CN109725329A - A kind of unmanned vehicle localization method and device - Google Patents
A kind of unmanned vehicle localization method and device Download PDFInfo
- Publication number
- CN109725329A CN109725329A CN201910126935.7A CN201910126935A CN109725329A CN 109725329 A CN109725329 A CN 109725329A CN 201910126935 A CN201910126935 A CN 201910126935A CN 109725329 A CN109725329 A CN 109725329A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- laser point
- unmanned vehicle
- coordinate position
- matched
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The disclosure is directed to a kind of unmanned vehicle localization method and devices.The described method includes: obtaining the laser point cloud altitude information and laser point cloud reflection intensity data of unmanned vehicle, wherein, the laser point cloud altitude information includes the coordinate information and height of characteristic point, and the laser point cloud reflection intensity data includes the coordinate information and reflected intensity of characteristic point;The laser point cloud altitude information is matched with default laser point cloud height map, obtains matched positioning result;The laser point cloud reflection intensity data is matched with default laser point cloud reflected intensity map, reflected intensity is obtained and matches positioning result;The matched positioning result and reflected intensity matching positioning result are merged, and determine the location information of the unmanned vehicle based on the positioning result of fusion.The technical solution provided using each embodiment of the disclosure, can exclude the interference of some dynamic barriers, promote the accuracy of unmanned vehicle positioning.
Description
Technical field
This disclosure relates to unmanned technical field more particularly to a kind of unmanned vehicle localization method and device.
Background technique
Unmanned technology is a significant change of the vehicles, no matter traffic safety or convenient traffic is come
It says, all has a very important significance.Currently, unmanned technology is continuously developed, therefore, pilotless automobile replaces passing
The manual drive automobile of system is also within sight.
In the related technology during carrying out unmanned vehicle positioning, the static context information around car body is tended to rely on
(such as building, road sign), but such method is poorly suited for the unmanned vehicle positioning of dynamic environment, this is because dynamic ring
Dynamic barrier (such as vehicle of pedestrian, traveling) in border often interferes the feature extraction of static context information, leads to nothing
Method realizes accurate unmanned vehicle positioning.
Therefore, one kind is needed in the related technology, and more accurately unmanned vehicle positioning method is realized in dynamic environment.
Summary of the invention
To overcome the problems in correlation technique, the disclosure provides a kind of unmanned vehicle localization method and device.
According to the first aspect of the embodiments of the present disclosure, a kind of unmanned vehicle localization method is provided, comprising:
Obtain the laser point cloud altitude information and laser point cloud reflection intensity data of unmanned vehicle, wherein the laser point cloud
Altitude information includes the coordinate information and height of characteristic point, and the laser point cloud reflection intensity data includes the coordinate letter of characteristic point
Breath and reflected intensity;
The laser point cloud altitude information is matched with default laser point cloud height map, obtains matched positioning
As a result;
The laser point cloud reflection intensity data is matched with default laser point cloud reflected intensity map, obtains reflection
Strength matching positioning result;
The matched positioning result and reflected intensity matching positioning result are merged, and based on fusion
Positioning result determines the location information of the unmanned vehicle.
Optionally, in one embodiment of the present disclosure, described by the laser point cloud altitude information and default laser point
Cloud height map is matched, and matched positioning result is obtained, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, using particle filter algorithm to the high degree of the laser point cloud
It is matched according to default laser point cloud height map, generates particle distribution data, include multiple in the particle distribution data
Particle filter estimated value, the particle filter estimated value is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, described by the laser point cloud reflection intensity data and default sharp
Luminous point cloud reflected intensity map is matched, and is obtained reflected intensity and is matched positioning result, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, the laser point cloud is reflected using histogram algorithm filter
Intensity data is matched with default laser point cloud reflected intensity map, generates histogram distribution data, the histogram distribution
It include multiple elements in data, the element is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, described by the matched positioning result and the reflection is strong
Degree matching positioning result is merged, and the location information of the unmanned vehicle is determined based on the positioning result of fusion, comprising:
The maximum population in the particle distribution data is determined, based on the particle filter for including in the maximum population
The first coordinate position and first variance is calculated in estimated value;
The second coordinate position and second variance is calculated based on the element for including in the histogram distribution data;
Using the first variance as the weight of first coordinate position, the second variance as second coordinate
The weight of position is weighted and averaged calculating to first coordinate position and second coordinate position, obtain it is described nobody
The coordinate position of vehicle.
Optionally, in one embodiment of the present disclosure, to be in the maximum population include first coordinate position
Particle filter estimated value corresponding to coordinate position average value.
Optionally, in one embodiment of the present disclosure, second coordinate position is in the histogram distribution data
The average value of coordinate position corresponding to the element for including.
Optionally, in one embodiment of the present disclosure, the laser point cloud altitude information and laser for obtaining unmanned vehicle
Point cloud reflection intensity data, comprising:
Indoors under environment, the laser point cloud altitude information and laser point of unmanned vehicle are obtained using laser point cloud acquisition device
Cloud reflection intensity data, wherein the laser projection direction of the laser point cloud acquisition device is set as upward.
According to the second aspect of an embodiment of the present disclosure, a kind of unmanned vehicle positioning device is provided, comprising:
Laser point cloud acquisition device, for obtaining the laser point cloud altitude information and laser point cloud reflected intensity number of unmanned vehicle
According to, wherein the laser point cloud altitude information includes the coordinate information and height of characteristic point, the laser point cloud reflected intensity number
According to coordinate information and reflected intensity including characteristic point;
Processor is obtained for matching the laser point cloud altitude information with default laser point cloud height map
Matched positioning result;And for by the laser point cloud reflection intensity data and default laser point cloud reflected intensity
Figure is matched, and is obtained reflected intensity and is matched positioning result;And it is used for the matched positioning result and the reflection
Strength matching positioning result is merged, and the location information of the unmanned vehicle is determined based on the positioning result of fusion.
Optionally, in one embodiment of the present disclosure, the processor, is also used to:
Obtain predetermined priori position location;
Using the priori position location as initial position, using particle filter algorithm to the high degree of the laser point cloud
It is matched according to default laser point cloud height map, generates particle distribution data, include multiple in the particle distribution data
Particle filter estimated value, the particle filter estimated value is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, described by the laser point cloud reflection intensity data and default sharp
Luminous point cloud reflected intensity map is matched, and is obtained reflected intensity and is matched positioning result, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, the laser point cloud is reflected using histogram algorithm filter
Intensity data is matched with default laser point cloud reflected intensity map, generates histogram distribution data, the histogram distribution
It include multiple elements in data, the element is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, the processor, is also used to:
The maximum population in the particle distribution data is determined, based on the particle filter for including in the maximum population
The first coordinate position and first variance is calculated in estimated value;
The second coordinate position and second variance is calculated based on the element for including in the histogram distribution data;
Using the first variance as the weight of first coordinate position, the second variance as second coordinate
The weight of position is weighted and averaged calculating to first coordinate position and second coordinate position, obtain it is described nobody
The coordinate position of vehicle.
Optionally, in one embodiment of the present disclosure, to be in the maximum population include first coordinate position
Particle filter estimated value corresponding to coordinate position average value.
Optionally, in one embodiment of the present disclosure, second coordinate position is in the histogram distribution data
The average value of coordinate position corresponding to the element for including.
Optionally, in one embodiment of the present disclosure, indoors under environment, the laser of the laser point cloud acquisition device
Projecting direction is arranged to upward.
According to the third aspect of an embodiment of the present disclosure, a kind of unmanned vehicle positioning device is provided, comprising:
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to executing unmanned vehicle localization method described in any of the above-described embodiment.
According to a fourth aspect of embodiments of the present disclosure, a kind of non-transitorycomputer readable storage medium is provided, when described
When instruction in storage medium is executed by processor, enable a processor to execute the positioning of unmanned vehicle described in any of the above-described embodiment
Method.
The technical scheme provided by this disclosed embodiment can include the following benefits: each embodiment of the disclosure provides
Unmanned vehicle localization method and device, nobody can be carried out based on laser point cloud altitude information and laser point cloud reflection intensity data
Vehicle positioning, wherein altitude information is more significant feature in some special screnes (such as indoor environment), by altitude information and
Reflection intensity data carries out alignment by union, can promote the accuracy of unmanned vehicle positioning.In addition, passing through the laser point cloud height
Data can acquire the height of object in higher spatial, such as ceiling, tunnel top, the overline bridge in garage, without acquire compared with
The information of object in low spatial.Most of dynamic barrier, such as the vehicle of pedestrian, traveling are all active in compared in low spatial,
Therefore, the interference of some dynamic barriers can be excluded using the laser point cloud altitude information, promote the standard of unmanned vehicle positioning
True property.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of flow chart of unmanned vehicle localization method shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of unmanned vehicle localization method shown according to an exemplary embodiment.
Fig. 3 is a kind of block diagram of unmanned vehicle positioning device shown according to an exemplary embodiment.
Fig. 4 is a kind of block diagram of device shown according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of device shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
For convenience those skilled in the art understand that technical solution provided by the embodiments of the present application, first below to technical side
The technological accumulation and inheritance that case is realized is illustrated.
Based on the unmanned vehicle localization method that above technical need, the disclosure provide, the high degree of laser point cloud can be based on
Unmanned vehicle positioning is carried out according to laser point cloud reflection intensity data.Wherein, the laser point cloud altitude information may include for nobody
The elevation informations such as building, marker in vehicle ambient enviroment, therefore, the unmanned vehicle localization method that the disclosure provides are particularly suitable for
Place under indoor environment, such as garage, tunnel, overline bridge.In addition, can be acquired by the laser point cloud altitude information higher
The height of object in space, such as ceiling, tunnel top, the overline bridge in garage, without acquiring compared with the object in low spatial
Information.Most of dynamic barrier, such as the vehicle of pedestrian, traveling are all active in compared in low spatial, therefore, utilize the laser
Point cloud altitude information can exclude the interference of some dynamic barriers, promote the accuracy of unmanned vehicle positioning.
The unmanned vehicle localization method described in the disclosure is described in detail with reference to the accompanying drawing.Fig. 1 is that the disclosure mentions
A kind of method flow diagram of embodiment of the determination car body pose method of confession.Although present disclose provides as the following examples or attached
Method operating procedure shown in figure, but based on it is conventional or without creative labor may include in the method it is more or
The less operating procedure of person.In the step of there is no necessary causalities in logicality, the execution sequence of these steps is unlimited
Sequence is executed in what the embodiment of the present disclosure provided.
A kind of embodiment for the unmanned vehicle localization method that the specific disclosure provides is as shown in Figure 1, may include:
In step 101, the laser point cloud altitude information and laser point cloud reflection intensity data of unmanned vehicle are obtained, wherein institute
The coordinate information and height that laser point cloud altitude information includes characteristic point are stated, the laser point cloud reflection intensity data includes feature
The coordinate information and reflected intensity of point;
In step 103, the laser point cloud altitude information is matched with default laser point cloud height map, is obtained high
Degree matching positioning result;
In step 105, by the laser point cloud reflection intensity data and the progress of default laser point cloud reflected intensity map
Match, obtains reflected intensity and match positioning result;
In step 107, the matched positioning result and reflected intensity matching positioning result are merged, and
The location information of the unmanned vehicle is determined based on the positioning result of fusion.
In the embodiment of the present disclosure, the laser point cloud altitude information can be adopted by the laser point cloud height on the unmanned vehicle
Acquisition means collect, and the laser point cloud height acquisition device may include the energy such as multi-line laser radar, single line laser radar
Enough collect any device of laser point cloud data.In one example, laser irradiation to object back reflection characteristic point seat
Be designated as (x, y, z), then it can be using z as the height of characteristic point, the coordinate information of (x, y) as the characteristic point.Characteristic point
Reflected intensity may include the intensity that laser point irradiation object back reflection is returned, and numberical range may include [0,255], together
When, it can be associated with the reflected intensity by the coordinate position where the laser point.It should be noted that the laser point
Cloud altitude information and the laser point cloud reflection intensity data can be obtained from the same frame laser point cloud data of same laser radar
It obtains, can also be from different laser radars in the data of the acquisition of synchronization, the disclosure is without limitation.
It, can be by the laser point cloud height after obtaining the laser point cloud altitude information in the embodiment of the present disclosure
Data are matched with default laser point cloud height map, obtain matched positioning result.It is described pre- in the embodiment of the present disclosure
If laser point cloud height map can be the high-precision map comprising laser spot position information and height of pre-production.Based on this,
The laser point cloud altitude information and the default laser point cloud height map that will acquire are matched, available height
Match positioning result.In order to reduce subsequent matching primitives amount, the laser point cloud altitude information and the default laser point cloud
Height map can be 2-D data.But in practical applications, the laser point cloud got using devices such as laser radars
Altitude information is three dimensional point cloud, therefore, can convert the laser point in plane for three-dimensional laser point cloud altitude information
The laser point cloud altitude information of coordinate position each in three-dimensional space is converted to each coordinate in ground level by cloud data for projection
The laser point cloud altitude information of position.
In one embodiment of the present disclosure, by the laser point cloud altitude information and default laser point cloud height map
It is matched, during obtaining matched positioning result, available predetermined priori position location, and will be described
Priori position location is as initial position, using particle filter algorithm to the laser point cloud altitude information and default laser point
Cloud height map is matched, and particle distribution data are generated, and includes that multiple particles filter estimated value in the particle distribution data,
The particle filter estimated value is for indicating the posterior probability of car body at different locations.Wherein, the priori position location can
To include the current location for the unmanned vehicle determined by other positioning methods (such as IMU, inertial navigation system sensor), alternatively,
It also may include the current location for the unmanned vehicle predicted by certain prediction algorithm.It is then possible to first be assaied based on described
Position position, using particle filter algorithm to the laser point cloud altitude information and the progress of default laser point cloud height map
Match.Particle filter algorithm (Particle Filter, PF) algorithm can by find one group propagated in state space with
Press proof approximatively indicates probability density function originally, replaces integral operation with sample average, and then obtain the minimum of sample state
The process of variance evaluation.In the embodiments of the present disclosure, the random sample is the particle, and the particle is filtered corresponding to particle
Wave estimated value, the particle filter estimated value is for indicating the posterior probability of car body at different locations.In the embodiment of the present disclosure,
The particle filter algorithm may include optimal Bayesian Estimation algorithm, the important sampling algorithm of sequence, auxiliary sampling-resampling
Algorithm, regularization sampling algorithm, adaptive particle filter algorithm etc..The advantage of particle filter is the solution to challenge
Ability, such as non-linear, non-gaussian dynamical system the state recurrence estimation or probability inference problem of height.Pass through resampling skill
Art link can constantly correct the accuracy to car body position estimation, to promote the accuracy of particle filter estimated value.
It, can be by the laser point cloud after obtaining the laser point cloud reflection intensity data in the embodiment of the present disclosure
Reflection intensity data is matched with default laser point cloud reflected intensity map, is obtained reflected intensity and is matched positioning result.This public affairs
Open in embodiment, the default laser point cloud reflected intensity map can be pre-production comprising laser spot position information and anti-
Penetrate the high-precision map of intensity.Based on this, the laser point cloud reflection intensity data and the default laser point cloud that will acquire
Reflected intensity map is matched, available matched positioning result.Similarly, in order to reduce subsequent matching primitives
Amount can convert the laser point cloud data for projection in plane for three-dimensional laser point cloud reflection intensity data, i.e., by three-dimensional space
The laser point cloud that the laser point cloud reflection intensity data of interior each coordinate position is converted to each coordinate position in ground level is anti-
Penetrate intensity data.
In one embodiment of the present disclosure, by the laser point cloud altitude information and default laser point cloud height map
It is matched, during obtaining matched positioning result, available predetermined priori position location, and will be described
It to the laser point cloud reflection intensity data and is preset as initial position using histogram algorithm filter priori position location
Laser point cloud reflected intensity map is matched, and histogram distribution data is generated, and includes multiple in the histogram distribution data
Element, the element is for indicating the posterior probability of car body at different locations.
In one embodiment, it to the laser point cloud reflection intensity data and is preset using histogram algorithm filter
During the progress of laser point cloud reflected intensity map is matched, the default laser point cloud reflected intensity map can be set more
A equal-sized map grid is based on this, the coordinate range of the laser point cloud reflection intensity data can be also divided into
With the equal-sized grid of the map grid.It is then possible to by the laser point cloud reflected intensity number after grid division
It is registrated according to the default laser point cloud reflected intensity map for being provided with map grid, and being registrated range is with the elder generation
Test the predeterminable area centered on position location.In registration process, the laser point cloud reflection in each grid can be calculated separately
Matching probability between intensity, and determine to reflect by force with the laser point cloud from the default laser point cloud reflected intensity map
For degree according to most matched target area, each grid in the target area corresponds respectively to a matching probability.The disclosure
In embodiment, it can use histogram algorithm filter and the matching probability in the target area optimized, described in generation
Histogram distribution data includes multiple elements in the histogram distribution data, and the element is for indicating car body in different positions
Set the posterior probability at place.Wherein, the element may include in the grid position and each position in the target area
With probability, the matching probability is the posterior probability.
In the embodiments of the present disclosure, the matched positioning result and reflected intensity matching positioning result are being determined
Later, the two results can be merged, and determines the location information of the unmanned vehicle based on the positioning result of fusion.Such as
Shown in Fig. 2, in one embodiment of the present disclosure, may include:
In step 201, the maximum population in the particle distribution data is determined, based on including in the maximum population
Particle filter estimated value the first coordinate position and first variance is calculated;
In step 203, the second coordinate position and are calculated based on the element for including in the histogram distribution data
Two variances;
In step 205, using the first variance as the weight of first coordinate position, the second variance as institute
The weight for stating the second coordinate position is weighted and averaged calculating to first coordinate position and second coordinate position, obtains
To the coordinate position of the unmanned vehicle.
In the embodiment of the present disclosure, it is described maximum population may include in the particle distribution data particle density it is maximum
Population in region.In practical applications, population is more intensive, and the probability value that unmanned vehicle is located at the position is bigger.Therefore,
Determine that maximum population is played an important role for being accurately determined the position of unmanned vehicle.Determine the maximum population it
Afterwards, the first coordinate position and first party can be calculated based on the particle filter estimated value for including in the maximum population
Difference.In one embodiment of the present disclosure, first coordinate position can be filtered for the particle for including in the maximum population
The average value of coordinate position corresponding to wave estimated value.The first variance is the particle filter estimated value of the maximum population
Variance yields.
In one embodiment of the present disclosure, it can be calculated based on the element for including in the histogram distribution data
Second coordinate position and second variance.In one example, second coordinate position can be the histogram distribution data
In include element corresponding to coordinate position average value, i.e., by the corresponding coordinate bit of each grid in the target area
It sets and averages.The second variance be the target area in each grid in posterior probability variance yields.
It, can be using the first variance as the weight of first coordinate position, institute in one embodiment of the disclosure
Weight of the second variance as second coordinate position is stated, first coordinate position and second coordinate position are carried out
Weighted average calculation obtains the coordinate position of the unmanned vehicle.In one example, the coordinate position of unmanned vehicle can be with are as follows:
(x, y)=α (x1+y1)+β(x2+y2)
Wherein, (x, y) is the coordinate position of unmanned vehicle, and (x1, y1) is first coordinate position, and α is the first party
Difference, (x2, y2) are second coordinate position, and β is the second variance.
In the embodiment of the present disclosure, laser point cloud acquisition device can also be utilized to obtain swashing for unmanned vehicle indoors under environment
Luminous point cloud altitude information and laser point cloud reflection intensity data, wherein the laser projection direction of the laser point cloud acquisition device
It is set as upward.The technical solution of the application is particularly suitable for place under indoor environment, such as garage, tunnel, overline bridge.Cause
This, can set in the laser projection direction of the laser point cloud acquisition device to upwards, such as by the projecting direction of laser radar
It points up, of course, it is possible to be also possible to the top for having in some angular ranges with Z axis right above being.
The unmanned vehicle localization method that each embodiment of the disclosure provides, can be based on laser point cloud altitude information and laser point
Cloud reflection intensity data carries out unmanned vehicle positioning, wherein altitude information is to compare mark in some special screnes (such as indoor environment)
Altitude information and reflection intensity data are carried out alignment by union, can promote the accuracy of unmanned vehicle positioning by the feature of will.Separately
Outside, the height that object in higher spatial can be acquired by the laser point cloud altitude information, ceiling, tunnel top such as garage
Portion, overline bridge etc., without acquiring the information compared with the object in low spatial.Most of dynamic barrier, such as pedestrian, the vehicle of traveling
Deng being all active in compared in low spatial, therefore, the dry of some dynamic barriers can be excluded using the laser point cloud altitude information
It disturbs, promotes the accuracy of unmanned vehicle positioning.
On the other hand the disclosure also provides a kind of unmanned vehicle positioning device, Fig. 3 is shown according to an exemplary embodiment
The block diagram of unmanned vehicle positioning device 300.Referring to Fig. 3, which includes laser point cloud acquisition device 301, processor 303, wherein
Laser point cloud acquisition device 301, the laser point cloud altitude information and laser point cloud reflection for obtaining unmanned vehicle are strong
Degree evidence, wherein the laser point cloud altitude information includes the coordinate information and height of characteristic point, and the laser point cloud reflection is strong
Degree is according to the coordinate information and reflected intensity for including characteristic point;
Processor 303 is obtained for matching the laser point cloud altitude information with default laser point cloud height map
Take matched positioning result;And it is used for the laser point cloud reflection intensity data and default laser point cloud reflected intensity
Map is matched, and is obtained reflected intensity and is matched positioning result;And for by the matched positioning result and described anti-
It penetrates strength matching positioning result to be merged, and determines the location information of the unmanned vehicle based on the positioning result of fusion.
Optionally, in one embodiment of the present disclosure, the processor, is also used to:
Obtain predetermined priori position location;
Using the priori position location as initial position, using particle filter algorithm to the high degree of the laser point cloud
It is matched according to default laser point cloud height map, generates particle distribution data, include multiple in the particle distribution data
Particle filter estimated value, the particle filter estimated value is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, described by the laser point cloud reflection intensity data and default sharp
Luminous point cloud reflected intensity map is matched, and is obtained reflected intensity and is matched positioning result, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, the laser point cloud is reflected using histogram algorithm filter
Intensity data is matched with default laser point cloud reflected intensity map, generates histogram distribution data, the histogram distribution
It include multiple elements in data, the element is for indicating the posterior probability of car body at different locations.
Optionally, in one embodiment of the present disclosure, the processor, is also used to:
The maximum population in the particle distribution data is determined, based on the particle filter for including in the maximum population
The first coordinate position and first variance is calculated in estimated value;
The second coordinate position and second variance is calculated based on the element for including in the histogram distribution data;
Using the first variance as the weight of first coordinate position, the second variance as second coordinate
The weight of position is weighted and averaged calculating to first coordinate position and second coordinate position, obtain it is described nobody
The coordinate position of vehicle.
Optionally, in one embodiment of the present disclosure, to be in the maximum population include first coordinate position
Particle filter estimated value corresponding to coordinate position average value.
Optionally, in one embodiment of the present disclosure, second coordinate position is in the histogram distribution data
The average value of coordinate position corresponding to the element for including.
Optionally, in one embodiment of the present disclosure, indoors under environment, the laser of the laser point cloud acquisition device
Projecting direction is arranged to upward.
Fig. 4 is a kind of block diagram of device 700 for resource distribution instruction shown according to an exemplary embodiment.Example
Such as, device 700 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, and plate is set
It is standby, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 4, device 700 may include following one or more components: processing component 702, memory 704, power supply
Component 706, multimedia component 708, audio component 710, the interface 712 of input/output (I/O), sensor module 714, and
Communication component 716.
The integrated operation of the usual control device 700 of processing component 702, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 702 may include that one or more processors 720 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 702 may include one or more modules, just
Interaction between processing component 702 and other assemblies.For example, processing component 702 may include multi-media module, it is more to facilitate
Interaction between media component 708 and processing component 702.
Memory 704 is configured as storing various types of data to support the operation in device 700.These data are shown
Example includes the instruction of any application or method for operating on device 700, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 704 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 706 provides electric power for the various assemblies of device 700.Power supply module 706 may include power management system
System, one or more power supplys and other with for device 700 generate, manage, and distribute the associated component of electric power.
Multimedia component 708 includes the screen of one output interface of offer between described device 700 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch-sensitive display, to transmit input signal from the user.Touch panel includes one or more touches
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments,
Multimedia component 708 includes a front camera and/or rear camera.When device 700 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can transmit external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 710 is configured as output and/or input audio signal.For example, audio component 710 includes a Mike
Wind (MIC), when device 700 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to transmission external audio signal.The audio signal transmitted can be further stored in memory 704 or via communication set
Part 716 is sent.In some embodiments, audio component 710 further includes a loudspeaker, is used for output audio signal.
I/O interface 712 provides interface between processing component 702 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 714 includes one or more sensors, and the state for providing various aspects for device 700 is commented
Estimate.For example, sensor module 714 can detecte the state that opens/closes of device 700, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 700, and sensor module 714 can be with 700 1 components of detection device 700 or device
Position change, the existence or non-existence that user contacts with device 700,700 orientation of device or acceleration/deceleration and device 700
Temperature change.Sensor module 714 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 714 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 716 is configured to facilitate the communication of wired or wireless way between device 700 and other equipment.Device
700 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, broadcast singal or broadcast related information of the communication component 716 via broadcast channel transmission from external broadcasting management system.
In one exemplary embodiment, the communication component 716 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 700 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 704 of instruction, above-metioned instruction can be executed by the processor 720 of device 700 to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
Fig. 5 is a kind of block diagram of device 800 for information processing shown according to an exemplary embodiment.For example, dress
Setting 800 may be provided as a server.Referring to Fig. 5, device 800 includes processing component 822, further comprises one or more
A processor, and the memory resource as representated by memory 832, can be by the finger of the execution of processing component 822 for storing
It enables, such as application program.The application program stored in memory 832 may include it is one or more each correspond to
The module of one group of instruction.In addition, processing component 822 is configured as executing instruction, to execute side described in any of the above-described embodiment
Method.
Device 800 can also include the power management that a power supply module 826 is configured as executive device 800, and one has
Line or radio network interface 850 are configured as device 800 being connected to network and input and output (I/O) interface 858.Dress
Setting 800 can operate based on the operating system for being stored in memory 832, such as Windows ServerTM, Mac OS XTM,
UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 832 of instruction, above-metioned instruction can be executed by the processing component 822 of device 800 to complete the above method.Example
Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (16)
1. a kind of unmanned vehicle localization method characterized by comprising
Obtain the laser point cloud altitude information and laser point cloud reflection intensity data of unmanned vehicle, wherein the laser point cloud height
Data include the coordinate information and height of characteristic point, the laser point cloud reflection intensity data include characteristic point coordinate information and
Reflected intensity;
The laser point cloud altitude information is matched with default laser point cloud height map, obtains matched positioning knot
Fruit;
The laser point cloud reflection intensity data is matched with default laser point cloud reflected intensity map, obtains reflected intensity
Match positioning result;
The matched positioning result and reflected intensity matching positioning result are merged, and the positioning based on fusion
As a result the location information of the unmanned vehicle is determined.
2. unmanned vehicle localization method according to claim 1, which is characterized in that described by the laser point cloud altitude information
It is matched with default laser point cloud height map, obtains matched positioning result, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, using particle filter algorithm to the laser point cloud altitude information with
Default laser point cloud height map is matched, and particle distribution data are generated, and includes multiple particles in the particle distribution data
Estimated value is filtered, the particle filter estimated value is for indicating the posterior probability of car body at different locations.
3. unmanned vehicle localization method according to claim 2, which is characterized in that described by the laser point cloud reflected intensity
Data are matched with default laser point cloud reflected intensity map, are obtained reflected intensity and are matched positioning result, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, using histogram algorithm filter to the laser point cloud reflected intensity
Data are matched with default laser point cloud reflected intensity map, generate histogram distribution data, the histogram distribution data
In include multiple elements, the element is for indicating the posterior probability of car body at different locations.
4. unmanned vehicle localization method according to claim 3, which is characterized in that described by the matched positioning result
It is merged with reflected intensity matching positioning result, and determines that the position of the unmanned vehicle is believed based on the positioning result of fusion
Breath, comprising:
The maximum population in the particle distribution data is determined, based on the particle filter estimation for including in the maximum population
The first coordinate position and first variance is calculated in value;
The second coordinate position and second variance is calculated based on the element for including in the histogram distribution data;
Using the first variance as the weight of first coordinate position, the second variance as second coordinate position
Weight, calculating is weighted and averaged to first coordinate position and second coordinate position, obtains the unmanned vehicle
Coordinate position.
5. unmanned vehicle localization method according to claim 4, which is characterized in that first coordinate position is the maximum
The average value of coordinate position corresponding to the particle filter estimated value for including in population.
6. unmanned vehicle localization method according to claim 4, which is characterized in that second coordinate position is the histogram
The average value of coordinate position corresponding to the element for including in figure distributed data.
7. unmanned vehicle localization method according to claim 1, which is characterized in that the laser point cloud level for obtaining unmanned vehicle
Degree evidence and laser point cloud reflection intensity data, comprising:
It is anti-using the laser point cloud altitude information and laser point cloud of laser point cloud acquisition device acquisition unmanned vehicle indoors under environment
Penetrate intensity data, wherein the laser projection direction of the laser point cloud acquisition device is set as upward.
8. a kind of unmanned vehicle positioning device characterized by comprising
Laser point cloud acquisition device, for obtaining the laser point cloud altitude information and laser point cloud reflection intensity data of unmanned vehicle,
Wherein, the laser point cloud altitude information includes the coordinate information and height of characteristic point, the laser point cloud reflection intensity data
Coordinate information and reflected intensity including characteristic point;
Processor obtains height for matching the laser point cloud altitude information with default laser point cloud height map
Match positioning result;And for by the laser point cloud reflection intensity data and default laser point cloud reflected intensity map into
Row matching obtains reflected intensity and matches positioning result;And it is used for the matched positioning result and the reflected intensity
Matching positioning result is merged, and the location information of the unmanned vehicle is determined based on the positioning result of fusion.
9. unmanned vehicle positioning device according to claim 8, which is characterized in that the processor is also used to:
Obtain predetermined priori position location;
Using the priori position location as initial position, using particle filter algorithm to the laser point cloud altitude information with
Default laser point cloud height map is matched, and particle distribution data are generated, and includes multiple particles in the particle distribution data
Estimated value is filtered, the particle filter estimated value is for indicating the posterior probability of car body at different locations.
10. unmanned vehicle positioning device according to claim 9, which is characterized in that described to reflect the laser point cloud by force
Degree obtains reflected intensity and matches positioning result according to being matched with default laser point cloud reflected intensity map, comprising:
Obtain predetermined priori position location;
Using the priori position location as initial position, using histogram algorithm filter to the laser point cloud reflected intensity
Data are matched with default laser point cloud reflected intensity map, generate histogram distribution data, the histogram distribution data
In include multiple elements, the element is for indicating the posterior probability of car body at different locations.
11. unmanned vehicle positioning device according to claim 10, which is characterized in that the processor is also used to:
The maximum population in the particle distribution data is determined, based on the particle filter estimation for including in the maximum population
The first coordinate position and first variance is calculated in value;
The second coordinate position and second variance is calculated based on the element for including in the histogram distribution data;
Using the first variance as the weight of first coordinate position, the second variance as second coordinate position
Weight, calculating is weighted and averaged to first coordinate position and second coordinate position, obtains the unmanned vehicle
Coordinate position.
12. unmanned vehicle positioning device according to claim 11, which is characterized in that first coordinate position be it is described most
The average value of coordinate position corresponding to the particle filter estimated value for including in big population.
13. unmanned vehicle positioning device according to claim 11, which is characterized in that second coordinate position is described straight
The average value of coordinate position corresponding to the element for including in square figure distributed data.
14. unmanned vehicle positioning device according to claim 8, which is characterized in that indoors under environment, the laser point cloud
The laser projection direction of acquisition device is arranged to upward.
15. a kind of unmanned vehicle positioning device characterized by comprising
Processor;
Memory for storage processor executable instruction;
Wherein, the processor is configured to perform claim requires method described in 1-7 any one.
16. a kind of non-transitorycomputer readable storage medium makes when the instruction in the storage medium is executed by processor
It obtains processor and is able to carry out method described in claim 1-7 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910126935.7A CN109725329B (en) | 2019-02-20 | 2019-02-20 | Unmanned vehicle positioning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910126935.7A CN109725329B (en) | 2019-02-20 | 2019-02-20 | Unmanned vehicle positioning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109725329A true CN109725329A (en) | 2019-05-07 |
CN109725329B CN109725329B (en) | 2021-12-07 |
Family
ID=66301564
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910126935.7A Active CN109725329B (en) | 2019-02-20 | 2019-02-20 | Unmanned vehicle positioning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109725329B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110488818A (en) * | 2019-08-08 | 2019-11-22 | 深圳市银星智能科技股份有限公司 | A kind of robot localization method, apparatus and robot based on laser radar |
CN110967011A (en) * | 2019-12-25 | 2020-04-07 | 苏州智加科技有限公司 | Positioning method, device, equipment and storage medium |
CN111510866A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技(深圳)有限公司 | Positioning system, method and equipment |
CN111983582A (en) * | 2020-08-14 | 2020-11-24 | 北京埃福瑞科技有限公司 | Train positioning method and system |
DE102019208504A1 (en) * | 2019-06-12 | 2020-12-17 | Robert Bosch Gmbh | Position determination based on environmental observations |
CN112154355A (en) * | 2019-09-19 | 2020-12-29 | 深圳市大疆创新科技有限公司 | High-precision map positioning method, system, platform and computer readable storage medium |
CN112446907A (en) * | 2020-11-19 | 2021-03-05 | 武汉中海庭数据技术有限公司 | Method and device for registering single-line point cloud and multi-line point cloud |
CN112762824A (en) * | 2020-12-24 | 2021-05-07 | 中南大学 | Unmanned vehicle positioning method and system |
WO2021143778A1 (en) * | 2020-01-14 | 2021-07-22 | 长沙智能驾驶研究院有限公司 | Positioning method based on laser radar |
CN116879870A (en) * | 2023-06-08 | 2023-10-13 | 哈尔滨理工大学 | Dynamic obstacle removing method suitable for low-wire-harness 3D laser radar |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103900583A (en) * | 2012-12-25 | 2014-07-02 | 联想(北京)有限公司 | Device and method used for real-time positioning and map building |
CN105180955A (en) * | 2015-10-21 | 2015-12-23 | 福州华鹰重工机械有限公司 | Real-time precise positioning method and real-time precise positioning device of motor vehicles |
CN106023210A (en) * | 2016-05-24 | 2016-10-12 | 百度在线网络技术(北京)有限公司 | Unmanned vehicle, and unmanned vehicle positioning method, device and system |
CN106052697A (en) * | 2016-05-24 | 2016-10-26 | 百度在线网络技术(北京)有限公司 | Driverless vehicle, driverless vehicle positioning method, driverless vehicle positioning device and driverless vehicle positioning system |
US20180192059A1 (en) * | 2016-12-30 | 2018-07-05 | DeepMap Inc. | Encoding lidar scanned data for generating high definition maps for autonomous vehicles |
CN108632761A (en) * | 2018-04-20 | 2018-10-09 | 西安交通大学 | A kind of indoor orientation method based on particle filter algorithm |
CN108732603A (en) * | 2017-04-17 | 2018-11-02 | 百度在线网络技术(北京)有限公司 | Method and apparatus for positioning vehicle |
CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术(北京)有限公司 | Accurately drawing generating method, device and storage medium |
CN109146976A (en) * | 2018-08-23 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | Method and apparatus for positioning unmanned vehicle |
CN109186625A (en) * | 2018-10-24 | 2019-01-11 | 北京奥特贝睿科技有限公司 | Intelligent vehicle carries out pinpoint method and system using mixing sampling filter |
-
2019
- 2019-02-20 CN CN201910126935.7A patent/CN109725329B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103900583A (en) * | 2012-12-25 | 2014-07-02 | 联想(北京)有限公司 | Device and method used for real-time positioning and map building |
CN105180955A (en) * | 2015-10-21 | 2015-12-23 | 福州华鹰重工机械有限公司 | Real-time precise positioning method and real-time precise positioning device of motor vehicles |
CN106023210A (en) * | 2016-05-24 | 2016-10-12 | 百度在线网络技术(北京)有限公司 | Unmanned vehicle, and unmanned vehicle positioning method, device and system |
CN106052697A (en) * | 2016-05-24 | 2016-10-26 | 百度在线网络技术(北京)有限公司 | Driverless vehicle, driverless vehicle positioning method, driverless vehicle positioning device and driverless vehicle positioning system |
US20180192059A1 (en) * | 2016-12-30 | 2018-07-05 | DeepMap Inc. | Encoding lidar scanned data for generating high definition maps for autonomous vehicles |
CN108732603A (en) * | 2017-04-17 | 2018-11-02 | 百度在线网络技术(北京)有限公司 | Method and apparatus for positioning vehicle |
CN108632761A (en) * | 2018-04-20 | 2018-10-09 | 西安交通大学 | A kind of indoor orientation method based on particle filter algorithm |
CN109064506A (en) * | 2018-07-04 | 2018-12-21 | 百度在线网络技术(北京)有限公司 | Accurately drawing generating method, device and storage medium |
CN109146976A (en) * | 2018-08-23 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | Method and apparatus for positioning unmanned vehicle |
CN109186625A (en) * | 2018-10-24 | 2019-01-11 | 北京奥特贝睿科技有限公司 | Intelligent vehicle carries out pinpoint method and system using mixing sampling filter |
Non-Patent Citations (1)
Title |
---|
陈慧岩等: "《无人驾驶汽车概论》", 31 July 2014 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102019208504A1 (en) * | 2019-06-12 | 2020-12-17 | Robert Bosch Gmbh | Position determination based on environmental observations |
CN110488818B (en) * | 2019-08-08 | 2020-07-17 | 深圳市银星智能科技股份有限公司 | Laser radar-based robot positioning method and device and robot |
CN110488818A (en) * | 2019-08-08 | 2019-11-22 | 深圳市银星智能科技股份有限公司 | A kind of robot localization method, apparatus and robot based on laser radar |
WO2021051361A1 (en) * | 2019-09-19 | 2021-03-25 | 深圳市大疆创新科技有限公司 | High-precision map positioning method and system, platform and computer-readable storage medium |
CN112154355B (en) * | 2019-09-19 | 2024-03-01 | 深圳市大疆创新科技有限公司 | High-precision map positioning method, system, platform and computer readable storage medium |
CN112154355A (en) * | 2019-09-19 | 2020-12-29 | 深圳市大疆创新科技有限公司 | High-precision map positioning method, system, platform and computer readable storage medium |
CN110967011A (en) * | 2019-12-25 | 2020-04-07 | 苏州智加科技有限公司 | Positioning method, device, equipment and storage medium |
WO2021143778A1 (en) * | 2020-01-14 | 2021-07-22 | 长沙智能驾驶研究院有限公司 | Positioning method based on laser radar |
CN111510866A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技(深圳)有限公司 | Positioning system, method and equipment |
CN111983582A (en) * | 2020-08-14 | 2020-11-24 | 北京埃福瑞科技有限公司 | Train positioning method and system |
CN112446907A (en) * | 2020-11-19 | 2021-03-05 | 武汉中海庭数据技术有限公司 | Method and device for registering single-line point cloud and multi-line point cloud |
CN112762824A (en) * | 2020-12-24 | 2021-05-07 | 中南大学 | Unmanned vehicle positioning method and system |
CN112762824B (en) * | 2020-12-24 | 2022-04-22 | 中南大学 | Unmanned vehicle positioning method and system |
CN116879870A (en) * | 2023-06-08 | 2023-10-13 | 哈尔滨理工大学 | Dynamic obstacle removing method suitable for low-wire-harness 3D laser radar |
Also Published As
Publication number | Publication date |
---|---|
CN109725329B (en) | 2021-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109725329A (en) | A kind of unmanned vehicle localization method and device | |
CN109725330A (en) | A kind of Location vehicle method and device | |
CN110967011B (en) | Positioning method, device, equipment and storage medium | |
CN111983635B (en) | Pose determination method and device, electronic equipment and storage medium | |
WO2019206270A1 (en) | Distance measurement method, intelligent control method and apparatus, electronic device and storage medium | |
CN108010060B (en) | Target detection method and device | |
CN110967024A (en) | Method, device, equipment and storage medium for detecting travelable area | |
EP3825960A1 (en) | Method and device for obtaining localization information | |
CN105959587B (en) | Shutter speed acquisition methods and device | |
CN109696173A (en) | A kind of car body air navigation aid and device | |
CN112433211B (en) | Pose determination method and device, electronic equipment and storage medium | |
CN114267041B (en) | Method and device for identifying object in scene | |
CN112149659A (en) | Positioning method and device, electronic equipment and storage medium | |
CN112991439B (en) | Method, device, electronic equipment and medium for positioning target object | |
CN105188027A (en) | Nearby user searching method and device | |
CN115407355B (en) | Library position map verification method and device and terminal equipment | |
CN113450459A (en) | Method and device for constructing three-dimensional model of target object | |
WO2022110801A1 (en) | Data processing method and apparatus, electronic device, and storage medium | |
CN113065392A (en) | Robot tracking method and device | |
CN112578338A (en) | Sound source positioning method, device, equipment and storage medium | |
CN113450298B (en) | Multi-sensor-based view map processing method, device and equipment | |
CN116772894B (en) | Positioning initialization method, device, electronic equipment, vehicle and storage medium | |
CN115469292B (en) | Environment sensing method and device, electronic equipment and storage medium | |
CN116934840A (en) | Object detection method, device, electronic apparatus, storage medium, and program product | |
des Aunais et al. | Analytical method for multimodal localization combination using Wi-Fi and camera |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |