 2020-10-28 | Vehicle pose determining method and device, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112327312A true CN112327312A (en) | 2021-02-05 |
Family
ID=74297240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011176628.9A Pending CN112327312A (en) | 2020-10-28 | 2020-10-28 | Vehicle pose determining method and device, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327312A (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06295400A (en) * | 1993-04-08 | 1994-10-21 | Daihatsu Motor Co Ltd | Preceding vehicle recognizing method for scan laser radar |
| CN103777220A (en) * | 2014-01-17 | 2014-05-07 | 西安交通大学 | Real-time and accurate pose estimation method based on fiber-optic gyroscope, speed sensor and GPS |
| CN106843222A (en) * | 2017-03-13 | 2017-06-13 | 苏州艾吉威机器人有限公司 | A kind of laser navigation AGV system of local paving reflecting plate |
| CN106908775A (en) * | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
| CN107239076A (en) * | 2017-06-28 | 2017-10-10 | 仲训昱 | The AGV laser SLAM methods matched based on virtual scan with ranging |
| US20170344015A1 (en) * | 2016-05-24 | 2017-11-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Driverless vehicle, method, apparatus and system for positioning driverless vehicle |
| CN107817500A (en) * | 2017-07-28 | 2018-03-20 | 浙江工业大学 | A kind of modularization stage laser positioning method |
| CN108562908A (en) * | 2017-12-21 | 2018-09-21 | 合肥中导机器人科技有限公司 | Laser navigation hybrid locating method, robot navigation method and Laser navigation system |
| CN110132130A (en) * | 2019-03-05 | 2019-08-16 | 上海宾通智能科技有限公司 | Laser radar position calibration method, system and its data processing method, system |
| US20190306666A1 (en) * | 2016-12-23 | 2019-10-03 | Cloudminds (Shenzhen) Robotics Systems Co., Ltd. | Positioning method, terminal and server |
| CN110456797A (en) * | 2019-08-19 | 2019-11-15 | 杭州电子科技大学 | A kind of AGV relocation system and method based on 2D laser sensor |
| CN110530368A (en) * | 2019-08-22 | 2019-12-03 | 浙江大华技术股份有限公司 | A kind of robot localization method and apparatus |
| CN110579215A (en) * | 2019-10-22 | 2019-12-17 | 上海木木机器人技术有限公司 | positioning method based on environmental feature description, mobile robot and storage medium |
| CN110705543A (en) * | 2019-08-23 | 2020-01-17 | 芜湖酷哇机器人产业技术研究院有限公司 | Method and system for recognizing lane lines based on laser point cloud |
| CN110927732A (en) * | 2019-10-21 | 2020-03-27 | 上海宾通智能科技有限公司 | Pose recognition method, electronic device, and storage medium |
| CN111174777A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Positioning method and device and electronic equipment |
| CN111307168A (en) * | 2020-03-19 | 2020-06-19 | 苏州艾吉威机器人有限公司 | AGV (automatic guided vehicle) map building method and positioning method and system |
| CN111337877A (en) * | 2020-03-19 | 2020-06-26 | 北京北特圣迪科技发展有限公司 | Reflector matching positioning method |
| CN111622145A (en) * | 2020-07-28 | 2020-09-04 | 北京主线科技有限公司 | Unmanned truck-collecting positioning method and system based on reflective spikes |
| CN111781609A (en) * | 2020-04-10 | 2020-10-16 | 昆山同孚智能技术有限公司 | AGV laser navigation multilateral positioning method |
| CN111830491A (en) * | 2020-08-04 | 2020-10-27 | 三一机器人科技有限公司 | Method and device for monitoring reflector in navigation system and electronic equipment |
-
2020
- 2020-10-28 CN CN202011176628.9A patent/CN112327312A/en active Pending
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06295400A (en) * | 1993-04-08 | 1994-10-21 | Daihatsu Motor Co Ltd | Preceding vehicle recognizing method for scan laser radar |
| CN103777220A (en) * | 2014-01-17 | 2014-05-07 | 西安交通大学 | Real-time and accurate pose estimation method based on fiber-optic gyroscope, speed sensor and GPS |
| US20170344015A1 (en) * | 2016-05-24 | 2017-11-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Driverless vehicle, method, apparatus and system for positioning driverless vehicle |
| US20190306666A1 (en) * | 2016-12-23 | 2019-10-03 | Cloudminds (Shenzhen) Robotics Systems Co., Ltd. | Positioning method, terminal and server |
| CN106908775A (en) * | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
| CN106843222A (en) * | 2017-03-13 | 2017-06-13 | 苏州艾吉威机器人有限公司 | A kind of laser navigation AGV system of local paving reflecting plate |
| CN107239076A (en) * | 2017-06-28 | 2017-10-10 | 仲训昱 | The AGV laser SLAM methods matched based on virtual scan with ranging |
| CN107817500A (en) * | 2017-07-28 | 2018-03-20 | 浙江工业大学 | A kind of modularization stage laser positioning method |
| CN108562908A (en) * | 2017-12-21 | 2018-09-21 | 合肥中导机器人科技有限公司 | Laser navigation hybrid locating method, robot navigation method and Laser navigation system |
| CN111174777A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Positioning method and device and electronic equipment |
| CN110132130A (en) * | 2019-03-05 | 2019-08-16 | 上海宾通智能科技有限公司 | Laser radar position calibration method, system and its data processing method, system |
| CN110456797A (en) * | 2019-08-19 | 2019-11-15 | 杭州电子科技大学 | A kind of AGV relocation system and method based on 2D laser sensor |
| CN110530368A (en) * | 2019-08-22 | 2019-12-03 | 浙江大华技术股份有限公司 | A kind of robot localization method and apparatus |
| CN110705543A (en) * | 2019-08-23 | 2020-01-17 | 芜湖酷哇机器人产业技术研究院有限公司 | Method and system for recognizing lane lines based on laser point cloud |
| CN110927732A (en) * | 2019-10-21 | 2020-03-27 | 上海宾通智能科技有限公司 | Pose recognition method, electronic device, and storage medium |
| CN110579215A (en) * | 2019-10-22 | 2019-12-17 | 上海木木机器人技术有限公司 | positioning method based on environmental feature description, mobile robot and storage medium |
| CN111307168A (en) * | 2020-03-19 | 2020-06-19 | 苏州艾吉威机器人有限公司 | AGV (automatic guided vehicle) map building method and positioning method and system |
| CN111337877A (en) * | 2020-03-19 | 2020-06-26 | 北京北特圣迪科技发展有限公司 | Reflector matching positioning method |
| CN111781609A (en) * | 2020-04-10 | 2020-10-16 | 昆山同孚智能技术有限公司 | AGV laser navigation multilateral positioning method |
| CN111622145A (en) * | 2020-07-28 | 2020-09-04 | 北京主线科技有限公司 | Unmanned truck-collecting positioning method and system based on reflective spikes |
| CN111830491A (en) * | 2020-08-04 | 2020-10-27 | 三一机器人科技有限公司 | Method and device for monitoring reflector in navigation system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4283328A1 (en) | Multi-radar and camera joint calibration method, system and device, and storage medium | |
| CN111413721B (en) | Vehicle positioning method, device, controller, intelligent vehicle and system | |
| EP2993490B1 (en) | Operating device, operating method, and program therefor | |
| CN112086010B (en) | Map generation method, map generation device, map generation equipment and storage medium | |
| CN111201448B (en) | Method and device for generating an inverted sensor model and method for identifying obstacles | |
| CN110807350A (en) | System and method for visual SLAM for scan matching | |
| WO2022142185A1 (en) | Pose data determination method and apparatus, and electronic device and vehicle | |
| CN111784835B (en) | Drawing method, drawing device, electronic equipment and readable storage medium | |
| US11029399B2 (en) | System and method for calibrating light intensity | |
| RU2767949C2 (en) | Method (options) and system for calibrating several lidar sensors | |
| CN112904358B (en) | Laser positioning method based on geometric information | |
| KR20230137395A (en) | 3D map construction method and device | |
| CN111552289A (en) | Detection method, virtual radar device, electronic apparatus, and storage medium | |
| CN116449392B (en) | Map construction method, device, computer equipment and storage medium | |
| JP2019192206A (en) | Charging stand recognition method, apparatus therefor, and robot | |
| CN111429515A (en) | Learning method of robot obstacle avoidance behavior based on deep learning | |
| CN113093128A (en) | Method and device for calibrating millimeter wave radar, electronic equipment and road side equipment | |
| CN107966702B (en) | construction method and device of environment map | |
| CN112255616B (en) | Multi-radar reflective column positioning method and reflective column positioning device | |
| CN113608170A (en) | Radar calibration method, radar, robot, medium, and computer program product | |
| CN112327312A (en) | Vehicle pose determining method and device, vehicle and storage medium | |
| CN116337062A (en) | Combined positioning method and system based on laser, reflector and two-dimensional code | |
| CN117818754B (en) | Course angle correction method and device, storage medium and electronic equipment | |
| US20240183984A1 (en) | Method and device for controlling mobile target robot for sensor calibration | |
| CN114462545A (en) | Map construction method and device based on semantic SLAM |
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 |