WO2022237221A1 - 取放货装置的调整方法、装置、设备、机器人及仓储系统 - Google Patents

取放货装置的调整方法、装置、设备、机器人及仓储系统 Download PDF

Info

Publication number
WO2022237221A1
WO2022237221A1 PCT/CN2022/071764 CN2022071764W WO2022237221A1 WO 2022237221 A1 WO2022237221 A1 WO 2022237221A1 CN 2022071764 W CN2022071764 W CN 2022071764W WO 2022237221 A1 WO2022237221 A1 WO 2022237221A1
Authority
WO
WIPO (PCT)
Prior art keywords
pick
target
location
place device
support part
Prior art date
Application number
PCT/CN2022/071764
Other languages
English (en)
French (fr)
Inventor
赵颖
Original Assignee
深圳市海柔创新科技有限公司
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 深圳市海柔创新科技有限公司 filed Critical 深圳市海柔创新科技有限公司
Priority to EP22806199.0A priority Critical patent/EP4339132A1/en
Publication of WO2022237221A1 publication Critical patent/WO2022237221A1/zh
Priority to US18/503,571 priority patent/US20240067450A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
    • B65G1/02—Storage devices
    • B65G1/04—Storage devices mechanical
    • B65G1/137—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed
    • B65G1/1373—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed for fulfilling orders in warehouses
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
    • B65G1/02—Storage devices
    • B65G1/04—Storage devices mechanical
    • B65G1/0407—Storage devices mechanical using stacker cranes
    • B65G1/0435—Storage devices mechanical using stacker cranes with pulling or pushing means on either stacking crane or stacking area
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
    • B65G2203/02—Control or detection
    • B65G2203/0208—Control or detection relating to the transported articles
    • B65G2203/0216—Codes or marks on the article
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
    • B65G2203/02—Control or detection
    • B65G2203/0266—Control or detection relating to the load carrier(s)
    • B65G2203/0283—Position of the load carrier

Definitions

  • the present disclosure relates to the technical field of intelligent warehousing, and in particular to an adjustment method, device, equipment, robot and warehousing system for a pick-and-place device.
  • the intelligent warehousing system based on the robot adopts the intelligent operating system, realizes the automatic take-out and storage of the container through the system command, and can run 24 hours a day without interruption, replacing manual management and operation, improving the efficiency of warehousing, and has been widely used and accepted. favor.
  • the existing technology often only moves to the target warehouse location based on the corresponding instructions, so that the goods are directly placed on the target warehouse location, or the goods placed on the target warehouse location are directly placed Taking out may easily lead to a collision between the pick-and-place device of the robot and the shelf, resulting in damage to the shelf or the robot, or even accidents such as the tipping of the shelf, resulting in poor safety in the pick-and-place operation.
  • the disclosure provides an adjustment method, device, equipment, robot, and storage system for a pick-and-place device.
  • the automatic calibration between the pick-and-place device and the target warehouse is realized based on an image acquisition device, which improves the efficiency of pick-and-place goods. security.
  • an embodiment of the present disclosure provides a method for adjusting a pick-and-place device.
  • the method includes: when the robot moves to the target ground mark, based on the image acquisition device, acquire a first detection image, wherein the The target ground mark is the ground mark corresponding to the target storage location, and the target storage position is provided with a support part, and the support part includes a first support part and a second support part that are at the same height level to coordinate the placement of goods; according to The information of the preset key points in the first detection image determines the pose relationship between the target storage location and the pick-and-place device, wherein the preset key points include shelf identification codes and/or the Each point corresponding to the support part; according to the pose relationship, adjust the pick-and-place device of the robot to align with the target warehouse location, so that the insertion plate of the pick-and-place device is placed on the first support part and the second supporting part, so as to pick up the goods on the target warehouse location or place the goods on the target warehouse location.
  • the shelf column corresponding to the target location is provided with a shelf identification code
  • the pose of the target location and the pick-and-place device is determined according to the preset key point information in the first detection image
  • the relationship includes: identifying the shelf identification code corresponding to the target storage location according to the first detection image; if the identification is successful, determining the pose relationship between the pick-and-place device and the target storage location according to the recognition result.
  • determining the pose relationship between the pick-and-place device and the target location according to the recognition result includes: determining the position and orientation of the pick-and-place device according to the position information of the feature point of the shelf identification code and the angle information of the identification pattern of the shelf identification code. Angle deviation, height deviation and movement deviation of the delivery device; wherein, the movement deviation is the deviation between the image center of the image acquisition device and the storage location center of the target storage location.
  • adjusting the pick-and-place device of the robot to align with the target location according to the pose relationship includes: determining the location type of the target location; type, to determine the preset deviation; adjust the pick-and-place device according to the preset deviation, so as to adjust the behavior deviation to the preset deviation; and according to the angle deviation and height deviation, respectively adjust the The angle and height of the pick-and-place device, so that the pick-and-place device is aligned with the target storage location.
  • the method further includes: if the shelf identification code corresponding to the target location is not identified according to the first detection image, adjusting the image acquisition device within a preset range, and during the adjustment process and /or when the adjustment is completed, collect at least one second detection image; if the second detection image includes the shelf identification code corresponding to the target location, identify the shelf identification code in the second detection image; As a result, the pose relationship between the pick-and-place device and the target storage location is determined.
  • the image acquisition device includes a first image acquisition device and a second image acquisition device, the first image acquisition device and the second image acquisition device are respectively arranged on both sides of the pick-and-place device, based on the According to the image acquisition device, collecting a first detection image includes: based on the first image acquisition device and the second image acquisition device, respectively collecting a first detection image to obtain two first detection images; correspondingly, according to the first detection image Detecting the information of the preset key points in the image, determining the pose relationship between the target location and the pick-and-place device, including: if the two first detection images include the shelf identification code corresponding to the target location , then respectively recognize the shelf identification codes in the two first detection images to obtain the first recognition result and the second recognition result; according to the first recognition result and the second recognition result, determine the target location The pose relationship with the pick-and-place device.
  • determining the pose relationship between the target location and the pick-and-place device includes: calculating the first recognition result and the second recognition result The average position of each point of the shelf identification code in the second recognition result, and the angular average value of the identification pattern of the shelf identification code in the first recognition result and the second recognition result; according to the position average value and the average value of the angle to determine the pose relationship between the target location and the pick-and-place device.
  • determining the pose relationship between the target storage location and the pick-and-place device includes: determining the first support based on the first detection image The position of the center point of the first support part and the second support part, wherein the first support part and the second support part are used to support the goods placed on the target warehouse location; according to the center point of the first support part and the second support part position, and determine the pose relationship between the pick-and-place device and the target warehouse location.
  • determining the positions of the center points of the first support part and the second support part based on the first detection image includes: determining the positions of the first support part and the second support part based on the first detection image the first spacing; according to the first spacing and preset size information, determine the position of the center point of the first support part and the position of the center point of the second support part in the first detection image, wherein, the preset size information is the size information of the first support part and/or the second support part.
  • determining the posture relationship between the pick-and-place device and the target storage location includes: according to the first support part and the second support part The position of the central point of the pick-and-place device determines the angle deviation, height deviation and behavior deviation of the pick-and-place device.
  • the method further includes: judging whether the center of the image of the image acquisition device is aligned with the center of the target location; If so, control the pick-and-place device to stretch out to the target storage location to pick up and/or store the target goods, wherein the target goods are the corresponding goods in the scheduling instruction.
  • the method further includes: based on the image acquisition device, collecting a third detection image of a preset layer of the temporary storage shelf of the robot; according to the third detection image, determining the The positions of the two preset points of the preset layer; according to the positions of the two preset points, the second angle deviation and the second height deviation between the pick-and-place device and the preset layer of the temporary storage rack are determined ; According to the second angle deviation and the second height deviation, determine whether the pick-and-place device will hit the temporary storage shelf after extending to the preset layer of the temporary storage shelf; if not , then control the pick-and-place device to place the target goods on the preset layer of the temporary storage shelf, or control the pick-and-place device to extract the target goods from the preset layer of the temporary storage shelf, so as to After the pick-and-place device is aligned with the target storage location, the target goods are placed in the target storage location.
  • an embodiment of the present disclosure also provides an adjustment device for a pick-and-place device, the device is applied to a robot, and an image acquisition device is provided on the pick-and-place device of the robot, and the device includes: a first image
  • the acquisition module is configured to collect a first detection image based on the image acquisition device when the robot moves to a target ground mark, wherein the target ground mark is a ground mark corresponding to the target warehouse location, and the target warehouse position
  • a support part is provided on the top, and the support part includes a first support part and a second support part that are at the same height level to coordinate the placement of goods; the pose determination module is used to determine the target storage location and the position according to the first detection image.
  • the pose relationship of the pick-and-place device wherein the preset key points include shelf identification codes and/or points corresponding to the support; the pick-and-place device alignment module is used to, according to the pose relationship, Adjusting the pick-and-place device of the robot to align with the target warehouse location, so that the insert plate of the pick-and-place device is placed between the first support part and the second support part, so as to carry out target storage Pick up goods on the location or place the goods on the target storage location.
  • an embodiment of the present disclosure also provides an adjustment device for a pick-and-place device, including a memory and at least one processor; the memory stores computer-executable instructions; the at least one processor executes the computer stored in the memory Executing the instructions causes the at least one processor to execute the method for adjusting a pick-and-place device provided in any embodiment corresponding to the first aspect of the present disclosure.
  • an embodiment of the present disclosure further provides a robot, including a pick-and-place device and an adjustment device for the pick-and-place device provided in the embodiment corresponding to the third aspect of the present disclosure.
  • the embodiment of the present disclosure further provides a storage system, including a shelf and the robot provided in the embodiment corresponding to the fourth aspect of the present disclosure.
  • the embodiments of the present disclosure also provide a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the computer-readable storage medium corresponding to the first aspect of the present disclosure can be implemented.
  • the method for adjusting the pick-and-place device provided by any embodiment of the invention.
  • the embodiments of the present disclosure also provide a computer program product, including a computer program, and when the computer program is executed by a processor, the method for adjusting the pick-and-place device provided in any embodiment corresponding to the first aspect of the present disclosure is implemented. .
  • each storage position on the shelf of the storage system is supported by a support part, and the support part includes the same height level to cooperate
  • a device that collects a first detection image, and based on the information of each point corresponding to the shelf identification code and/or the support portion in the first detection image determines the pose relationship between the target storage location and the image acquisition device, and then based on the pose relationship , adjust the pick-and-place device of the robot to align with the target location, so that after alignment, the pick-and-place device places the insert plate between the two supports of the target location to pick up or store the goods.
  • the robot Before loading and unloading, the robot’
  • FIG. 1 is an application scene diagram of a method for adjusting a pick-and-place device provided by an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a method for adjusting a pick-and-place device provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a storage location of a shelf provided in an embodiment of the present disclosure
  • FIG. 4A is a schematic structural diagram of a robot provided by an embodiment of the present disclosure.
  • FIG. 4B is a schematic structural diagram of a pick-and-place device for a robot provided by an embodiment of the present disclosure
  • FIG. 4C is a schematic structural diagram of a pick-and-place device for a robot provided in another embodiment of the present disclosure.
  • FIG. 4D is a schematic structural diagram of a pick-and-place device for a robot provided by another embodiment of the present disclosure.
  • FIG. 4E is a schematic diagram of the plug-in picking provided by an embodiment of the present disclosure.
  • FIG. 4F is a schematic diagram of the plug-in picking provided by an embodiment of the present disclosure.
  • Fig. 5 is a flow chart of a method for adjusting a pick-and-place device provided by another embodiment of the present disclosure
  • FIG. 6 is a schematic structural view of the shelf in the embodiment shown in FIG. 5 of the present disclosure.
  • FIG. 7A is a schematic diagram of the pose relationship between the image acquisition device and the target storage location in the embodiment shown in FIG. 5 of the present disclosure
  • FIG. 7B is a schematic diagram of the pose relationship between the image acquisition device and the target storage location in the embodiment shown in FIG. 5 of the present disclosure
  • Fig. 8 is a flow chart of a method for adjusting a pick-and-place device provided by another embodiment of the present disclosure.
  • Fig. 9 is a flowchart of a method for adjusting a pick-and-place device provided by another embodiment of the present disclosure.
  • Fig. 10 is a schematic structural diagram of an adjustment device for a pick-and-place device provided by an embodiment of the present disclosure
  • Fig. 11 is a schematic structural diagram of an adjustment device for a pick-and-place device provided by an embodiment of the present disclosure
  • FIG. 12 is a schematic structural diagram of a robot provided by an embodiment of the present disclosure.
  • Fig. 13 is a schematic structural diagram of a storage system provided by an embodiment of the present disclosure.
  • FIG 1 is an application scene diagram of the adjustment method of the pick-and-place device provided by the embodiment of the present disclosure.
  • the adjustment method of the pick-and-place device provided by the embodiment of the present disclosure can be run on the pick-and-place device adjusted on the device.
  • the intelligent storage system 100 includes a robot 110, a shelf 120, and a dispatching device 130. After the dispatching device 130 receives a pick-and-place instruction, it generates a pick-and-place instruction, so that the robot 110 performs the pick-and-place order of the goods on the target location 121 based on the pick-and-place instruction. Pick up or place the goods on the target warehouse location 121 .
  • the robot 120 After the robot 120 arrives at the location corresponding to the target storage location 121 , it will directly pick up the goods on the target storage location 121 , or directly place the goods on the robot 120 on the target storage location 121 of the shelf 120 .
  • the robot 120 due to the walking error of the robot 120, the error in placing the goods, or other reasons, the robot 120 will not be aligned with the target warehouse location 121 when picking up and placing the goods, and the goods will be picked and placed directly.
  • the pick-and-place device of the robot 120 may It will collide with the shelf 120 and cause losses. For the task of putting goods, it will also cause the goods to be unable to be placed in the center of the target warehouse location 121.
  • the warehouse positions are hollow and only consist of two separate support parts. When the time is off, it is easy for the goods to drop, resulting in losses.
  • the main idea of the adjustment method of the picking and placing device is: before picking and placing the goods, through the image acquisition set on the picking and placing device of the robot A device that collects a first detection image, and based on the shelf identification code in the image and/or the information of each point corresponding to the support part, determines the pose relationship between the target warehouse location and the image acquisition device, so as to realize the The calibration between the target storage location and the pick-and-place device of the robot, after the calibration, the corresponding pick-and-place tasks are performed, thereby improving the safety of pick-and-place goods.
  • Fig. 2 is a flow chart of a method for adjusting a pick-and-place device provided by an embodiment of the present disclosure.
  • the method for adjusting the pick-and-place device can be performed by a robot, specifically by the robot's pick-and-place device.
  • the pick-and-place device of the robot is provided with an image acquisition device.
  • the adjustment method of the pick-and-place device provided in this embodiment comprises the following steps:
  • Step S201 when the robot moves to the target ground mark, based on the image acquisition device, acquire a first detection image.
  • the target ground mark is the ground mark corresponding to the target warehouse location, and a support part is set on the target warehouse position, and the support part includes a first support part and a second support part that are at the same height level for cooperatively placing goods.
  • the image acquisition device can be a 2D camera or a 3D camera, the number of which can be one, two or other values, and the image acquisition device can be arranged on the left, right, middle or other positions of the pick-and-place device of the robot.
  • the form of the target ground mark can be a two-dimensional code, bar code, code or other forms, and the robot can determine whether the current position is the position corresponding to the target warehouse location according to the target ground mark.
  • the first support part and the second support part are arranged on both sides of the target storage position, and there is a certain distance between the first support part and the second support part.
  • FIG. 3 is a schematic structural diagram of a storage location of a shelf provided in an embodiment of the present disclosure.
  • the first support part 320 and the second support part 330 that is, the middle part of the target warehouse location 300 is suspended, and it is supported by the first support part 320 and the second support part 330 to place it on the target. Goods on storage location 300.
  • the distances corresponding to different shelves may be different, so that the sizes of the target storage locations 300 are also different.
  • the shelf is a corbel shelf, and the support portion on the storage location of the shelf may also be called a corbel shelf.
  • the robot can determine the target ground mark and the movement path according to the dispatching instruction of the dispatching device, and then move from the current position to the target ground mark according to the movement path. After the robot moves to the target ground mark, the image acquisition device on the pick-and-place device of the robot is turned on to collect the first detection image within the field of view.
  • the moving route of the robot can be adjusted according to the moving path and the ground image collected by the image acquisition device until reaching the target ground mark.
  • the dispatching device can determine the target warehouse location and its corresponding target ground identification according to the pick-and-place task, and then generate a dispatch instruction based on the target warehouse location and its corresponding target ground identification, and send the dispatch instruction to the robot, so that The robot moves to the target ground mark based on the scheduling instruction, and performs the task of picking and placing goods at the target warehouse location.
  • the pick-and-place device of the robot is controlled to rotate 90° in the direction of the target warehouse location, so that the pick-and-place device is directly facing the target warehouse location, and the pick-and-place device is turned on.
  • the image acquisition device captures the first detection image corresponding to the target storage location.
  • FIG. 4A is a schematic structural diagram of a robot provided by an embodiment of the present disclosure.
  • the robot includes a pick-and-place device 410, a temporary storage shelf 420, a lifting assembly 430, and a chassis 440, wherein the pick-and-place
  • the device 410 uses a plug-in method to pick up goods; the temporary storage shelf 420 is used for temporarily storing goods.
  • the temporary storage shelf 420 shown in FIG. there is a cutout 423 between the left back pan 421 and the right back pan 422;
  • FIG. 4B is a structural schematic diagram of a pick-and-place device of a robot provided by an embodiment of the present disclosure. As shown in FIG. Fix the image acquisition device 413 on the side stop 412 and the lighter 414 of the image acquisition device 413 . In FIG. 4B , there is one image acquisition device 413 , which is installed on one of the fixed side stops 412 .
  • Fig. 4C is a schematic structural diagram of a pick-and-place device for a robot provided in another embodiment of the present disclosure. Combining Fig. 4B and Fig. 4C, it can be seen that, unlike Fig. 4B, the number of image acquisition devices 413 in Fig.
  • FIG. 4C is two, An illuminator 414 is arranged above each image acquisition device 413 .
  • the image acquisition device in FIG. 4B and FIG. 4C may be a 2D camera.
  • Fig. 4D is a structural schematic diagram of a pick-and-place device for a robot provided in another embodiment of the present disclosure. Combining Fig. 4B and Fig. 4D, it can be seen that, unlike Fig. 4B, the image acquisition device 413 in Fig. 4D is set at the rear fixed limit In bit 415, the image acquisition device 413 in FIG. 4D may be a 3D camera.
  • FIG. 4E and FIG. 4F are schematic diagrams of plug-and-lift picking provided by an embodiment of the present disclosure. It can be seen from FIG. 4E and FIG.
  • the shelf identification code 301 of the warehouse location 300 aligns the pick-and-place device 410 of the robot 400 with the target warehouse location 300, and then, as shown in FIG. And place the inserting plate of the pick-and-place device 410 in the space below the target cargo 500, and control the inserting plate of the pick-and-place device 410 to rise until the target cargo 500 is lifted.
  • the robot 400 controls its pick-and-place device 410 to retract, and then takes the target goods 500 out of the target warehouse location 300 .
  • Step S202 according to the preset key point information in the first detection image, determine the pose relationship between the target location and the pick-and-place device.
  • the preset key points include shelf identification codes and/or points corresponding to the support parts.
  • the shelf identification code is set on the shelf column corresponding to the target storage location, and its form may be a two-dimensional code, a bar code or other identification codes containing an identifying pattern.
  • the pose relationship may include the positional relationship between the target location and the pick-and-place device in the horizontal, vertical, and depth directions, and may also include the angular relationship between the pick-and-place device and the target location.
  • the pose relationship between the target warehouse location and the pick-and-place device can be determined.
  • the shelf column corresponding to the target location is provided with a shelf identification code, and the pose of the target location and the pick-and-place device is determined according to the preset key point information in the first detection image relationships, including:
  • the shelf identification code can be identified, decoded, and the position of each preset key point on the shelf identification code is determined, and then based on the shelf identification code Determine the position and posture relationship between the target warehouse location and the image acquisition device based on the position of each preset key point.
  • the pose relationship between the image acquisition device and the target warehouse location determines the pose relationship between the image acquisition device and the target warehouse location, and determine the image acquisition device and the pick-and-place device according to the installation position of the image acquisition device The first positional relationship, and then based on the first positional relationship and the pose relationship between the image acquisition device and the target warehouse location, determine the pose relationship between the pick-and-place device and the target warehouse location.
  • determining the pose relationship between the target storage location and the pick-and-place device includes:
  • the first support part and the second support part are arranged on opposite sides of the target storage position, and keep a certain distance, and the center point of the first support part and the center of the second support part can be identified through the first detection image
  • the position of the point is based on the position of the center point of the first support part and the position of the center point of the second support part to determine the pose relationship between the pick-and-place device and the target warehouse location.
  • Step S203 adjust the pick-and-place device of the robot to align with the target warehouse location, so that the insertion plate of the pick-and-place device is placed on the first support part and the second support part. Between the two supporting parts, it is used to pick up the goods on the target warehouse location or place the goods on the target warehouse location.
  • the position of the pick-and-place device of the robot can be adjusted according to the deviations between the corresponding image acquisition device and the target warehouse location in the pose relationship, including angle deviation and position deviation, so that the pick-and-place device is aligned with the target warehouse bit.
  • the inserting plate that controls the pick-and-place device is stretched out and placed between the first support part and the second support part, thereby completing the storage of the goods on the target storage location.
  • the method for adjusting the pick-and-place device is aimed at each position on the shelf of the storage system is supported by a support part, and the support part includes a first support at the same height level to coordinate the placement of goods part and the second support part, when the robot performs the task of picking and placing goods, when the robot is in place, that is, after moving to the ground mark corresponding to the target warehouse location, based on the image acquisition device set on the picking and placing device of the robot, the first detection is collected.
  • the delivery device is aligned with the target location, so that after the alignment, the pick-and-place device places the insert plate between the two supports of the target location to pick up or store the goods. Before the robot picks up and places the goods, it realizes Align the pick-and-place device of the robot with the target location, avoiding collisions during the pick-and-place process, and improving the safety of pick-up and storage.
  • the robot when the robot picks and places goods from the temporary storage shelf of the robot, it is also necessary to judge whether the pick-and-place goods device of the robot will hit the temporary storage shelf of the robot, and if not, pick and place the goods.
  • the method further includes: based on the image acquisition device, collecting the preset layer of the temporary storage shelf of the robot The third detection image; according to the third detection image, determine the positions of two preset points on the preset layer of the temporary storage shelf; according to the positions of the two preset points, determine the pick-and-place goods The second angle deviation and the second height deviation between the device and the preset layer of the temporary storage shelf; according to the second angle deviation and the second height deviation, it is judged that the pick-and-place device is moving to the temporary storage After the preset layer of the shelf stretches out, whether it will hit the temporary storage shelf; if not, then control the pick-and-place device to extract the target goods from the preset layer of the temporary storage shelf, so as to After the cargo device is aligned with the target warehouse location, the target goods are placed in the target warehouse location.
  • the method further includes: based on the The image acquisition device collects the third detection image of the preset layer of the temporary storage shelf of the robot; according to the third detection image, determines the positions of the two preset points of the preset layer of the temporary storage shelf; The positions of the two preset points determine the second angle deviation and the second height deviation between the pick-and-place device and the preset layer of the temporary storage rack; according to the second angle deviation and the second Height deviation, judging whether the pick-and-place device will bump into the temporary storage shelf after stretching out to the preset layer of the temporary storage shelf; if not, then control the pick-and-place device to move the target The goods are placed on the preset layer of the temporary storage shelf.
  • the temporary storage shelf of the robot is used for temporarily storing the goods during the process of the robot carrying or transporting the goods
  • the temporary storage shelf may include only one layer or multiple layers.
  • the two preset points of the preset layer can be two points set symmetrically with respect to the center of the preset layer, or two points symmetrically arranged along the center of the cutout corresponding to the preset layer, such as the left pannier of the preset layer and the Two points on the edge of the right pannier.
  • the robot executes the delivery instruction, after the robot moves to the target ground mark, the robot needs to take out the target goods placed on the preset layer of the temporary storage shelf of the robot through its pick-and-place device, and then the pick-and-place device and the After the target storage location is aligned, place the target goods on the target storage location.
  • the third detection image of the preset layer of the temporary storage shelf of the robot collected by the image acquisition device arranged on the pick-and-place device is required, Determine the positions of the two preset points symmetrically set on the preset layer, so as to make a fool-proof judgment based on the positions of the two preset points, specifically, it can be based on the first layer of the preset layer of the pick-and-place device and the temporary storage shelf.
  • the second angle deviation and the second height deviation determine whether the pick-and-place device will collide with the temporary storage shelf after extending to the preset layer of the temporary storage shelf. If not, the pick-and-place device can be controlled for preset The extraction of the target goods placed by the layer.
  • the robot executes the picking instruction, after the pick-and-place device is aligned with the target warehouse location, the robot needs to take out the target goods placed on the target warehouse location through its pick-and-place device. The target goods are taken out, and then the target goods are placed on the preset layer of the temporary storage shelf of the robot.
  • the third detection image of the preset layer of the temporary storage shelf of the robot collected by the image acquisition device set on the pick-and-place device is required to determine The positions of the two preset points symmetrically arranged on the preset layer, so that fool-proof judgments can be made based on the positions of the two preset points, can be based on the second preset layer of the pick-and-place device and the temporary storage shelf.
  • the angle deviation and the second height deviation are used to determine whether the pick-and-place device will collide with the temporary storage shelf after extending to the preset layer of the temporary storage shelf. If not, the pick-and-place device can be controlled to place the target goods In the default layer of the temporary storage shelf of the robot.
  • the robot’s pick-and-place device can be aligned through the first detection image, the goods in the storage system, including the target goods, do not need to be provided with an identification code for the robot to identify, which reduces the cost. Before the goods are put into the warehouse, there is no need to paste the identification codes for each goods, which improves the efficiency of the goods into the warehouse.
  • Fig. 5 is a flow chart of an adjustment method for a pick-and-place device provided by another embodiment of the present disclosure.
  • the shelf identification code is set on the shelf column corresponding to the target storage position of the storage system targeted by this embodiment.
  • the pick-and-place device provided by this embodiment The adjustment method of the delivery device is based on the embodiment shown in Figure 2, further refinement of step S202 and step S203, as shown in Figure 5, the adjustment method of the delivery device provided by this embodiment includes the following steps :
  • Step S501 when the robot moves to the target ground mark, based on the image acquisition device, acquire a first detection image.
  • Step S502 identifying the shelf identification code corresponding to the target storage location according to the first detection image.
  • the shelf identification code corresponding to the target storage location is set on any shelf column within the range of the target storage location.
  • each location on the shelf of the storage system corresponds to a shelf identification code.
  • FIG. 6 is a schematic structural diagram of a shelf in the embodiment shown in FIG. 5 of the present disclosure.
  • the shelf identification code is 622, and each storage location corresponds to a shelf identification code.
  • the identification patterns of the shelf identification codes corresponding to different storage locations can be the same or different.
  • the identification pattern on the shelf identification code is "L" type Pattern as an example.
  • the width D of the goods placed in the storage positions corresponding to different shelves can be different, so the size of the support parts can also be different.
  • the storage position of the shelf 610 is a small storage position, and the size of the support part 613 is small.
  • the distance between the parts 613 is also correspondingly small, and the storage location of the shelf 620 is a large storage location, the size of its supporting part is relatively large, and the distance between the two supporting parts 623 is correspondingly relatively large.
  • the identification pattern of the shelf identification code shown in FIG. 6 is only an example, and the identification pattern may also be other patterns with identification characteristics, which is not limited in the present disclosure.
  • the identification pattern of the shelf identification code is included in the first detection image, the identification pattern is recognized to obtain a recognition result.
  • the recognition result may include the orientation of the identification pattern of the shelf identification code, the position information of each feature point in the identification pattern, and the like.
  • Step S503 if the identification is successful, then determine the angle deviation, height deviation and behavior deviation of the pick-and-place device according to the position information of the feature point of the shelf identification code and the angle information of the identification pattern of the shelf identification code.
  • the movement deviation is the deviation between the image center of the image acquisition device and the storage location center of the target storage location.
  • the movement deviation is 0 or a preset deviation, it means that the image center of the image acquisition device coincides with the storage location center of the target storage location.
  • the characteristic point of the shelf identification code can be the inflection point of the identification pattern of the shelf identification code, and can also include other characteristic points of the identification pattern.
  • the orientation or angle of the identification pattern can be determined through the position information of the feature point, and the position of the identification pattern can also be determined.
  • the pose relationship includes the angle deviation, height deviation, depth deviation and behavior deviation of the image acquisition device relative to the target location, and may also include the image acquisition device relative to the target location. The depth deviation of the destination location.
  • FIG. 7A and FIG. 7B are schematic diagrams of the pose relationship between the image acquisition device and the target storage location in the embodiment shown in FIG.
  • the pose relationship of the storage location 720 includes the angle deviation yaw1, the height deviation dz1, the depth deviation dy1 and the travel deviation dx1 of the image acquisition device 710 relative to the target storage location 720, wherein the height deviation dz1 is the difference between the image acquisition device 710 and the target storage location
  • the deviation dx1 is the deviation in the horizontal direction between the center line c1 of the shelf identification code corresponding to the target location 720 and the image acquisition device 710;
  • the depth deviation dy1 is the image on the robot 700
  • the angular deviation yaw1 is the angular deviation between the orientation of the robot
  • step S507 After determining the angle deviation yaw1, height deviation dz1, depth deviation dy1 and movement deviation dx1 of the image acquisition device relative to the target storage location, it is judged whether the angle deviation yaw1, height deviation dz1, depth deviation dy1 and movement deviation dx1 are all within Within the preset threshold; if yes, proceed to the next step, that is, step S507; if not, report to the system for abnormal warning, so as to detect abnormalities in target storage locations, ground signs, robots, etc.
  • Step S504 if the shelf identification code corresponding to the target location is not recognized according to the first detection image, adjust the image acquisition device within a preset range, and acquire At least one second inspection image.
  • the preset range may be a set range.
  • the shelf identification code corresponding to the target location is not identified according to the first detection image, which may include that the first detection image does not include a complete identification pattern, so that the shelf identification code corresponding to the target location cannot be identified according to the first detection image, That is, if the recognition of the shelf identification code fails, it is necessary to adjust the image acquisition device provided on the pick-and-place device to expand its field of view to search for the shelf identification code.
  • controlling the movement of the image acquisition device within a preset range may be controlling the movement of the image acquisition device according to a set movement mode, and collecting various second detection images during the movement.
  • control the movement of the image acquisition device within the preset range it may be to move a certain distance to the left and right, and then to move a certain distance to the up and down, and to continuously collect the second detection images during the movement, or to move to the target
  • the second detection image is acquired after the position, eg, after moving to the leftmost position.
  • the first warning message is generated to report that the storage system has not found the shelf identification code , requesting human intervention.
  • Step S505 if the second detection image includes the shelf identification code corresponding to the target location, identify the shelf identification code in the second detection image.
  • the specific manner of identifying the shelf identification code in the second detection image is similar to the specific manner of step S502, only the object is replaced by the second detection image from the first detection image, and will not be repeated here.
  • Step S506 determining the pose relationship between the pick-and-place device and the target storage location according to the recognition result.
  • the position information of the feature points of the shelf identification code corresponding to the second detection image and the angle information of the identification pattern of the shelf identification code determine the angle deviation, height deviation, depth deviation and Behavioral deviation.
  • the pose relationship between the pick-and-place device and the target location is determined according to the recognition result corresponding to the second detection image, and the position and posture relationship between the image acquisition device and the target location is determined based on the recognition result corresponding to the first detection image.
  • the specific steps of pose relationship are similar, that is, similar to step S503, only the recognition result corresponding to the first detection image of the object is replaced with the recognition result corresponding to the second detection image, and will not be repeated here.
  • Step S507 determining the location type of the target location.
  • the location type of the target location can be determined according to the distance between two supporting parts corresponding to the target location, or based on the size of the target goods that can be stored or placed in the target location, such as based on the width of the target goods.
  • the storage location type may include a small storage location type and a large storage location type.
  • the storage location type of the target storage location may be determined based on scheduling instructions, such as a picking instruction, a delivery instruction, and the like.
  • the location type of the target location may be determined based on the location identifier of the target location in the scheduling instruction and the first corresponding relationship.
  • the first correspondence is used to describe the correspondence between each location identifier and location type.
  • Step S508 determining a preset deviation according to the location type of the target location.
  • the preset deviation is used to describe the distance between the center of the shelf identification code of the target warehouse location and the warehouse location center of the target warehouse location.
  • different types of storage locations correspond to different preset deviations, and the preset deviation may be determined based on the above-mentioned first correspondence and the storage location type of the target storage location.
  • Table 1 is the first correspondence relationship table in the embodiment shown in FIG.
  • the default deviation is a
  • the default deviation corresponding to the large storage location type is b, where b>a.
  • the preset deviation may be determined based on the second corresponding relationship and the storage location type of the target storage location, wherein the second corresponding relationship is used to describe the corresponding relationship between various storage location types and the preset deviation.
  • step S507 and step S508 may be performed first, and step S507 may be performed after performing step S501, or performing step S501 and step S507 in parallel, or performing step S507 before, after or when performing any of the steps from step S501 to step S506 and step S508.
  • Step S509 adjust the pick-and-place device according to the preset deviation, so as to adjust the behavior deviation to the preset deviation, and adjust the pick-and-place device respectively according to the angle deviation and height deviation angle and height so that the pick-and-place device is aligned with the target warehouse location.
  • the movement deviation dx1 of the image acquisition device relative to the target storage location is the preset deviation; the angle deviation yaw1 is 0; the height deviation dz1 is The height is preset, so that after the pick-and-place device is stretched out, its inserting plate is lower than the height corresponding to the supporting surface of the supporting part of the target warehouse location.
  • the extension distance of the pick-and-place device can be determined, so that after the pick-and-place device is aligned with the target location, the pick-and-place goods can be controlled according to the extension distance
  • the inserting plate of the device is protruded, so that the target goods on the target warehouse position can be inserted through the inserting plate, or the target goods can be placed on the target warehouse position.
  • the robot picks and places the goods through the pick-and-place device.
  • the image acquisition device collects the first detection image of the target warehouse location, and judges based on the first detection image whether the identification pattern of the complete shelf identification code can be read. the second detection image until the complete shelf identification code is read, and then, based on the angle information of the shelf identification code’s identification pattern and the position information of each feature point on it, determine the distance between the image acquisition device and the target location.
  • Pose relationship including angle deviation, height deviation, behavior deviation and depth deviation, and then realize the automatic alignment of the pick-and-place device with the target storage location based on the pose relationship, and pick and place the goods based on the aligned pick-and-place device , Improve the safety of cargo extraction and storage, and avoid collisions.
  • Fig. 8 is a flow chart of a method for adjusting a pick-and-place device provided by another embodiment of the present disclosure.
  • the pick-and-place device of the robot targeted in this embodiment is provided with two image acquisition devices, namely the first image acquisition device and the second image acquisition device.
  • Two image acquisition devices are respectively arranged on both sides of the pick-and-place device, and the adjustment method of the pick-and-place device provided in this embodiment is based on the embodiment shown in Figure 2, further refinement of step S201 and step S202 , as shown in Figure 8, the adjustment method of the pick-and-place device provided by the present embodiment includes the following steps:
  • Step S801 when the robot moves to the target ground mark, based on the first image acquisition device and the second image acquisition device, respectively collect a first detection image to obtain two first detection images.
  • the first image acquisition device and the second image acquisition device set on the robot's pick-and-place device are controlled to collect a first detection image respectively, thereby obtaining two The first detection image.
  • Step S802 if the two first detection images both include the shelf identification code corresponding to the target storage location, then respectively identify the shelf identification codes in the two first detection images to obtain the first recognition result and the second recognition result result.
  • first detection images captured by the first image acquisition device and the second image acquisition device both include shelf identification codes
  • first detection images captured by the first image acquisition device and the second image acquisition device both include shelf identification codes
  • the first identification result corresponding to the device, and the second identification result corresponding to the second image acquisition device may include position information of each feature point of the identification pattern of the shelf identification code on the corresponding first detection image and angle information of the identification pattern.
  • Step S803 according to the first recognition result and the second recognition result, determine the pose relationship between the target storage location and the pick-and-place device.
  • the first pose relationship between the first image acquisition device and the target storage location can be determined; according to the first The position information of each feature point of the identification pattern of the shelf identification code in the second recognition result and the angle information of the identification pattern determine the second pose relationship between the second image acquisition device and the target storage location. Furthermore, based on the first pose relationship and the second pose relationship, the pose relationship between the pick-and-place device and the target storage location is determined.
  • the first deviation between the pick-and-place device and the target storage location can be determined based on the first pose relationship, wherein the first deviation includes the first angle deviation, the first height deviation and the first height deviation between the pick-and-place device and the target storage location.
  • the first behavior deviation based on the second pose relationship, determine the second deviation between the pick-and-place device and the target warehouse location, wherein the second deviation includes the second angle deviation and the second height deviation between the pick-and-place device and the target warehouse location and the second behavior deviation; judge whether the difference between the first deviation and the second deviation is greater than the corresponding preset difference, if so, generate the second early warning information, report it to the system, and request manual inspection of each related equipment ; If not, based on the first pose relationship and the second pose relationship, determine the pose relationship between the pick-and-place device and the target storage location, specifically, based on the first angle deviation, the first Height deviation, first path deviation and first depth deviation, as well as the second angle deviation, second height deviation, second line deviation and second depth deviation in the
  • determining the pose relationship between the target location and the pick-and-place device includes: calculating the first recognition result and the second recognition result The average position of each point of the shelf identification code in the second recognition result, and the angular average value of the identification pattern of the shelf identification code in the first recognition result and the second recognition result; according to the position average value and the average value of the angle to determine the pose relationship between the target location and the pick-and-place device.
  • the first recognition result and the second recognition result meet the preset condition, including: the difference between the corresponding first deviation in the first recognition result and the corresponding second deviation in the second recognition result is less than or equal to the corresponding Default difference.
  • Step S804 according to the pose relationship, adjust the pick-and-place device of the robot to align with the target storage location, so that the insertion plate of the pick-and-place device is placed on the first support part and the second support part. Between the two supporting parts, it is used to pick up the goods on the target warehouse location or place the goods on the target warehouse location.
  • the pick-and-place device of the robot of the storage system is provided with two image acquisition devices, and each location of the shelf of the storage system corresponds to a shelf identification code, and the shelf identification code is set on the shelf column.
  • the first image acquisition device and the second image acquisition device are turned on, and a first detection image corresponding to the target warehouse location is collected respectively, and then the shelf identification in the two first detection images
  • the information corresponding to the shelf code can determine the position and posture relationship between the pick-and-place device and the target warehouse location.
  • Two image acquisition devices are used to expand the field of view of the acquisition and improve the efficiency of shelf identification code recognition.
  • Determining the pose relationship improves the accuracy of determining the pose relationship, and then aligns the pick-and-place device based on the pose relationship, which improves the alignment accuracy of the pick-and-place device and further improves the safety of pick-and-place .
  • Fig. 9 is a flow chart of another real-time adjustment method of the pick-and-place device of the present disclosure.
  • the pick-and-place device for this embodiment is a 3D camera or a 2D camera with a wide field of view.
  • the pick-and-place device provided by this embodiment The adjustment method is on the basis of the embodiment shown in Figure 2, step S202 and step S203 are further refined, as shown in Figure 9, the adjustment method of the pick-and-place device provided by this embodiment includes the following steps:
  • Step S901 when the robot moves to the target ground mark, based on the image acquisition device, acquire a first detection image.
  • Step S902 based on the first detection image, determine a first distance between the first support part and the second support part.
  • the first support part and the second support part of the target warehouse location there is a certain distance between the first support part and the second support part of the target warehouse location, that is, the above-mentioned first distance, and the first support part and the second support part can be identified through the first detection image and the preset image recognition algorithm.
  • the supporting part further determines the first distance between the first supporting part and the second supporting part.
  • the first detection image is point cloud data captured by a 3D camera. After the first detection image is collected, it is necessary to perform preprocessing on the first detection image.
  • the preprocessing includes noise reduction processing, segmentation processing, etc., and then based on The preprocessed first detection image determines the first distance between the first support part and the second support part.
  • Step S903 according to the first distance and preset size information, determine the position of the center point of the first support part and the position of the center point of the second support part in the first detection image.
  • the preset size information is size information of the first support part and/or the second support part.
  • Step S904 according to the positions of the center points of the first support part and the second support part, determine the angle deviation, height deviation and movement deviation of the pick-and-place device.
  • the location angle, location height, and location center of the target location can be determined, and then the pick-and-place can be determined based on the location angle.
  • Angle deviation of the pick-up device relative to the target location determine the height deviation of the pick-and-place device relative to the target location based on the height of the location, and determine the behavior of the pick-and-place device relative to the target location based on the location center and location type deviation.
  • Step S905 adjusting the pick-and-place device of the robot to align with the target storage location according to the angle deviation, height deviation, depth deviation and behavior deviation of the image acquisition device.
  • Step S906 judging whether the center of the image of the image acquisition device is aligned with the center of the target location.
  • the inserting board of the pick-and-place device is controlled to extend toward the target warehouse location, so that the insert board is located at the first support portion and the second support portion of the target warehouse location.
  • it is necessary to further judge whether the pick-and-place device is aligned with the target storage location which can be realized by judging whether the image center of the image acquisition device is aligned with the storage location center of the target storage location.
  • Step S907 if yes, control the pick-and-place device to extend toward the target storage location, so as to pick up and/or store the target goods.
  • the target cargo is the corresponding cargo in the scheduling instruction.
  • control the inserting board of the pick-and-place device to extend toward the target warehouse location, so as to place the inserting board at the first position of the target warehouse location.
  • the target goods are placed on the target warehouse location, or the target goods are taken out from the target warehouse location to be placed on the preset layer of the temporary storage shelf of the robot.
  • the first detection image of the target location is collected by the image acquisition device of the robot, and the first support of the target location is determined based on the first detection image.
  • the position of the central point of the first and second support parts so as to determine the pose relationship between the pick-and-place device and the target warehouse location, based on the pose relationship, the automatic alignment of the pick-and-place device is realized, and the alignment efficiency and accuracy are improved. , which improves the safety of picking and placing goods; and there is no need to paste additional identification codes on shelves or goods, which reduces costs and improves storage efficiency.
  • Fig. 10 is a structural schematic diagram of an adjustment device for a pick-and-place device provided by an embodiment of the present disclosure.
  • the adjustment device for the pick-and-place device is applied to a robot, and the pick-and-place device of the robot is provided with an image acquisition device, as shown in Fig. 10
  • the adjustment device of the pick-and-place device includes: a first image acquisition module 1010 , a pose determination module 1020 and a pick-and-place device alignment module 1030 .
  • the shelf column corresponding to the target storage location is provided with a shelf identification code
  • the pose determination module 1020 includes: an identification code recognition unit, configured to identify the storage column corresponding to the target storage location according to the first detection image. Shelf identification code; the first pose determination unit is configured to determine the pose relationship between the pick-and-place device and the target storage location according to the recognition result if the recognition is successful.
  • the first pose determination unit is specifically configured to: if the recognition is successful, determine the location of the pick-and-place goods according to the location information of the feature points of the shelf identification code and the angle information of the identification pattern of the shelf identification code. Angle deviation, height deviation and movement deviation of the device; wherein, the movement deviation is the deviation between the image center of the image acquisition device and the storage location center of the target storage location.
  • the pick-and-place device alignment module 1030 is specifically configured to: determine the location type of the target location; determine a preset deviation according to the location type of the target location; , adjust the pick-and-place device to adjust the behavior deviation to the preset deviation; and adjust the angle and height of the pick-and-place device according to the angle deviation and height deviation, so that the The pick-and-place device is aligned with the target warehouse location.
  • the adjustment device of the pick-and-place device further includes: if the shelf identification code corresponding to the target location is not recognized according to the first detection image, adjusting the image acquisition device within a preset range, And during the adjustment process and/or when the adjustment is completed, at least one second detection image is collected; if the second detection image includes the shelf identification code corresponding to the target location, then identify the Shelf identification code; determine the pose relationship between the pick-and-place device and the target storage location according to the identification result.
  • the image acquisition device includes a first image acquisition device and a second image acquisition device, the first image acquisition device and the second image acquisition device are respectively arranged on both sides of the pick-and-place device, the first The image acquisition module 1010 is specifically used for: based on the first image acquisition device and the second image acquisition device, respectively acquire a first detection image to obtain two first detection images; correspondingly, the pose determination module 1020 includes: A recognition result acquisition unit, configured to recognize the shelf identification codes in the two first detection images respectively if the two first detection images include the shelf identification code corresponding to the target location, to obtain the first recognition result and the second recognition result; a second pose determination unit, configured to determine the pose relationship between the target warehouse location and the pick-and-place device according to the first recognition result and the second recognition result.
  • the pose relationship determination unit is specifically configured to: calculate the average position of each point of the shelf identification code in the first recognition result and the second recognition result, and calculate the position average of each point of the shelf identification code in the first recognition result and the second recognition result.
  • the angle average value of the identification pattern of the shelf identification code in the second recognition result according to the position average value and the angle average value, determine the pose relationship between the target location and the pick-and-place device .
  • the pose determination module 1020 includes: a center point determination unit, configured to determine the positions of the center points of the first support part and the second support part based on the first detection image, wherein the first support part part and the second support part are used to support the goods placed on the target warehouse location; the third pose determination unit is used to determine the pick-and-place device according to the positions of the center points of the first support part and the second support part The pose relationship with the target location.
  • a center point determination unit configured to determine the positions of the center points of the first support part and the second support part based on the first detection image, wherein the first support part part and the second support part are used to support the goods placed on the target warehouse location
  • the third pose determination unit is used to determine the pick-and-place device according to the positions of the center points of the first support part and the second support part The pose relationship with the target location.
  • the center point determination unit is specifically configured to: determine a first distance between the first support part and the second support part based on the first detection image; information to determine the position of the center point of the first support part and the position of the center point of the second support part in the first detection image, wherein the preset size information is the first support part And/or the size information of the second supporting part.
  • the third pose determination unit is specifically configured to: determine the angle deviation, height deviation and behavior deviation of the pick-and-place device according to the positions of the center points of the first support part and the second support part.
  • the adjustment device of the pick-and-place device further includes: a fool-proof module, used to judge the image center of the image acquisition device after adjusting the pick-and-place device of the robot to align with the target warehouse location. Whether it is aligned with the center of the target warehouse position; the pick-and-place module is used to control the pick-and-place device to the target warehouse if the image center of the image acquisition device is aligned with the center of the target warehouse position The position is stretched out to pick up and/or deposit the target goods, wherein the target goods are the corresponding goods in the dispatching instruction.
  • a fool-proof module used to judge the image center of the image acquisition device after adjusting the pick-and-place device of the robot to align with the target warehouse location. Whether it is aligned with the center of the target warehouse position
  • the pick-and-place module is used to control the pick-and-place device to the target warehouse if the image center of the image acquisition device is aligned with the center of the target warehouse position The position is stretched out to pick up
  • the adjustment device of the pick-and-place device further includes: an internal pick-and-place module, configured to collect a third detection image of a preset layer of the temporary storage shelf of the robot based on the image acquisition device;
  • the third detection image determines the positions of two preset points on the preset layer of the temporary storage shelf; according to the positions of the two preset points, it is determined that the pick-and-place device and the temporary storage shelf The second angle deviation and the second height deviation of the preset layer; according to the second angle deviation and the second height deviation, it is judged that the pick-and-place device is extending toward the preset layer of the temporary storage shelf After that, whether it will hit the temporary storage shelf; if not, then control the pick-and-place device to place the target goods on the preset layer of the temporary storage shelf, or control the pick-and-place device from The preset layer of the temporary storage rack picks up the target goods, so that after the pick-and-place device is aligned with the target warehouse position, the target goods are placed in the target warehouse
  • the adjustment device of the pick-and-place device provided by the embodiments of the present disclosure can execute the adjustment method of the pick-and-place device provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the method.
  • FIG. 11 is a schematic structural diagram of an adjustment device for a pick-and-place device provided by an embodiment of the present disclosure.
  • the adjustment device for the pick-and-place device includes: a memory 1110 , a processor 1120 and a computer program.
  • the computer program is stored in the memory 1110, and is configured to be executed by the processor 1120 to realize the pick-and-place device provided by any of the embodiments corresponding to Fig. 2 , Fig. 5 , Fig. 8 and Fig. 9 of the present disclosure adjustment method.
  • the memory 1110 and the processor 1120 are connected through a bus 1130 .
  • Fig. 12 is a schematic structural diagram of a robot provided by an embodiment of the present disclosure. As shown in Fig. 12 , the robot includes: a pick-and-place device 1210, a temporary storage shelf 1220, and an adjustment device 1230 for the pick-and-place device.
  • the pick-and-place device 1210 is provided with an image acquisition device 1211; the temporary storage shelf 1220 is used to temporarily store goods during the process of robot handling goods; the adjustment device 1230 of the pick-and-place device is provided by the embodiment shown in FIG. The adjustment equipment of the pick-and-place device.
  • the pick-up method of the pick-and-place device 1210 is a plug-and-lift method.
  • the pick-and-place device includes a slide plate. When the goods need to be picked up, the slide plate is controlled to extend to place the slide plate bottom of the cargo, and then take out the cargo.
  • FIG. 13 is a schematic structural diagram of a storage system provided by an embodiment of the present disclosure. As shown in FIG. 13 , the storage system includes: a shelf 1310 and a robot 1320 .
  • the robot 1320 is the robot provided in the embodiment shown in FIG. 12 of the present disclosure, and the pick-and-place device of the robot is provided with an image acquisition device 1321 .
  • the storage system further includes a dispatching device 1330, configured to send a dispatching instruction to the robot 1320, so that the robot 1320 performs a corresponding pick-and-place operation based on the dispatching instruction.
  • a dispatching device 1330 configured to send a dispatching instruction to the robot 1320, so that the robot 1320 performs a corresponding pick-and-place operation based on the dispatching instruction.
  • the storage system further includes one or more of an operation platform, an unloader, an elevator, a conveying line, and the like.
  • An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement any of the embodiments corresponding to FIG. 2 , FIG. 5 , FIG. 8 and FIG. 9 of the present disclosure.
  • the adjustment method of the pick-and-place device provided by the embodiment.
  • the computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device and the like.
  • An embodiment of the present disclosure also provides a program product, the program product includes executable instructions, the executable instructions are stored in a readable storage medium, and at least one processor of the adjustment device of the pick-and-place device or the storage system can read from the The storage medium reads the execution instruction, and at least one processor executes the execution instruction so that the shelf scheduling device implements the method for adjusting the pick-and-place device provided in the various embodiments above.
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the modules is only a logical function division. In actual implementation, there may be other division methods, for example, multiple modules can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or modules may be in electrical, mechanical or other forms.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in each embodiment of the present disclosure may be integrated into one processing unit, each module may exist separately physically, or two or more modules may be integrated into one unit.
  • the units formed by the above modules can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above-mentioned integrated modules implemented in the form of software function modules may be stored in a computer-readable storage medium.
  • the above-mentioned software function modules are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) or a processor (English: processor) to execute the functions described in various embodiments of the present disclosure. part of the method.
  • processor may be a central processing unit (Central Processing Unit, referred to as CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processor, referred to as DSP), application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC) and so on.
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the steps of the method disclosed in conjunction with the invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the storage may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage, and may also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disk.
  • NVM non-volatile storage
  • the bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component
  • EISA Extended Industry Standard Architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the buses in the drawings of the present disclosure are not limited to only one bus or one type of bus.
  • the above-mentioned storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable In addition to programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM programmable read-only memory
  • ROM read-only memory
  • magnetic memory magnetic memory
  • flash memory magnetic disk or optical disk.
  • a storage media may be any available media that can be accessed by a general purpose or special purpose computer.
  • An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium.
  • the storage medium may also be a component of the processor.
  • the processor and the storage medium may be located in Application Specific Integrated Circuits (ASIC for short).
  • ASIC Application Specific Integrated Circuits
  • the processor and the storage medium can also exist in the electronic device or the main control device as discrete components.
  • the aforementioned program can be stored in a computer-readable storage medium.
  • the program executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)
  • Warehouses Or Storage Devices (AREA)

Abstract

一种取放货装置（410，1210）的调整方法、装置、设备、机器人（110，400，700，1320）及仓储系统，该方法包括：当机器人（110，400，700，1320）移动至目标地面标识时，基于图像采集装置（413，710，1321），采集第一检测图像，其中，目标地面标识为目标库位（121，300，720）对应的地面标识；根据第一检测图像中的预设关键点的信息，确定目标库位（121，300，720）与图像采集装置（413，710，1321）的位姿关系，其中，预设关键点包括货架标识码（301，612，622）和/或支撑部对应的各点；根据位姿关系，调整机器人（110，400，700，1320）的取放货装置（410，1210）对准目标库位（121，300，720），以使取放货装置（410，1210）的插板（411）放置于第一支撑部（320）和第二支撑部（330）之间，以进行目标库位（121，300，720）上货物的提取或将货物放置于目标库位（121，300，720），实现了在取放货之前，对机器人（110，400，700，1320）的取放货装置（410，1210）进行校准，避免了在取放货过程中发生碰撞，提高了机器人（110，400，700，1320）作业的安全性。

Description

取放货装置的调整方法、装置、设备、机器人及仓储系统
本公开要求于2021年05月12日提交中国专利局、申请号为202110517215.0、申请名称为“取放货装置的调整方法、装置、设备、机器人及仓储系统”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及智能仓储技术领域，尤其涉及一种取放货装置的调整方法、装置、设备、机器人及仓储系统。
背景技术
基于机器人的智能仓储系统采用智能操作系统，通过系统指令实现货箱的自动取出和存放，同时可以24小时不间断运行，代替了人工管理和操作，提高了仓储的效率，受到了广泛地应用和青睐。
在基于机器人进行货架上的货物的提取或存放时，现有技术往往仅基于相应的指令移动至目标库位，从而直接将货物放置于该目标库位，或者直接将目标库位上放置的货物取出，容易导致机器人的取放货装置与货架发生碰撞，从而导致货架或机器人损坏，甚至货架倾倒等事故的发生，导致取放货操作的安全性较差。
发明内容
本公开提供一种取放货装置的调整方法、装置、设备、机器人及仓储系统，在取放货之前，基于图像采集装置实现取放货装置与目标库位的自动校准，提高了取放货的安全性。
第一方面，本公开实施例提供了一种取放货装置的调整方法，该方法包括：当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像，其中，所述目标地面标识为所述目标库位对应的地面标识，所述目标库位上设置有支撑部，所述支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部；根据所述第一检测图像中的预设关键点的信息，确定所述目标库位与所述取放货装置的位姿关系，其中，所述预设关键点包括货架标识码和/或所述支撑部对应的各点；根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
可选的，所述目标库位对应的货架立柱上设置有货架标识码，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：根据第一检测图像识别所述目标库位对应的货架标识码；若识别成功，则根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
可选的，根据识别结果确定所述取放货装置与所述目标库位的位姿关系，包括：根据货架标识码的特征点的位置信息以及货架标识码的标识图案的角度信息，确定取放货装置的角度偏差、高度偏差和行径偏差；其中，所述行径偏差为所述图像采集装置的图像中心与所述目标库位的库位中心的偏差。
可选的，根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，包括：确定所述目标库位的库位类型；根据所述目标库位的库位类型，确定预设偏差；根据所述预设偏差，调整所述取放货装置，以将所述行径偏差调整为所述预设偏差；并根据所述角 度偏差和高度偏差，分别调整所述取放货装置的角度和高度，以使所述取放货装置对准所述目标库位。
可选的，所述方法还包括：若根据所述第一检测图像未识别所述目标库位对应的货架标识码，则在预设范围内调整所述图像采集装置，并在调整过程中和/或调整完毕时，采集至少一个第二检测图像；若所述第二检测图像中包括所述目标库位对应的货架标识码，则识别所述第二检测图像中的货架标识码；根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
可选的，所述图像采集装置包括第一图像采集装置和第二图像采集装置，所述第一图像采集装置和第二图像采集装置分别设置在所述取放货装置的两侧，基于所述图像采集装置，采集第一检测图像，包括：基于第一图像采集装置和第二图像采集装置，分别采集一张第一检测图像，得到两张第一检测图像；相应的，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：若所述两张第一检测图像中均包括目标库位对应的货架标识码，则分别识别两张所述第一检测图像中的货架标识码，得到第一识别结果和第二识别结果；根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系。
可选的，根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系，包括：计算所述第一识别结果和所述第二识别结果中所述货架标识码的各点的位置平均值，以及所述第一识别结果和所述第二识别结果中所述货架标识码的标识图案的角度平均值；根据所述位置平均值和所述角度平均值，确定目标库位与取放货装置的位姿关系。
可选的，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，其中，所述第一支撑部和第二支撑部用于支撑放置于目标库位上的货物；根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系。
可选的，基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，包括：基于第一检测图像，确定所述第一支撑部与所述第二支撑部的第一间距；根据所述第一间距以及预设尺寸信息，确定在所述第一检测图像中所述第一支撑部的中心点的位置和所述第二支撑部的中心点的位置，其中，预设尺寸信息为所述第一支撑部和/或所述第二支撑部的尺寸信息。
可选的，根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系，包括：根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置的角度偏差、高度偏差和行径偏差。
可选的，在调整所述机器人的取放货装置对准所述目标库位之后，所述方法还包括：判断所述图像采集装置的图像中心与所述目标库位的中心是否对准；若是，则控制所述取放货装置向所述目标库位伸出，以提取和/或存放目标货物，其中，所述目标货物为所述调度指令中对应的货物。
可选的，所述方法还包括：基于所述图像采集装置，采集所述机器人的暂存货架的预设层的第三检测图像；根据所述第三检测图像，确定所述暂存货架的预设层的两个预设点的位置；根据所述两个预设点的位置，确定所述取放货装置与所述暂存货架的预设层的第二角度偏差和第二高度偏差；根据所述第二角度偏差和所述第二高度偏差，判断所述取放货装置在向所述暂存货架的预设层伸出后，是否会撞到所述暂存货架；若否，则控制所述取放货装置将所述目标货物放置于所述暂存货架的预设层，或，控制所述取放货装置从所述暂存货架的预设层提取目标货物，以在所述取放货装置与目标库位对准之后，将所述目标货物放置于所述目标库位。
第二方面，本公开实施例还提供了一种取放货装置的调整装置，所述装置应用于机器人，所述机器人的取放货装置上设置有图像采集装置，该装置包括：第一图像采集模块，用于当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像，其中，所述目标地面标识为所述目标库位对应的地面标识，所述目标库位上设置有支撑部，所述支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部；位姿确定模块，用于根据所述第一检测图像，确定目标库位与所述取放货装置的位姿关系，其中，所述预设关键点包括货架标识码和/或支撑部对应的各点；取放货装置对准模块，用于根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
第三方面，本公开实施例还提供了一种取放货装置的调整设备，包括存储器和至少一个处理器；所述存储器存储计算机执行指令；所述至少一个处理器执行所述存储器存储的计算机执行指令，使得所述至少一个处理器执行如本公开第一方面对应的任意实施例提供的取放货装置的调整方法。
第四方面，本公开实施例还提供了一种机器人，包括取放货装置以及本公开第三方面对应的实施例提供的取放货装置的调整设备。
第五方面，本公开实施例还提供了一种仓储系统，包括货架和本公开第四方面对应的实施例提供的机器人。
第六方面，本公开实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行计算机执行指令时，实现如本公开第一方面对应的任意实施例提供的取放货装置的调整方法。
第七方面，本公开实施例还提供了一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现本公开第一方面对应的任意实施例提供的取放货装置的调整方法。
本公开实施例提供的取放货装置的调整方法、装置、设备、机器人及仓储系统，该仓储系统的货架上的各个库位是由支撑部进行支撑，该支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部，在机器人执行取放货任务时，当机器人到位，即移动至目标库位对应的地面标识之后，基于机器人的取放货装置上设置的图像采集装置，采集第一检测图像，基于该第一检测图像中的货架标识码和/或支撑部对应的各点的信息，确定目标库位与图像采集装置的位姿关系，进而基于该位姿关系，调整机器人的取放货装置以对准目标库位，以在对准之后使得取放货装置将插板放置于目标库位的两个支撑部之间进行货物提取或存放，在机器人取放货之前，实现了将机器人的取放货装置与目标库位对准，避免了在取放货过程中发生碰撞，提高了货物提取和存放的安全性。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1为本公开实施例提供的取放货装置的调整方法的一种应用场景图；
图2为本公开一个实施例提供的取放货装置的调整方法的流程图；
图3为本公开一个实施例中提供的货架的库位的结构示意图；
图4A为本公开一个实施例提供的机器人的结构示意图；
图4B为本公开一个实施例提供的机器人的取放货装置的结构示意图；
图4C为本公开另一个实施例提供的机器人的取放货装置的结构示意图；
图4D为本公开另一个实施例提供的机器人的取放货装置的结构示意图；
图4E为本公开一个实施例提供的插举式取货的示意图；
图4F为本公开一个实施例提供的插举式取货的示意图；
图5为本公开另一个实施例提供的取放货装置的调整方法的流程图；
图6为本公开图5所示实施例中货架的结构示意图；
图7A为本公开图5所示实施例中图像采集装置与目标库位的位姿关系的示意图；
图7B为本公开图5所示实施例中图像采集装置与目标库位的位姿关系的示意图；
图8为本公开另一个实施例提供的取放货装置的调整方法的流程图；
图9为本公开另一个实施例提供的取放货装置的调整方法的流程图；
图10为本公开一个实施例提供的取放货装置的调整装置的结构示意图；
图11为本公开一个实施例提供的取放货装置的调整设备的结构示意图；
图12为本公开一个实施例提供的机器人的结构示意图；
图13为本公开一个实施例提供的仓储系统的结构示意图。
通过上述附图，已示出本公开明确的实施例，后文中将有更详细的描述。这些附图和文字描述并不是为了通过任何方式限制本公开构思的范围，而是通过参考特定实施例为本领域技术人员说明本公开的概念。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
下面以具体地实施例对本公开的技术方案以及本公开的技术方案如何解决上述技术问题进行详细说明。下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程可能在某些实施例中不再赘述。下面将结合附图，对本公开的实施例进行描述。
下面对本公开实施例的应用场景进行解释：
图1为本公开实施例提供的取放货装置的调整方法的一种应用场景图，如图1所示，本公开实施例提供的取放货装置的调整方法可以运行在取放货装置的调整设备上。智能仓储系统100包括机器人110、货架120和调度设备130，调度设备130在接收到取放货指令之后，生成取放货指令，从而机器人110基于该取放货指令进行目标库位121上货物的提取或者将货物放置于目标库位121上。
在现有技术中，机器人120到达目标库位121对应的位置之后，会直接进行目标库位121上货物的提取，或者直接将机器人120上的货物放置于货架120的目标库位121上。然而由于机器人120的行走误差、货物摆放误差或者其他原因等，会导致机器人120在取放货时，未与目标库位121对准，直接进行取放货，机器人120的取放货装置可能会与货架120发生碰撞，造成损失。对于放货任务，还会导致货物无法放置于目标库位121的中心，对于横梁式货架、牛腿式货架等，其库位是中空的，仅由两个分立的支撑部组成，当货物放偏时，容易发生货物掉落，从而造成损失。
针对上述问题，为了提高机器人取放货的安全性，本公开实施例提供的取放货装置的调整方法的主要构思为：在取放货之前，通过机器人的取放货装置上设置的图像采集装置，采集第一检测图像，基于该图像中的货架标识码和/或所述支撑部对应的各点的信息，确定目标库位与图像采集装置的位姿关系，从而基于该位姿关系实现目标库位与机器人的取放货装置之间的校准，在校准之后进行相应的取放货任务，从而提高了取放货的安全性。
图2为本公开一个实施例提供的取放货装置的调整方法的流程图，如图2所示，该取放货装置的调整方法可以由机器人执行，具体可以由机器人的取放货装置的调整设备执行，该机器人的取放货装置上设置有图像采集装置。本实施例提供的取放货装置的调整方 法包括以下步骤：
步骤S201，当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像。
其中，所述目标地面标识为所述目标库位对应的地面标识，所述目标库位上设置有支撑部，所述支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部。该图像采集装置可以是2D相机或3D相机，其数量可以为一个、两个或者其他数值，图像采集装置可以设置在机器人的取放货装置的左侧、右侧、中间或者其他位置。
其中，目标地面标识的形式可以为二维码、条形码、编码或者其他形式，机器人可以根据该目标地面标识确定当前位置是否为目标库位对应的位置。第一支撑部和第二支撑部设置在目标库位的两侧，且第一支撑部和第二支撑部之间间距一定的距离。
示例性的，图3为本公开一个实施例中提供的货架的库位的结构示意图，如图3所示，目标库位300由相应部分的货架立柱310、第一支撑部320和第二支撑部330组成，第一支撑部320和第二支撑部330之间存在一定的间距，即目标库位300的中间部分是悬空的，由第一支撑部320和第二支撑部330支撑放置于目标库位300上的货物。不同的货架对应的间距可以不同，从而使得目标库位300的尺寸也不相同。
在一些实施例中，该货架为牛腿货架，该货架的库位上的支撑部也可以称为牛腿架。
具体的，机器人可以根据调度设备的调度指令确定目标地面标识以及移动路径，进而根据移动路径由当前位置移动至目标地面标识处。在机器人移动至目标地面标识之后，开启机器人的取放货装置上的图像采集装置，采集视野范围内的第一检测图像。
进一步地，机器人在向目标地面标识移动期间，可以根据移动路径以及图像采集装置采集的地面图像调整机器人的移动路线，直至达到目标地面标识处。
具体的，调度设备可以根据取放货任务，确定目标库位及其对应的目标地面标识，进而基于目标库位及其对应的目标地面标识生成调度指令，将该调度指令发送至机器人，以使机器人基于该调度指令移动至目标地面标识，并进行目标库位的取放货任务。
进一步地，在机器人根据调度指令移动至目标地面标识之后，控制机器人的取放货装置向着目标库位的方向旋转90°，使得取放货装置直对目标库位，开启取放货装置上的图像采集装置，拍摄目标库位对应的第一检测图像。
示例性的，图4A为本公开一个实施例提供的机器人的结构示意图，如图4A所示，机器人包括取放货装置410、暂存货架420、升降组件430和底盘440，其中，取放货装置410采用插举式提取货物；暂存货架420用于暂时存放货物，图4A中所示的暂存货架420为阶梯背篓，包括5层，每一层由一个左背篓421和右背篓422组成，左背篓421和右背篓422之间存在一个切口423；升降组件430用于将取放货装置410移动至机器人暂存货架420的各层。
示例性的，图4B为本公开一个实施例提供的机器人的取放货装置的结构示意图，如图4B所示，取放货装置410包括插板411、侧边固定限位412、设置在侧边固定限位412上的图像采集装置413以及图像采集装置413的打光器414。在图4B中，图像采集装置413的数量为一个，安装在其中一个侧边固定限位412上。图4C为本公开另一个实施例提供的机器人的取放货装置的结构示意图，结合图4B和图4C可知，与图4B不同的是，在图4C中图像采集装置413的数量为两个，每个图像采集装置413上方设置有一个打光器414。图4B和图4C中的图像采集装置可以为2D相机。图4D为本公开另一个实施例提供的机器人的取放货装置的结构示意图，结合图4B和图4D可知，与图4B不同的是，图4D中的图像采集装置413设置在后侧固定限位415上，图4D中的图像采集装置413可以为3D相机。
示例性的，图4E和图4F为本公开一个实施例提供的插举式取货的示意图，结合图4E和图4F可知，机器人400在提取目标库位300上的目标货物500时，通过目标库位300 的货架标识码301，将机器人400的取放货装置410与目标库位300对准，之后如图4E所示，机器人400控制其取放货装置410向目标库位300伸出，并将取放货装置410的插板置于目标货物500的下方空间，并控制取放货装置410的插板上升，直至将目标货物500抬起。取放货装置410提取目标货物500之后，如图4F所示，机器人400控制其取放货装置410缩回，进而将目标货物500从目标库位300中取出。
步骤S202，根据所述第一检测图像中的预设关键点的信息，确定所述目标库位与所述取放货装置的位姿关系。
其中，所述预设关键点包括货架标识码和/或所述支撑部对应的各点。货架标识码设置在目标库位对应的货架立柱上，其形式可以为二维码、条形码或者其他含有标识性图案的标识码。位姿关系可以包括目标库位与取放货装置在横向、纵向和深度方向的位置关系，还可以包括取放货装置与目标库位的角度关系。
具体的，可以根据各个预设关键点在第一检测图像中的位置，确定目标库位与取放货装置的位姿关系。
可选的，所述目标库位对应的货架立柱上设置有货架标识码，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：
根据所述第一检测图像识别所述目标库位对应的货架标识码；若识别成功，则根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
具体的，当第一检测图像中包括目标库位对应的货架标识码时，可以识别该货架标识码，进行解码，确定该货架标识码上各个预设关键点的位置，进而基于该货架标识码上各个预设关键点的位置确定目标库位与图像采集装置的位姿关系。
进一步地，根据所述第一检测图像中的预设关键点的信息，确定图像采集装置与目标库位的位姿关系，并根据图像采集装置的安装位置，确定图像采集装置与取放货装置的第一位置关系，进而基于该第一位置关系以及图像采集装置与目标库位的位姿关系，确定取放货装置与目标库位的位姿关系。
可选的，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：
基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，其中，所述第一支撑部和第二支撑部用于支撑放置于目标库位上的货物；根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系。
具体的，第一支撑部和第二支撑部设置在目标库位相对的两侧，且保持一定的间距，可以通过第一检测图像，识别第一支撑部的中心点以及第二支撑部的中心点的位置，基于第一支撑部的中心点以及第二支撑部的中心点的位置确定取放货装置与目标库位的位姿关系。
步骤S203，根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
具体的，可以根据位姿关系中对应的图像采集装置与目标库位的各个偏差，包括角度偏差以及位置偏差等，调整机器人的取放货装置的位置，从而使得取放货装置对准目标库位。
具体的，当取放货装置与目标库位对准之后，控制该取放货装置的插板伸出并放置于第一支撑部和第二支撑部之间，从而完成目标库位上货物的提取，或者将货物放置于目标库位上，以完成取放货任务。
本公开实施例提供的取放货装置的调整方法，该方法针对的仓储系统的货架上的各个库位是由支撑部进行支撑，该支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部，在机器人执行取放货任务时，当机器人到位，即移动至目标库位 对应的地面标识之后，基于机器人的取放货装置上设置的图像采集装置，采集第一检测图像，基于该第一检测图像中的货架标识码和/或支撑部对应的各点的信息，确定目标库位与取放货装置的位姿关系，进而基于该位姿关系，调整机器人的取放货装置以对准目标库位，以在对准之后使得取放货装置将插板放置于目标库位的两个支撑部之间进行货物提取或存放，在机器人取放货之前，实现了将机器人的取放货装置与目标库位对准，避免了在取放货过程中发生碰撞，提高了货物提取和存放的安全性。
在一些实施例中，在机器人从机器人的暂存货架上取放货时，还需要判断机器人的取放货装置是否会撞到机器人的暂存货架，若否则进行取放货。
可选的，若调度指令为放货指令，即机器人需要将目标货物存放于目标库位上，所述方法还包括：基于所述图像采集装置，采集所述机器人的暂存货架的预设层的第三检测图像；根据所述第三检测图像，确定所述暂存货架的预设层的两个预设点的位置；根据所述两个预设点的位置，确定所述取放货装置与所述暂存货架的预设层的第二角度偏差和第二高度偏差；根据所述第二角度偏差和所述第二高度偏差，判断所述取放货装置在向所述暂存货架的预设层伸出后，是否会撞到所述暂存货架；若否，则控制所述取放货装置从所述暂存货架的预设层提取目标货物，以在所述取放货装置与目标库位对准之后，将所述目标货物放置于所述目标库位。
可选的，若调度指令为取货指令，即机器人需要提取目标库位上目标货物，在取放货装置与目标库位对准，并提取目标货物之后，所述方法还包括：基于所述图像采集装置，采集所述机器人的暂存货架的预设层的第三检测图像；根据所述第三检测图像，确定所述暂存货架的预设层的两个预设点的位置；根据所述两个预设点的位置，确定所述取放货装置与所述暂存货架的预设层的第二角度偏差和第二高度偏差；根据所述第二角度偏差和所述第二高度偏差，判断所述取放货装置在向所述暂存货架的预设层伸出后，是否会撞到所述暂存货架；若否，则控制所述取放货装置将所述目标货物放置于所述暂存货架的预设层。
其中，机器人的暂存货架用于在机器人搬运或运输货物的过程中，暂时存放货物，该暂存货架可以仅包括一层，也可以包括多层。预设层的两个预设点可以为相对于该预设层的中心对称设置的两个点，可以是该预设层对应的切口沿中心对称的两个点，如预设层左背篓和右背篓边缘上的两个点。
具体的，在机器人执行放货指令时，在机器人移动至目标地面标识之后，机器人需要通过其取放货装置将放置在机器人暂存货架预设层的目标货物取出，进而在取放货装置与目标库位对准之后，将目标货物放置于目标库位上。
进一步地，在取放货装置取出机器人暂存货架预设层的目标货物之前，需要通过取放货装置上设置的图像采集装置采集的机器人的暂存货架的预设层的第三检测图像，确定该预设层的对称设置的两个预设点的位置，从而基于该两个预设点的位置，进行防呆判断，具体可以基于取放货装置与暂存货架的预设层的第二角度偏差和第二高度偏差，判断取放货装置在向暂存货架的预设层伸出后是否会与暂存货架发生碰撞，若不会，则可以控制该取放货装置进行预设层放置的目标货物的提取。
具体的，在机器人执行取货指令时，在取放货装置与目标库位对准之后机器人需要通过其取放货装置将放置在目标库位上目标货物取出，具体是通过插举式方式将目标货物取出，进而，将目标货物放置于机器人的暂存货架的预设层。
进一步地，在将目标货物放置于机器人的暂存货架的预设层之前，需要通过取放货装置上设置的图像采集装置采集的机器人的暂存货架的预设层的第三检测图像，确定该预设层的对称设置的两个预设点的位置，从而基于该两个预设点的位置，进行防呆判断，具体可以基于取放货装置与暂存货架的预设层的第二角度偏差和第二高度偏差，判断取放货装置在向暂存货架的预设层伸出后是否会与暂存货架发生碰撞，若不会，则可 以控制该取放货装置将目标货物放置于机器人的暂存货架的预设层。
本公开提供的实施例中，由于通过第一检测图像可以进行机器人的取放货装置的对准，从而使得仓储系统的货物，包括目标货物上无需设置供机器人识别的标识码，降低了成本，在货物入库之前，无需为各个货物粘贴标识码，提高了货物入库效率。
图5为本公开另一个实施例提供的取放货装置的调整方法的流程图，本实施例针对的仓储系统的目标库位对应的货架立柱上设置有货架标识码，本实施例提供的取放货装置的调整方法是在图2所示实施例的基础上，对步骤S202和步骤S203的进一步细化，如图5所示，本实施例提供的取放货装置的调整方法包括以下步骤：
步骤S501，当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像。
步骤S502，根据所述第一检测图像识别所述目标库位对应的货架标识码。
其中，目标库位对应的货架标识码设置在目标库位范围内的任意一根货架立柱上。
具体的，在本实施例中，仓储系统的货架上每个库位都对应一个货架标识码。
示例性的，图6为本公开图5所示实施例中货架的结构示意图，如图6所示，货架610的货架立柱611上设置有货架标识码612，货架620的货架立柱621上设置有货架标识码622，且每个库位对应一个货架标识码，不同库位对应的货架标识码的标识图案可以相同，也可以不同，图6中以货架标识码上的标识图案为“L”型图案为例。不同的货架对应的库位放置的货物的宽度D可以不同，从而支撑部的尺寸也可以不同，图6中货架610的库位为小库位，其支撑部613的尺寸较小，两个支撑部613之间的间距也相应较小，而货架620的库位为大库位，其支撑部的尺寸较大，两个支撑部623之间的间距也相应较大。图6中所示的货架标识码的标识图案仅作为示例，标识图案还可以是其他具备标识特点的图案，本公开对此不进行限定。
具体的，当第一检测图像中包括货架标识码的标识图案时，识别该标识图案，从而得到识别结果。
具体的，该识别结果中可以包括货架标识码的标识图案的朝向、识别图案中各个特征点的位置信息等。
步骤S503，若识别成功，则根据所述货架标识码的特征点的位置信息以及所述货架标识码的标识图案的角度信息，确定所述取放货装置的角度偏差、高度偏差和行径偏差。
其中，所述行径偏差为所述图像采集装置的图像中心与所述目标库位的库位中心的偏差。当行径偏差为0或预设偏差时，表示图像采集装置的图像中心与目标库位的库位中心重合。货架标识码的特征点可以为货架标识码的标识图案的拐点，还可以包括标识图案的其他特征点，通过特征点的位置信息可以确定标识图案的朝向或角度，还可以确定标识图案的位置。
具体的，在成功识别货架标识码，即得到货架标识码的标识图案上特征点的位置信息以及标识图案的角度信息之后，根据货架标识码的特征点的位置信息以及货架标识码的标识图案的角度信息，确定图像采集装置与目标库位的位姿关系，该位姿关系包括图像采集装置相对于目标库位的角度偏差、高度偏差、深度偏差和行径偏差，还可以包括图像采集装置相对于目标库位的深度偏差。
示例性的，图7A和图7B为本公开图5所示实施例中图像采集装置与目标库位的位姿关系的示意图，结合图7A和图7B可知，机器人700的图像采集装置710与目标库位720的位姿关系，包括图像采集装置710相对于目标库位720的角度偏差yaw1、高度偏差dz1、深度偏差dy1和行径偏差dx1，其中，高度偏差dz1为图像采集装置710与目标库位720对应的货架标识码721的在高度方向的偏差；行径偏差dx1为目标库位720对应的货架标识码的中心线c1与图像采集装置710在水平方向的偏差；深度偏差dy1为机器人700上图像采集装置710的中心线c2与目标库位720对应的货架标识码在深度方向的距离； 角度偏差yaw1为机器人700的朝向与目标库位720的朝向的角度偏差。
进一步地，在确定图像采集装置相对于目标库位的角度偏差yaw1、高度偏差dz1、深度偏差dy1和行径偏差dx1之后，判断角度偏差yaw1、高度偏差dz1、深度偏差dy1和行径偏差dx1是否均在预设阈值内；若是，则继续执行后续步骤，即步骤S507；若否，则上报系统，进行异常预警，以对目标库位、地面标识、机器人等进行异常检测。
步骤S504，若根据所述第一检测图像未识别所述目标库位对应的货架标识码，则在预设范围内调整所述图像采集装置，并在调整过程中和/或调整完毕时，采集至少一个第二检测图像。
其中，预设范围内可以是设定的一个范围。
具体的，根据第一检测图像未识别目标库位对应的货架标识码，可以包括第一检测图像中不包括完整的标识图案，从而无法根据第一检测图像识别目标库位对应的货架标识码，即货架标识码识别失败，则需要调整取放货装置上设置的图像采集装置，从而扩大其视野范围，以搜寻货架标识码。
具体的，控制图像采集装置在预设范围内移动，可以是按照设定移动方式控制图像采集装置移动，并在移动过程中采集各个第二检测图像。
进一步地，控制图像采集装置在预设范围内移动，可以是先向左右各移动一定距离，进而向上下各移动一定距离，并在移动过程中不断采集各个第二检测图像，或者在移动至目标位置之后采集第二检测图像，如移动至最左侧的位置之后。
进一步地，若通过在预设范围内调整图像采集装置之后，各个第二检测图像中仍不包括货架标识码的完整的标识图案，则生成第一预警信息，以上报仓储系统未找到货架标识码，请求人工干涉。
步骤S505，若所述第二检测图像中包括所述目标库位对应的货架标识码，则识别所述第二检测图像中的货架标识码。
具体的，识别第二检测图像中的货架标识码的具体方式与步骤S502的具体方式相似，仅将对象由第一检测图像替换为第二检测图像即可，在此不再赘述。
步骤S506，根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
具体的，根据第二检测图像对应的货架标识码的特征点的位置信息以及货架标识码的标识图案的角度信息，确定取放货装置相对于目标库位的角度偏差、高度偏差、深度偏差和行径偏差。
具体的，根据第二检测图像对应的识别结果确定取放货装置与所述目标库位的位姿关系，与根据第一检测图像对应的识别结果确定图像采集装置与所述目标库位的位姿关系，的具体步骤相似，即与步骤S503相似，仅将对象由第一检测图像对应的识别结果替换为第二检测图像对应的识别结果即可，在此不再赘述。
步骤S507，确定所述目标库位的库位类型。
其中，目标库位的库位类型可以根据目标库位对应的两个支撑部的间距确定，或者基于目标库位所能存放或放置的目标货物的尺寸确定，如基于目标货物的宽度确定。示例性的，库位类型可以包括小库位类型和大库位类型。
具体的，可以基于调度指令，如取货指令、放货指令等，确定目标库位的库位类型。
进一步地，可以基于调度指令中目标库位的库位标识以及第一对应关系，确定目标库位的库位类型。其中，第一对应关系用于描述各个库位标识与库位类型的对应关系。
步骤S508，根据所述目标库位的库位类型，确定预设偏差。
其中，预设偏差用于描述目标库位的货架标识码的中心与目标库位的库位中心的距离。
具体的，不同库位类型的库位对应不同的预设偏差，可以基于上述第一对应关系以及目标库位的库位类型，确定预设偏差。
示例性的，表1为本公开图5所示实施例中第一对应关系表，如表1所示，库位类型包括小库位类型和大库位类型两种，小库位类型对应的预设偏差为a，大库位类型对应的预设偏差为b，其中，b>a。
表1 第一对应关系表
库位标识 库位类型 预设偏差
L1 小库位 a
L2 大库位 b
具体的，可以基于第二对应关系以及目标库位的库位类型，确定预设偏差，其中，第二对应关系用于描述各种库位类型与预设偏差的对应关系。
在一些实施例中，可以先执行步骤S507和步骤S508，在执行步骤S501，或者并行执行步骤S501和步骤S507，或者在执行步骤S501至步骤S506中任意步骤之前、之后或之时，执行步骤S507和步骤S508。
步骤S509，根据所述预设偏差，调整所述取放货装置，以将所述行径偏差调整为所述预设偏差，并根据所述角度偏差和高度偏差，分别调整所述取放货装置的角度和高度，以使所述取放货装置对准所述目标库位。
具体的，在确定预设偏差之后，通过调整取放货装置的位置和角度，使得图像采集装置相对于目标库位的行径偏差dx1为该预设偏差；角度偏差yaw1为0；高度偏差dz1为预设高度，从而使得取放货装置伸出之后，其插板低于目标库位的支撑部的支撑面对应的高度。
进一步地，还可以根据图像装置相对于目标库位的深度偏差dy1，确定取放货装置的伸出距离，以在取放货装置对准目标库位之后，按照该伸出距离控制取放货装置的插板伸出，以使通过该插板插取目标库位上的目标货物，或者将目标货物放置于目标库位上。
在本实施例中，针对在目标库位对应的一个货架立柱上设置有货架标识码的仓储系统，当机器人移动至目标库位对应的目标地面标识之后，通过机器人的取放货装置上设置的图像采集装置采集目标库位的第一检测图像，基于该第一检测图像判断是否可以读取完整的货架标识码的标识图案，若不能，则通过调整图像采集装置，以扩大视野范围，采集多个第二检测图像，直至读取到完整的货架标识码的标识图案，进而，基于货架标识码的标识图案的角度信息以及其上各个特征点的位置信息，确定图像采集装置与目标库位的位姿关系，包括角度偏差、高度偏差、行径偏差和深度偏差，进而基于该位姿关系实现取放货装置与目标库位的自动对准，基于对准后的取放货装置进行取放货，提高了货物提取和存放的安全性，避免了发生碰撞。
图8为本公开另一个实施例提供的取放货装置的调整方法的流程图，本实施例针对的机器人的取放货装置上设置有两个图像采集装置，即第一图像采集装置和第二图像采集装置，分别设置于取放货装置的两侧，本实施例提供的取放货装置的调整方法是在图2所示实施例的基础上，对步骤S201和步骤S202的进一步细化，如图8所示，本实施例提供的取放货装置的调整方法包括以下步骤：
步骤S801，当机器人移动至目标地面标识时，基于第一图像采集装置和第二图像采集装置，分别采集一张第一检测图像，得到两张第一检测图像。
具体的，当机器人移动至目标库位对应的目标地面标识之后，控制机器人取放货装置上设置的第一图像采集装置和第二图像采集装置分别采集一张第一检测图像，从而得到两张第一检测图像。
步骤S802，若所述两张第一检测图像中均包括目标库位对应的货架标识码，则分别识别两张所述第一检测图像中的货架标识码，得到第一识别结果和第二识别结果。
具体的，若第一图像采集装置和第二图像采集装置采集的第一检测图像均包括货架标识码，则分别识别所采集的两张第一检测图像中的货架标识码，得到第一图像采集装置对 应的第一识别结果，和第二图像采集装置对应的第二识别结果。第一识别结果和第二识别结果可以包括对应的第一检测图像上货架标识码的标识图案的各个特征点的位置信息以及标识图案的角度信息。
进一步地，若该两张第一检测图像中仅有一张第一检测图像中包括目标库位对应的货架标识码，则采用图5所示实施例中提供的方法进行后续的货架标识码的识别以及取放货装置的对准的相关步骤。
步骤S803，根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系。
具体的，可以根据第一识别结果中的货架标识码的标识图案的各个特征点的位置信息以及标识图案的角度信息，确定第一图像采集装置与目标库位的第一位姿关系；根据第二识别结果中的货架标识码的标识图案的各个特征点的位置信息以及标识图案的角度信息，确定第二图像采集装置与目标库位的第二位姿关系。进而基于该第一位姿关系和第二位姿关系，确定取放货装置与目标库位的位姿关系。
进一步地，可以基于第一位姿关系，确定取放货装置与目标库位的第一偏差，其中，第一偏差包括取放货装置与目标库位的第一角度偏差、第一高度偏差和第一行径偏差；基于第二位姿关系，确定取放货装置与目标库位的第二偏差，其中，第二偏差包括取放货装置与目标库位的第二角度偏差、第二高度偏差和第二行径偏差；判断第一偏差和第二偏差中各项的差值是否大于相应的预设差值，若是，则生成第二预警信息，以上报系统，请求人工进行各个相关设备的检查；若否，则基于第一位姿关系和第二位姿关系，确定取放货装置与目标库位的位姿关系，具体为，基于第一位姿关系中的第一角度偏差、第一高度偏差、第一行径偏差和第一深度偏差，以及第二位姿关系中的第二角度偏差、第二高度偏差、第二行径偏差和第二深度偏差，确定取放货装置与目标库位的角度偏差、高度偏差、行径偏差和深度偏差。
可选的，根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系，包括：计算所述第一识别结果和所述第二识别结果中所述货架标识码的各点的位置平均值，以及所述第一识别结果和所述第二识别结果中所述货架标识码的标识图案的角度平均值；根据所述位置平均值和所述角度平均值，确定目标库位与取放货装置的位姿关系。
具体的，当第一识别结果和第二识别结果满足预设条件时，计算第一识别结果和第二识别结果中货架标识码的各点的位置平均值以及货架标识码的标识图案的角度平均值。
其中，第一识别结果和第二识别结果满足预设条件，包括：第一识别结果中对应的第一偏差和第二识别结果中对应的第二偏差中各项的差值小于或等于相应的预设差值。
步骤S804，根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
在本实施例中，仓储系统的机器人的取放货装置上设置有两个图像采集装置，且仓储系统的货架的每个库位对应一个货架标识码，该货架标识码设置于货架立柱上，当机器人移动至调度指令对应的位置之后，开启第一图像采集装置和第二图像采集装置，分别采集目标库位对应的一张第一检测图像，进而通过该两张第一检测图像中货架标识码对应的信息，确定取放货装置与目标库位的位姿关系，采用两个图像采集装置，扩大了采集的视野范围，提高了货架标识码识别的效率，且通过两张第一检测图像确定位姿关系，提高了位姿关系确定的准确度，进而基于该位姿关系进行取放货装置的对准，提高了取放货装置对准的精度，进一步提高了取放货的安全性。
图9为本公开另一个实时提供的取放货装置的调整方法的流程图，本实施例针对的取放货装置为3D相机或者广视野范围的2D相机，本实施例提供的取放货装置的 调整方法是在图2所示实施例的基础上，对步骤S202和步骤S203的进一步细化，如图9所示，本实施例提供的取放货装置的调整方法包括以下步骤：
步骤S901，当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像。
步骤S902，基于所述第一检测图像，确定所述第一支撑部与所述第二支撑部的第一间距。
具体的，目标库位的第一支撑部和第二支撑部之间间隔一定的距离，即上述第一间距，通过第一检测图像以及预设图像识别算法，可以识别第一支撑部和第二支撑部，进而确定第一支撑部与第二支撑部之间的第一间距。
进一步地，该第一检测图像为3D相机拍摄的点云数据，在采集第一检测图像之后，还需要对第一检测图像进行预处理，该预处理包括降噪处理、分割处理等，进而基于预处理后的第一检测图像，确定第一支撑部与第二支撑部的第一间距。
步骤S903，根据所述第一间距以及预设尺寸信息，确定在所述第一检测图像中所述第一支撑部的中心点的位置和所述第二支撑部的中心点的位置。
其中，所述预设尺寸信息为所述第一支撑部和/或所述第二支撑部的尺寸信息。
步骤S904，根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置的角度偏差、高度偏差和行径偏差。
具体的，可以根据目标库位的第一支撑部和第二支撑部的中心点的位置，可以确定目标库位的库位角度、库位高度和库位中心，进而基于库位角度确定取放货装置相对于目标库位的角度偏差，基于库位高度确定取放货装置相对于目标库位的高度偏差，基于库位中心以及库位类型，确定取放货装置相对于目标库位的行径偏差。
步骤S905，根据所述图像采集装置的角度偏差、高度偏差、深度偏差和行径偏差，调整所述机器人的取放货装置对准所述目标库位。
步骤S906，判断所述图像采集装置的图像中心与所述目标库位的中心是否对准。
具体的，在机器人的取放货装置对准目标库位之后，在控制取放货装置的插板向目标库位伸出，以使该插板位于目标库位的第一支撑部和第二支撑部之间之前，需要进一步判断取放货装置是否与目标库位对准，可以通过判断图像采集装置的图像中心是否与目标库位的库位中心对准实现。
进一步地，若未对准，则基于图像采集装置的图像中心与目标库位的中心的偏差，调整取放货装置，直至图像采集装置的图像中心与目标库位的中心对准。
步骤S907，若是，则控制所述取放货装置向所述目标库位伸出，以提取和/或存放目标货物。
其中，所述目标货物为所述调度指令中对应的货物。
具体的，当判断图像采集装置的图像中心与目标库位的中心对准之后，控制去取放货装置的插板向目标库位伸出，以将该插板置于目标库位的第一支撑部和第二支撑部之间，从将目标货物放置于目标库位上，或者从目标库位上取出目标货物以放置于机器人的暂存货架的预设层。
在本实施例中，在进行目标库位的取放货操作之前，通过机器人的图像采集装置，采集目标库位的第一检测图像，基于该第一检测图像，确定目标库位的第一支撑部和第二支撑部的中心点的位置，从而确定取放货装置与目标库位的位姿关系，基于该位姿关系实现取放货装置的自动对准，提高了对准效率和准确度，提高了取放货的安全性；且无需在货架或货物上额外粘贴标识码，降低了成本，提高了仓储效率。
图10为本公开一个实施例提供的取放货装置的调整装置的结构示意图，该取放货装置的调整装置应用于机器人，该机器人的取放货装置上设置有图像采集装置，如图10所述，该取放货装置的调整装置包括：第一图像采集模块1010、位姿确定模块1020和取放 货装置对准模块1030。
可选的，所述目标库位对应的货架立柱上设置有货架标识码，位姿确定模块1020，包括：标识码识别单元，用于根据所述第一检测图像识别所述目标库位对应的货架标识码；第一位姿确定单元，用于若识别成功，则根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
可选的，第一位姿确定单元，具体用于：若识别成功，根据所述货架标识码的特征点的位置信息以及所述货架标识码的标识图案的角度信息，确定所述取放货装置的角度偏差、高度偏差和行径偏差；其中，所述行径偏差为所述图像采集装置的图像中心与所述目标库位的库位中心的偏差。
可选的，取放货装置对准模块1030，具体用于：确定所述目标库位的库位类型；根据所述目标库位的库位类型，确定预设偏差；根据所述预设偏差，调整所述取放货装置，以将所述行径偏差调整为所述预设偏差；并根据所述角度偏差和高度偏差，分别调整所述取放货装置的角度和高度，以使所述取放货装置对准所述目标库位。
可选的，所述取放货装置的调整装置还包括：若根据所述第一检测图像未识别所述目标库位对应的货架标识码，则在预设范围内调整所述图像采集装置，并在调整过程中和/或调整完毕时，采集至少一个第二检测图像；若所述第二检测图像中包括所述目标库位对应的货架标识码，则识别所述第二检测图像中的货架标识码；根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
可选的，所述图像采集装置包括第一图像采集装置和第二图像采集装置，所述第一图像采集装置和第二图像采集装置分别设置在所述取放货装置的两侧，第一图像采集模块1010，具体用于：基于第一图像采集装置和第二图像采集装置，分别采集一张第一检测图像，得到两张第一检测图像；相应的，位姿确定模块1020，包括：识别结果获取单元，用于若所述两张第一检测图像中均包括目标库位对应的货架标识码，则分别识别两张所述第一检测图像中的货架标识码，得到第一识别结果和第二识别结果；第二位姿确定单元，用于根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系。
可选的，位姿关系确定单元，具体用于：计算所述第一识别结果和所述第二识别结果中所述货架标识码的各点的位置平均值，以及所述第一识别结果和所述第二识别结果中所述货架标识码的标识图案的角度平均值；根据所述位置平均值和所述角度平均值，确定所述目标库位与所述取放货装置的位姿关系。
可选的，位姿确定模块1020，包括：中心点确定单元，用于基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，其中，所述第一支撑部和第二支撑部用于支撑放置于目标库位上的货物；第三位姿确定单元，用于根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系。
可选的，中心点确定单元，具体用于：基于所述第一检测图像，确定所述第一支撑部与所述第二支撑部的第一间距；根据所述第一间距以及预设尺寸信息，确定在所述第一检测图像中所述第一支撑部的中心点的位置和所述第二支撑部的中心点的位置，其中，所述预设尺寸信息为所述第一支撑部和/或所述第二支撑部的尺寸信息。
可选的，第三位姿确定单元，具体用于：根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置的角度偏差、高度偏差和行径偏差。
可选的，所述取放货装置的调整装置还包括：防呆模块，用于在调整所述机器人的取放货装置对准所述目标库位之后，判断所述图像采集装置的图像中心与所述目标库位的中心是否对准；取放货模块，用于若图像采集装置的图像中心与所述目标库位的中心对准，则控制所述取放货装置向所述目标库位伸出，以提取和/或存放目标货物，其中，所述目标货物为所述调度指令中对应的货物。
可选的，所述取放货装置的调整装置还包括：内部取放货模块，用于基于所述图像采集装置，采集所述机器人的暂存货架的预设层的第三检测图像；根据所述第三检测图像，确定所述暂存货架的预设层的两个预设点的位置；根据所述两个预设点的位置，确定所述取放货装置与所述暂存货架的预设层的第二角度偏差和第二高度偏差；根据所述第二角度偏差和所述第二高度偏差，判断所述取放货装置在向所述暂存货架的预设层伸出后，是否会撞到所述暂存货架；若否，则控制所述取放货装置将所述目标货物放置于所述暂存货架的预设层，或，控制所述取放货装置从所述暂存货架的预设层提取目标货物，以在所述取放货装置与目标库位对准之后，将所述目标货物放置于所述目标库位。
本公开实施例所提供的取放货装置的调整装置可执行本公开任意实施例所提供的取放货装置的调整方法，具备执行方法相应的功能模块和有益效果。
图11为本公开一个实施例提供的取放货装置的调整设备的结构示意图，如图11所示，该取放货装置的调整设备包括：存储器1110，处理器1120以及计算机程序。
其中，计算机程序存储在存储器1110中，并被配置为由处理器1120执行以实现本公开图2、图5、图8和图9所对应的实施例中任一实施例提供的取放货装置的调整方法。
其中，存储器1110和处理器1120通过总线1130连接。
相关说明可以对应参见图2、图5、图8和图9的步骤所对应的相关描述和效果进行理解，此处不做过多赘述。
图12为本公开一个实施例提供的机器人的结构示意图，如图12所示，该机器人包括：取放货装置1210、暂存货架1220和取放货装置的调整设备1230。
其中，取放货装置1210上设置有图像采集装置1211；暂存货架1220用于在机器人搬运货物的过程中暂时存放货物；取放货装置的调整设备1230为本公开图11所示实施例提供的取放货装置的调整设备。
在一些实施例中，该取放货装置1210的取货方式为插举式方式，该取放货装置包括插板，当需要提取货物时，控制该插板伸出，以将插板置于货物底部，进而取出货物。
图13为本公开一个实施例提供的仓储系统的结构示意图，如图13所示，该仓储系统包括：货架1310和机器人1320。
其中，机器人1320为本公开图12所示实施例提供的机器人，该机器人的取放货装置上设置有图像采集装置1321。
在一些实施例中，该仓储系统还包括调度设备1330，用于将调度指令发送至机器人1320，以使机器人1320基于该调度指令进行相应的取放货操作。
在一些实施例中，该仓储系统还包括操作台、卸料机、提升机、输送线等中的一项或多项。
本公开一个实施例提供一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行以实现本公开图2、图5、图8和图9所对应的实施例中任一实施例提供的取放货装置的调整方法。
其中，计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
本公开实施例还提供一种程序产品，该程序产品包括可执行指令，该可执行指令存储在可读存储介质中，取放货装置的调整设备或仓储系统的至少一个处理器可以从可读存储介质读取该执行指令，至少一个处理器执行该执行指令使得货架调度装置实施上述各种实施方式提供的取放货装置的调整方法。
在本公开所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相 互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本公开各个实施例中的各功能模块可以集成在一个处理单元中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个单元中。上述模块成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能模块的形式实现的集成的模块，可以存储在一个计算机可读取存储介质中。上述软件功能模块存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(英文：processor)执行本公开各个实施例所述方法的部分步骤。
应理解，上述处理器可以是中央处理单元(Central Processing Unit，简称CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合发明所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
存储器可能包含高速RAM存储器，也可能还包括非易失性存储NVM，例如至少一个磁盘存储器，还可以为U盘、移动硬盘、只读存储器、磁盘或光盘等。
总线可以是工业标准体系结构(Industry Standard Architecture，简称ISA)总线、外部设备互连(Peripheral Component，简称PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture，简称EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，本公开附图中的总线并不限定仅有一根总线或一种类型的总线。
上述存储介质可以是由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。存储介质可以是通用或专用计算机能够存取的任何可用介质。
一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于专用集成电路(Application Specific Integrated Circuits，简称ASIC)中。当然，处理器和存储介质也可以作为分立组件存在于电子设备或主控设备中。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本公开的技术方案，而非对其限制；尽管参照前述各实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本公开各实施例技术方案的范围。

Claims (18)

  1. 一种取放货装置的调整方法，其特征在于，所述方法应用于机器人，所述机器人的取放货装置上设置有图像采集装置，所述方法包括：
    当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像，其中，所述目标地面标识为所述目标库位对应的地面标识，所述目标库位上设置有支撑部，所述支撑部包括同高度水平以协同进行货物放置的第一支撑部和第二支撑部；
    根据所述第一检测图像中的预设关键点的信息，确定所述目标库位与所述取放货装置的位姿关系，其中，所述预设关键点包括货架标识码和/或所述支撑部对应的各点；
    根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
  2. 根据权利要求1所述的方法，其特征在于，所述目标库位对应的货架立柱上设置有货架标识码，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：
    根据所述第一检测图像识别所述目标库位对应的货架标识码；
    若识别成功，则根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
  3. 根据权利要求2所述的方法，其特征在于，根据识别结果确定所述取放货装置与所述目标库位的位姿关系，包括：
    根据所述货架标识码的特征点的位置信息以及所述货架标识码的标识图案的角度信息，确定所述取放货装置的角度偏差、高度偏差和行径偏差；
    其中，所述行径偏差为所述图像采集装置的图像中心与所述目标库位的库位中心的偏差。
  4. 根据权利要求3所述的方法，其特征在于，根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，包括：
    确定所述目标库位的库位类型；
    根据所述目标库位的库位类型，确定预设偏差；
    根据所述预设偏差，调整所述取放货装置，以将所述行径偏差调整为所述预设偏差；
    并根据所述角度偏差和高度偏差，分别调整所述取放货装置的角度和高度，以使所述取放货装置对准所述目标库位。
  5. 根据权利要求2-4任一项所述的方法，其特征在于，所述方法还包括：
    若根据所述第一检测图像未识别所述目标库位对应的货架标识码，则在预设范围内调整所述图像采集装置，并在调整过程中和/或调整完毕时，采集至少一个第二检测图像；
    若所述第二检测图像中包括所述目标库位对应的货架标识码，则识别所述第二检测图像中的货架标识码；
    根据识别结果确定所述取放货装置与所述目标库位的位姿关系。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述图像采集装置包括第一图像采集装置和第二图像采集装置，所述第一图像采集装置和第二图像采集装置分别设置在所述取放货装置的两侧，基于所述图像采集装置，采集第一检测图像，包括：
    基于第一图像采集装置和第二图像采集装置，分别采集一张第一检测图像，得到两张第一检测图像；
    根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：
    若所述两张第一检测图像中均包括目标库位对应的货架标识码，则分别识别两张所述第一检测图像中的货架标识码，得到第一识别结果和第二识别结果；
    根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系。
  7. 根据权利要求6所述的方法，其特征在于，根据所述第一识别结果和所述第二识别结果，确定所述目标库位与所述取放货装置的位姿关系，包括：
    计算所述第一识别结果和所述第二识别结果中所述货架标识码的各点的位置平均值，以及所述第一识别结果和所述第二识别结果中所述货架标识码的标识图案的角度平均值；
    根据所述位置平均值和所述角度平均值，确定所述目标库位与所述取放货装置的位姿关系。
  8. 根据权利要求1所述的方法，其特征在于，根据所述第一检测图像中的预设关键点的信息，确定目标库位与所述取放货装置的位姿关系，包括：
    基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，其中，所述第一支撑部和第二支撑部用于支撑放置于目标库位上的货物；
    根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系。
  9. 根据权利要求8所述的方法，其特征在于，基于所述第一检测图像，确定第一支撑部和第二支撑部的中心点的位置，包括：
    基于所述第一检测图像，确定所述第一支撑部与所述第二支撑部的第一间距；
    根据所述第一间距以及预设尺寸信息，确定在所述第一检测图像中所述第一支撑部的中心点的位置和所述第二支撑部的中心点的位置，其中，所述预设尺寸信息为所述第一支撑部和/或所述第二支撑部的尺寸信息。
  10. 根据权利要求8所述的方法，其特征在于，根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置与所述目标库位的位姿关系，包括：
    根据第一支撑部和第二支撑部的中心点的位置，确定所述取放货装置的角度偏差、高度偏差和行径偏差。
  11. 根据权利要求1-10任一项所述的方法，其特征在于，在调整所述机器人的取放货装置对准所述目标库位之后，所述方法还包括：
    判断所述图像采集装置的图像中心与所述目标库位的中心是否对准；
    若所述图像采集装置的图像中心与所述目标库位的中心对准，则控制所述取放货装置向所述目标库位伸出，以提取和/或存放目标货物，其中，所述目标货物为所述调度指令中对应的货物。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    基于所述图像采集装置，采集所述机器人的暂存货架的预设层的第三检测图像；
    根据所述第三检测图像，确定所述暂存货架的预设层的两个预设点的位置；
    根据所述两个预设点的位置，确定所述取放货装置与所述暂存货架的预设层的第二角度偏差和第二高度偏差；
    根据所述第二角度偏差和所述第二高度偏差，判断所述取放货装置在向所述暂存货架的预设层伸出后，是否会撞到所述暂存货架；
    若不会撞到所述暂存货架，则控制所述取放货装置将所述目标货物放置于所述暂存货架的预设层，或，控制所述取放货装置从所述暂存货架的预设层提取目标货物，以在所述取放货装置与目标库位对准之后，将所述目标货物放置于所述目标库位。
  13. 一种取放货装置的调整装置，其特征在于，所述装置应用于机器人，所述机器人的取放货装置上设置有图像采集装置，所述装置包括：
    第一图像采集模块，用于当机器人移动至目标地面标识时，基于所述图像采集装置，采集第一检测图像，其中，所述目标地面标识为所述目标库位对应的地面标识，所述目标库位上设置有支撑部，所述支撑部包括同高度水平以协同进行货物放置的第一支撑部和第 二支撑部；
    位姿确定模块，用于根据所述第一检测图像，确定目标库位与所述取放货装置的位姿关系，其中，所述预设关键点包括货架标识码和/或支撑部对应的各点；
    取放货装置对准模块，用于根据所述位姿关系，调整所述机器人的取放货装置对准所述目标库位，以使所述取放货装置的插板放置于所述第一支撑部和所述第二支撑部之间，以进行目标库位上货物的提取或将货物放置于所述目标库位。
  14. 一种取放货装置的调整设备，其特征在于，包括：存储器和至少一个处理器；
    所述存储器存储计算机执行指令；
    所述至少一个处理器执行所述存储器存储的计算机执行指令，使得所述至少一个处理器执行如权利要求1-12任一项所述的取放货装置的调整方法。
  15. 一种机器人，其特征在于，包括：取放货装置以及权利要求14所述的取放货装置的调整设备。
  16. 一种仓储系统，其特征在于，包括货架以及权利要求15所述的机器人。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如权利要求1-12任一项所述的取放货装置的调整方法。
  18. 一种计算机程序产品，其特征在于，包括计算机程序，所述计算机程序被处理器执行时实现如权利要求1-12任一项所述的取放货装置的调整方法。
PCT/CN2022/071764 2021-05-12 2022-01-13 取放货装置的调整方法、装置、设备、机器人及仓储系统 WO2022237221A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP22806199.0A EP4339132A1 (en) 2021-05-12 2022-01-13 Adjustment method, apparatus, and device for goods retrieval and placement apparatus, robot, and warehouse system
US18/503,571 US20240067450A1 (en) 2021-05-12 2023-11-07 Adjustment method, apparatus, and device for material handling apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110517215.0A CN113213054B (zh) 2021-05-12 2021-05-12 取放货装置的调整方法、装置、设备、机器人及仓储系统
CN202110517215.0 2021-05-12

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/503,571 Continuation US20240067450A1 (en) 2021-05-12 2023-11-07 Adjustment method, apparatus, and device for material handling apparatus

Publications (1)

Publication Number Publication Date
WO2022237221A1 true WO2022237221A1 (zh) 2022-11-17

Family

ID=77094969

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/071764 WO2022237221A1 (zh) 2021-05-12 2022-01-13 取放货装置的调整方法、装置、设备、机器人及仓储系统

Country Status (5)

Country Link
US (1) US20240067450A1 (zh)
EP (1) EP4339132A1 (zh)
CN (1) CN113213054B (zh)
TW (1) TWI801123B (zh)
WO (1) WO2022237221A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116061148A (zh) * 2023-03-17 2023-05-05 上海仙工智能科技有限公司 一种用于示教机械臂与背篓交互的方法及系统、存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113213054B (zh) * 2021-05-12 2023-05-30 深圳市海柔创新科技有限公司 取放货装置的调整方法、装置、设备、机器人及仓储系统
CN113619980B (zh) * 2021-08-12 2023-04-07 上海擎朗智能科技有限公司 物体运输方法、装置、计算机设备、存储介质及系统
CN115456437B (zh) * 2022-09-22 2023-08-11 山东开正信息产业有限公司 一种物流仓储柜调度管控系统
CN115599066B (zh) * 2022-12-15 2023-04-07 浙江凯乐士科技集团股份有限公司 窄巷道取放货作业调度方法、装置、调度设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106556341A (zh) * 2016-10-08 2017-04-05 浙江国自机器人技术有限公司 一种基于特征信息图形的货架位姿偏差检测方法和系统
JP2017116482A (ja) * 2015-12-25 2017-06-29 パナソニックＩｐマネジメント株式会社 測定装置、宅配ボックス装置
CN108217045A (zh) * 2018-01-03 2018-06-29 广州供电局有限公司 一种用于数据中心物理设备上下架的智能机器人
CN111169894A (zh) * 2019-11-08 2020-05-19 成都图灵时代科技有限公司 基于潜伏式搬运机器人的货架对准方法
CN210654762U (zh) * 2019-08-02 2020-06-02 佛山市金连硕货架制造有限公司 一种驶入式货架
CN111348361A (zh) * 2020-01-21 2020-06-30 深圳市海柔创新科技有限公司 取、放货控制方法、装置、搬运装置及搬运机器人
CN112660686A (zh) * 2021-03-17 2021-04-16 杭州蓝芯科技有限公司 基于深度相机的料笼堆叠方法及装置、电子设备、系统
CN113213054A (zh) * 2021-05-12 2021-08-06 深圳市海柔创新科技有限公司 取放货装置的调整方法、装置、设备、机器人及仓储系统

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5928748B2 (ja) * 2014-07-31 2016-06-01 インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ 同一種類の複数の認識対象物体が検索対象画像中に存在する場合に、それぞれの認識対象物体の位置および向きを精度良く求める手法
CN105752888B (zh) * 2016-05-11 2018-03-13 深圳普智联科机器人技术有限公司 具有简便定位功能的机器人叉车
CN109650292B (zh) * 2019-02-02 2019-11-05 北京极智嘉科技有限公司 一种智能叉车以及智能叉车的位置调整方法和介质
CN110135439B (zh) * 2019-05-09 2021-05-04 上海木木聚枞机器人科技有限公司 一种自动识别货架的方法及装置、移动机器人
CN111798183A (zh) * 2020-07-07 2020-10-20 深圳市海柔创新科技有限公司 理库方法、设备、系统以及存储介质
CN111890343B (zh) * 2020-07-29 2021-10-15 浙江广合智能科技有限公司 一种机器人载物碰撞检测方法及装置
CN112124304B (zh) * 2020-11-24 2021-02-05 天津天瞳威势电子科技有限公司 一种库位定位方法、装置及车载设备

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017116482A (ja) * 2015-12-25 2017-06-29 パナソニックＩｐマネジメント株式会社 測定装置、宅配ボックス装置
CN106556341A (zh) * 2016-10-08 2017-04-05 浙江国自机器人技术有限公司 一种基于特征信息图形的货架位姿偏差检测方法和系统
CN108217045A (zh) * 2018-01-03 2018-06-29 广州供电局有限公司 一种用于数据中心物理设备上下架的智能机器人
CN210654762U (zh) * 2019-08-02 2020-06-02 佛山市金连硕货架制造有限公司 一种驶入式货架
CN111169894A (zh) * 2019-11-08 2020-05-19 成都图灵时代科技有限公司 基于潜伏式搬运机器人的货架对准方法
CN111348361A (zh) * 2020-01-21 2020-06-30 深圳市海柔创新科技有限公司 取、放货控制方法、装置、搬运装置及搬运机器人
CN112660686A (zh) * 2021-03-17 2021-04-16 杭州蓝芯科技有限公司 基于深度相机的料笼堆叠方法及装置、电子设备、系统
CN113213054A (zh) * 2021-05-12 2021-08-06 深圳市海柔创新科技有限公司 取放货装置的调整方法、装置、设备、机器人及仓储系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116061148A (zh) * 2023-03-17 2023-05-05 上海仙工智能科技有限公司 一种用于示教机械臂与背篓交互的方法及系统、存储介质

Also Published As

Publication number Publication date
TW202243832A (zh) 2022-11-16
EP4339132A1 (en) 2024-03-20
TWI801123B (zh) 2023-05-01
CN113213054A (zh) 2021-08-06
CN113213054B (zh) 2023-05-30
US20240067450A1 (en) 2024-02-29

Similar Documents

Publication Publication Date Title
WO2022237221A1 (zh) 取放货装置的调整方法、装置、设备、机器人及仓储系统
CN111674817B (zh) 仓储机器人的控制方法、装置、设备及可读存储介质
TWI821796B (zh) 貨物存放方法、裝置、機器人、倉儲系統和儲存媒體
US20230286750A1 (en) Method and device for storing goods, robot, warehousing system and storage medium
TW202220915A (zh) 貨物取放方法、裝置、倉儲機器人和倉儲系統
EP3512785B1 (en) Integrated obstacle detection and payload centering sensor system
CN112407722A (zh) 货物存放空间异常处理方法、装置、设备及仓储系统
WO2023001125A1 (zh) 货物处理方法、装置、机器人、分拣装置及仓储系统
CN116374474B (zh) 一种基于机器视觉的拣选智能决策系统
JP2013532451A (ja) 倉庫内の物体の位置を特定するための方法及び装置
US11666948B2 (en) Projection instruction device, parcel sorting system, and projection instruction method
CN116468791A (zh) 拆垛定位方法、装置、系统及存储介质
WO2023036212A1 (zh) 货架定位方法、货架对接方法以及装置、设备、介质
CN113978987B (zh) 栈板物品打包提货方法、装置、设备及介质
CN114347040A (zh) 目标物的拾取方法、装置、机器人以及存储介质
CN112288038B (zh) 基于图像分类的物体识别或物体注册的方法及计算系统
JP7385424B2 (ja) 移載対象ワーク向き認識システム
CN115908573B (zh) 一种橡胶手套开口定位方法、系统、电子设备及存储介质
CN113091730B (zh) 一种轨迹确定方法及装置
CN112605986A (zh) 自动取货的方法、装置、设备及计算机可读存储介质
CN116038715A (zh) 取箱方法、装置、机器人和存储介质
CN117985389A (zh) 料箱取还装置及其控制方法、系统及存储介质
CN117735130A (zh) 一种应用于堆垛机的二次标定方法及相关设备
CN116266392A (zh) 遗留件检测定位方法、装置、服务器及存储介质
CN117934916A (zh) 物品码放方法、装置、计算机设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22806199

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022806199

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022806199

Country of ref document: EP

Effective date: 20231212