CN115848878A - AGV-based cigarette frame identification and stacking method and system - Google Patents
AGV-based cigarette frame identification and stacking method and system Download PDFInfo
- Publication number
- CN115848878A CN115848878A CN202310173761.6A CN202310173761A CN115848878A CN 115848878 A CN115848878 A CN 115848878A CN 202310173761 A CN202310173761 A CN 202310173761A CN 115848878 A CN115848878 A CN 115848878A
- Authority
- CN
- China
- Prior art keywords
- agv
- cigarette
- stacking
- cigarette frame
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Warehouses Or Storage Devices (AREA)
- Manipulator (AREA)
Abstract
The invention provides a method and a system for identifying and stacking cigarette frames based on AGV, wherein the system comprises: AGV, install the first vision sensor of horizontal visual angle shooting pile position cigarette frame in the middle of the AGV in level and forward, install in AGV fork side and perpendicular overlook downwards and shoot the second vision sensor that is located the cigarette frame that the AGV fork below is in cigarette frame pile position, install and be used for detecting the inclination sensor of AGV fork inclination to the side of AGV fork, and receive cigarette frame image data and AGV fork inclination data and carry out the cigarette frame and pile up the visual identification controller that position calculation obtained the relative position appearance of cigarette frame. According to the invention, the AGV is designed according to the characteristics of the cigarette frames, so that the accurate stacking of the cigarette frames is realized, and the stacking error is less than +/-20 mm.
Description
Technical Field
The invention relates to the technical field of cigarette frame stacking, in particular to a method and a system for identifying and stacking cigarette frames based on an AGV.
Background
In the field of plane storage, due to the fact that no goods shelf is adopted, ground storage of goods has high requirements on space, occupied area is large, the storage cost is low, storage cost is higher and higher, but storage of planning of the warehouse is not flexible and variable due to the adoption of the goods shelf, and a plurality of plane type warehouses belong to the leasing property, or the floor height is not enough, the ground and other infrastructure does not meet the scheme of adopting the goods shelf. More and more customers are proposing that multiple stacked storage of goods is done by AGVs, for example, a great deal of application needs have emerged in the tobacco, dairy, beer, gypsum, etc. industries.
Disclosure of Invention
In order to solve the problem that the precision and the efficiency are lower when the manual stacking method is used for stacking the cigarette frames in the tobacco industry at present, the invention provides the method and the system for identifying and stacking the cigarette frames based on the AGV.
The specific scheme is as follows:
the invention provides a method for identifying and stacking cigarette frames based on AGV, which comprises the following steps:
s1: the method comprises the steps that a first vision sensor is horizontally and positively arranged in the middle of an AGV, a cigarette frame in a stacking position is shot at a horizontal visual angle, a second vision sensor is arranged on the side face of a fork of the AGV, and the cigarette frame in the stacking position is shot vertically downwards in a downward overlooking mode after the AGV runs to the stacking position; calibrating installation parameters among the first visual sensor, the second visual sensor and the AGV, and transmitting the installation parameters to the AGV controller;
s2: installing an inclination angle sensor on the lateral surface of the AGV fork to detect the inclination angle of the AGV fork;
s3: planning a running path of the AGV for stacking the cigarette frames as a planned path, stopping running at a platform before the AGV runs to the planned path, sending a horizontal visual angle image acquisition command to a visual recognition controller through the AGV controller, and sending an acquisition command to a first visual sensor by the visual recognition controller so as to acquire cigarette frame image data of a stacking position and send the data to the visual recognition controller; the front point platform is a transfer point arranged in an AGV planning path, and the AGV at the position can shoot the cigarette frames at the stacking position at a horizontal visual angle by using a first vision sensor;
s4: the visual recognition controller filters the image data of the cigarette frames acquired in the S3, extracts characteristic data describing the stacking positions of the cigarette frames, calculates the placing angles of the cigarette frames at the stacking positions and the distances between the placing angles and a front point platform where the AGV is located as relative poses by utilizing the characteristic data, and transmits the relative poses to the AGV controller;
s5: the AGV controller calculates a temporary dynamic path of the AGV reaching a cigarette frame stacking preparation point of the cigarette frame stacking position according to the relative pose in the S4;
s6: the AGV controller controls the AGV to drive to a cigarette frame stacking preparation point according to a new temporary dynamic path;
s7: after the vehicle runs to the cigarette frame stacking preparation point in the S6, cigarette frames are stacked, and the AGV controller sends a vertical visual angle image acquisition command to the visual recognition controller; after the AGV equipment travels to the cigarette frame stacking preparation point, the AGV equipment does not displace, and the cigarette frame stacking is completed only by moving a pallet fork on the AGV;
s8: the visual recognition controller sends an acquisition command to the second visual sensor to enable the second visual sensor to shoot the cigarette frames located below the AGV fork and at the cigarette frame stacking position from top to bottom in an overlooking mode to obtain vertical image data, the vertical image data are transmitted to the visual recognition controller, and the visual recognition controller filters and extracts features of the vertical image data to finally calculate left and right position deviation between the cigarette frames below the fork and the AGV fork;
s9: the AGV controller calculates the left and right adjustment amount of the AGV fork according to the left and right position deviation data in the S8, and controls the AGV fork to complete left and right adjustment;
s10: the AGV controller controls the descending of the AGV fork to complete the stacking of the cigarette frames.
Preferably, the planned path in S3 is a theoretical path for the AGV to place the single fork-picked cigarette frame on the ground or on a transport vehicle to the cigarette frame stacking position in the stacking area, and the number of cigarette frame layers stored in the stacking area is not more than 4.
Preferably, the first vision sensor can move up and down under the control of the AGV, so that the horizontal visual angles of the smoke frames with different stacking layers are shot; second vision sensor is along with AGV fork up-and-down motion, realizes piling up the shooting of the perpendicular visual angle of number of piles of layers cigarette frame to the difference. Preferably, after the AGV forks the cigarette frames from the ground or the transport vehicle, the AGV controller controls the AGV forks to be adjusted to the horizontal state according to the inclination angle values of the AGV forks collected by the inclination angle sensor.
Preferably, the front point station in S3 is 1m to 5m from the cigarette frame stacking position.
Preferably, the cigarette frame characteristic data is data expressing cigarette frame shape size and position information, and includes: the cigarette frame covers the bowl-shaped supporting leg and the angular point.
Preferably, the required error of the stacking precision of the cigarette frame is within +/-20 mm, and the bowl covering structure below the supporting leg of the cigarette frame is embedded with the supporting leg of the cigarette frame below the supporting leg of the cigarette frame after stacking.
Preferably, the method for identifying the cigarette frame feature data comprises the steps of firstly establishing a feature parameter template of the cigarette frame, wherein the feature parameter template comprises the overall dimension, the width and the height of an upright post of the cigarette frame and also comprises point cloud feature data of the cigarette frame; and then the AGV identifies the fork-taken or stacked cigarette frames by the following method, including:
step a: the visual sensor collects the image data of the cigarette frame and the visual recognition controller carries out filtering processing;
step b: the vision recognition controller acquires depth information of a recognition object from the filtered image data;
step c: obtaining point cloud data of the detected object according to the depth data of the identified object;
step d: carrying out point cloud registration according to the point cloud data of the object to be detected and the point cloud data in the pre-established smoke frame characteristic parameter template;
step e: extracting key angular points and edge straight line characteristics of the point cloud data of the measured cigarette frame, calculating basic data of the outline dimension, the width and the height of the stand column of the cigarette frame, and comparing the basic data with cigarette frame data in cigarette frame characteristic parameters established in advance;
step f: and calculating the coordinates of the reference points of the cigarette frame according to the extracted key angular points and edge straight line characteristics of the cigarette frame, wherein the calculated coordinates of the cigarette frame stacking preparation points are the relative poses (dx, dy, dtheta) of the cigarette frame relative to the vision sensor.
Preferably, when the first layer of cigarette frames stored in the stacking storage area are placed, the AGV places the cigarette frames according to the set planning path without adjusting the horizontal inclination angle.
An AGV-based cigarette frame identification and stacking system, comprising: the system comprises an AGV, a first visual sensor, a second visual sensor, an inclination angle sensor and a visual identification controller, wherein the first visual sensor is horizontally and forwardly installed in the middle of the AGV and used for shooting a cigarette frame at a stacking position at a horizontal visual angle, the second visual sensor is installed on the side face of an AGV fork and used for vertically downwards overlooking to shoot the cigarette frame which is positioned below the AGV fork and is at the stacking position of the cigarette frame, the inclination angle sensor is installed on the side face of the AGV fork and used for detecting the inclination angle of the AGV fork, and the visual identification controller is used for receiving the image data of the cigarette frame of the first visual sensor and the second visual sensor and the inclination angle data of the AGV fork of the inclination angle sensor, and calculating the stacking position of the cigarette frame to obtain the relative pose of the cigarette frame; the AGV includes: the AGV control system comprises an AGV controller for receiving the relative pose data of the visual recognition controller and an AGV fork controlled by the AGV controller.
Preferably, the first and second vision sensors are depth cameras.
The invention provides a method and a system for identifying and stacking cigarette frames based on an AGV (automatic guided vehicle), which realize multilayer and accurate stacking of the cigarette frames. According to the characteristics of the cigarette frame, the first visual sensor and the second visual sensor are installed at the specific position of the AGV, and the posture and the position of the cigarette frame are recognized through shooting at a specific visual angle. Meanwhile, the posture and the position deviation of the cigarette frame are obtained through comparison with the planned path, and after the adjustment amount is calculated, the inclination angle sensor adjusts the angle of the AGV fork, so that high-precision cigarette frame stacking is realized. And thirdly, the first visual sensor and the second visual sensor can be adjusted up and down according to the number of layers of the cigarette frame, and data of a horizontal visual angle and a vertical visual angle of the cigarette frame can be acquired in real time. In conclusion, according to the AGV-based cigarette frame identification and stacking method and system, AGV stacking design is carried out through the structural characteristics of the cigarette frame, stacking space is saved, stacking stability is guaranteed, the characteristics of the cigarette frame are identified through a visual identification method, the covered bowl type supporting legs of the cigarette frame and cylinders or cuboids or other structures protruding above the supporting legs are utilized, the cigarette frame is more stable through mutual matching and embedding, and stacking accuracy reaches +/-20 mm.
Simultaneously, in carrying out cigarette frame feature identification, to the characteristics that the lid bowl formula structure of the landing leg below of cigarette frame mutually supported with cigarette frame landing leg upper portion salient structure, discerned and markd, when making two cigarette frames pile up together, stability is higher, and supplementary cigarette frame piles up, promotes the precision that cigarette frame multilayer piled up, avoids the cigarette frame landing, realizes the automation that the cigarette frame was deposited.
Drawings
FIG. 1: provided is a flow chart of a method for identifying and stacking cigarette frames based on an AGV.
FIG. 2: a method flow chart of cigarette frame characteristic data identification.
FIG. 3: a smoke frame identification and stacking system structure diagram based on an AGV.
FIG. 4: and point cloud data schematic diagram showing the partial structural features of the cigarette frame.
FIG. 5 is a schematic view of: an effect map of the relative position of an AGV at the front of a station to a stack of frames.
FIG. 6: and (5) stacking the tobacco frames to form an effect picture.
In the figure: 1: AGV;2: a first vision sensor; 3: a second vision sensor; 4: a tilt sensor; 5: AGV forks; 6: planning a path; 7: a temporary dynamic path; 8: an actual cigarette frame; 9: an actual cigarette frame stacking preparation point; 10: planning a cigarette frame; 11: planning a cigarette frame stacking preparation point; 12: a front point station; 13: structural point cloud data of the lower part of the cigarette frame; 14: point cloud data of a partial frame structure on the cigarette frame; 15: a bowl-type supporting leg is covered on the cigarette frame; 16: preliminarily forming a cigarette frame edge frame according to the point cloud data; 17: the protruding structures are matched and embedded with the supporting legs of the upper cigarette frame.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
As shown in fig. 1 and 5, the present invention provides an AGV-based method for recognizing and stacking cigarette frames:
s1: the method comprises the following steps of horizontally and forwardly installing a first vision sensor 2 in the middle of an AGV1, shooting cigarette frames at a stacking position at a horizontal visual angle, installing a second vision sensor 3 on the side face of a fork of the AGV, and vertically downwards overlooking and shooting the cigarette frames at the stacking position after the AGV drives to the stacking position; calibrating installation parameters between the first visual sensor 2, the second visual sensor 3 and the AGV1 and transmitting the installation parameters to the AGV controller;
s2: installing an inclination angle sensor 4 on the lateral surface of the AGV fork to detect the inclination angle of the AGV fork 5;
s3: planning a running path of the AGV for stacking the cigarette frames to serve as a planned path 6, stopping running at a station 12 at the front point of the planned path 6 when the AGV runs to the planned path, sending a horizontal visual angle image acquisition command to a visual recognition controller through the AGV controller, and sending an acquisition command to a first visual sensor by the visual recognition controller so as to acquire cigarette frame image data of a stacking position and send the data to the visual recognition controller; the front point platform 12 is a transit point arranged in the planned path of the AGVs, and the AGVs at the position can shoot the cigarette frames at the stacking position at a horizontal visual angle by using a first visual sensor;
s4: the visual recognition controller filters the image data of the cigarette frames acquired in the S3, extracts characteristic data describing the stacking positions of the cigarette frames, calculates the placing angle of the cigarette frames at the stacking positions and the distance between the placing angle and the front point platform 12 where the AGV is located as relative poses by utilizing the characteristic data, and transmits the relative poses to the AGV controller;
s5: the AGV controller calculates a temporary dynamic path of the AGV reaching a cigarette frame stacking preparation point of the cigarette frame stacking position according to the relative pose in the S4;
s6: the AGV controller controls the AGV to drive to a cigarette frame stacking preparation point according to a new temporary dynamic path;
s7: after the vehicle runs to the cigarette frame stacking preparation point in the S6, cigarette frames are stacked, and the AGV controller sends a vertical visual angle image acquisition command to the visual recognition controller; after the AGV equipment runs to the cigarette frame stacking preparation point, the AGV equipment does not displace, and only the fork on the AGV is moved to complete cigarette frame stacking;
s8: the visual recognition controller sends an acquisition command to the second visual sensor 3 to enable the second visual sensor to shoot a cigarette frame located below the AGV fork 5 and located at the cigarette frame stacking position from top to bottom in an overlooking mode to obtain vertical image data, the vertical image data are transmitted to the visual recognition controller, and the visual recognition controller filters and extracts features of the vertical image data to finally calculate left and right position deviation between the cigarette frame below the fork and the AGV fork;
s9: the AGV controller calculates the left and right adjustment amount of the AGV fork according to the left and right position deviation data in the S8, and controls the AGV fork to complete left and right adjustment;
s10: the AGV controller controls the AGV fork 5 to descend to complete the stacking of the cigarette frames.
Preferably, the planned path 6 in S3 is a theoretical path for the AGV to place the single fork-picked cigarette frame on the ground or on a transport vehicle to a cigarette frame stacking position in the stacking area, and the number of cigarette frame layers stored in the stacking area is not more than 4. The cigarette frame stacking position reached by the planned path 6 in the AGV system is a planned cigarette frame stacking preparation point 11, and is different from an actual cigarette frame stacking preparation point 9, errors exist between the planned cigarette frame stacking preparation point 11 and the actual cigarette frame stacking preparation point 9, if the errors between the planned cigarette frame stacking preparation point 11 and the actual cigarette frame stacking preparation point 9 are large, an alarm is generated, and the error range is 20mm.
Preferably, the first vision sensor can move up and down under the control of the AGV, so that the horizontal visual angles of the smoke frames with different stacking layers are shot; second vision sensor is along with AGV fork up-and-down motion, realizes piling up the shooting at the perpendicular visual angle of number of piles of layer cigarette frame to the difference.
Preferably, after the AGV forks the cigarette frame from the ground or the transport vehicle, the AGV controller controls the AGV fork to be adjusted to the horizontal state according to the AGV fork inclination angle value collected by the inclination angle sensor.
Preferably, the front point station in S3 is 1m to 5m from the cigarette frame stacking position.
Preferably, the cigarette frame characteristic data is data expressing cigarette frame shape size and position information, and includes: the cigarette frame covers the bowl-shaped supporting leg and the angular point.
Preferably, the stacking precision of the cigarette frame requires that the error is within +/-20 mm, and the bowl-covering structure below the supporting leg of the cigarette frame is embedded with the supporting leg of the cigarette frame below the supporting leg of the cigarette frame after stacking.
Preferably, as shown in fig. 2, the method for identifying the cigarette frame feature data includes firstly establishing a feature parameter template of the cigarette frame, where the feature parameter template includes an external dimension of the cigarette frame, a width of an upright post, a height of the upright post, and point cloud feature data of the cigarette frame; and then the AGV identifies the fork-taken or stacked cigarette frames by the following method, including:
step a: the visual sensor collects the image data of the cigarette frame and the visual recognition controller carries out filtering processing;
step b: the vision recognition controller acquires depth information of the recognition object from the filtered image data;
step c: according to the depth data of the identification object, point cloud data of the measured object are obtained;
step d: carrying out point cloud registration according to the point cloud data of the object to be detected and the point cloud data in the pre-established smoke frame characteristic parameter template;
step e: extracting key angular points and edge straight line characteristics of the point cloud data of the measured cigarette frame, calculating basic data of the outline dimension, the width and the height of the stand column of the cigarette frame, and comparing the basic data with cigarette frame data in cigarette frame characteristic parameters established in advance;
step f: according to the extracted key angular points and edge linear characteristics of the cigarette frame, reference point coordinates of the cigarette frame are calculated, the calculated cigarette frame stacking preparation point coordinates are the relative pose of the cigarette frame relative to the vision sensor, the relative pose can be expressed through coordinates (dx, dy, dtheta), the AGV device is used as the origin of coordinates, and the dtheta is used as the inclination angle of the cigarette frame.
As shown in fig. 4, when stacking the cigarette frames, only a part of the structure of the cigarette frame needs to be identified due to the limitation of the shooting distance or the viewing angle, for example, when stacking the cigarette frame on the pallet fork to the cigarette frame stored in the stacking storage area, only the lower part structure of the cigarette frame on the pallet fork needs to be obtained, that is, the point cloud data 13 of the lower part structure of the cigarette frame in fig. 4, and the size data of the cigarette frame, such as the support legs, the width, and the like, can be displayed; for the cigarette frames stored in the stacking storage area, only the point cloud data of the partial frame structure on the cigarette frame needs to be acquired, for example, the protruding structure which is needed in the stacking process and is matched and embedded with the supporting legs of the cigarette frame above, namely 14 in fig. 4, is subjected to feature recognition on partial structural features needed in the stacking process to acquire the point cloud data, the limitation of the distance for shooting the cigarette frame by a camera is avoided, and the calculated amount is saved.
Preferably, when the first layer of cigarette frames stored in the stacking storage area are placed, the AGV places the cigarette frames according to the set planning path without adjusting the horizontal inclination angle. To accommodate the ability to stack or extract each frame, the planned path is typically arranged horizontally with a space between rows that allows the AGV device to pass.
As shown in FIG. 3, an AGV based smoke frame identification and stacking system comprises: the system comprises an AGV, a first visual sensor, a second visual sensor, an inclination angle sensor and a visual identification controller, wherein the first visual sensor is horizontally and forwardly installed in the middle of the AGV and used for shooting a cigarette frame at a stacking position at a horizontal visual angle, the second visual sensor is installed on the side face of an AGV fork and used for vertically downwards overlooking to shoot the cigarette frame which is positioned below the AGV fork and is at the stacking position of the cigarette frame, the inclination angle sensor is installed on the side face of the AGV fork and used for detecting the inclination angle of the AGV fork, and the visual identification controller is used for receiving the image data of the cigarette frame of the first visual sensor and the second visual sensor and the inclination angle data of the AGV fork of the inclination angle sensor, and calculating the stacking position of the cigarette frame to obtain the relative pose of the cigarette frame; the AGV includes: the AGV control system comprises an AGV controller for receiving the relative pose data of the visual recognition controller and an AGV fork controlled by the AGV controller.
Preferably, the first and second vision sensors are depth cameras.
The height of the smoke frame in the embodiment of the invention is 1400-1500mm.
It should be noted that the above-mentioned embodiments enable a person skilled in the art to more fully understand the invention, without restricting it in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention.
Claims (11)
1. A method for identifying and stacking cigarette frames based on AGV is characterized in that,
s1: the method comprises the steps that a first vision sensor is horizontally and positively arranged in the middle of an AGV, a cigarette frame in a stacking position is shot at a horizontal visual angle, a second vision sensor is arranged on the side face of a fork of the AGV, and the cigarette frame in the stacking position is shot vertically downwards in a downward overlooking mode after the AGV runs to the stacking position; calibrating installation parameters among the first visual sensor, the second visual sensor and the AGV, and transmitting the installation parameters to the AGV controller;
s2: installing an inclination angle sensor on the side face of the AGV fork to detect the inclination angle of the AGV fork;
s3: planning a running path of the AGV for stacking the cigarette frames as a planned path, stopping running at a platform before the AGV runs to the planned path, sending a horizontal visual angle image acquisition command to a visual recognition controller through the AGV controller, and sending an acquisition command to a first visual sensor by the visual recognition controller so as to acquire cigarette frame image data of a stacking position and send the data to the visual recognition controller; the front point platform is a transfer point arranged in an AGV planning path, and the AGV at the position can utilize a first vision sensor to shoot cigarette frames at a stacking position at a horizontal visual angle;
s4: the visual recognition controller filters the cigarette frame image data acquired in the S3, extracts characteristic data describing the stacking position of the cigarette frames, calculates the placing angle of the cigarette frames at the stacking position and the distance between the placing angle and a front point platform where the AGV is located as relative poses by using the characteristic data, and transmits the relative poses to the AGV controller;
s5: the AGV controller calculates a temporary dynamic path of the AGV reaching a cigarette frame stacking preparation point of the cigarette frame stacking position according to the relative pose in the S4;
s6: the AGV controller controls the AGV to travel to a cigarette frame stacking preparation point according to a new temporary dynamic path;
s7: after the vehicle runs to the cigarette frame stacking preparation point in the S6, cigarette frames are stacked, and the AGV controller sends a vertical visual angle image acquisition command to the visual recognition controller; after the AGV equipment travels to the cigarette frame stacking preparation point, the AGV equipment does not displace, and the cigarette frame stacking is completed only by moving a pallet fork on the AGV;
s8: the visual recognition controller sends an acquisition command to the second visual sensor to enable the second visual sensor to shoot the cigarette frames located below the AGV fork and at the cigarette frame stacking position from top to bottom in an overlooking mode to obtain vertical image data, the vertical image data are transmitted to the visual recognition controller, and the visual recognition controller filters and extracts features of the vertical image data to finally calculate left and right position deviation between the cigarette frames below the fork and the AGV fork;
s9: the AGV controller calculates the left and right adjustment amount of the AGV fork according to the left and right position deviation data in the S8, and controls the AGV fork to complete left and right adjustment;
s10: and the AGV controller controls the AGV fork to descend to complete the stacking of the cigarette frames.
2. The AGV cigarette frame identification and stacking method according to claim 1, wherein the planned path in S3 is a theoretical path for the AGV to place the single cigarette frame picked up by the ground or transport vehicle to the cigarette frame stacking position in the stacking area, and the number of cigarette frame layers stored in the stacking area is not more than 4.
3. The AGV based smoke frame identification and stacking method of claim 2, wherein the first vision sensor can move up and down under the control of the AGV to capture the horizontal visual angle of the smoke frames with different stacking layers; second vision sensor is along with AGV fork up-and-down motion, realizes piling up the shooting at the perpendicular visual angle of number of piles of layer cigarette frame to the difference.
4. The AGV based cigarette frame identification and stacking method according to claim 2, wherein after the AGV forks the cigarette frames from the ground or the transport vehicle, the AGV controller controls the AGV forks to be adjusted to a horizontal state according to the inclination angle values of the AGV forks collected by the inclination angle sensor.
5. The AGV cigarette frame identification and stacking method of claim 2 wherein said front point platform in S3 is located 1m-5m from the cigarette frame stacking position.
6. An AGV cigarette frame identification and stacking method according to claim 2, wherein said cigarette frame characteristic data is data expressing cigarette frame shape size and position information, and includes: the cigarette frame covers the bowl-shaped supporting leg and the angular point.
7. The AGV based smoke frame identification and stacking method of claim 2, wherein the smoke frame stacking accuracy requires an error within ± 20mm, and the bowl covering structure below the smoke frame support leg is embedded with the support leg of the smoke frame below the smoke frame support leg after stacking.
8. The AGV based cigarette frame identification and stacking method according to claim 2, wherein the cigarette frame feature data identification method comprises the steps of firstly establishing a feature parameter template of the cigarette frame, wherein the feature parameter template comprises the external dimension, the upright column width and the upright column height of the cigarette frame, and further comprises point cloud feature data of the cigarette frame; and then the AGV identifies the fork-taken or stacked cigarette frames by the following method, including:
a, step a: the visual sensor collects the image data of the cigarette frame and the visual recognition controller carries out filtering processing;
step b: the vision recognition controller acquires depth information of a recognition object from the filtered image data;
step c: according to the depth data of the identification object, point cloud data of the measured object are obtained;
step d: carrying out point cloud registration according to the point cloud data of the object to be detected and the point cloud data in the pre-established smoke frame characteristic parameter template;
step e: extracting key angular points and edge straight line characteristics of the point cloud data of the measured cigarette frame, calculating basic data of the outline dimension, the width and the height of the stand column of the cigarette frame, and comparing the basic data with cigarette frame data in cigarette frame characteristic parameters established in advance;
step f: and calculating the coordinates of the reference points of the cigarette frame according to the extracted key angular points and edge straight line characteristics of the cigarette frame, wherein the calculated coordinates of the cigarette frame stacking preparation points are the relative poses (dx, dy, dtheta) of the cigarette frame relative to the vision sensor.
9. The AGV based cigarette frame identification and stacking method of claim 2, wherein when the first layer of cigarette frames stored in the stacking storage area are placed, the AGV places according to the set planned path without adjusting the horizontal inclination angle.
10. A system for identifying and stacking cigarette frames based on AGV comprises: the system comprises an AGV, a first visual sensor, a second visual sensor, an inclination angle sensor and a visual identification controller, wherein the first visual sensor is horizontally and forwardly installed in the middle of the AGV and used for shooting a cigarette frame at a stacking position at a horizontal visual angle, the second visual sensor is installed on the side face of an AGV fork and used for vertically downwards overlooking to shoot the cigarette frame which is positioned below the AGV fork and is at the stacking position of the cigarette frame, the inclination angle sensor is installed on the side face of the AGV fork and used for detecting the inclination angle of the AGV fork, and the visual identification controller is used for receiving the image data of the cigarette frame of the first visual sensor and the second visual sensor and the inclination angle data of the AGV fork of the inclination angle sensor, and calculating the stacking position of the cigarette frame to obtain the relative pose of the cigarette frame; the AGV includes: the AGV control system comprises an AGV controller for receiving the relative pose data of the visual recognition controller and an AGV fork controlled by the AGV controller.
11. An AGV-based smoke frame identification and stacking system according to claim 10, wherein said first and second visual sensors are depth cameras.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310173761.6A CN115848878B (en) | 2023-02-28 | 2023-02-28 | AGV-based tobacco frame identification and stacking method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310173761.6A CN115848878B (en) | 2023-02-28 | 2023-02-28 | AGV-based tobacco frame identification and stacking method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115848878A true CN115848878A (en) | 2023-03-28 |
CN115848878B CN115848878B (en) | 2023-05-26 |
Family
ID=85659218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310173761.6A Active CN115848878B (en) | 2023-02-28 | 2023-02-28 | AGV-based tobacco frame identification and stacking method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115848878B (en) |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008230736A (en) * | 2007-03-19 | 2008-10-02 | Daifuku Co Ltd | Article carrying device |
CN106672859A (en) * | 2017-01-05 | 2017-05-17 | 深圳市有光图像科技有限公司 | Method for visually identifying tray based on forklift and forklift |
US9715232B1 (en) * | 2016-09-19 | 2017-07-25 | X Development Llc | Using planar sensors for pallet detection |
CN109437058A (en) * | 2018-12-18 | 2019-03-08 | 云南昆船智能装备有限公司 | One kind being applied to high lifting V shape AGV pallet fork leveling device |
CN110001661A (en) * | 2019-04-15 | 2019-07-12 | 安徽意欧斯物流机器人有限公司 | A kind of binocular vision navigation fork-lift type AGV control system and method |
WO2019163378A1 (en) * | 2018-02-23 | 2019-08-29 | コニカミノルタ株式会社 | Forklift image processing device and control program |
US20200009638A1 (en) * | 2018-07-03 | 2020-01-09 | Komatsu Industries Corporation | Workpiece conveying system, and workpiece conveying method |
CN110884901A (en) * | 2019-10-12 | 2020-03-17 | 浙江大华机器人技术有限公司 | Deviation rectifying method, device and equipment for AGV butt joint of stacking vehicle and storage medium |
US20200231386A1 (en) * | 2019-01-18 | 2020-07-23 | United States Postal Service | Systems and methods for automated guided vehicle control |
CN112125226A (en) * | 2020-09-16 | 2020-12-25 | 中建材创新科技研究院有限公司 | Visual detection system and method for laser navigation forklift |
CN112660686A (en) * | 2021-03-17 | 2021-04-16 | 杭州蓝芯科技有限公司 | Depth camera-based material cage stacking method and device, electronic equipment and system |
CN112678724A (en) * | 2019-10-18 | 2021-04-20 | 北京极智嘉科技有限公司 | Intelligent forklift and control method thereof |
US20210114826A1 (en) * | 2019-10-16 | 2021-04-22 | Symbotic Canada, Ulc | Vision-assisted robotized depalletizer |
CN113050636A (en) * | 2021-03-15 | 2021-06-29 | 广东省农业科学院 | Control method, system and device for autonomous tray picking of forklift |
CN215679136U (en) * | 2021-09-27 | 2022-01-28 | 东风本田发动机有限公司 | Navigation system and AGV dolly |
CN113998626A (en) * | 2021-09-27 | 2022-02-01 | 诺力智能装备股份有限公司 | AGV attitude adjusting method applied to tray recognition/positioning |
CN114772142A (en) * | 2021-11-29 | 2022-07-22 | 苏州百年职业学院 | Intelligent logistics storage system based on visual analysis and material scheduling method |
CN115123839A (en) * | 2022-09-02 | 2022-09-30 | 杭叉集团股份有限公司 | AGV-based bin stacking method, device, equipment and storage medium |
CN115346211A (en) * | 2022-08-31 | 2022-11-15 | 中电科机器人有限公司 | Visual recognition method, visual recognition system and storage medium |
-
2023
- 2023-02-28 CN CN202310173761.6A patent/CN115848878B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008230736A (en) * | 2007-03-19 | 2008-10-02 | Daifuku Co Ltd | Article carrying device |
US9715232B1 (en) * | 2016-09-19 | 2017-07-25 | X Development Llc | Using planar sensors for pallet detection |
CN106672859A (en) * | 2017-01-05 | 2017-05-17 | 深圳市有光图像科技有限公司 | Method for visually identifying tray based on forklift and forklift |
WO2019163378A1 (en) * | 2018-02-23 | 2019-08-29 | コニカミノルタ株式会社 | Forklift image processing device and control program |
US20200009638A1 (en) * | 2018-07-03 | 2020-01-09 | Komatsu Industries Corporation | Workpiece conveying system, and workpiece conveying method |
CN109437058A (en) * | 2018-12-18 | 2019-03-08 | 云南昆船智能装备有限公司 | One kind being applied to high lifting V shape AGV pallet fork leveling device |
US20200231386A1 (en) * | 2019-01-18 | 2020-07-23 | United States Postal Service | Systems and methods for automated guided vehicle control |
CN110001661A (en) * | 2019-04-15 | 2019-07-12 | 安徽意欧斯物流机器人有限公司 | A kind of binocular vision navigation fork-lift type AGV control system and method |
CN110884901A (en) * | 2019-10-12 | 2020-03-17 | 浙江大华机器人技术有限公司 | Deviation rectifying method, device and equipment for AGV butt joint of stacking vehicle and storage medium |
US20210114826A1 (en) * | 2019-10-16 | 2021-04-22 | Symbotic Canada, Ulc | Vision-assisted robotized depalletizer |
CN112678724A (en) * | 2019-10-18 | 2021-04-20 | 北京极智嘉科技有限公司 | Intelligent forklift and control method thereof |
CN112125226A (en) * | 2020-09-16 | 2020-12-25 | 中建材创新科技研究院有限公司 | Visual detection system and method for laser navigation forklift |
CN113050636A (en) * | 2021-03-15 | 2021-06-29 | 广东省农业科学院 | Control method, system and device for autonomous tray picking of forklift |
CN112660686A (en) * | 2021-03-17 | 2021-04-16 | 杭州蓝芯科技有限公司 | Depth camera-based material cage stacking method and device, electronic equipment and system |
CN215679136U (en) * | 2021-09-27 | 2022-01-28 | 东风本田发动机有限公司 | Navigation system and AGV dolly |
CN113998626A (en) * | 2021-09-27 | 2022-02-01 | 诺力智能装备股份有限公司 | AGV attitude adjusting method applied to tray recognition/positioning |
CN114772142A (en) * | 2021-11-29 | 2022-07-22 | 苏州百年职业学院 | Intelligent logistics storage system based on visual analysis and material scheduling method |
CN115346211A (en) * | 2022-08-31 | 2022-11-15 | 中电科机器人有限公司 | Visual recognition method, visual recognition system and storage medium |
CN115123839A (en) * | 2022-09-02 | 2022-09-30 | 杭叉集团股份有限公司 | AGV-based bin stacking method, device, equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
吴年祥;吴卫东;: "基于双目视觉的无人引导运输装置的研究", 阴山学刊(自然科学版) * |
曾群生等: "多目视角定位协同引导自动运输车研究", 《计算机工程与应用》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115848878B (en) | 2023-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109436820B (en) | Destacking method and destacking system for goods stack | |
CN112849898B (en) | Self-driven robot and carrying method thereof | |
CN114035584B (en) | Method for detecting obstacle by robot, robot and robot system | |
US8267264B2 (en) | Calibration device, method and system for a container crane | |
CN104379489B (en) | Container crane | |
US20140267703A1 (en) | Method and Apparatus of Mapping Landmark Position and Orientation | |
CN109636272B (en) | Intelligent detection device and detection method for goods shortage of goods shelf | |
EP3347672B1 (en) | An apparatus for the determination of the features of at least a moving load | |
CN112660686B (en) | Depth camera-based material cage stacking method and device, electronic equipment and system | |
CN111824668B (en) | Robot and robot-based container storage and retrieval method | |
CN114241269B (en) | A collection card vision fuses positioning system for bank bridge automatic control | |
AU2020202364A1 (en) | Load handling module for a material handling vehicle | |
CN114170521B (en) | Forklift pallet butt joint identification positioning method | |
CN115848878B (en) | AGV-based tobacco frame identification and stacking method and system | |
CN106904442A (en) | Fully automatic feeding machine people's system of view-based access control model | |
KR102269502B1 (en) | Multi-unloading manipulator for cargo | |
JPH03252707A (en) | Unmanned forklift with vision | |
CN115289966A (en) | Goods shelf detecting and positioning system and method based on TOF camera | |
CN216470499U (en) | Robot | |
CN112611344B (en) | Autonomous mobile flatness detection method, device and storage medium | |
EP4284733A1 (en) | System and method for using a camera to detect robot position on grid | |
CN114029953A (en) | Method for determining ground plane based on depth sensor, robot and robot system | |
CN114186908A (en) | Automatic checking system for three-dimensional warehouse | |
CN220867034U (en) | Cargo handling system | |
CN213301104U (en) | Size detection system |
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 |