DESC:FIELD OF THE DISCLOSURE
The present disclosure relates to the field of remote shelf-stock monitoring and assessment in the retail industry.

BACKGROUND
In the retail industry, particularly the one where the products to be sold are displayed and made readily available to customers, it is desirable that the products are stocked on shelves (on display or in a store room) beforehand, and immediately restocked upon exhaustion. In retail establishments temporary out-of-stock (OOS) situations are considered to be a problem. It has been estimated that the global average out-of-stock rate is about 8% and it costs retailers about 4% losses in sales.
There can be several reasons for out-of-stock situations. However, it has been estimated that about 70-90% of stock-outs are caused by defective shelf replenishment practices as opposed to 10-30% resulting from the problems in the supply chain. Usually fast moving consumer goods (FMCG) are depleted faster than their replenishment. A solution for this situation is to increase frequency of checking the stock. Usually, checks are carried out by humans at pre-defined intervals in order to reduce the OOS related problems. But, such higher frequency checks by humans typically lead to increased costs and in turn lesser profit margins. Moreover, the data collected through humans can also be erroneous and unreliable. To accommodate these changes, the stock assessment and the retail monitoring methods must be adaptable to provide effective and smooth operation.
Therefore there is felt a need for a system that limits the aforementioned drawbacks by remotely monitoring and assessing stock.

OBJECTS
Some of the objects of the present disclosure aimed to ameliorate one or more problems of the prior art or to at least provide a useful alternative are described herein below:
An object of the present disclosure is to provide a system for remote monitoring and stock assessment.
Another object of the present disclosure is to provide one or more moveable devices for remote monitoring and stock assessment.
Further object of the present disclosure is to provide one or more movable devices that monitor shelves and detect out-of-stock and/or misplaced items.
Yet, another object of the present disclosure is to provide moveable devices for monitoring that can be remotely controlled by human operator and/or can move in a controlled manner.
Still, another object of the present disclosure is to provide moveable devices that can monitor shelves on either side of an aisle simultaneously.
Another object of the present disclosure is to provide a system that collects monitored data and processes the collected data to generate reports and analytics.
Yet, another object of the present disclosure is to provide moveable devices that can provide services like providing useful information to customers, providing automatic check-outs and provide warehouse monitoring and surveillance during night time.
An additional object of the present disclosure is to provide moveable devices that can be used for checking planogram compliance either manually through visual inspection by a remote operator or automatically by running image processing algorithms.
Still, another object of the present disclosure is to provide a graphical user interface (GUI) that allows an operator to remotely control the movable monitoring devices and reflects the actual position of the monitoring devices on a virtual 2D/3D environment in real-time.
Other objects and advantages of the present disclosure will be more apparent from the following description when read in conjunction with the accompanying figures, which are not intended to limit the scope of the present disclosure.

SUMMARY
The present disclosure envisages a system for remote monitoring and assessing stock in an enclosed environment comprising an area of shelves and aisles between the shelves where the shelves are adapted to removably hold the stock comprising clusters of items.
Typically, in accordance with the present disclosure, the system for remote monitoring and assessing stock comprises at least one monitoring device, a controlling device and a comparator. The monitoring device moves between the aisles and collectively provides images of the clusters of items from various angles. The controlling device is configured to control movements of the monitoring device along the aisles and the comparator is configured to compare images of each of the cluster of items provided by the monitoring device with stored images of corresponding clusters of items to determine balance items in the clusters and provide percentage occupancy of shelves and thereby assessing stock.
Further, in accordance with the present disclosure, each of the monitoring devices include a receiver configured to receive commands from the controlling device for controlling movements of the monitoring devices between the aisles, a plurality of sensors configured to sense objects including shelves present in the enclosed environment to avoid collision of the monitoring devices with the objects, a camera configured to capture images of the clusters of items placed on the shelves in various angles and a transmitter configured to collectively transmit images of the clusters of items to the comparator.
Furthermore, in accordance with the present disclosure, the controlling device includes a planogram generator configured to generate planogram of the enclosed environment, an input module configured to accept a set of navigation rules from a user and a processor cooperating with the planogram generator and the input module and configured to provide controlling commands to control movements of the monitoring devices with respect to the planogram in response to the navigation rules.
In accordance with the present invention, there is provided a method for remote monitoring and assessing stock in an enclosed environment comprising an area of shelves and aisles between the shelves where the shelves are adapted to removably hold the stock comprising clusters of items. The method comprises the following:
• collectively providing images of the clusters of items from various angles with the help of at least one monitoring device moving between the aisles;
• controlling movements of the monitoring device along the aisles; and
• comparing images of each of the cluster of items provided by the monitoring device with stored images of corresponding clusters of items for determining balance items in the clusters and providing percentage occupancy of shelves thereby assessing stock.
Additionally, in accordance with the present disclosure, each of the monitoring devices comprises the steps of:
• receiving commands for controlling movement of the monitoring devices between the aisles;
• sensing objects including shelves present in the enclosed environment to avoid collision of the monitoring devices with the objects;
• capturing images of the clusters of items placed on the shelves in various angles; and
• collectively transmitting images of the clusters of items for comparison.
Further, in accordance with the present disclosure, the controlling device comprises the steps of:
• generating planogram of the enclosed environment;
• accepting a set of navigation rules from a user; and
• providing controlling commands to control movements of the monitoring devices with respect to the planogram in response to the navigation rules.

BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS
A computer implemented system for remote monitoring and stock assessment of the present disclosure will now be described with the help of accompanying drawings, in which:
Figure 1 illustrates a schematic of an embodiment of the system for remote monitoring and assessing stock in an enclosed environment comprising an area of shelves and aisles between the shelves.
Figure 2 illustrates a schematic of an embodiment of a retail framework that uses monitoring devices for monitoring and survey.
Figure 3 illustrates the schematic of an embodiment of a monitoring device and its communication with an operator through a graphical user interface.
Figure 4 illustrates an exemplary embodiment of a 2D grid map used for achieving synchronization in real time between an actual monitoring device and a virtual monitoring device.
DETAILED DESCRIPTION
A preferred embodiment of the present disclosure will now be described in detail with reference to the accompanying drawings. The preferred embodiment does not limit the scope and ambit of the disclosure. The description provided is purely by way of example and illustration.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The present disclosure envisages a system for automating data collection and carrying out surveys/checks in a retail store with the help of monitoring devices capable of movements. In one embodiment, these monitoring devices are robots that can be used for automated monitoring and stock assessment. According to the present disclosure, one or more monitoring devices that can be tele-operated from a remote location are deployed in the retail store to reduce the amount of manpower needed for carrying out checks/surveys. This increases the number of surveys that can be carried out in a given time interval which in turn results in lesser losses caused by out-of-stock (OOS) situations. The monitoring device envisaged by the present disclosure can move in autonomous or semi-autonomous mode to record images and/or videos of the racks/shelves in order to check the presence and/or absence of the items. These recorded images and/or videos are then processed over a remote server to generate analytics useful in assessing profits and losses of the retail store. Typically, the stock assessment data collected by the monitoring devices tends to be accurate as compared to the data collected by humans. Frequency of this stock assessment is also higher when the monitoring devices are used. Additionally, use of the monitoring devices provides flexibility to monitor/check a shelf on-demand whenever needed.
The monitoring device envisaged in the present disclosure is operated/ controlled by an operator through a console with a virtual 3D/2D environment of the retail store. This virtual environment is also made available as a web-based graphical user interface (GUI) to the operator which enables the operator to access the system of the present disclosure over Internet irrespective of the operating system used. Actual real-time position of the monitoring device is updated continuously on this virtual environment. The operator can run the monitoring device in an autonomous or tele-operated mode depending on the situation. In the day time, when customers are present in the retail store, the operator may like to check a particular shelf using the monitoring device through a tele-operated mode. On the other hand, the operator can run the monitoring device in an autonomous mode at night to collect images and/or videos from all the shelves by moving the monitoring device around the retail store. In both the cases, the monitoring devices must avoid obstacles and collisions with animate and/or inanimate objects, for this the monitoring devices co-operate with an obstacle detection and collision avoidance module. The monitoring device can also raise an alarm, with the help of indicators on the remote console or on the web-based GUI, in case of an empty shelf or misplaced item(s) by detecting these situations through image processing techniques. A single operator sitting at one location can thus monitor multiple shelves or multiple stores through multiple monitoring device interfaces. The data collected by such monitoring devices is then processed on a remote server for further analysis.
In one embodiment, the present disclosure proposes the use of a monitoring device to automate data collection in a retail store environment. The monitoring device envisaged in the present disclosure collects images and/or videos of the shelves, which are then processed in order to generate several analytics. These analytics are useful in carrying out frequent checks/surveys which in turn limit the cost per survey. Additionally, the possibility of human error is limited due to the use of the monitoring devices. These monitoring devices can also provide additional services to the customers for a better shopping experience. The monitoring devices can provide useful information to customers in the form of promotions or discounts; they can also allow automatic check-out in order to avoid queues at point of sales (POS) counters.
Referring to accompanying drawings, Figure 1 illustrates a schematic of an embodiment of the system for remote monitoring and assessing stock in an enclosed environment. The enclosed environment is an area containing shelves and aisles between the shelves. These shelves removably hold the stock which is essentially plurality of clusters of items. The system 10 includes at least one monitoring device 20 that moves between the aisles in order to assess stock. The monitoring devices 20 present in the system 10 each include a receiver 22 to receive controlling commands from a controlling device 30 present in the system 10. Based on the controlling commands, the monitoring devices 20 move about in the enclosed environment and capture images, in various angles, of the clusters of items placed on the shelves with the help of cameras 26 included in each of the monitoring devices 20. The monitoring devices 20 also include a plurality of sensors 24 to sense objects including shelves present in the enclosed environment to avoid collision of monitoring devices 20 with the objects. A transmitter 28 present in each of the monitoring devices 20 collectively transmits the captured images of the clusters of items to a comparator 40. The movements of the monitoring devices 20 along the aisles are controlled by the controlling device 30. This controlling device 30 includes a planogram generator 31 which generates planogram of the enclosed environment, an input module 32 which accepts a set of navigation rules from a user and also includes a processor 34 that provides controlling commands to control movements of the monitoring devices 20 with respect to the accepted planogram in response to the navigation rules. The system 10 can also accept planogram from the user though the input module 32 or other source. The planogram can also be used for verifying planogram compliance. The system 10 includes a repository 50 that stores images of corresponding clusters of items for determining balance items in order to assess stock. The images provided by the transmitter 28 to the comparator 40 are compared by the comparator 40 with stored images of corresponding clusters of items from the repository 50 to determine balance items in the clusters and thereby assess stock. Percentage occupancy is also determined based on the balance items. The comparator 40 also compares the provided images with the corresponding stored images to determine misplaced items. In one embodiment, the system 10 uses various image processing techniques to determine misplaced items. The system 10 includes a report generation module 60 that receives information related to the assessed stock from the comparator 40 and generates analytical reports providing stock assessment.
The cameras 26 attached to the monitoring devices 20 enable them to capture and provide images of the clusters of items placed on shelves on either side of the aisles simultaneously.
Referring to accompanying drawings, Figure 2 illustrates a schematic of an embodiment of a retail framework that uses monitoring devices for monitoring and survey. Monitoring devices 100 used in a retail store can be controlled and managed by a remote call center 300 that provides round-the-clock service. The product manufacturers 400 can obtain survey reports 3 from these call centers 300 as and when required. A customer 200 can obtain various product related information 2 from the call centers 300 through telephone calls or from servers 500 using mobile phone applications 5. The customer 200 can also get the real-time data availability of a product 1 from the nearest store through the use of this system. The retail stores with the help of monitoring devices 100 co-ordinate with the product manufacturers 400 to recognize the supply/demand chain 4 and also co-ordinate with the server 500 to provide to the server 500 information collected 8 related to the availability of the products in the store. The server 500 in turn processes the available information to provide data analytics 7 to the product manufactures 400 and co-ordinates with the call centers 300 to provide and receive service and maintenance information 6.
Referring to the accompanying drawings, Figure 3 illustrates the schematic 1000 of an embodiment of a monitoring device and its communication with an operator through a graphical user interface. The schematic 1000 includes two parts - a physical system consisting of a monitoring device 1002 and a virtual environment with graphical user interface (GUI) 1004. These two systems communicate over a wireless network and consist of three basic components: a server, a client and a communication network. In one embodiment of the present disclosure, the monitoring device 1002 employed in a retail store acts as a server and a remote machine acts as a client. Virtual environment/GUI 1004 of the retail store and an operator console runs on this remote client machine. The device of the present disclosure has three important modules which comprise of several nodes running either on the server or on one of the many clients. The first module is a navigation module which is used for autonomous navigation of the monitoring device 1002. The second module updates position of the monitoring device 1002 in a virtual 3D environment. Typically, this is achieved using a Gazebo simulator. Typically, Dijkstra algorithm can also be implemented to find path between the current node (cell) and the goal node. Odometry is obtained from on-board sensors and is used to find the nearest cell in a 2D grid. The third module runs the virtual environment/graphical user interface (GUI) 1004 through which the operator can control the actual monitoring device 1002. The virtual environment/ graphical user interface 1004 runs as a node talker which provides goals to the monitoring device 1002 and can also be used for capturing live images and/or videos on demand.
The graphical user interface 1004 is thus by an operator to control or monitor the monitoring device 1002 located at a remote retail store. It is also possible for the operator to provide pre-defined goal locations for autonomous monitoring device 1002 navigation. Apart from viewing the views transmitted from on-board cameras of the monitoring device 1002, the updated monitoring device position is presented in the 3D virtual environment.
A 3D store model is created of the retail store, where, the store model needs to mirror the real store in terms of its structural and interior layout and have items on virtual shelves placed according to the stores planogram. Both of these requirements aid the remote operator’s tasks of controlling the monitoring device 1002 and determining whether the items have been placed on shelves correctly. A floor plan of the store is used to compute its structural layout wherein the walls are represented as thick, straight lines in the plan and symbols or geometric shapes are used to represent other objects such as racks. These are detected in the floor plan image using simple algorithms for line and shape detection. Typically, a Hough transform and template matching can be used for the same. Once the positions of walls are known, these are extruded to form a basic 3D model of the store’s structural layout. Models from this layout are then built procedurally as functions of the dimensions and number of shelves in each rack. Textures and colors are assigned using real world photos of the store if available, or else by using a default set to create a final model. Other objects such as a checkout counter, line of shopping carts are added if desired. An ordering is assigned to the shelves in accordance with that used in the store’s planogram. Further, 3D models of the items in the store are constructed and a database of models is formed. The mapping of items to shelves is obtained from the planogram and is used to automatically place the 3D models of items on the correct shelf in the 3D model. Thus a 3D model of the store is built which can be used in a virtual environment 1004 for controlling the monitoring device 1002.
Once the model is created, the simulated monitoring device 1002 and the actual monitoring device 1002 can be driven with the same velocity. However, the same velocity leads to a motion that is different from a motion in the virtual world. This is due to the fact that the physical properties of the virtual environment might differ from those of the actual world. In order to synchronize the motion of the monitoring device between the real and the virtual world, two separate velocity nodes are created where one node drives the actual monitoring device and the other node drives the virtual monitoring device. The motion commands for the virtual monitoring device are generated and a virtual 2D space is divided into equally spaced grids. Figure 4 of the accompanying drawings illustrates an exemplary embodiment of a virtual 2D space. Real time monitoring device coordinates are obtained from the corrected odometry and the shortest path between current location of the monitoring device in the virtual world and the goal position of the real monitoring device is then obtained with the help of this virtual 2D space.
A map of the virtual environment is created, and a depth map obtained by sensors is used as a fake laser scan for generating the map. Once the map is available, current laser scan is used for localizing the monitoring device wherein the monitoring device position is obtained from the corrected odometry. External surveillance cameras present in stores can also be used for increasing the accuracy of monitoring device localization.
The position of the monitoring device is updated regularly in the virtual environment available at the operator’s console/ GUI. Rendering and updating information in a 3D environment requires computational resources, hence, when a 3D environment may not be needed, only the location of the monitoring device can be shown in a 2D grid map.
Referring to the accompanying drawings, Figure 4 illustrates an exemplary embodiment of a 2D grid map used for achieving synchronization in real time between an actual monitoring device and a virtual monitoring device. In Figure 4, 4a displays the last location of a virtual monitoring device, 4b is the path obtained using Dijkstra algorithm, 4c are the cells that are traversable and 4d is the new location obtained from actual monitoring device. The 2D grid map updates and synchronizes position of the virtual monitoring device with respect to position of the actual monitoring device. The available area is divided into grids. The grids that are partially occupied and are smaller than the dimension of monitoring device are considered as non-traversable. In one embodiment, once the new position is obtained from the actual monitoring device, the path between the current virtual monitoring device location on the 2D map and the closest cell corresponding to the new position is computed using Dijkstra path planning algorithm. Since the actual odometry is erroneous, the corrected odometry of the actual monitoring device is obtained with the help of simultaneous localization and mapping (SLAM) technique.
The moveable monitoring devices of the system of the present disclosure provide arrangement of products on the shelves. In one embodiment, this is achieved by fitting a bounding box around each of the product thereby allowing the identification of each product. Once every product is identified and their arrangement is known, the product placement is controlled.
According to the present disclosure, the operator has flexibility of viewing and storing images and/or videos as seen by the on-board cameras of the monitoring device. This human in-loop solution provides a system with limited possibilities of errors.
TECHNICAL ADVANCEMENTS
The technical advancements offered by the present disclosure include the realization of:
• a system for remote monitoring and stock assessment;
• moveable devices for remote monitoring and stock assessment;
• one or more moveable devices that monitor shelves and detect out-of-stock and/or misplaced items;
• moveable devices for monitoring that can be remotely controlled by a human operator
• moveable devices that can monitor shelves on either side of an aisle simultaneously;
• a system that collects monitored data and processes the collected data to generate reports and analytics;
• moveable devices that can provide services like providing useful information to customers, providing automatic check-outs and provide warehouse monitoring and surveillance during night time;
• moveable devices that can be used for checking planogram compliance either manually through visual inspection by a remote operator or automatically by running image processing algorithms;
• a graphical user interface (GUI) that allows an operator to remotely control the monitoring devices and reflects the actual position of the monitoring devices on a virtual 2D/3D environment in real-time;
• moveable devices that provide the arrangement of products;
• moveable devices that can be controlled / operated through an operating system independent web interface.
The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein. ,CLAIMS:1. A computer implemented system for remote monitoring and assessing stock in an enclosed environment comprising an area of shelves and aisles between the shelves, said shelves adapted to removably hold said stock comprising clusters of items, said system comprising:
• at least one monitoring device adapted to move between the aisles and collectively provide images of the clusters of items from various angles;
• a controlling device configured to control movements of said at least one monitoring device along the aisles; and
• a comparator configured to compare images of each of the cluster of items provided by said at least one monitoring device with stored images of corresponding clusters of items to determine balance items in the clusters and provide percentage occupancy of shelves and thereby assess stock.

2. The system as claimed in claim 1, wherein said at least one monitoring device comprises:
• a receiver configured to receive commands from said controlling device for controlling movement of said at least one monitoring device between the aisles;
• a plurality of sensors configured to sense objects including shelves present in the enclosed environment to avoid collision of said at least one monitoring device with the objects;
• a camera configured to capture images of said clusters of items placed on the shelves in various angles; and
• a transmitter configured to collectively transmit images of the clusters of items to said comparator.

3. The system as claimed in claim 1, wherein said controlling device comprises:
• a planogram generator configured to generate planogram of the enclosed environment;
• an input module configured to accept a set of navigation rules from a user; and
• a processor cooperating with the planogram generator and the input module and configured to provide controlling commands to control movements of said at least one monitoring device with respect to said planogram in response to said navigation rules.

4. The system as claimed in claim 1, wherein said system comprises a repository configured to store said images of corresponding clusters of items for determining balance items.

5. The system as claimed in claim 1, wherein said comparator compares said provided images with the corresponding stored images to determine misplaced items.

6. The system as claimed in claim 1, wherein said system comprises a report generation module cooperating with the comparator to receive information related to said assessed stock and configured to generate analytical reports providing stock assessment.

7. The system as claimed in claim 1, wherein said system simultaneously provides images of the clusters of items placed on shelves on either side of the aisles.

8. The system as claimed in claim 1, wherein said system comprises a graphical user interface configured to allow a user to remotely control said at least one monitoring device and also configured to display actual position of said monitoring device on a virtual environment in real-time.
9. The system as claimed in claim 1, wherein said system utilizes image processing techniques to determine misplaced items.

10. The system as claimed in claim 3, wherein said input module is configured to accept planogram of the enclosed environment from a user.

11. A computer implemented method for remote monitoring and assessing stock in an enclosed environment comprising an area of shelves and aisles between the shelves, said shelves adapted to removably hold said stock comprising clusters of items, said method comprising the following:
• collectively providing images of the clusters of items from various angles with the help of at least one monitoring device moving between the aisles;
• controlling movements of said at least one monitoring device along the aisles; and
• comparing images of each of the cluster of items provided by said at least one monitoring device with stored images of corresponding clusters of items for determining balance items in the clusters and providing percentage occupancy of shelves thereby assessing stock.

12. The method as claimed in claim 10, wherein said plurality of monitoring devices comprise the following:
• receiving commands for controlling movement of said at least one monitoring device between the aisles;
• sensing objects including shelves present in the enclosed environment to avoid collision of said at least one monitoring device with the objects;
• capturing images of said clusters of items placed on the shelves in various angles; and
• collectively transmitting images of the clusters of items for comparison.

13. The method as claimed in claim 10, wherein said controlling device comprises the following:
• generating planogram of the enclosed environment;
• accepting a set of navigation rules from a user; and
• providing controlling commands to control movements of said at least one monitoring device with respect to said planogram in response to said navigation rules.

14. The method as claimed in claim 10, wherein said method comprises step of receiving information related to said assessed stock and generating analytical reports providing stock assessment.

15. The method as claimed in claim 10, wherein said method includes step of simultaneously providing images of the clusters of items placed on shelves on either side of the aisles.

16. The method as claimed in claim 10, wherein said method comprises step of remotely controlling said at least one monitoring device and displaying actual position of said monitoring device on a virtual environment in real-time.

17. The method as claimed in claim 10, wherein said method comprises step of storing said images of corresponding clusters of items for determining balance items.

18. The method as claimed in claim 10, wherein said method includes step of comparing said provided images with the corresponding stored images to determine misplaced items.

19. The method as claimed in claim 10, wherein said method utilizes image processing techniques to determine misplaced items.

20. The method as claimed in claim 13, wherein said method includes step of accepting planogram of the enclosed environment from a user.