CN113268065A - AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence - Google Patents

AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence Download PDF

Info

Publication number
CN113268065A
CN113268065A CN202110810318.6A CN202110810318A CN113268065A CN 113268065 A CN113268065 A CN 113268065A CN 202110810318 A CN202110810318 A CN 202110810318A CN 113268065 A CN113268065 A CN 113268065A
Authority
CN
China
Prior art keywords
turning
agv
point
speed
straight line
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
Application number
CN202110810318.6A
Other languages
Chinese (zh)
Other versions
CN113268065B (en
Inventor
林立峰
袁绪龙
郭东进
李栓柱
袁绪彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Huali Electromechanical Co Ltd
Original Assignee
Shandong Huali Electromechanical Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong Huali Electromechanical Co Ltd filed Critical Shandong Huali Electromechanical Co Ltd
Priority to CN202110810318.6A priority Critical patent/CN113268065B/en
Publication of CN113268065A publication Critical patent/CN113268065A/en
Application granted granted Critical
Publication of CN113268065B publication Critical patent/CN113268065B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence. According to the method, when the AGV needs to turn according to the edge profile information of the color band, the turning type of the AGV is judged according to the distance between edge straight lines of the color band before and after the AGV turns, the initial turning speed of the AGV during turning is obtained according to the turning type of the AGV, the initial speed is adjusted through the obstacle communication domain detected in the turning process to obtain the optimal turning speed, and then the AGV turns by utilizing the optimal turning speed. In the process of AGV turning, the turning speed of the AGV is adjusted in real time according to the detected size of the obstacle, so that the AGV can turn at the optimal turning speed under the condition that the obstacle is not collided, and meanwhile, the conditions of discontinuity, blockage, stagnation and the like of turning are avoided, so that the AGV works normally.

Description

AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence.
Background
An automated guided vehicle, abbreviated as AGV, is a vehicle equipped with an electromagnetic or optical automatic guide device, which can travel along a predetermined guide path and has safety protection and various transfer functions. The AGV is an unmanned vehicle which takes a battery as power and is provided with a non-contact guiding device, and has the main functions of accurately walking and stopping to a specified place according to path planning and operation requirements under the monitoring of a computer to complete a series of operation functions.
The AGV car can automatically run and needs a guiding device. The commonly used guidance methods fall into two broad categories: an off-board predetermined path and a non-predetermined path pattern. The external preset path guidance mode is a guidance mode that an information medium for guidance is arranged on a running path, and the AGV obtains guidance by detecting the information of the information medium, such as electromagnetic guidance, ribbon guidance, tape guidance and the like; the non-predetermined path guiding mode refers to a path where the AGV does not have a fixed path when the AGV is running, and is generally a laser guiding mode, which can try to know the position where the AGV is running and autonomously determine the guiding mode of the running path.
In practice, the inventors found that the above prior art has the following disadvantages: in the prior art, a turning reminding point is usually arranged on a guide medium before a turning road section to remind that the turning road section exists in front of a vehicle, and the advancing direction needs to be changed after the speed is reduced to zero. However, the turning method not only increases the running time of the vehicle, but also prevents the AGV from continuing to work due to the influence of the obstacle when the AGV is turning.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides an AGV adaptive turn obstacle avoidance method based on artificial intelligence, where the method includes:
collecting a ground image, wherein the ground image comprises a guiding medium of an AGV; performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of a guide medium;
when the AGV needs to turn according to the edge profile information, detecting edge straight lines of the guiding medium before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning, wherein the first edge straight line and the second edge straight line are edge straight lines positioned on the inner side of the guiding medium before and after turning; judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line;
obtaining an initial turning speed of the AGV during turning according to the turning type; when the in-process of turning meets the barrier, connect in the barrier intercommunication domain apart from turn remind the nearest first pixel with turn and remind the point to obtain first straight line, acquire first straight line and turn the back the first nodical point of guide medium, according to maximum turning radius and turning point are acquireed to the position of first nodical point, and then based on the turning point, will initial turning speed adjustment does the maximum turning speed that maximum turning radius corresponds utilizes maximum turning speed accomplishes the AGV turns.
Further, after obtaining the maximum turning speed, the method further includes:
in the process that the AGV reaches the turning point, when a shielded barrier is detected, a second pixel point which is closest to the turning point in a shielded barrier communication domain in a turning influence range is obtained; the turning influence range is a range formed by the first intersection point and the turning reminding point; the inflection point is an intersection between the first edge straight line and the second edge straight line;
and acquiring an optimal turning radius and an optimal turning point according to the second pixel point, and adjusting the maximum turning speed to the optimal turning speed corresponding to the optimal turning radius based on the optimal turning point.
Further, the method for correcting the maximum turning speed includes:
and carrying out image blur correction on the ground image, correcting the maximum turning radius according to the degree of blur before and after the image correction, and further obtaining the corresponding maximum turning speed according to the corrected maximum turning radius.
Further, the method for correcting the optimal turning speed includes:
and carrying out image blur correction on the ground image, correcting the optimal turning radius according to the blur degree before and after the image correction, and further obtaining the corresponding optimal turning speed according to the corrected optimal turning radius.
Further, the optimization method for performing image blur correction on the ground image comprises the following steps:
determining a range of the image blur correction, the range being a circular range of the optimal turning radius formed on the ground image.
Further, the method for judging the turn type of the AGV according to the distance between the first edge straight line and the second edge straight line includes:
when the pixel point positions between the first edge straight line and the second edge straight line are overlapped, determining that the turning type is a right-angle turning; otherwise, it is a curve with radian.
Further, the method for obtaining the initial turning speed of the AGV during turning according to the turning type comprises the following steps:
when the turning type is right angle turning, based on the turning reminding point and the length between the inflection points, the AGV is combined with the speed variation obtained by the running speed of the turning reminding point, and then the initial turning speed corresponding to the uniform speed circular motion is obtained by the speed variation and the running speed.
Further, the method for obtaining the maximum turning radius according to the first intersection point comprises the following steps:
establishing a rectangular coordinate system by taking the first edge straight line as a vertical coordinate, the second edge straight line as a horizontal coordinate and an intersection point between the first edge straight line and the second edge straight line as an origin, and taking the horizontal coordinate value of the first intersection point as the maximum turning radius;
the position where the circle formed by the maximum turning radius is tangent to the ordinate is taken as the turning point.
In a second aspect, another embodiment of the present invention provides an AGV adaptive turn obstacle avoidance apparatus based on artificial intelligence, including:
the system comprises an image processing unit, a ground image acquisition unit and a display unit, wherein the image processing unit is used for acquiring a ground image which comprises a guiding medium of an AGV; performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of a guide medium;
a turning judgment unit, configured to detect edge straight lines of the guiding medium before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning when it is determined that the AGV needs to turn based on the edge profile information, where the first edge straight line and the second edge straight line are edge straight lines located on inner sides of the guiding medium before and after turning; judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line;
the speed adjusting unit is used for obtaining the initial turning speed of the AGV during turning according to the turning type; when the in-process of turning meets the barrier, connect in the barrier intercommunication domain apart from turn remind the nearest first pixel with turn and remind the point to obtain first straight line, acquire first straight line and turn the back the first nodical point of guide medium, according to maximum turning radius and turning point are acquireed to the position of first nodical point, and then based on the turning point, will initial turning speed adjustment does the maximum turning speed that maximum turning radius corresponds utilizes maximum turning speed accomplishes the AGV turns.
Further, an electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.
The embodiment of the invention has at least the following beneficial effects: in the process of AGV turning, the turning speed of the AGV is adjusted in real time according to the detected size of the obstacle, so that the AGV can turn at the optimal turning speed under the condition that the obstacle is not collided, and meanwhile, the conditions of discontinuity, blockage, stagnation and the like of turning are avoided, so that the AGV works normally.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart illustrating steps of an AGV adaptive turning obstacle avoidance method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a uniform circular motion of a quarter turn type according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a uniform circular motion of a curved type of turn according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a path of movement for an AGV during a turn that includes an obstacle detected in accordance with an embodiment of the present invention;
FIG. 5 is a block diagram of an AGV adaptive turning obstacle avoidance apparatus based on artificial intelligence according to another embodiment of the present invention;
fig. 6 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description will be given to an AGV adaptive turning obstacle avoidance method, apparatus and device based on artificial intelligence according to the present invention, and its specific implementation, structure, features and functions with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of an AGV adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence in detail with reference to the accompanying drawings.
The application scenarios aimed by the invention are as follows: in the external predetermined path guidance system, a medium for guiding the AGV needs to be continuously laid on the floor.
Preferably, the guiding medium in the embodiment of the present invention is a ribbon.
Referring to the attached drawing 1, an embodiment of the present invention provides an AGV adaptive turning obstacle avoidance method based on artificial intelligence, which includes the following specific steps:
step S001, collecting a ground image, wherein the ground image comprises a guiding medium of the AGV; and performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of the guide medium.
Specifically, the AGV is used for carrying the RGB camera, and when the AGV runs, the road condition in the field range is photographed to obtain a ground image. And obtaining a color band image from the ground image through a semantic segmentation network, and further obtaining edge contour information of the color band according to the color band image.
Preferably, the embodiment of the present invention employs a DNN network of an encoder-decoder structure to perform semantic segmentation on the ground image.
The specific training content of the DNN network includes:
1) and (3) marking the acquired ground image as a training data set, wherein the data set is marked with a colored tape marked as 1, the obstacles marked as 2 and the others marked as 0. Where 80% of the data set was randomly selected as the training set and the remaining 20% as the validation set.
2) Inputting image data and label data into a network, extracting network characteristics by an encoder, and converting the number of channels into the number of categories; the height and width of the feature map are then transformed into the size of the input image by a decoder, thereby outputting a class of each pixel.
3) The loss function is trained using a cross entropy loss function.
Step S002, when confirming that the AGV needs to turn according to the edge profile information, detecting edge straight lines of guiding media before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning, wherein the first edge straight line and the second edge straight line are edge straight lines positioned on the inner sides of the guiding media before and after turning; and judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line.
Specifically, hough line detection is performed on the contour of the color band edge in the color band image. According to priori knowledge, the directions of the edge straight lines of the two color bands before and after turning are parallel or vertical, so that in order to reduce the calculation amount and obtain more accurate edge straight lines of the color bands during Hough straight line detection, only the edge straight lines at a specific angle are extracted in the embodiment of the invention, and the specific process is as follows:
1) and transforming each pixel point on the edge straight line of the color band to Hough space, namely, one point in a Cartesian rectangular coordinate system corresponds to one curve in the Hough space.
2) After the step 1) is finished, the coordinate point with the brightest intersection point of the curves in the Hough space
Figure 778881DEST_PATH_IMAGE001
Namely, a plurality of pixel points in the representative image are positioned on the same straight line.
3) After the image is converted into the Hough space, only the respective selection is made in the Hough space
Figure 836967DEST_PATH_IMAGE002
The angle is
Figure 960912DEST_PATH_IMAGE003
The size of each pixel value in hough transform space represents how many pixel points on the straight line determined by the parameter.
Judging the coincidence degree of the extracted edge straight line and the contour of the color band to filter the straight line, whereinThe process of coincidence degree judgment is as follows: if the coordinates of each pixel point on the edge straight line exceed those of the pixel points in the same direction
Figure 965908DEST_PATH_IMAGE004
And if the pixel coordinate points are all located in the same linear equation, retaining the edge straight lines corresponding to the pixel coordinate points, and otherwise, filtering.
Further, judge AGV's turn type according to the distance between the marginal straight line of typewriter ribbon after the screening, specific process is:
1) if the obtained edge straight line has only one direction, the current AGV can be judged to run along the straight line direction without turning; otherwise, it is confirmed that the AGV needs to turn at the front.
2) When the fact that the AGV needs to turn is confirmed, detecting edge straight lines of guiding media before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning, wherein the first edge straight line and the second edge straight line are edge straight lines located on the inner sides of the guiding media before and after turning; and judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line.
As an example, in the embodiment of the present invention, any one first edge straight line in the guidance media in which the AGV is located before turning is selected, and a second edge straight line in the guidance media in which the AGV is located after turning is selected, where the first edge straight line and the second edge straight line are edge straight lines located on inner sides of the guidance media before and after turning, and a distance between pixel points between the first edge straight line and the second edge straight line is calculated, and when the distance between the pixel points is 0, that is, when there is coincidence between pixel points between the first edge straight line and the second edge straight line, it is determined that the turning type is a right-angle turn; otherwise, it is a curve with radian.
Step S003, obtaining an initial turning speed of the AGV during turning according to the turning type; when meeting the barrier in the process of turning, a first pixel point which is closest to the turning reminding point in the barrier communicating domain and the turning reminding point are connected to obtain a first straight line, a first intersection point of the first straight line and the turning rear guide medium is obtained, the maximum turning radius and the turning point are obtained according to the position of the first intersection point, then the initial turning speed is adjusted to be the maximum turning speed corresponding to the maximum turning radius based on the turning point, and the AGV turning is finished by utilizing the maximum turning speed.
Specifically, the AGV can generally consider that it does circular motion when turning, and therefore, based on the circular motion, the initial turning speed of the AGV is acquired after confirming the turning type, wherein the acquisition process is as follows:
1) in the embodiment of the invention, the AGV performs uniform circular motion in the process of uniform turning. Because the camera has a wider visual field and a longer visible distance, a turning point can be detected in a longer distance in an actual scene, and when the turning point is far away, the turning point has certain angular distortion due to projection transformation, so that an induction tag, namely a turning reminding point, is arranged at a position 5 meters away from the turning point of the AGV, so as to remind the AGV to turn.
The inflection point is an intersection between the first edge line and the second edge line.
2) Because the AGV does uniform circular motion when turning, the friction force and the centripetal force at the corresponding speed need to be calculated, otherwise, the AGV can turn over because of the over-high speed under the condition of a certain turning radius.
In particular, friction of the AGV
Figure 655647DEST_PATH_IMAGE005
The calculation formula is as follows:
Figure 150213DEST_PATH_IMAGE006
wherein the content of the first and second substances,
Figure 292613DEST_PATH_IMAGE007
the coefficient of friction between the AGV and the ground can be obtained according to prior data;
Figure 366879DEST_PATH_IMAGE008
is the gravity of the AGV.
It should be noted that, in the following description,
Figure 911124DEST_PATH_IMAGE009
wherein
Figure 983116DEST_PATH_IMAGE010
The total mass of the AGV and the carried goods is composed of the AGV standard mass and the carried goods mass, and the goods mass can be obtained by a weighing sensor carried on the AGV.
Centripetal force of AGV during turning
Figure 878391DEST_PATH_IMAGE011
The calculation formula is as follows:
Figure 490769DEST_PATH_IMAGE012
wherein
Figure 889521DEST_PATH_IMAGE013
The driving speed of the AGV at the turning reminding point is determined;
Figure 194731DEST_PATH_IMAGE014
the radius of the circular path is corresponding to the uniform circular motion of the AGV during turning.
3) When the turning type is right-angle turning, based on the length between the turning reminding point and the turning point, the speed variation is obtained by combining the running speed of the AGV at the turning reminding point, and then the initial turning speed corresponding to the uniform-speed circular motion of the AGV is obtained according to the speed variation.
Specifically, to ensure that the speed of the AGV is smoothly and smoothly turned at a constant speed on the premise of not reducing the speed, the turning radius of the AGV at the driving speed corresponding to the turning reminding point is calculated at first
Figure 311723DEST_PATH_IMAGE015
Because AGV is the circular motion at the uniform velocity, consequently centripetal force equals to the stiction this moment, then:
Figure 462213DEST_PATH_IMAGE016
Figure 981050DEST_PATH_IMAGE017
referring to fig. 2, point a is a turn alert point; the point B is a corresponding turning point when the constant-speed circular motion track of the AGV is tangent to the color ribbon;
Figure 191582DEST_PATH_IMAGE018
the points are tangent points;
Figure 795870DEST_PATH_IMAGE019
the point is the center of a circle of the uniform-speed circular motion, and in order to enable the AGV to just enter a specified direction to perform the uniform-speed circular motion after turning, the circle where the uniform-speed circular motion is performed by the AGV must be tangent to the color band after turning.
Turning radius of AGV (automatic guided vehicle) performing uniform circular motion
Figure 484472DEST_PATH_IMAGE015
The method comprises the steps that the change is carried out along with the change of the speed of the AGV, in order to enable the AGV to stably turn at the maximum speed before the inflection point, the running speed of the AGV needs to be regulated to obtain the initial turning speed, the regulation process is based on the length between the turning reminding point and the inflection point, acceleration is obtained by combining the running speed of the AGV at the turning reminding point, and then the initial turning speed corresponding to the uniform-speed circular motion of the AGV is obtained according to the acceleration.
As an example, the length between the turning reminding point and the inflection point in the embodiment of the invention
Figure 857815DEST_PATH_IMAGE020
Based on the formula of acceleration
Figure 849036DEST_PATH_IMAGE021
And displacement formula
Figure 675041DEST_PATH_IMAGE022
Calculate the acceleration of the AGV
Figure 354284DEST_PATH_IMAGE023
Wherein, in the step (A),
Figure 637325DEST_PATH_IMAGE024
is the changed speed;
Figure 720819DEST_PATH_IMAGE025
is the initial speed;
Figure 34119DEST_PATH_IMAGE026
is time. At an initial speed of the AGV
Figure 64523DEST_PATH_IMAGE013
In order to bring the AGV to a full stop at the inflection point, i.e., in the process
Figure 333831DEST_PATH_IMAGE024
=0, velocity of AGV according to acceleration
Figure 57067DEST_PATH_IMAGE023
And (3) decelerating, and calculating whether the constant-speed circular motion track at the real-time speed is tangent to the turned ribbon track in the deceleration process, wherein the tangent judging method comprises the following steps: calculating the distance from the circle center of the uniform-speed circular motion track to the turned ribbon track, and considering the distance as tangent when the distance is equal to the turning radius of the uniform-speed circular motion track, or considering the distance as not tangent; if the two are tangent, the speed at the moment is the initial turning speed of the AGV, and the turn is carried out at the initial turning speed; if the two are not tangent, the speed is reduced to 0 at the inflection point, and then the curve is made.
It should be noted that there are three AGV steering devices, which are a front-wheel steering rear-wheel drive three-wheel vehicle type, a differential steering four-wheel vehicle type, and an all-wheel steering four-wheel vehicle type. The differential steering type four-wheel vehicle type is simple in structure, high in positioning accuracy and most widely applied.
Preferably, in the embodiment of the invention, the speed of the AGV two wheels in the differential steering mode is mainly adjusted.
4) When the turning type is the turning with radian, the arc length with the radian and the corresponding arc angle are calculated to ensure that the speed of the AGV turns smoothly at a constant speed on the premise of not reducing the speed, and then based on the arc angle, the acceleration is obtained by utilizing the arc length, and then the initial turning speed corresponding to the uniform-speed circular motion of the AGV is obtained according to the acceleration.
As an example, referring to fig. 3, a broken line indicates an initial attitude of the vehicle body; the solid line indicates that the vehicle body is at the initial time difference of
Figure 857664DEST_PATH_IMAGE027
The attitude of the user; the running speeds of the left and right wheels of the AGV are respectively
Figure 754076DEST_PATH_IMAGE028
(ii) a The AGV makes circular arc motion along the point A, and the turning radius is d. According to the similarity of the circular arc patterns of the left wheel and the right wheel, the following results can be obtained:
Figure 159781DEST_PATH_IMAGE029
wherein the content of the first and second substances,
Figure 319498DEST_PATH_IMAGE030
the distance between the left and right wheels.
When the AGV moves by an arc of
Figure 341811DEST_PATH_IMAGE031
Then, the relation between the arc length formula and the speed of the left wheel and the right wheel is as follows:
Figure 245177DEST_PATH_IMAGE032
calculating the motion offset radian of the AGV when the AGV turns according to the similarity formula and the arc length formula, wherein the motion offset radian is
Figure 98863DEST_PATH_IMAGE033
When the vehicle is turned, the current overall speed is kept unchanged, and the ratio relation of the two differential wheels is only changed to turn; when the movement deviates by less than arc
Figure 163902DEST_PATH_IMAGE033
Time, based on arc length, using the formula for acceleration
Figure 673512DEST_PATH_IMAGE021
And displacement formula
Figure 787093DEST_PATH_IMAGE022
Calculate the acceleration of the AGV
Figure 698548DEST_PATH_IMAGE023
The speed of the AGV is determined according to the acceleration
Figure 934488DEST_PATH_IMAGE023
Carrying out deceleration, calculating whether the constant-speed circular motion track at the real-time speed is tangent to the turned ribbon track in the deceleration process, if so, taking the speed at the moment as the initial turning speed of the AGV, and turning at the initial turning speed; if the two are not tangent, the speed is reduced to 0 at the inflection point, and then the curve is made.
It should be noted that, because the embodiment of the present invention is directed to an external guidance mode in which the AGV is guided by an ink ribbon or a magnetic tape, the AGV may be disengaged from the ink ribbon guidance when turning in the above process, but because the AGV performs a uniform circumferential motion in the process, only the arc length displacement corresponding to the travel of the left and right wheels needs to be obtained by the arc length formula, and the respective speeds of the left and right wheels can obtain the time when the AGV is disengaged from the ink ribbon, so that the time can be obtained by the arc length formula
Figure 993711DEST_PATH_IMAGE026
The inner AGV does not need color tape guide and only needs to do uniform circular motion at a constant speed.
Further, when AGV meets the barrier at the turn in-process, according to the influence range when the barrier is to AGV turn, adjust AGV's initial turn speed, refer to FIG. 4, specific process is:
1) a rectangular coordinate system is established according to color bands before and after the AGV turns, namely the rectangular coordinate system is established by taking the first edge straight line 1 as the ordinate axis, the second edge straight line 2 as the abscissa axis and the inflection point 3 as the origin.
2) If the AGV does not detect the obstacle in the process of reaching the turning reminding point A, the AGV turns according to a preset constant-speed circular motion track BC; when the AGV detects an obstacle in the process of reaching the turning reminding point A, the AVG plans the turning path again, determines a new turning point and turns at the new turning point. The method for replanning the turning path comprises the following steps: when the camera detects that the obstacle 6 exists in the rectangular coordinate system range where the AGV turns, a first pixel point P which is closest to the turning reminding point A in the obstacle communicating region and the turning reminding point A are connected to obtain a first straight line, and a first intersection point of the first straight line and a second edge straight line is obtained
Figure 238879DEST_PATH_IMAGE034
According to the first intersection point
Figure 739262DEST_PATH_IMAGE034
The method comprises the steps of obtaining a maximum turning radius and a turning point, adjusting an initial turning speed to be the maximum turning speed corresponding to the maximum turning radius based on the turning point, and completing the turn of the AGV by using the maximum turning speed.
The method specifically comprises the following steps: obtaining a first pixel point P which is closest to a turning reminding point in an obstacle communicating region, connecting the turning reminding point A with the first pixel point P to obtain a first straight line, and further obtaining a first intersection point of an extension line of the first straight line on an abscissa axis
Figure 333054DEST_PATH_IMAGE034
The first intersection point
Figure 817256DEST_PATH_IMAGE034
The abscissa value of (a) is taken as the maximum turning radius, and the maximum turning radius is taken as the radius of a circle and is tangent to the abscissa and ordinate axesAnd the position where the circle formed by the maximum turning radius is tangent to the ordinate axis is taken as the turning point, i.e. the abscissa value of the first intersection point
Figure 866115DEST_PATH_IMAGE035
Determining maximum turning radius
Figure 486583DEST_PATH_IMAGE036
Then, at this time, the tangent point of the uniform velocity circular motion track 4 of the AGV and the abscissa axis needs to be located at [0,
Figure 595484DEST_PATH_IMAGE035
]within the range. Make the maximum turning radius
Figure 301403DEST_PATH_IMAGE037
The point of the uniform-speed circular motion track 4 with the radius tangent to the ordinate axis is
Figure 153953DEST_PATH_IMAGE038
Then point of
Figure 628928DEST_PATH_IMAGE038
Is the turning point of the AGV.
The maximum turning speed of the AGV in uniform circular motion can be obtained according to the maximum turning radius; obtaining the distance between the turning reminding point and the turning point, and utilizing an acceleration formula
Figure 643151DEST_PATH_IMAGE021
And displacement formula
Figure 898683DEST_PATH_IMAGE022
Acceleration of the AGV in the process from the turning reminding point to the turning point can be obtained
Figure 758186DEST_PATH_IMAGE023
And further adjusting the initial turning speed to the maximum turning speed according to the acceleration.
3) Because the image acquisition uses the RGB camera and the three-dimensional profile of the obstacle cannot be obtained after the camera detects the obstacle, the maximum turning radius range obtained in step 2) is too large, so that the AGV may collide with the blocked obstacle during the turning process. Therefore, when the AGV reaches a turning point and a shielded barrier 7 is detected, a second pixel point I which is closest to the inflection point in a shielded barrier communication domain in a turning influence range is obtained; and acquiring the optimal turning radius and the optimal turning point according to the second pixel point, and adjusting the maximum turning speed to the optimal turning speed corresponding to the optimal turning radius based on the optimal turning point.
The turning influence range is a range formed by the first intersection point and the turning reminding point based on a rectangular coordinate system;
the method specifically comprises the following steps: obtaining a second pixel point I which is closest to the inflection point in the communication domain of the sheltered obstacle, wherein the abscissa value of the second pixel point I is the abscissa value of the first intersection point
Figure 618826DEST_PATH_IMAGE035
In the range of (3), the uniform circular motion track 5 of the AGV8 is obtained by using the length corresponding to the abscissa value of the second pixel point I as the radius, and at this time, the uniform circular motion track 5 is tangent to the point on the ordinate axis
Figure 827388DEST_PATH_IMAGE039
Then point of
Figure 180003DEST_PATH_IMAGE039
The radius corresponding to the uniform circular motion track 5 is used as the optimal turning radius for the AGV8, the optimal turning speed corresponding to the uniform circular motion of the AGV8 is determined according to the optimal turning radius, and the acceleration is obtained based on the distance between the AGV8 and the optimal turning point
Figure 108776DEST_PATH_IMAGE023
And adjusting the maximum turning speed to the optimal turning speed according to the acceleration.
Further, when the camera collects images, the captured images may be blurred due to the relative motion between the AGV and the obstacle, and therefore a corresponding confidence error also exists in the optimal turning radius calculated on the basis. Therefore, in the embodiment of the present invention, the image blur correction is performed on the ground image, the maximum turning radius is corrected according to the degree of blur before and after the image correction, and the corresponding maximum turning speed is obtained according to the corrected maximum turning radius, and then the specific method is as follows:
1) and carrying out ambiguity detection on the ground image when the first intersection point is detected for the first time by using a Reblu secondary ambiguity algorithm to obtain a first ambiguity degree of the ground image.
2) Based on point spread function
Figure 823922DEST_PATH_IMAGE040
And carrying out fuzzy correction on the ground image.
Specifically, the most important content for correcting the blurred image is to determine the point spread function
Figure 179948DEST_PATH_IMAGE040
Because the strong edge of the image has a large influence on the image quality after being blurred and can reflect the blurring degree of the image more sensitively, the strong edge prediction method is used for accurately estimating the image quality in the embodiment of the invention
Figure 144493DEST_PATH_IMAGE040
The value is obtained.
In the strong edge prediction method, a region obtained by setting a radius is generally acquired, and the spatial variation is estimated by using the pixel value in the region as an effective pixel
Figure 611378DEST_PATH_IMAGE040
The value is obtained. To obtain
Figure 102402DEST_PATH_IMAGE040
And after the value is obtained, carrying out fuzzy recovery on the region by using a non-blind deconvolution algorithm.
Preferably, in the embodiment of the present invention, the image blur correction is performed in a circular range formed in the ground image by the maximum turning radius.
3) And carrying out ambiguity detection on the ground image after the ambiguity recovery by using a Reblu secondary ambiguity algorithm to obtain a second ambiguity degree of the ground image after the ambiguity recovery.
4) The maximum turning speed is corrected based on the degrees of blur before and after the image correction. The method specifically comprises the following steps: and acquiring the ratio of the first fuzzy degree to the second fuzzy degree, acquiring a new maximum turning radius according to the product of the ratio and the maximum turning radius, and further acquiring a corresponding maximum turning speed according to the new maximum turning radius to finish the turning of the AGV.
Similarly, the image blur correction is carried out on the ground image, the optimal turning radius is corrected according to the blur degree before and after the image correction, and then the corresponding optimal turning speed is obtained according to the corrected optimal turning radius.
Preferably, a range of the image blur correction is determined, the range being a circular range in which the optimum turning radius is formed on the ground image.
In summary, the embodiment of the invention provides an AGV adaptive turning obstacle avoidance method based on artificial intelligence, which determines the turning type of an AGV according to the distance between edge straight lines of an ink ribbon before and after the AGV turns when the AGV needs to turn according to edge profile information of the ink ribbon, obtains the initial turning speed when the AGV turns according to the turning type of the AGV, adjusts the initial speed through an obstacle connected domain detected in the turning process to obtain the optimal turning speed, and further completes the AGV turning by using the optimal turning speed. In the process of AGV turning, the turning speed of the AGV is adjusted in real time according to the detected size of the obstacle, so that the AGV can turn at the optimal turning speed under the condition that the obstacle is not collided, and meanwhile, the conditions of discontinuity, blockage, stagnation and the like of turning are avoided, so that the AGV works normally.
Based on the same inventive concept as the method, the embodiment of the invention provides an AGV self-adaptive turning obstacle avoidance device based on artificial intelligence.
Referring to fig. 5, an embodiment of the present invention provides an AGV adaptive turning obstacle avoidance apparatus based on artificial intelligence, including: an image processing unit 10, a turn determination unit 20, and a speed adjustment unit.
The image processing unit 10 is used for collecting a ground image, and the ground image comprises a guiding medium of the AGV; and performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of the guide medium.
The turning judgment unit 20 is configured to detect edge straight lines of the guiding medium before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning when confirming that the AGV needs to turn based on the edge profile information, where the first edge straight line and the second edge straight line are edge straight lines located on inner sides of the guiding medium before and after turning; and judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line.
The speed adjusting unit 30 is used for obtaining an initial turning speed when the AGV turns according to the turning type; when meeting the barrier in the process of turning, a first pixel point which is closest to the turning reminding point in the barrier communicating domain and the turning reminding point are connected to obtain a first straight line, a first intersection point of the first straight line and the turning rear guide medium is obtained, the maximum turning radius and the turning point are obtained according to the position of the first intersection point, then the initial turning speed is adjusted to be the maximum turning speed corresponding to the maximum turning radius based on the turning point, and the AGV turning is finished by utilizing the maximum turning speed.
Further, please refer to fig. 6, which illustrates a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device in this embodiment includes: an acquisition device, a processor, a memory, and a computer program stored in the memory and executable on the processor. Wherein the acquisition device is an RGB camera. The processor, when executing the computer program, implements the steps of one of the above-described AGV adaptive turn obstacle avoidance method embodiments based on artificial intelligence, such as the steps shown in fig. 1. Or the processor executes a computer program to realize the functions of the units in the AGV adaptive turning obstacle avoidance device based on artificial intelligence.
Illustratively, a computer program may be divided into one or more units, where one or more units are stored in the memory and executed by the processor to implement the invention. One or more of the elements may be a sequence of computer program instruction segments for describing the execution of the computer program in the electronic device, which can perform certain functions.
The electronic device is an AGV. The electronic device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagrams are merely examples of the electronic device and do not constitute a limitation of the electronic device, and may include more or less components than those shown, or some components in combination, or different components, e.g. the electronic device may also include input-output devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center for an electronic device and that connects the various parts of the overall electronic device using various interfaces and wires.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. An AGV self-adaptive turning obstacle avoidance method based on artificial intelligence is characterized by comprising the following steps:
collecting a ground image, wherein the ground image comprises a guiding medium of an AGV; performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of a guide medium;
when the AGV needs to turn according to the edge profile information, detecting edge straight lines of the guiding medium before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning, wherein the first edge straight line and the second edge straight line are edge straight lines positioned on the inner side of the guiding medium before and after turning; judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line;
obtaining the initial turning speed when the AGV turns according to the turning type; when the in-process of turning meets the barrier, connect in the barrier intercommunication domain apart from turn remind the nearest first pixel with turn and remind the point to obtain first straight line, acquire first straight line and turn the back the first nodical point of guide medium, according to maximum turning radius and turning point are acquireed to the position of first nodical point, and then based on the turning point, will initial turning speed adjustment does the maximum turning speed that maximum turning radius corresponds utilizes maximum turning speed accomplishes the AGV turns.
2. The method of claim 1, wherein obtaining the maximum turning speed further comprises:
in the process that the AGV reaches the turning point, when a shielded barrier is detected, a second pixel point which is closest to the turning point in a shielded barrier communication domain in a turning influence range is obtained; the turning influence range is a range formed by the first intersection point and the turning reminding point; the inflection point is an intersection between the first edge straight line and the second edge straight line;
and acquiring an optimal turning radius and an optimal turning point according to the second pixel point, and adjusting the maximum turning speed to the optimal turning speed corresponding to the optimal turning radius based on the optimal turning point.
3. The method according to claim 1, wherein the method of correcting the maximum turning speed comprises:
and carrying out image blur correction on the ground image, correcting the maximum turning radius according to the degree of blur before and after image correction, and further obtaining the corresponding maximum turning speed according to the corrected maximum turning radius.
4. The method according to claim 2, wherein the method of correcting the optimum turning speed comprises:
and carrying out image blur correction on the ground image, correcting the optimal turning radius according to the blur degree before and after the image correction, and further obtaining the corresponding optimal turning speed according to the corrected optimal turning radius.
5. The method of claim 4, wherein the optimization method for image blur correction of the ground image comprises:
determining a range of the image blur correction, the range being a circular range of the optimal turning radius formed on the ground image.
6. The method of claim 1 wherein said method of determining the turn type of the AGV based on the distance between the first edge line and the second edge line comprises:
when the pixel point positions between the first edge straight line and the second edge straight line are overlapped, determining that the turning type is a right-angle turning; otherwise, it is a curve with radian.
7. The method of claim 6 wherein said deriving an initial turn speed for said AGV when turning based on said turn type comprises:
when the turning type is right angle turning, based on the turning reminding point and the length between the inflection points, the AGV is combined with the speed variation obtained by the running speed of the turning reminding point, and then the initial turning speed corresponding to the uniform speed circular motion is obtained by the speed variation and the running speed.
8. The method of claim 1, wherein the method of obtaining a maximum turn radius from the first intersection point comprises:
establishing a rectangular coordinate system by taking the first edge straight line as a vertical coordinate, the second edge straight line as a horizontal coordinate and an intersection point between the first edge straight line and the second edge straight line as an origin, and taking the horizontal coordinate value of the first intersection point as the maximum turning radius;
the position where the circle formed by the maximum turning radius is tangent to the ordinate is taken as the turning point.
9. The utility model provides a AGV self-adaptation turns and keeps away barrier device based on artificial intelligence which characterized in that, the device includes:
the system comprises an image processing unit, a ground image acquisition unit and a display unit, wherein the image processing unit is used for acquiring a ground image which comprises a guiding medium of an AGV; performing semantic segmentation on the ground image to obtain a guide medium image and edge contour information of a guide medium;
a turning judgment unit, configured to detect edge straight lines of the guiding medium before and after turning to obtain a first edge straight line before turning and a second edge straight line after turning when it is determined that the AGV needs to turn based on the edge profile information, where the first edge straight line and the second edge straight line are edge straight lines located on inner sides of the guiding medium before and after turning; judging the turning type of the AGV according to the distance between the first edge straight line and the second edge straight line;
the speed adjusting unit is used for obtaining the initial turning speed of the AGV during turning according to the turning type; when the in-process of turning meets the barrier, connect in the barrier intercommunication domain apart from turn remind the nearest first pixel with turn and remind the point to obtain first straight line, acquire first straight line and turn the back the first nodical point of guide medium, according to maximum turning radius and turning point are acquireed to the position of first nodical point, and then based on the turning point, will initial turning speed adjustment does the maximum turning speed that maximum turning radius corresponds utilizes maximum turning speed accomplishes the AGV turns.
10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-8 when executing the computer program.
CN202110810318.6A 2021-07-19 2021-07-19 AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence Active CN113268065B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110810318.6A CN113268065B (en) 2021-07-19 2021-07-19 AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110810318.6A CN113268065B (en) 2021-07-19 2021-07-19 AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN113268065A true CN113268065A (en) 2021-08-17
CN113268065B CN113268065B (en) 2021-09-24

Family

ID=77236668

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110810318.6A Active CN113268065B (en) 2021-07-19 2021-07-19 AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN113268065B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435417A (en) * 2021-08-26 2021-09-24 山东华力机电有限公司 Double-wheel-driven AGV steering visual control method
CN117671646A (en) * 2024-01-30 2024-03-08 深圳唯创安全技术有限公司 Anti-collision auxiliary system and method for forklift based on AI image

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102822881A (en) * 2010-04-05 2012-12-12 丰田自动车株式会社 Vehicle collision judgment device
CN103335658A (en) * 2013-06-19 2013-10-02 华南农业大学 Autonomous vehicle obstacle avoidance method based on arc path
US20180059674A1 (en) * 2016-08-25 2018-03-01 Toyota Jidosha Kabushiki Kaisha Vehicle control apparatus
CN112000099A (en) * 2020-08-26 2020-11-27 大连理工大学 Collaborative robot flexible path planning method under dynamic environment
CN112363491A (en) * 2019-07-24 2021-02-12 杭州萤石软件有限公司 Robot turning control method and device
US20210123750A1 (en) * 2019-10-29 2021-04-29 Hyundai Motor Company Autonomous vehicle and method for planning u-turn path thereof
CN113110456A (en) * 2021-04-16 2021-07-13 河南六米电子科技有限公司 AGV trolley stable driving method and system based on artificial intelligence

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102822881A (en) * 2010-04-05 2012-12-12 丰田自动车株式会社 Vehicle collision judgment device
CN103335658A (en) * 2013-06-19 2013-10-02 华南农业大学 Autonomous vehicle obstacle avoidance method based on arc path
US20180059674A1 (en) * 2016-08-25 2018-03-01 Toyota Jidosha Kabushiki Kaisha Vehicle control apparatus
CN112363491A (en) * 2019-07-24 2021-02-12 杭州萤石软件有限公司 Robot turning control method and device
US20210123750A1 (en) * 2019-10-29 2021-04-29 Hyundai Motor Company Autonomous vehicle and method for planning u-turn path thereof
CN112000099A (en) * 2020-08-26 2020-11-27 大连理工大学 Collaborative robot flexible path planning method under dynamic environment
CN113110456A (en) * 2021-04-16 2021-07-13 河南六米电子科技有限公司 AGV trolley stable driving method and system based on artificial intelligence

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435417A (en) * 2021-08-26 2021-09-24 山东华力机电有限公司 Double-wheel-driven AGV steering visual control method
CN117671646A (en) * 2024-01-30 2024-03-08 深圳唯创安全技术有限公司 Anti-collision auxiliary system and method for forklift based on AI image
CN117671646B (en) * 2024-01-30 2024-04-09 深圳唯创安全技术有限公司 Anti-collision auxiliary system and method for forklift based on AI image

Also Published As

Publication number Publication date
CN113268065B (en) 2021-09-24

Similar Documents

Publication Publication Date Title
CN113268065B (en) AGV self-adaptive turning obstacle avoidance method, device and equipment based on artificial intelligence
US11216673B2 (en) Direct vehicle detection as 3D bounding boxes using neural network image processing
CN110007675B (en) Vehicle automatic driving decision-making system based on driving situation map and training set preparation method based on unmanned aerial vehicle
US11136027B2 (en) Vehicle control device
CN105216794A (en) The drive assistance device of vehicle
US20140118552A1 (en) Road shape determining device, in-vehicle image recognizing device, imaging axis adjusting device, and lane recognizing method
JPH02226310A (en) Autonomous running vehicle
CN108032859A (en) It is automatic to become channel control method, device and automobile
CN110320908A (en) A kind of AGV real-time emulation system
CN112567264A (en) Apparatus and method for acquiring coordinate transformation information
CN111474930A (en) Tracking control method, device, equipment and medium based on visual positioning
CN106985142A (en) A kind of double vision for omni-directional mobile robots feels tracking device and method
CN115923839A (en) Vehicle path planning method
CN114012732B (en) Robot control method, device, equipment and medium
CN108944899A (en) A kind of automatic driving vehicle steering disk control system and method based on fuzzy control
Manivannan et al. Vision based intelligent vehicle steering control using single camera for automated highway system
Yang et al. Vision-based intelligent vehicle road recognition and obstacle detection method
CN110083158B (en) Method and equipment for determining local planning path
CN113075716A (en) Image-based vehicle positioning method and device, storage medium and electronic equipment
EP4071512A1 (en) Sensor fusion for object-avoidance detection
Chen et al. From perception to control: an autonomous driving system for a formula student driverless car
CN113110456B (en) AGV trolley stable driving method and system based on artificial intelligence
CN115755888A (en) AGV obstacle detection system with multi-sensor data fusion and obstacle avoidance method
CN113625718B (en) Vehicle travel path planning method
CN113793371B (en) Target segmentation tracking method, device, electronic equipment and 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
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: AGV adaptive turning obstacle avoidance method, device and equipment based on Artificial Intelligence

Effective date of registration: 20220519

Granted publication date: 20210924

Pledgee: Bank of China Limited Wenshang sub branch

Pledgor: SHANDONG HUALI ELECTROMECHANICAL Co.,Ltd.

Registration number: Y2022980005841