CN111445624A - Self-moving vending robot and method for identifying goods - Google Patents
Self-moving vending robot and method for identifying goods Download PDFInfo
- Publication number
- CN111445624A CN111445624A CN201910044130.8A CN201910044130A CN111445624A CN 111445624 A CN111445624 A CN 111445624A CN 201910044130 A CN201910044130 A CN 201910044130A CN 111445624 A CN111445624 A CN 111445624A
- Authority
- CN
- China
- Prior art keywords
- tray
- self
- information
- moving
- commodities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012806 monitoring device Methods 0.000 claims abstract description 26
- 230000000875 corresponding effect Effects 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims description 29
- 230000000007 visual effect Effects 0.000 claims description 29
- 238000005303 weighing Methods 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000001960 triggered effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 3
- 239000000571 coke Substances 0.000 description 14
- 229910052500 inorganic mineral Inorganic materials 0.000 description 12
- 239000011707 mineral Substances 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 238000006073 displacement reaction Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 3
- 235000013361 beverage Nutrition 0.000 description 3
- 230000005674 electromagnetic induction Effects 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/52—Weighing apparatus combined with other objects, e.g. furniture
Abstract
Embodiments of the present application provide a self-moving vending robot and a method of identifying goods. Wherein, from removing vending machine people includes: self-moving cargo sales outlets; the tray is arranged in the self-moving vending cabin, is used for bearing commodities and makes corresponding actions when the load of the tray changes; and the monitoring device is connected with the processor of the self-moving vending robot and used for informing the processor when the tray acts so that the processor can identify the pick-and-place information of the commodities in the self-moving vending cabin. The self-moving vending robot provided by the application can reduce the cost of identifying commodities.
Description
Technical Field
The application relates to the technical field of robots, in particular to a self-moving vending robot and a method for identifying commodities.
Background
A self-moving vending robot is a robot that can move to the side of a consumer to provide a sales service thereto. With the continuous progress of the technology, the self-moving vending robot has great improvement on autonomous navigation, target recognition and scene understanding, and has good development prospect as a device capable of effectively saving labor cost.
In the self-moving vending robot, the most important technical problem is how to recognize the goods sold by itself and realize the price counting of the goods.
Disclosure of Invention
The embodiment of the application provides a self-moving vending robot and a method for identifying commodities, and aims to reduce the cost of identifying the commodities.
In order to solve the above problems or at least partially solve the above technical problems, in one embodiment of the present application, there is provided a self-moving vending robot including:
self-moving cargo sales outlets; the tray is arranged in the self-moving vending cabin, is used for bearing commodities and makes corresponding actions when the load of the tray changes; and the monitoring device is connected with the processor of the self-moving vending robot and used for informing the processor when the tray acts so that the processor can identify the pick-and-place information of the commodities in the self-moving vending cabin.
In another embodiment of the present application, there is also provided a method of identifying an article, including:
after monitoring signals generated by at least one monitoring device when the corresponding tray acts are monitored, first load information of each tray is determined; and identifying the picking and placing information of the commodities in the self-moving vending cabin according to the first load information of each tray.
In yet another embodiment of the present application, there is also provided a self-moving vending robot, including:
self-moving cargo sales outlets; the tray is arranged in the self-moving vending cabin and used for bearing commodities; a weighing sensor connected with the processor of the self-moving vending robot for sensing load information of the tray; the vision sensor is connected with the processor of the self-moving vending robot and is used for collecting commodity images in the self-moving vending cabin; and the processor is used for identifying the picking and placing information and the types of the commodities in the self-moving vending cabin according to the load information of the tray and the commodity image.
In yet another embodiment of the present application, there is also provided a method of identifying an article, including:
acquiring load information of each corresponding tray sensed by at least one weighing sensor; acquiring commodity images in the self-moving vending cabin, which are acquired by at least one visual sensor at different moments; and identifying the picking and placing information and the types of the commodities in the self-moving vending cabin according to the load information of at least one tray and the commodity images acquired by at least one visual sensor at different moments.
In yet another embodiment of the present application, there is also provided a self-moving vending robot, including:
self-moving cargo sales outlets;
the tray is arranged in the self-moving vending cabin and used for bearing commodities;
the commodity identification device is used for monitoring the change information of the commodities on the tray; and identifying the picking and placing information of the commodities on the tray according to the change information.
In yet another embodiment of the present application, there is also provided a method of identifying an article, including:
monitoring the change information of the commodities on the tray;
and identifying the picking and placing information of the commodities on the tray according to the change information.
In one technical scheme provided by the embodiment of the application, a tray bearing commodities can make corresponding actions when the load changes, and the monitoring device informs the processor when the tray acts so that the processor can identify the pick-and-place information of the commodities in the mobile vending cabin; compared with the prior art, the method has the advantages of low cost, good realizability, stability and reliability.
In another technical scheme provided by the embodiment of the application, a multi-sensor fusion mode is adopted to mutually make up the inherent defects of each sensor, so that the commodity identification result is more reliable and accurate, the robustness of the system is improved, and the cost is saved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be clear that the drawings in the following description are only intended to illustrate some embodiments of the present application, and that for a person skilled in the art, it is possible to derive from these drawings, without inventive effort, technical features, connections or even method steps not mentioned in the other drawings.
FIG. 1 is an exploded view of a pallet and its associated structure according to an embodiment of the present application;
FIG. 2 is a schematic view of a tray and its associated structure when a monitoring device is activated according to an embodiment of the present application;
FIG. 3 is a schematic view of a tray and its associated structure without triggering a monitoring device according to an embodiment of the present application;
fig. 4 is a flowchart of an article identification device according to an embodiment of the present application;
fig. 5 is a flowchart of an article identification device according to another embodiment of the present application.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a" and "an" typically include at least two, but do not exclude the presence of at least one.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a monitoring", depending on the context. Similarly, the phrase "if it is determined" or "if it is monitored (a stated condition or event)" may be interpreted as "when determining" or "in response to determining" or "when monitoring (a stated condition or event)" or "in response to monitoring (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
The application provides a self-moving vending robot. In one embodiment, as shown in fig. 1, a self-moving vending robot includes:
self-moving cargo holds (not shown); the tray 3 is arranged in the self-moving vending cabin, is used for bearing commodities and makes corresponding actions when the load of the tray changes; and the monitoring device 2 is connected with the processor of the self-moving vending robot and is used for informing the processor when the tray 3 acts so that the processor can identify the pick-and-place information of the commodities in the self-moving vending cabin.
In the prior art, identification is often performed by means of complex and costly sensors, such as RFID sensors. In the technical scheme provided by the embodiment, the tray bearing the commodities can make corresponding actions when the load changes, and the monitoring device informs the processor when the tray acts so that the processor can identify the pick-and-place information of the commodities in the mobile vending cabin; compared with the prior art, the method has the advantages of low cost, good realizability and more accurate identification.
Further, the tray 3 includes: a tray body 31; an elastic body 4 having one end disposed on the tray body 31 and the other end disposed in the cabin of the self-moving cargo selling compartment; when the load of the tray body 31 is increased, the elastic body 4 deforms, and the tray 3 sinks; when the load of the tray body 31 is reduced, the elastic body 4 returns, and the tray 3 moves upward.
Further, the elastic coefficient of the elastic body 4 should satisfy: the tray 3 is deformed when the load increase amount is larger than a threshold value; the threshold is determined by the weight of the article.
The elastic body 4 may be a spring or a tension spring. The elastic body 4 may be held against the tray 3. The type of the elastic member used may be adjusted according to the weight of the goods. Specifically, a spring with an elastic force slightly smaller than the weight of the article may be provided, so that only articles close to or larger than the weight of the article can trigger the sinking motion of the tray 3, and certain illegal operations can be avoided. For example, the goods are removed and then the empty goods packaging box/bag/bottle is placed. Since the weight of the empty package placed is small and the tray 3 cannot be triggered to sink, it is still possible to obtain a correct judgment that the product has been taken out.
Further, the tray 3 has a first position and a second position, and when the tray 3 moves from the first position to the second position, the monitoring device 2 is triggered to notify the processor. The first position may be a position after the tray 3 performs a lifting operation, and the second position may be a position after the tray 3 performs a sinking operation, or vice versa.
Further, the monitoring device 2 may include: electromagnetic induction device, microswitch or photoelectric coupler.
In the embodiment of the present application, the elastic body 4 may be a return spring when the tray 3 can be displaced under the pressure of the loaded commodity; the elastic body 4 is abutted against the tray 3 for resetting the displacement of the tray 3. The monitoring mechanism may directly monitor the displacement state of the tray body 31 of the tray 3, or may monitor the displacement state of the tray 3 through a trigger 32 provided on the tray 3.
Taking the monitoring device 2 as a microswitch as an example, when the tray 3 moves from the first position to the second position, the microswitch is pressed by the trigger part 32 and then triggered; at this time, the micro switch is turned on, and the signal is transmitted to the processor, whereby the processor can determine that the current position of the tray 3 is in the second position. That is, if the tray 3 is in the first position after being pressed by the product, once the tray 3 returns to the second position, it can be said that the tray 3 is not pressed by the product, that is, the product on the tray 3 is taken out.
Similarly, the trigger portion 32 may be configured to trigger the micro switch when the tray 3 moves from the second position to the first position.
The monitoring device 2 may be an electromagnetic induction device or a photocoupler, and the following description will be made by taking the photocoupler as an example. As shown in fig. 2 and 3, the monitoring mechanism includes a light generator 21 and a light receiver 22, wherein:
when the tray 3 is located at one of the first position and the second position, the trigger portion 32 forms a block to a light path between the light generator 21 and the light receiver 22, and when the tray 3 is located at the other of the first position and the second position, the light generated by the light generator 21 can reach the light receiver 22.
At this time, as shown in fig. 2, the light generator 21 and the light receiver 22 may be oppositely disposed at both sides of the triggering part 32.
Of course, various modifications are possible for the triggering method of the light generator 21 and the light receiver 22 of the present application. For example, the triggering portion 32 may be provided with a reflective surface, when the tray 3 is located at one of the first position and the second position, the light generated by the light generator 21 passes through the reflective surface on the triggering portion 32 and is reflected to reach the light receiver 22, and when the tray 3 is located at the other of the first position and the second position, the light generated by the light generator 21 cannot reach the light receiver 22 due to the movement of the triggering portion 32.
At this time, the light generator 21 and the light receiver 22 may be disposed side by side to save space.
Further, as shown in fig. 1, the vending robot of the present application may further include:
the supporting frame 1 is used for supporting the tray 3 and guiding the movement of the tray 3; a touch control part is arranged on the tray 3; the monitoring device 2 is arranged on the support frame 1.
Further, the support frame 1 may include: a supporting plate 11 and a supporting rod 12, wherein the supporting plate 11 is provided with a through hole through which the tray 3 can pass; one end of the support rod 12 is arranged on the lower end face of the support plate 11, and the other end of the support rod can be fixed in a cabin body of the self-moving cargo selling cabin; the periphery of tray 3 corresponds the position department of bracing piece 12 is equipped with supporting seat 33, it has the through-hole to open on the supporting seat 33, and pass through the through-hole cup joints on bracing piece 12.
In specific implementation, the return spring may be sleeved on the supporting pillar and abutted against the supporting seat 33.
In addition, as shown in fig. 1, the vending robot of the present application may further include:
a bolt 6 and a washer 5. Wherein, the gasket 5 is sleeved on the bolt 6, and the bolt 6 is connected into the support rod 12, so as to position the support seat 33 between the gasket 5 and the support plate 11. In addition, the elastic body 4 may also be sleeved on the bolt 6, one end of the elastic body 4 is supported on the gasket 5, and the other end is abutted against the supporting seat 33, so as to provide a restoring force when the tray 3 is reset.
The movement of the supporting seat 33 and the elastic body 4 is limited by the bolt 6 and the gasket 5, so that the supporting frame 1 is more integrated and modularized, the assembly difficulty is simplified, and the installation cost is reduced.
The monitoring mechanism of the present application may be mounted not only on the support plate 11 as shown in fig. 1 to 3, but also on the tray 3.
When mounted on the tray 3, the monitoring mechanism moves along with the tray 3, and by sensing the relative movement of the external object with respect to the monitoring mechanism, the progress state of the ascending movement and the descending movement of the tray 3 can be accurately known.
In another embodiment of the present application, a method of identifying an article is also disclosed, as shown in fig. 4, including:
and S11, after monitoring signals generated by at least one monitoring device when the corresponding tray acts, determining first load information of each tray.
And S12, identifying the commodity taking and placing information in the self-moving vending cabin according to the first load information of each tray.
That is, by monitoring the displacement state of the tray carrying the commodity under the pressure of the commodity, it is possible to determine whether the commodity is taken out. When a customer takes and puts commodities in the mobile vending cabin, the commodities are taken out, so that the tray acts corresponding to the taking and putting of the commodities to generate first load information, and at the moment, the information of the taking and putting of the commodities in the mobile vending cabin can be identified according to the change of the first loads. According to the pick-and-place information, the counting of the commodities can be obtained. If the tray is monitored to be reset to the position which is not subjected to the pressure of the commodity, the commodity can be judged to be taken out, and if the tray is monitored to be displaced to the position which is subjected to the pressure of the commodity, the commodity is judged to be put back.
Further, the method provided by this embodiment may further include:
and S13, when the pick-and-place information indicates that at least one commodity is taken out, calculating selling price information according to the number of the taken commodities.
Before that, the opening and closing state of the cabin door can be monitored, if the cabin door is monitored to be opened, the commodity monitoring step can be carried out, and if the cabin door is monitored to be closed, the commodity monitoring step is not required.
Accordingly, the embodiment of the application also provides a use scene of the self-moving vending robot as follows:
1. the self-moving vending robot moves to the front of the user to display the commodity, and in the use scene, the vending of the beverage commodity is taken as an example. The movable selling cargo hold is divided into an upper layer and a lower layer, a plurality of bottles of cola are placed in the upper layer, and mineral water is placed in the lower layer.
2. The vision sensor acquires images in the mobile vending cabin, and records and analyzes the content of the images. For example, according to the image analysis result, 13 bottles of cola and 12 bottles of mineral water are also arranged in the mobile vending cabin.
3. The user opens the hatch of the self-moving vending bay, picks and removes a bottle of cola, and closes the hatch.
4. Referring to fig. 2, the tray 3 where the coke is located is bounced upwards due to no longer being pressed by the coke, and the monitoring device 2 feeds back the ascending action of the tray 3 to the processor of the mobile vending robot, so that the processor can know that a bottle of coke has been taken away. The total price of the goods is played in an output device of the vending robot, such as a display and/or a sound box, to remind the user of payment.
5. Of course, if the user changes mind, he may reopen the mobile vending bay, replace the coke in the mobile vending bay, and remove a bottle of mineral water. Referring to fig. 3, after the coke is returned, the lowering of the tray 3 is also fed back to the processor of the self-moving vending robot. The processor can re-bill as the status of the respective tray 3 changes.
In addition, in some embodiments of the present application, the self-moving vending robot may further include at least one of the following sensors:
a weighing sensor, a vision sensor;
the weighing sensor is arranged on the tray 3; the visual sensor is disposed within the self-moving vending bay and directed toward the merchandise within the bay for capturing image information related to the merchandise.
That is, the embodiments of the present application can simultaneously count the commodities by combining the following three counting manners:
(1) the trays 3 are counted.
As described above, since the article on the corresponding tray 3 is taken out by the ascending operation of the tray 3, the taken-out article can be counted.
(2) And counting the weighing mode.
The weight of all the commodities on the platform is weighed, and the number of the taken commodities can be obtained by dividing the reduced weight of the commodities by the weight of each unit of commodity.
(3) And counting the image modes.
The number of different levels of the goods category is identified by means of a visual sensor by means of and/or a machine learning method, so that a count of the goods taken out is obtained.
When a load cell is included, in yet another embodiment of the present application, the method of identifying an item may further include:
s14, after receiving a weighing signal sent by a weighing sensor on at least one tray, determining second load information of each tray; and according to the second load information of each tray, authorizing the pick-and-place information and identifying the types of the picked and placed commodities.
By means of the second load information provided by the weighing sensor, the pick-and-place information can be more accurately checked, preventing counting errors.
When the visual sensor is included, the method of identifying an article may further include:
s15, acquiring image information collected at different moments by a visual sensor in the mobile vending cabin;
s16, carrying out image recognition and comparison on the image information collected at different moments;
and S17, based on the identification and comparison result, approving the pick-and-place information and identifying the type of the picked and placed commodity.
Further, the image information collected at different times includes: the image information collected at the opening time of the cabin door of the self-moving cargo selling cabin and the image information collected at the closing time of the cabin door.
Likewise, based on the results compared by the visual sensor, further verification can be made as to the type of merchandise to ensure that the count is correct. And only the image information collected at the moment when the cabin door is opened and the image information collected at the moment when the cabin door is closed are collected, so that the calculation burden can be reduced and the cost can be reduced on the premise of ensuring the identification precision.
Further, the method for identifying the commodity may further include:
and S18, determining whether the goods in the self-moving vending cabin are abnormally placed according to the image information.
And outputting error reporting information when the commodity placing abnormity is determined. Further, the abnormal condition includes: one or two of the commodity arrangement staggered layer and the commodity arrangement attitude abnormity.
The abnormal placing conditions comprise multiple conditions of staggered placing, toppling placing and the like. The recognition accuracy can be further improved by recognizing the abnormal placement using the image information, compared to other sensors.
Further, when it is determined that there is a commodity placement abnormality, error information is output, including:
s19, when the commodity placement is determined to be abnormal, obtaining the placement position and abnormal conditions of the abnormally placed commodity;
and S110, generating and outputting the error reporting information according to the placing position and the abnormal condition.
The output error reporting information can be played in a voice or screen display mode. The user can correct the placement timely and accurately according to the received error reporting information.
Accordingly, embodiments of the present application present yet another usage scenario of a self-moving vending robot as follows:
1. the self-moving vending robot moves to the front of the user to display the commodity, and in the use scene, the vending of the beverage commodity is taken as an example. The movable selling cargo hold is divided into an upper layer and a lower layer, a plurality of bottles of cola are placed in the upper layer, and mineral water is placed in the lower layer.
2. The vision sensor acquires images in the mobile vending cabin, and records and analyzes the content of the images. For example, according to the image analysis result, 13 bottles of cola and 12 bottles of mineral water are also arranged in the mobile vending cabin.
3. The user opens the hatch of the self-moving vending bay, picks and removes a bottle of cola, and closes the hatch.
4. This tray 3 that coke belongs to upwards bounce owing to no longer receive the pressure of coke, and monitoring devices 2 feeds back to the treater from removing the robot that sells goods after monitoring tray 3's the action that rises, and in view of the above, the treater can learn that a bottle of coke has been taken away. Meanwhile, the processor also knows from the weighing sensor that the weight of the upper layer is reduced by 600g, which is exactly the weight of one bottle of coke, and the visual sensor also shows that one bottle of coke is less on the upper layer. The processor thus alerts the user to pay the total price of a bottle of cola 5 dollars through the output device of the vending robot.
5. The user suddenly changes his mind and does not intend to purchase it. He reopens the door of the mobile sales space and replaces the coke. However, since the movements are hasty, he has a skew of putting the coke. No displacement of the tray 3 occurred despite the weight sensor detecting an increase in the weight of the upper layer of 600 g. At this time, the processor can know that the cola is placed askew through the visual sensor, and can remind the user to re-align the cola through the output device of the automatic vending robot.
6. In practice, the user is likely to place the cola in the lower layer, i.e., the area of mineral water. For such a staggered layer situation, correction can be obtained by means of a load cell and a vision sensor as well.
In the embodiment, by means of mutual compensation of various counting modes, a reasonable and accurate counting result can be obtained under the condition of strong interference, the types and the quantity of the taken-out goods are obtained, and the states of staggered layers, toppling and the like are detected, so that an error prompt is given.
In yet another embodiment of the present application, there is also disclosed a self-moving vending robot comprising:
self-moving cargo sales outlets; the tray 3 is arranged in the self-moving vending cabin and used for bearing commodities; a weighing sensor connected to a processor of the self-moving vending robot for sensing load information of the tray 3; the vision sensor is connected with the processor of the self-moving vending robot and is used for collecting commodity images in the self-moving vending cabin; and the processor is used for identifying the picking and placing information and the types of the commodities in the self-moving vending cabin according to the load information of the tray 3 and the commodity image.
Further, the processor is further configured to determine whether goods in the self-moving vending cabin are abnormally placed according to the goods image; and outputting error reporting information when the commodity placing abnormity is determined.
Further, the processor is further configured to calculate selling price information according to the number of the taken out commodities when the taking and placing information indicates that at least one commodity is taken out.
Accordingly, in another embodiment of the present application, a method of identifying an article is also disclosed. As shown in fig. 5, the method includes:
s21, acquiring load information of each corresponding tray sensed by at least one weighing sensor;
s22, acquiring commodity images in the self-moving vending cabin, which are acquired by at least one visual sensor at different moments;
and S23, identifying the pick-and-place information and the types of the commodities in the self-moving vending cabin according to the load information of at least one tray and the commodity images acquired by at least one visual sensor at different moments.
Further, in the step S23, identifying the pick-and-place information and the types of the commodities in the self-moving vending cabin according to the load information of the at least one tray and the commodity images acquired by the at least one visual sensor at different times may specifically be implemented by the following steps:
according to the load information of the at least one tray, identifying first picking and placing information of commodities in the self-moving vending cabin; respectively identifying and comparing the commodity images acquired by the at least one vision sensor at different moments, and determining second pick-and-place information of the commodities in the self-moving vending cabin based on the identification and comparison results; and integrating the first taking and placing information and the second taking and placing information to obtain the taking and placing information.
In a specific implementation technical solution, the step of "synthesizing the first pick-and-place information and the second pick-and-place information to obtain the pick-and-place information" may include:
comparing the first pick-and-place information with the second pick-and-place information; if the comparison is the same, taking the first taking and placing information or the second taking and placing information as the taking and placing information; and if the comparison is different, selecting one of the first pick-and-place information or the second pick-and-place information as the pick-and-place information according to a preset selection rule.
For example, the preset selection rule is based on the first pick-and-place information sensed by the load cell. The preset selection rule may be set manually, which is not limited in this embodiment.
Further, the method also comprises the following steps:
and when the pick-and-place information represents that at least one commodity with at least one type is taken out, calculating selling price information according to the type and the quantity of the taken-out commodity.
Specifically, the unit price of the commodity can be obtained according to the commodity class of the taken commodity; then, the selling price information can be calculated according to the unit price and the quantity.
Further, the method also comprises the following steps:
determining whether goods in the self-moving vending cabin are abnormally placed according to goods images acquired by at least one visual sensor; and outputting error reporting information when the commodity placing abnormity is determined.
Wherein, the placing abnormality can include but is not limited to: wrong commodity placing position, wrong commodity placing posture and the like.
The counting can be carried out in a weighing mode and a visual mode at the two moments of opening and closing the cabin door, so that the type and the quantity of the goods taken out are judged according to the weight difference and/or the image recognition result.
Taking the counting in a weighing mode as an example, under the condition that the weight of a single commodity is known, the change of the quantity of the commodities can be judged through the weight difference of the commodities in the cabin before and after the opening and closing of the cabin door. If a plurality of bays are provided, the variety and number of the commodities can be determined by loading different kinds of commodities in different bays and monitoring the weight change of each bay.
Taking the example of using the visual counting, since the types of the goods sold in the self-moving vending robot are known, the number of the types of the goods can be determined by the difference of the recognition results of the goods images before and after the opening and closing of the doors of different layers.
Since the weighing sensor only knows the weight of a single commodity, the two commodities with the same weight are staggered, so that the two commodities are difficult to identify, and the two commodities can be distinguished by the aid of the visual sensor. The problem of wrong layer is prevented, and the problem of weighing caused by errors is solved.
In addition, generally, the visual sensor can identify the number of different-layer goods types by using a deep learning and/or machine learning method, but is easy to cause identification errors due to influences of hardware, light, shading and the like. Therefore, missing detection and error detection caused by the image recognition method can be compensated in a weighing mode.
Accordingly, embodiments of the present application present yet another usage scenario of a self-moving vending robot as follows:
1. the self-moving vending robot moves to the front of the user to display the commodity, and in the use scene, the vending of the beverage commodity is taken as an example. The movable selling cargo hold is divided into an upper layer and a lower layer, a plurality of bottles of cola are placed in the upper layer, and mineral water is placed in the lower layer.
2. The vision sensor acquires images in the mobile vending cabin, and records and analyzes the content of the images. For example, according to the image analysis result, 13 bottles of cola and 12 bottles of mineral water are also arranged in the mobile vending cabin.
3. The user opens the hatch of the self-moving vending bay, picks and takes out a bottle of cola and a bottle of mineral water, and closes the hatch.
4. The processor knows from weighing sensor that the weight of upper and lower floor has all alleviateed 600g, and visual sensor has also shown that there is a bottle of coke less in the upper strata, and there is a bottle of mineral water less in the lower floor. The processor thus alerts the user to pay a total of 7 dollars of merchandise through the output device of the vending robot.
5. The user suddenly changes his mind and does not intend to purchase the cola. He reopens the door of the mobile sales space and replaces the coke. But due to hurry, he places the cola in the underlying mineral water.
6. Although the weight sensor detects an increase in the weight of the lower layer by 600g, the image of the returned item detected by the visual sensor does not correspond to mineral water. At this time, an error message is presented to remind the user to correctly replace the commodity.
In yet another embodiment of the present application, there is also disclosed a self-moving vending robot comprising:
self-moving cargo sales outlets; the tray 3 is arranged in the self-moving vending cabin and used for bearing commodities; the commodity identification device is used for monitoring the change information of the commodities on the tray 3; and identifying the picking and placing information of the commodities on the tray according to the change information. The variation information referred to in this embodiment includes, but is not limited to, the weight information of the commodity, the image information of the area where the commodity is located, and the signal duration information of the commodity as the signal source, and the variation information monitored can be selected according to the sensor actually used.
The article identification device of the present embodiment includes, but is not limited to, the aforementioned monitoring device, weighing sensor, visual sensor, and some other feasible devices for identifying an article, such as a two-dimensional code scanning device, a near field communication device, and the like.
Specifically, the tray 3 can make corresponding actions when the goods on the tray are changed; and, the article recognition device may include:
the monitoring device is used for generating a monitoring signal when the tray acts;
and the processor is used for identifying the picking and placing information of the commodities on the tray according to the monitoring signals.
Or further, the article recognition device may include:
a load cell for sensing load variation information of the tray;
the visual sensor is used for acquiring images before and after the change of the commodity on the tray;
the processor is connected with the weighing sensor and the vision sensor and used for identifying the picking and placing information and the types of the commodities on the tray according to the load change information of the tray and the images of the commodities on the tray before and after the change.
The working principles of the tray 3, the monitoring device, the processor, the weighing sensor and the vision sensor have been described in detail in the foregoing embodiments, and are not described herein again.
Also in accordance therewith, in another embodiment of the present application, there is disclosed a method of identifying an article, comprising:
and S31, monitoring the change information of the commodities on the tray.
And S32, identifying the pick-and-place information of the commodities on the tray according to the change information.
The above S31 can be implemented by, but not limited to, the following methods:
in an implementation solution, the tray can move when the load on the tray changes, for example, in the structure shown in fig. 2 and 3 in the above embodiment, when the load of the tray increases, the tray moves downwards; when the load of the tray is reduced, the tray is lifted. Accordingly, the step S31 may specifically be:
s311, after monitoring signals generated when the tray acts, determining the load information of the tray;
and S312, identifying the goods taking and placing conditions on the tray according to the load information of the tray.
Wherein, the monitoring device can be an electromagnetic induction device, a microswitch or a photoelectric coupler. The monitoring device can be triggered to generate the monitoring signal when the tray sinks; or triggered to generate the monitoring signal when the tray makes a lifting action.
In another realizable technical scheme, a vision sensor is arranged in the self-moving vending robot, and a weighing sensor is arranged on the tray. Accordingly, the step S31 may specifically be:
s311', acquiring load information of the tray sensed by the weighing sensor;
s312', acquiring commodity images on the tray, which are acquired by a visual sensor at different moments;
s313', identifying the picking and placing information and the types of the commodities on the tray according to the load information of the tray and the commodity images on the tray at different moments.
The visual sensor may collect the commodity image on the tray at a time when the user opens the door of the self-moving vending robot, and then collect the commodity image on the tray again at a time when the user closes the door. Here, it should be noted that: the specific implementation of the step S313' can refer to the corresponding content in the above embodiments, and is not described herein again.
In addition, the visual sensor can be used for identifying the picking and placing information and the types of the commodities on the tray, and also can be used for identifying whether the placing positions of the commodities are wrong or whether the placing postures of the commodities are abnormal (such as incorrect placing). In specific implementation, the image recognition technology in the prior art can be used for recognizing the commodity types and the placing postures.
In the embodiment, by means of mutual compensation of various counting modes, a reasonable and accurate counting result can be obtained under the condition of strong interference, the types and the quantity of the taken-out goods are obtained, and the states of staggered layers, toppling and the like are detected, so that an error prompt is given.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (21)
1. A self-moving vending robot, comprising:
self-moving cargo sales outlets;
the tray is arranged in the self-moving vending cabin, is used for bearing commodities and makes corresponding actions when the load of the tray changes;
and the monitoring device is connected with the processor of the self-moving vending robot and used for informing the processor when the tray acts so that the processor can identify the pick-and-place information of the commodities in the self-moving vending cabin.
2. The vending robot of claim 1, wherein said tray comprises:
a tray body;
one end of the elastic body is arranged on the tray body, and the other end of the elastic body is arranged in the cabin body of the self-moving cargo selling cabin;
when the load of the tray body is increased, the elastic body deforms, and the tray makes a sinking action;
when the load of the tray body is reduced, the elastic body returns, and the tray makes a lifting action.
3. The vending robot according to claim 2, wherein the elastic modulus of said elastic body is such that: deformation occurs when the load increase of the tray is greater than a threshold value;
the threshold is determined by the weight of the article.
4. The vending robot of claim 2,
the tray has a first position and a second position, and when the tray moves from the first position to the second position, the monitoring device is triggered to notify the processor.
5. The vending robot according to any one of claims 1 to 4, further comprising:
the supporting frame is used for supporting the tray and guiding the action of the tray;
a touch control part is arranged on the tray;
the monitoring device is arranged on the supporting frame.
6. The vending robot of claim 5, wherein said support shelf comprises: the tray comprises a supporting plate and a supporting rod, wherein a through hole through which the tray can pass is formed in the supporting plate; one end of the supporting rod is arranged on the lower end face of the supporting plate, and the other end of the supporting rod is fixed in a cabin body of the self-moving cargo selling cabin;
the supporting seat is arranged at the position, corresponding to the supporting rod, of the periphery of the tray, and a through hole is formed in the supporting seat and is sleeved on the supporting rod through the through hole.
7. The vending robot of any one of claims 1-4, further comprising a sensor connected to the processor, at least one of: a weighing sensor, a vision sensor;
the weighing sensor is arranged on the tray; the visual sensor is disposed within the self-moving vending bay and directed toward the merchandise within the bay for capturing image information related to the merchandise.
8. A method of identifying an article, comprising:
after monitoring signals generated by at least one monitoring device when the corresponding tray acts are monitored, first load information of each tray is determined;
and identifying the picking and placing information of the commodities in the self-moving vending cabin according to the first load information of each tray.
9. The method of identifying an article of merchandise of claim 8, further comprising:
and when the pick-and-place information represents that at least one commodity is taken out, calculating selling price information according to the quantity of the taken-out commodities.
10. The method of identifying an article of claim 8 or 9, further comprising:
after a weighing signal sent by a weighing sensor on at least one tray is received, second load information of each tray is determined;
and according to the second load information of each tray, authorizing the pick-and-place information and identifying the types of the picked and placed commodities.
11. The method of identifying an article of claim 8 or 9, further comprising:
acquiring image information acquired by a visual sensor in a mobile vending cabin at different moments;
carrying out image identification and comparison on the image information acquired at different moments;
and based on the identification and comparison result, the picking and placing information is approved and the categories of the picked and placed commodities are identified.
12. The method of identifying an article of claim 11, wherein the image information captured at different times includes: the image information collected at the opening time of the cabin door of the self-moving cargo selling cabin and the image information collected at the closing time of the cabin door.
13. The method of identifying an article of merchandise of claim 11, further comprising:
determining whether goods in the self-moving vending cabin are abnormally placed according to the image information;
and outputting error reporting information when the commodity placing abnormity is determined.
14. The method of identifying a commodity according to claim 13, wherein outputting error information when it is determined that there is a commodity placement abnormality includes:
when the commodity placement abnormity is determined, the placement position and the abnormal condition of the abnormally placed commodity are obtained;
and generating and outputting the error reporting information according to the placing position and the abnormal condition.
15. The method of identifying merchandise of claim 13, wherein the abnormal condition comprises: one or two of the commodity arrangement staggered layer and the commodity arrangement attitude abnormity.
16. A self-moving vending robot, comprising:
self-moving cargo sales outlets;
the tray is arranged in the self-moving vending cabin and used for bearing commodities;
a weighing sensor connected with the processor of the self-moving vending robot for sensing load information of the tray;
the vision sensor is connected with the processor of the self-moving vending robot and is used for collecting commodity images in the self-moving vending cabin;
and the processor is used for identifying the picking and placing information and the types of the commodities in the self-moving vending cabin according to the load information of the tray and the commodity image.
17. A method of identifying an article, comprising:
acquiring load information of each corresponding tray sensed by at least one weighing sensor;
acquiring commodity images in the self-moving vending cabin, which are acquired by at least one visual sensor at different moments;
and identifying the picking and placing information and the types of the commodities in the self-moving vending cabin according to the load information of at least one tray and the commodity images acquired by at least one visual sensor at different moments.
18. A self-moving vending robot, comprising:
self-moving cargo sales outlets;
the tray is arranged in the self-moving vending cabin and used for bearing commodities;
the commodity identification device is used for monitoring the change information of the commodities on the tray; and identifying the picking and placing information of the commodities on the tray according to the change information.
19. The self-moving vending robot of claim 18, wherein the tray performs a corresponding action when a change in the goods thereon occurs; and the number of the first and second groups,
the article recognition device includes:
the monitoring device is used for generating a monitoring signal when the tray acts;
and the processor is used for identifying the picking and placing information of the commodities on the tray according to the monitoring signals.
20. The self-moving vending robot according to claim 18, wherein the article recognition device comprises:
a load cell for sensing load variation information of the tray;
the visual sensor is used for acquiring images before and after the change of the commodity on the tray;
the processor is connected with the weighing sensor and the vision sensor and used for identifying the picking and placing information and the types of the commodities on the tray according to the load change information of the tray and the images of the commodities on the tray before and after the change.
21. A method of identifying an article, comprising:
monitoring the change information of the commodities on the tray;
and identifying the picking and placing information of the commodities on the tray according to the change information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910044130.8A CN111445624A (en) | 2019-01-17 | 2019-01-17 | Self-moving vending robot and method for identifying goods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910044130.8A CN111445624A (en) | 2019-01-17 | 2019-01-17 | Self-moving vending robot and method for identifying goods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111445624A true CN111445624A (en) | 2020-07-24 |
Family
ID=71653877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910044130.8A Pending CN111445624A (en) | 2019-01-17 | 2019-01-17 | Self-moving vending robot and method for identifying goods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111445624A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207587071U (en) * | 2017-10-30 | 2018-07-06 | 文彬 | A kind of cargo bearing device for Vending Machine |
| CN207587066U (en) * | 2017-12-04 | 2018-07-06 | 文彬 | A kind of Vending Machine and its cargo bearing device |
| CN108335406A (en) * | 2018-02-08 | 2018-07-27 | 合肥美的智能科技有限公司 | Self-service equipment and its good selling method and self-service system |
| CN108564714A (en) * | 2018-04-08 | 2018-09-21 | 合肥美的智能科技有限公司 | Vending cabinet, self-service vending method and control method of server |
| CN209486782U (en) * | 2019-01-17 | 2019-10-11 | 科沃斯商用机器人有限公司 | From mobile vending machine people |
-
2019
- 2019-01-17 CN CN201910044130.8A patent/CN111445624A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207587071U (en) * | 2017-10-30 | 2018-07-06 | 文彬 | A kind of cargo bearing device for Vending Machine |
| CN207587066U (en) * | 2017-12-04 | 2018-07-06 | 文彬 | A kind of Vending Machine and its cargo bearing device |
| CN108335406A (en) * | 2018-02-08 | 2018-07-27 | 合肥美的智能科技有限公司 | Self-service equipment and its good selling method and self-service system |
| CN108564714A (en) * | 2018-04-08 | 2018-09-21 | 合肥美的智能科技有限公司 | Vending cabinet, self-service vending method and control method of server |
| CN209486782U (en) * | 2019-01-17 | 2019-10-11 | 科沃斯商用机器人有限公司 | From mobile vending machine people |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101887685B1 (en) | Vending machine for self service including operating system | |
| CN108875664B (en) | Method and device for identifying purchased goods and vending machine | |
| KR102378059B1 (en) | Weight monitoring-based article detection system and article detection method | |
| CN108549851B (en) | Method and device for identifying goods in intelligent container and intelligent container | |
| WO2019196500A1 (en) | Self-service retail system and control method therefor, vending apparatus and cloud server | |
| US11715082B2 (en) | Shopping cart and system | |
| CN108335406A (en) | Self-service equipment and its good selling method and self-service system | |
| WO2021170126A1 (en) | Product recognition method, product recognition system, and electronic apparatus | |
| CN114548882A (en) | Information management system and method suitable for intelligent inventory management | |
| CN103052343A (en) | A Checkout Counter | |
| CN107590926B (en) | Unattended sales system | |
| CN108564713A (en) | A kind of commodity identification of the unattended retail based on composite measurement mode and anti-cheating system and its method | |
| CN110050284A (en) | Register system in a kind of automatic shop | |
| CN110853235B (en) | Goods feeding method and selling method of vending machine | |
| US11301984B1 (en) | System to determine user interaction with fixture | |
| CN108140188A (en) | Fraud detection system and method | |
| CN209486782U (en) | From mobile vending machine people | |
| CN108205737A (en) | The method and system that a kind of cargo delivery state suitable for unmanned dispensing vehicle monitors | |
| CN108257315A (en) | Logistics station and logistics consignment method | |
| US10540631B1 (en) | System to determine load cell failure | |
| CN113554802B (en) | Weighing device and unmanned vending system | |
| CN113624314B (en) | Weighing processing method and device and weighing equipment | |
| CN111445624A (en) | Self-moving vending robot and method for identifying goods | |
| WO2020086748A1 (en) | Systems and methods for dynamic processing of objects with data verification | |
| US20180225647A1 (en) | Systems and methods for detecting retail items stored in the bottom of the basket (bob) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |