CN108181905A - A kind of obstacle avoidance method and system of pilotless automobile - Google Patents
A kind of obstacle avoidance method and system of pilotless automobile Download PDFInfo
- Publication number
- CN108181905A CN108181905A CN201810005169.4A CN201810005169A CN108181905A CN 108181905 A CN108181905 A CN 108181905A CN 201810005169 A CN201810005169 A CN 201810005169A CN 108181905 A CN108181905 A CN 108181905A
- Authority
- CN
- China
- Prior art keywords
- information
- pilotless automobile
- obstacle
- complaint message
- target
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
Abstract
The invention discloses a kind of obstacle avoidance methods of pilotless automobile, pilotless automobile acquires complaint message and obtains other vehicles from high in the clouds and is uploaded to the environmental information of the running environment residing for current pilotless automobile to control pilotless automobile avoidance by the information collecting device of itself, since the target information in high in the clouds is corresponding with the environmental information residing for pilotless automobile, therefore, pilotless automobile can know the complaint message for being presently in environment from high in the clouds, with reference to the complaint message detected by pilotless automobile itself, so as to fulfill accurate avoidance, when avoiding the obstacle avoidance apparatus exception of pilotless automobile itself or relatively low accuracy, cause avoidance mortality higher, the problem of traffic accident incidence is higher.Meanwhile the invention also discloses a kind of obstacle avoidance systems of pilotless automobile, equally can realize above-mentioned technique effect.
Description
Technical field
The present invention relates to artificial intelligence field, the obstacle avoidance method and system of more particularly to a kind of pilotless automobile.
Background technology
In recent years, with the fast development of artificial intelligence, pilotless automobile also progresses into people’s lives.Nobody drives
It is a kind of intelligent automobile to sail automobile, can also be referred to as wheeled mobile robot, rely primarily on it is interior using computer system as
Main intelligent driving instrument is realized unmanned.Compared to traditional driving, pilotless automobile avoid first people to automobile into
Row control and operation simultaneously as pilotless automobile is controlled by computer system, therefore, avoid user and drive vapour
Che Shi causes traffic accident accident due to fatigue driving.
At present, since the development course of pilotless automobile is shorter, still there are many technologies for pilotless automobile
Problem, wherein, most important problem is pilotless automobile in motion to the obstacle probe that encounters and the problem of hide.But
It is that traditional avoidance mode is to detect avoidance after barrier, avoidance mode by the obstacle avoidance apparatus of pilotless automobile itself
It is single, when obstacle avoidance apparatus exception or obstacle avoidance apparatus the detection barrier of pilotless automobile are inaccurate, nobody can be caused to drive
The failure of automobile avoidance is sailed, traffic accident incidence is higher.
Therefore, the accuracy of pilotless automobile avoidance how is improved, and then reduces the failure of pilotless automobile avoidance
Rate, the incidence for further reducing traffic accident is those skilled in the art's problem to be solved.
Invention content
The purpose of the present invention is to provide a kind of obstacle avoidance method and system of pilotless automobile, improve nobody and drive
The accuracy of automobile avoidance is sailed, and then reduces the mortality of pilotless automobile avoidance, further reduced the incidence of traffic accident.
To achieve the above object, an embodiment of the present invention provides following technical solutions:
On the one hand, an embodiment of the present invention provides a kind of obstacle avoidance method of pilotless automobile, including:
The environmental information in the driving range of the pilotless automobile of information collecting device acquisition is obtained to detect the row
It whether there is target vehicle in the range of sailing;
If so, determine the first complaint message in the driving range;
Target information corresponding with the environmental information is obtained from high in the clouds and to the target information and first obstacle
Information is analyzed to obtain the first analysis result, wherein the target information for the target vehicle be uploaded to the high in the clouds with
The corresponding information of the environmental information;
The pilotless automobile is controlled to hide according to first analysis result corresponding with first complaint message
First obstacle.
Preferably, if there are the target vehicles in the driving range of the pilotless automobile, it is determined that institute
State the second complaint message in driving range;
Second complaint message is analyzed to obtain the second analysis result;
The pilotless automobile is controlled to hide according to second analysis result corresponding with second complaint message
Second obstacle.
Preferably, if there are the target vehicle, the methods in the driving range of the pilotless automobile
It further includes:
Whether abnormal detect described information harvester;
If so, it obtains the target information from the high in the clouds and the target information is analyzed to obtain third analysis
As a result;
The pilotless automobile is controlled to hide third corresponding with the target information according to the third analysis result
Obstacle.
Preferably, the environmental information packet in the driving range of the pilotless automobile for obtaining information collecting device acquisition
It includes:
Obtain the ambient image in the thermal camera shooting driving range in described information harvester;
Feature extraction is carried out to the ambient image to obtain the environmental information.
Preferably, it is described to obtain target information corresponding with the environmental information and to the target information and institute from high in the clouds
It states the first complaint message and is analyzed to obtain the first analysis result and include:
Mathematical model corresponding with the environmental information is established with first complaint message according to the target information;
The confidence level of first obstacle corresponding with first complaint message is determined according to the mathematical model;
Judge whether the confidence level is more than credible threshold value;
If so, determine the avoidance information of first obstacle corresponding with first complaint message with by the avoidance
Information is as first analysis result.
Preferably, the avoidance information for determining first obstacle corresponding with first complaint message includes:
Determine the target location of the pilotless automobile corresponding with the environmental information, the obstacle of first obstacle
Position;
The target location that the laser range finder in described information harvester measures is obtained to the obstacle location
Distance of obstacle;
Keeping away for the pilotless automobile is determined according to the target location, the obstacle location and the distance of obstacle
Hinder direction.
On the other hand, an embodiment of the present invention provides a kind of obstacle avoidance system of pilotless automobile, including:
Information collecting device, processor, steering control device;
Described information harvester is used for the environmental information in the driving range for acquiring pilotless automobile;
The processor is used to obtain the environmental information of described information harvester acquisition to detect the traveling model
With the presence or absence of target vehicle in enclosing, if in the presence of, it is determined that the first complaint message in the driving range;
It determines to obtain target information corresponding with the environmental information and to the target from high in the clouds after the first complaint message
Information is analyzed to obtain the first analysis result with first complaint message, wherein the target information is the target vehicle
It is uploaded to the information corresponding with the environmental information in the high in the clouds;
The steering control device is used to be hidden according to first analysis result control pilotless automobile and institute
State corresponding first obstacle of the first complaint message.
Preferably, described information harvester includes:Thermal camera;
The thermal camera is used to shoot the ambient image in the driving range.
Preferably, the processor is specifically used for:
Mathematical model corresponding with the environmental information is established with first complaint message according to the target information;
The confidence level of first obstacle corresponding with first complaint message is calculated according to the mathematical model;
Judge whether the confidence level is more than credible threshold value;
If so, determine the avoidance information of first obstacle corresponding with first complaint message with by the avoidance
Information is as first analysis result.
As it can be seen that a kind of obstacle avoidance method of pilotless automobile disclosed by the embodiments of the present invention, obtains information and adopts first
Environmental information in the driving range of the pilotless automobile of acquisition means acquisition whether there is target carriage to detect in driving range
, if it is present determining the first complaint message in driving range, and target letter corresponding with environmental information is obtained from high in the clouds
It ceases and target information and the first complaint message is analyzed to obtain the first analysis result;Wherein target information is on target vehicle
Reach the information corresponding with environmental information in high in the clouds;Pilotless automobile is controlled to hide and the first obstacle according to the first analysis result
Corresponding first obstacle of information.
Therefore, pilotless automobile acquires complaint message by the information collecting device of itself and obtains other from high in the clouds
Vehicle is uploaded to the environmental information of the running environment residing for current pilotless automobile to control pilotless automobile avoidance, by
Target information in high in the clouds is corresponding with the environmental information residing for pilotless automobile, and therefore, pilotless automobile can be from
The complaint message for being presently in environment is known in high in the clouds, with reference to the complaint message detected by pilotless automobile itself, so as to real
Now accurate avoidance when avoiding the obstacle avoidance apparatus exception of pilotless automobile itself or relatively low accuracy, causes avoidance mortality
Higher, the problem of traffic accident incidence is higher.Meanwhile the embodiment of the invention also discloses a kind of obstacle avoidances of pilotless automobile
System equally can realize above-mentioned technique effect.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of obstacle avoidance method flow schematic diagram of pilotless automobile disclosed by the embodiments of the present invention;
Fig. 2 is a kind of mathematical model schematic diagram of pilotless automobile disclosed by the embodiments of the present invention;
Fig. 3 is a kind of obstacle avoidance system structure diagram of pilotless automobile disclosed by the embodiments of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a kind of obstacle avoidance method and system of pilotless automobile, improve unmanned
The accuracy of automobile avoidance, and then the mortality of pilotless automobile avoidance is reduced, it further reduced the incidence of traffic accident.
Fig. 1 is referred to, Fig. 1 is that a kind of obstacle avoidance method flow of pilotless automobile disclosed by the embodiments of the present invention shows
It is intended to, including:
S101, the environmental information in the driving range for the pilotless automobile that information collecting device acquires is obtained to detect row
It whether there is target vehicle in the range of sailing.
Specifically, in the present embodiment, information acquisition module can acquire the unmanned of current pilotless automobile acquisition
The environmental information of automobile local environment, the running condition information of current pilotless automobile, pilotless automobile are presently in
Location information etc., wherein, environmental information is included in the layout information and current environment of the environment residing for pilotless automobile
Size, shape of barrier etc.;Information collecting device can include infrared camera, laser range finder, positioning element, speed and pass
Sensor etc., infrared camera are used for the ambient image of environment where shooting pilotless automobile, and laser range finder is used to measure nothing
The distance between people's driving and barrier, velocity sensor are used to measure the current travel speed letter of pilotless automobile
Breath, positioning element are used to be detected the location of current pilotless automobile.Certainly, information collecting device can also wrap
Other harvester types are included, for example, 360 degree rotation camera etc., herein and is not construed as limiting.Driving range is that currently nobody drives
Sail the running region residing for automobile, i.e. the collectable current pilotless automobile of information collecting device of pilotless automobile can
Depending in the range of.Target vehicle is existing vehicle in the range of current pilotless automobile current driving, and the quantity of target vehicle can
Think multiple, or one, herein and be not construed as limiting.Certainly, the type of target vehicle also and is not construed as limiting herein.
S102, if so, determine driving range in the first complaint message.
Specifically, in the present embodiment, obstacle of first complaint message where current pilotless automobile in driving range
Information mainly includes, the position of the target vehicle in driving range or the position of other barriers and each barrier away from
With a distance from target vehicle, size, shape of barrier etc., certainly, according to actual environment situation, the first complaint message can also
For other information, herein and it is not construed as limiting.
S103, it obtains target information corresponding with environmental information from high in the clouds and target information and the first complaint message is carried out
Analysis obtains the first analysis result, and wherein target information is uploaded to the information corresponding with environmental information in high in the clouds for target vehicle.
Specifically, in the present embodiment, high in the clouds is used to storing target vehicle and is uploaded to row residing for current pilotless automobile
Environmental information in the range of sailing, can include current automatic driving vehicle local environment integral layout information and, traveling
In the range of existing barrier information.Certainly, according to actual environment, the information of high in the clouds memory storage may be other kinds of
Information herein and is not construed as limiting.
S104, pilotless automobile is controlled to hide the first barrier corresponding with the first complaint message according to the first analysis result
Hinder.
Specifically, in the present embodiment, the first analysis result is after analyzing the first complaint message, obtains the first obstacle
The avoidance information of barrier in information, for example, barrier in the first complaint message to pilotless automobile distance, be in
The orientation of pilotless automobile then obtains the avoidance direction of pilotless automobile according to the distance and orientation, avoidance speed, keeps away
Hinder route etc..
Certainly, according to actual environment, other avoidance information can also be included in the first analysis result, are not limited herein
It is fixed.
It should be noted that in the present embodiment, it, then can be from information collection when target vehicle is not present in driving range
Device acquisition pilotless automobile driving range in environmental information in determine complaint message, so as to the complaint message into
Row analysis, is analyzed according to the complaint message, so as to obtain avoidance information corresponding with the complaint message.
As it can be seen that a kind of obstacle avoidance method of pilotless automobile disclosed by the embodiments of the present invention, obtains information and adopts first
Environmental information in the driving range of the pilotless automobile of acquisition means acquisition whether there is target carriage to detect in driving range
, if it is present determining the first complaint message in driving range, and target letter corresponding with environmental information is obtained from high in the clouds
It ceases and target information and the first complaint message is analyzed to obtain the first analysis result;Wherein target information is on target vehicle
Reach the information corresponding with environmental information in high in the clouds;Pilotless automobile is controlled to hide and the first obstacle according to the first analysis result
Corresponding first obstacle of information.
Therefore, pilotless automobile acquires complaint message by the information collecting device of itself and obtains other from high in the clouds
Vehicle is uploaded to the environmental information of the running environment residing for current pilotless automobile to control pilotless automobile avoidance, by
Target information in high in the clouds is corresponding with the environmental information residing for pilotless automobile, and therefore, pilotless automobile can be complete
Face, which understands, is presently in the complaint message of environment, with reference to the complaint message detected by pilotless automobile itself, so as to fulfill
Accurate avoidance, when avoiding the obstacle avoidance apparatus exception of pilotless automobile itself or relatively low accuracy, cause avoidance mortality compared with
High, the problem of traffic accident incidence is higher.
Based on above-described embodiment, in the present embodiment, if there is no target vehicle in the driving range of pilotless automobile,
Then determine the second complaint message in driving range;
Second complaint message is analyzed to obtain the second analysis result;
Pilotless automobile is controlled to hide the second obstacle corresponding with the second complaint message according to the second analysis result.
Specifically, in the present embodiment, the second complaint message is includes obstacle in the environmental information of information collecting device acquisition
The complaint message of object, position that shape, size including barrier, pilotless automobile are presently in, the position of barrier
Deng.Second analysis result is comprising the avoidance scheme to corresponding second obstacle of second obstacle information, for example, when the second barrier
The information is hindered to be:There is barrier at 200 meters of pilotless automobile, then the second analysis result then includes obstacle distance nobody drives
It sails the distance of automobile and controls pilotless automobile Reduced Speed Now and change travel direction.
Based on above-described embodiment, in the present embodiment, if there are target vehicle in the driving range of pilotless automobile,
It further includes:
Whether detection information harvester is abnormal;
If so, it obtains target information from high in the clouds and target information is analyzed to obtain third analysis result;
Pilotless automobile is controlled to hide third obstacle corresponding with target information according to third analysis result.
Specifically, in the present embodiment, when information collecting device can not normal acquisition pilotless automobile environmental information when,
Other vehicles then directly downloaded in the range of current driving from high in the clouds are uploaded to the environmental information in high in the clouds, and in the environmental information
Comprising complaint message analyzed.Third analysis result is to be uploaded to what is included in the environmental information in high in the clouds comprising other vehicles
The analysis result of complaint message.It can include:Pilotless automobile is to the distance of barrier, position, the size of barrier etc..
Certainly, according to actual environment, which can also include other information, herein and be not construed as limiting.
Further, in the present embodiment, if the information collecting device of pilotless automobile is abnormal, and the row of pilotless automobile
There is no other vehicles in the range of sailing, i.e., when can not obtain the target information in the range of pilotless automobile current driving from high in the clouds,
Pilotless automobile automatic stopping is then controlled, at this point, pilotless automobile sends out alarm, driver is prompted to be changed to drive manually
It sails.
Based on above-described embodiment, in the present embodiment, the traveling of the pilotless automobile of information collecting device acquisition is obtained
In the range of environmental information include:
Obtain the ambient image in the thermal camera shooting driving range in information collecting device;
Feature extraction is carried out to ambient image to obtain environmental information.
Based on above-described embodiment, in the present embodiment, target information corresponding with environmental information is obtained and to mesh from high in the clouds
Mark information and the first complaint message, which are analyzed to obtain the first analysis result, to be included:
Mathematical model corresponding with environmental information is established with the first complaint message according to target information;
The confidence level of the first obstacle corresponding with the first complaint message is determined according to mathematical model;
Judge whether confidence level is more than credible threshold value;
If so, determine the avoidance information of the first obstacle corresponding with the first complaint message using by avoidance information as first
Analysis result.
Specifically, in the present embodiment, Fig. 2 is referred to, Fig. 2 is a kind of pilotless automobile disclosed by the embodiments of the present invention
Mathematical model schematic diagram as shown in Fig. 2, mathematical model establishes that principle is as follows, is adopted according to the information acquisition module of automobile first
The target information of the first complaint message and target vehicle in the ambient condition information of collection draws surrounding's ring of pilotless automobile
Border image divides the image into the identical fritter one by one of size.Then global static coordinate system (X-O-Y) and automobile office are established
Portion's dynamic coordinate system (X '-O '-Y '), using the initial position of automobile as the origin O of global static coordinate system, X-direction is directed toward
Due east, Y direction are directed toward due north.The geometric center point of pilotless automobile is defined as to the origin O ' of dynamic local coordinate system.
The posture of automobile Y-axis and the angle theta of Y ' axis represent (clockwise for just).Global coordinate system is used for describing entire environment
Information, the local message that local coordinate system description is currently detected.
Then the confidence level of the first barrier of current information harvester acquisition is determined according to established mathematical model,
The determination process of confidence level is as follows:The environmental area embodiment of the present invention in the driving range that pilotless automobile can detect
Defined in be aware space.The shape size of this environmental area is different with detectivity because of the sensor configuration of pilotless automobile
And it is different, therefore, the size and shape of environmental area herein and is not construed as limiting, and laser ranging is used in the embodiment of the present invention
Instrument and thermal camera are with the environmental area residing for the pilotless automobile that perceives.Such as the chain-dotted line rectangular area in Fig. 2, obstacle
Object is likely to be in this rectangular area, it is also possible on the boundary of rectangular area or not in rectangular area.It is driven according to nobody
The size of the aware space of automobile is sailed, sets the block size of X and Y direction as Δ x and Δ y, and Δ x=Δs y.It is unmanned
Autocentre point uses (i in global coordinate systemr,jr) represent.Coordinate (the i of cell block residing for pilotless automobile central pointr,
jr) calculation formula be:
Define CijRepresent that there are the confidence levels of barrier in (i, j) cell block.CijThere are obstacles for the high expression this element block of value
The certainty of object is big, works as CijValue when being 1, then illustrate the confidence level of barrier for maximum.CijValue led to by pilotless automobile
Cross the sensor detection being installed on pilotless automobile and carry out real-time update, such as the thermal camera in the embodiment of the present invention and
Laser range finder.The C of initial cell block described in pilotless automobileij=0.If the obstacle distance pilotless automobile measured
Distance be lu, confidence level C at this timeij=1, then the coordinate calculation formula of the cell block residing for barrier be:
When the cell block that barrier is not detected in aware space or the cell block beyond automobile aware space, automobile
It can not determine whether there is barrier at this element block, we are believed that this element block traveling current to automobile does not have an impact,
So C of these cell blocksijIt is maintained 0.
When confidence level is more than credible threshold value, wherein, credible threshold value can be the arbitrary number more than 0 less than 1, for example, can
It is 0.5 to believe threshold value;Certainly, according to actual environment, the size of credible threshold value herein and is not construed as limiting.Avoidance information can be by following
Mode obtains, that is, constructs field of force method and obtain the avoidance scheme of pilotless automobile, as shown in Fig. 2, Fig. 2 includes unmanned vapour
The coordinate of cell block residing for the home position coordinate and barrier of vehicle.
The basic thought in the construction field of force is the low-potential energy area that source location is set as to the construction field of force, i.e. suction zone;It will barrier
Object is hindered to be set as the high potential energy area in the construction field of force, i.e. rejection area;With attraction of the comprehensive function on automobile and the vector of repulsive force
Summation direction is automobile next step moving direction.Automobile updates a direction of motion per run-down environment.
First, to the confidence level C of the barrier where each cell blockij≠ 0 cell block applies what a simulation constructed
Repulsive force, first, each Cij≠ 0 cell block applies automobile the repulsive force F of one simulation constructionij, calculation formula is:
F in formulacrTo repel force constant (positive number);dijFor the distance between (i, j) cell block and autocentre point;(xi,
yi) be cell block coordinate;X, y represent the unit vector of X-axis and Y-axis respectively.By formula it is found that repulsive force FcrSize and list
First blockIt is directly proportional, with d2 ijIt is inversely proportional.For automobile closer to cell block, cell block is bigger to its repulsive force.When automobile is separate
When, repulsive force is reduced by.The repulsive force vector F that cell block is appliedijSummation form repel force vector:Fr=∑ijFij。
Secondly, source location applies automobile the attraction F of simulation constructiontIt can be acquired by following formula:
F in formulactAttract force constant (positive number) for source location;dtBetween source location and autocentre point away from
From;(xt, yt) be source location coordinate.
Finally all cell block repulsive forces and the vector sum of source location attraction constitute resultant force vector R.
R=Ft+Fr, the direction of resultant force vector R is exactly the direction that automobile hides obstacle.
Certainly, the avoidance direction of pilotless automobile can also be determined by other means, herein and be not construed as limiting.
Based on above-described embodiment, in the present embodiment, the avoidance letter of the first obstacle corresponding with the first complaint message is determined
Breath includes:
Determine the target location of pilotless automobile corresponding with environmental information, the obstacle location of the first obstacle;
The target location of the laser range finder measurement in information collecting device is obtained to the distance of obstacle of obstacle location;
The avoidance direction of pilotless automobile is determined according to target location, obstacle location and distance of obstacle.
Fig. 3 is referred to, Fig. 3 is that a kind of obstacle avoidance system structure of pilotless automobile disclosed by the embodiments of the present invention is shown
It is intended to, based on the obstacle avoidance method for the pilotless automobile that as above any one embodiment is mentioned, the barrier of pilotless automobile
Avoidance system 30 is hindered to include:Information collecting device 301, processor 302, steering control device 303;
Information collecting device 301 is used for the environmental information in the driving range for acquiring pilotless automobile;
Whether the environmental information that processor 302 is used to obtain the acquisition of information collecting device 301 is deposited with detecting in driving range
In target vehicle, if in the presence of, it is determined that the first complaint message in driving range;
It determines to obtain target information corresponding with environmental information and to target information and the from high in the clouds after the first complaint message
One complaint message is analyzed to obtain the first analysis result, and wherein target information is uploaded to believing with environment for high in the clouds for target vehicle
Cease corresponding information;
Steering control device 303 is used to pilotless automobile be controlled to hide and the first complaint message according to the first analysis result
Corresponding first obstacle.
Based on above-described embodiment, in the present embodiment, information collecting device 301 includes:Thermal camera;
Thermal camera is used to shoot the ambient image in driving range.
Based on above-described embodiment, in the present embodiment, processor 302 is specifically used for:
Mathematical model corresponding with environmental information is established with the first complaint message according to target information;
The confidence level of the first obstacle corresponding with the first complaint message is calculated according to mathematical model;
Judge whether confidence level is more than credible threshold value;
If so, determine the avoidance information of the first obstacle corresponding with the first complaint message using by avoidance information as first
Analysis result.
The obstacle avoidance method and system of pilotless automobile provided herein are described in detail above.This
Specific case is applied in text, and the principle and implementation of this application are described, the explanation of above example is only intended to
Help understands the present processes and its core concept.It should be pointed out that for those skilled in the art,
Under the premise of not departing from the application principle, can also to the application, some improvement and modification can also be carried out, these improvement and modification are also fallen
Enter in the application scope of the claims.
Each embodiment is described by the way of progressive in specification, the highlights of each of the examples are with other realities
Apply the difference of example, just to refer each other for identical similar portion between each embodiment.For device disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part is referring to method part illustration
.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only include that
A little elements, but also including other elements that are not explicitly listed or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except also there are other identical elements in the process, method, article or apparatus that includes the element.
Claims (9)
1. a kind of obstacle avoidance method of pilotless automobile, which is characterized in that including:
The environmental information in the driving range of the pilotless automobile of information collecting device acquisition is obtained to detect the traveling model
With the presence or absence of target vehicle in enclosing;
If so, determine the first complaint message in the driving range;
Target information corresponding with the environmental information is obtained from high in the clouds and to the target information and first complaint message
Analyzed to obtain the first analysis result, wherein the target information be uploaded to the high in the clouds for the target vehicle with it is described
The corresponding information of environmental information;
The pilotless automobile is controlled to hide and first complaint message corresponding first according to first analysis result
Obstacle.
2. the obstacle avoidance method of pilotless automobile according to claim 1, which is characterized in that if described unmanned
There are the target vehicles in the driving range of automobile, it is determined that the second complaint message in the driving range;
Second complaint message is analyzed to obtain the second analysis result;
The pilotless automobile is controlled to hide and second complaint message corresponding second according to second analysis result
Obstacle.
3. the obstacle avoidance method of pilotless automobile according to claim 1, which is characterized in that if described unmanned
There are the target vehicle in the driving range of automobile, then the method further includes:
Whether abnormal detect described information harvester;
If so, it obtains the target information from the high in the clouds and the target information is analyzed to obtain third analysis knot
Fruit;
The pilotless automobile is controlled to hide third obstacle corresponding with the target information according to the third analysis result.
4. the obstacle avoidance method of pilotless automobile according to claim 1, which is characterized in that the acquisition information is adopted
Environmental information in the driving range of the pilotless automobile of acquisition means acquisition includes:
Obtain the ambient image in the thermal camera shooting driving range in described information harvester;
Feature extraction is carried out to the ambient image to obtain the environmental information.
5. the obstacle avoidance method of pilotless automobile according to claim 1, which is characterized in that described to be obtained from high in the clouds
Target information corresponding with the environmental information is simultaneously analyzed to obtain the to the target information and first complaint message
One analysis result includes:
Mathematical model corresponding with the environmental information is established with first complaint message according to the target information;
The confidence level of first obstacle corresponding with first complaint message is determined according to the mathematical model;
Judge whether the confidence level is more than credible threshold value;
If so, determine the avoidance information of first obstacle corresponding with first complaint message with by the avoidance information
As first analysis result.
6. the obstacle avoidance method of pilotless automobile according to claim 5, which is characterized in that it is described determine with it is described
The avoidance information of corresponding first obstacle of first complaint message includes:
Determine the target location of the pilotless automobile corresponding with the environmental information, the obstacle position of first obstacle
It puts;
The target location of the laser range finder measurement in described information harvester is obtained to the obstacle of the obstacle location
Distance;
The avoidance side of the pilotless automobile is determined according to the target location, the obstacle location and the distance of obstacle
To.
7. a kind of obstacle avoidance system of pilotless automobile, based on the unmanned vapour described in claim 1-6 any one
The obstacle avoidance method of vehicle, which is characterized in that including:
Information collecting device, processor, steering control device;
Described information harvester is used for the environmental information in the driving range for acquiring pilotless automobile;
The processor is used to obtain the environmental information of described information harvester acquisition to detect in the driving range
With the presence or absence of target vehicle, if in the presence of, it is determined that the first complaint message in the driving range;After determining the first complaint message
Target information corresponding with the environmental information is obtained from high in the clouds and the target information and first complaint message are carried out
Analysis obtains the first analysis result, wherein the target information is being uploaded to the high in the clouds with the environment for the target vehicle
The corresponding information of information;
The steering control device is used to the pilotless automobile be controlled to hide and described the according to first analysis result
Corresponding first obstacle of one complaint message.
8. the obstacle avoidance system of pilotless automobile according to claim 7, which is characterized in that described information acquisition dress
Put including:Thermal camera;
The thermal camera is used to shoot the ambient image in the driving range.
9. the obstacle avoidance system of pilotless automobile according to claim 7, which is characterized in that the processing implement body
For:
Mathematical model corresponding with the environmental information is established with first complaint message according to the target information;
The confidence level of first obstacle corresponding with first complaint message is calculated according to the mathematical model;
Judge whether the confidence level is more than credible threshold value;
If so, determine the avoidance information of first obstacle corresponding with first complaint message with by the avoidance information
As first analysis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810005169.4A CN108181905A (en) | 2018-01-03 | 2018-01-03 | A kind of obstacle avoidance method and system of pilotless automobile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810005169.4A CN108181905A (en) | 2018-01-03 | 2018-01-03 | A kind of obstacle avoidance method and system of pilotless automobile |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108181905A true CN108181905A (en) | 2018-06-19 |
Family
ID=62549950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810005169.4A Pending CN108181905A (en) | 2018-01-03 | 2018-01-03 | A kind of obstacle avoidance method and system of pilotless automobile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108181905A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108827336A (en) * | 2018-09-26 | 2018-11-16 | 广东工业大学 | One kind being based on unpiloted paths planning method, device and equipment |
CN109582018A (en) * | 2018-12-04 | 2019-04-05 | 黄昊 | The intelligent driving method, apparatus and system of four-dimensional framework based on block chain |
CN109614886A (en) * | 2018-11-23 | 2019-04-12 | 中国人民解放军63966部队 | It is a kind of nobody/performance evaluation methodology and device of autonomous driving system |
WO2020042859A1 (en) * | 2018-08-29 | 2020-03-05 | 上海商汤智能科技有限公司 | Smart driving control method and apparatus, vehicle, electronic device, and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100274429A1 (en) * | 2009-04-28 | 2010-10-28 | Electronics And Telecommunications Research Institute | System and method for autonomous vehicle guiding using information technology infrastructure and server apparatus therefor |
CN203267899U (en) * | 2013-06-06 | 2013-11-06 | 重庆渝速科技有限公司 | Driving system in foggy days |
CN105739534A (en) * | 2016-04-22 | 2016-07-06 | 百度在线网络技术(北京)有限公司 | Multi-vehicle cooperative driving method and apparatus for driverless vehicles based on Internet-of-vehicles |
CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
CN106394513A (en) * | 2016-09-28 | 2017-02-15 | 鄂尔多斯市普渡科技有限公司 | Traveling device and strategy for driverless vehicle in rainy and snowy weather |
CN107454969A (en) * | 2016-12-19 | 2017-12-08 | 深圳前海达闼云端智能科技有限公司 | Obstacle detection method and device |
-
2018
- 2018-01-03 CN CN201810005169.4A patent/CN108181905A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100274429A1 (en) * | 2009-04-28 | 2010-10-28 | Electronics And Telecommunications Research Institute | System and method for autonomous vehicle guiding using information technology infrastructure and server apparatus therefor |
CN203267899U (en) * | 2013-06-06 | 2013-11-06 | 重庆渝速科技有限公司 | Driving system in foggy days |
CN105739534A (en) * | 2016-04-22 | 2016-07-06 | 百度在线网络技术(北京)有限公司 | Multi-vehicle cooperative driving method and apparatus for driverless vehicles based on Internet-of-vehicles |
CN105741595A (en) * | 2016-04-27 | 2016-07-06 | 常州加美科技有限公司 | Unmanned vehicle navigation driving method based on cloud database |
CN106394513A (en) * | 2016-09-28 | 2017-02-15 | 鄂尔多斯市普渡科技有限公司 | Traveling device and strategy for driverless vehicle in rainy and snowy weather |
CN107454969A (en) * | 2016-12-19 | 2017-12-08 | 深圳前海达闼云端智能科技有限公司 | Obstacle detection method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020042859A1 (en) * | 2018-08-29 | 2020-03-05 | 上海商汤智能科技有限公司 | Smart driving control method and apparatus, vehicle, electronic device, and storage medium |
CN108827336A (en) * | 2018-09-26 | 2018-11-16 | 广东工业大学 | One kind being based on unpiloted paths planning method, device and equipment |
CN109614886A (en) * | 2018-11-23 | 2019-04-12 | 中国人民解放军63966部队 | It is a kind of nobody/performance evaluation methodology and device of autonomous driving system |
CN109614886B (en) * | 2018-11-23 | 2022-06-24 | 中国人民解放军63966部队 | Performance evaluation method and device of unmanned/autonomous driving system |
CN109582018A (en) * | 2018-12-04 | 2019-04-05 | 黄昊 | The intelligent driving method, apparatus and system of four-dimensional framework based on block chain |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108181905A (en) | A kind of obstacle avoidance method and system of pilotless automobile | |
CN106598039B (en) | A kind of Intelligent Mobile Robot barrier-avoiding method based on laser radar | |
CN108007464A (en) | Ultra-high-tension power transmission line inspection robot autonomous navigation method and system | |
CN106808482B (en) | A kind of crusing robot multisensor syste and method for inspecting | |
CN111693050B (en) | Indoor medium and large robot navigation method based on building information model | |
CN106970641B (en) | Control method for unmanned aerial vehicle to fly around object outline | |
CN105912018A (en) | Aircraft and obstacle avoiding method for the aircraft | |
CN106919181A (en) | A kind of unmanned plane barrier-avoiding method | |
CN208953962U (en) | A kind of robot tracking control and robot | |
US20180050694A1 (en) | Method and device for monitoring a setpoint trajectory to be traveled by a vehicle for being collision free | |
CN109460739A (en) | Method for detecting lane lines and device | |
US20220383484A1 (en) | Tunnel defect detecting method and system using unmanned aerial vehicle | |
CN107783103B (en) | A kind of flying bird tracking intelligent method of the lightweight with self-learning function | |
CN107813817A (en) | Unmanned Systems, unmanned method and vehicle | |
CN104608772A (en) | System and method for judging environmental failure of automatic aided driving | |
CN110211420A (en) | Judge current scene whether be parking lot method, system and computer readable storage medium | |
CN110275167A (en) | A kind of control method of radar detection, controller and terminal | |
CN108593213A (en) | The inspection of unmanned plane sub-terrain mines and odoriferous homing device | |
CN106627368A (en) | Vehicle running environment display method and vehicle-mounted equipment | |
CN104898675A (en) | Robot intelligent navigation control method | |
CN111002346A (en) | Robot trapped detection method and robot | |
CN115993597A (en) | Visual radar perception fusion method and terminal equipment | |
CN113532499B (en) | Sensor security detection method and device for unmanned system and storage medium | |
CN110673627A (en) | Forest unmanned aerial vehicle searching method | |
CN113158779A (en) | Walking method and device and computer storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |
|
RJ01 | Rejection of invention patent application after publication |