System and method for categorizing unsegregated healthcare supplies into predefined storage chambers using healthcare supply metadata

1 . A system for categorizing unsegregated healthcare supplies into predefined storage chambers using healthcare supply metadata, the system comprising:

an input container configured to receive and retain the unsegregated healthcare supplies;

one or more robotic manipulators configured with one or more actuators, one or more end-effectors, and one or more manipulator image capturing units, to move in at least three degrees of freedom for gripping and releasing at least one healthcare supply from the unsegregated healthcare supplies in the input container;

an inspection chamber operatively positioned proximate to the input container, configured to receive the at least one healthcare supply from the input container through the one or more robotic manipulators for inspecting the at least one healthcare supply for extracting the healthcare supply metadata;

one or more inspection image capturing units operatively positioned at one or more defined angles with reference to the inspection chamber, configured to capture multi-perspective healthcare supply images of the at least one healthcare supply positioned on the inspection chamber;

a plurality of storage chambers operatively positioned proximate to one of the input container or the inspection chamber, each storage chamber of the plurality of storage chambers operatively coupled to a chamber positioning mechanism configured to selectively position the predefined storage chambers within the plurality of storage chambers into an access position for receiving the at least one healthcare supply from the one or more robotic manipulators;

one or more hardware processors;

a non-transitory memory unit operatively connected to the one or more hardware processors, wherein the non-transitory memory unit comprises a set of computer-readable instructions in form of a plurality of subsystems, configured to be executed by the one or more hardware processors, wherein the plurality of subsystems comprises:

a data obtaining subsystem configured to obtain positional data associated with the one or more robotic manipulators and the predefined storage chambers, color data and depth data from the one or more manipulator image capturing units, the multi-perspective healthcare supply images and orientation data from the one or more inspection image capturing units, storage chamber metadata associated with the plurality of storage chambers, and pressure sensor data associated with the one or more end-effectors;

a manipulator triggering subsystem configured to generate a control command to trigger the one or more actuators for providing a motion to the one or more robotic manipulators based on the positional data, the color data and the depth data to reach towards the at least one healthcare supply in the input container;

an end-effector actuation subsystem configured to operate the one or more end-effectors based on the pressure sensor data for performing gripping the at least one healthcare supply from the input container and the inspection chamber, and releasing the at least one healthcare supply in the inspection chamber and the predefined storage chambers;

a data extraction subsystem configured with one or more artificial intelligence (AI) models to process the multi-perspective healthcare supply images for extracting the healthcare supply metadata;

the manipulator triggering subsystem configured to modify the control command based on the orientation data to change an orientation of the at least one healthcare supply using the one or more robotic manipulators, to capture additional multi-perspective healthcare supply images if the multi-perspective healthcare supply images are inadequate for extracting the healthcare supply metadata;

a data mapping subsystem configured to map the extracted healthcare supply metadata with the storage chamber metadata associated with the plurality of storage chambers to determine the predefined storage chambers for receiving the at least one healthcare supply;

a chamber actuating subsystem configured to operate the chamber positioning mechanism to actuate the predefined storage chambers into the access position for receiving the at least one healthcare supply based on mapping analysis performed by the data mapping subsystem, between the extracted healthcare supply metadata and the storage chamber metadata; and

the manipulator triggering subsystem configured to:

generate the control command to trigger the one or more actuators; and

cause the one or more actuators to provide the motion to the one or more robotic manipulators based on the positional data associated with the predefined storage chambers for releasing the at least one healthcare supply into the predefined storage chambers to categorize the unsegregated healthcare supplies.

2 . The system of claim 1 , wherein the one or more actuators comprise at least one of: a stepper motor, a servo motor, a linear actuator, a pneumatic actuator, and a hydraulic actuator.

3 . The system of claim 1 , wherein the one or more end-effectors comprise at least one of: a suction-based gripper, a mechanical gripper, and a hybrid gripper.

4 . The system of claim 1 , wherein the at least three degrees of freedom provided by the one or more actuators operatively coupled to a mechanical transmission assembly configured to generate the motion across multiple axes,

the mechanical transmission assembly comprises at least one of: manipulator assembly, linkages, gear trains, cam systems, differential mechanisms, clutches, timing belts, and timing pulleys.

5 . The system of claim 1 , wherein the one or more manipulator image capturing units and the one or more inspection image capturing units comprise at least one of: a Red-Green-Blue (RGB) camera, a Red-Green-Blue with Depth (RGB-D) camera, a depth sensor, a stereo vision camera, a multi-spectral imaging camera, and a thermal imaging camera.

6 . The system of claim 1 , wherein

the inspection chamber is formed of a transparent material selected from a group comprises one of: glass, acrylic, polycarbonate, and transparent polymer, for enabling unobstructed multi-perspective imaging of the at least one healthcare supply by the one or more inspection image capturing units; and

the inspection chamber operatively coupled to a rotating mechanism configured to rotate the inspection chamber about a predetermined axis for capturing the multi-perspective healthcare supply images of the at least one healthcare supply.

7 . The system of claim 1 , wherein each storage chamber of the plurality of storage chambers configured with a unique chamber identifier,

each storage chamber with the unique chamber identifier mapped with the storage chamber metadata,

the storage chamber metadata comprises at least one of: a healthcare supply name, a dosage strength, a lot number, an expiry date, a manufacturer identifier, a barcode value, a quick response (QR) code value, and a healthcare supply category identifier, generated based on user-defined sorting rules input through a user interface.

8 . The system of claim 1 , wherein the chamber positioning mechanism comprises at least one of: a linear sliding mechanism, a rotary carousel mechanism, a scissor-lift mechanism, a spring-loaded pop-out mechanism, and an elevator mechanism.

9 . The system of claim 1 , wherein the positional data is obtained from one or more of: encoder feedback signals generated by encoders operatively associated with the one or more actuators, limit switch signals defining reference positions of the one or more robotic manipulators and the chamber positioning mechanism, step count data generated by actuator drives of the one or more actuators, and the depth data captured by the one or more manipulator image capturing units.

10 . The system of claim 1 , wherein the manipulator triggering subsystem further configured to:

process the positional data using a mathematical representation model to determine a current location of the one or more robotic manipulators;

process the color data and the depth data using a vision-based object detection model associated with the one or more artificial intelligence (AI) models to determine a target location of the at least one healthcare supply within the input container; and

generate the control command by computing a motion trajectory from the current location to the target location using a motion planning model associated with the one or more artificial intelligence (AI) models, the motion planning model comprising at least one of: an inverse kinematics solver, a trajectory optimization model, and a reinforcement learning-based motion policy.

11 . The system of claim 1 , wherein the end-effector actuation subsystem is further configured to:

process the pressure sensor data by monitoring one of: vacuum levels in the suction-based gripper and gripping force in the mechanical gripper, to compare the monitored one of: the vacuum levels and the gripping force against predefined threshold values to verify successful gripping and releasing of the at least one healthcare supply; and

modify the control command to initiate one of: a re-grasp sequence and a repositioning sequence based on:

the pressure sensor data indicating one of: an ineffective gripping and releasing; and

comparative analysis between one of: the vacuum levels and the gripping force against the predefined threshold values,

the predefined threshold values generated based on historical pressure sensor data associated with gripping of the unsegregated healthcare supplies.

12 . The system of claim 1 , wherein the one or more artificial intelligence (AI) models in the data extraction subsystem comprises at least one of:

an image segmentation model trained to segment label region on the multi-perspective healthcare supply images from nearby packaging information;

an object detection model trained to localize alphanumeric text within the segmented label regions to extract the healthcare supply metadata;

an optical character recognition (OCR) model trained to extract the alphanumeric text from the multi-perspective healthcare supply images;

a barcode or quick response (QR) code recognition model to decode machine-readable identifiers for extracting the healthcare supply metadata;

a vision-language model configured to interpret at least one of: textual features and visual features in combination to extract the healthcare supply metadata; and

a unit-count estimation model configured to identify healthcare supply boundaries within the multi-perspective healthcare supply images for generating healthcare supply count data based on the identified healthcare supply boundaries.

13 . The system of claim 1 , wherein the data mapping subsystem further configured to:

perform the mapping by comparing the extracted healthcare supply metadata against the storage chamber metadata using at least one of: direct string-matching procedure, barcode matching procedure, quick response (QR) code matching procedure, numerical matching procedure, and fuzzy logic-based matching procedure of textual data; and

assign the at least one healthcare supply to a default storage chamber within the plurality of storage chambers designated for unrecognized healthcare supplies if metadata correlation is absent between the extracted healthcare supply metadata and the storage chamber metadata; and

assign the at least one healthcare supply to a trash storage chamber within the plurality of storage chambers if the extracted healthcare supply metadata indicates the at least one healthcare supply is one of: expired, damaged, excluded from restocking based on supply characteristics, and nominal consumed.

14 . A method for categorizing unsegregated healthcare supplies into predefined storage chambers using healthcare supply metadata, the method comprising:

receiving, in an input container, the unsegregated healthcare supplies;

moving one or more robotic manipulators configured with one or more actuators, one or more end-effectors, and one or more manipulator image capturing units, at least three degrees of freedom to grip and release at least one healthcare supply within the unsegregated healthcare supplies;

inspecting, in an inspection chamber, the at least one healthcare supply from the input container to extract the healthcare supply metadata;

capturing, by one or more inspection image capturing units, multi-perspective healthcare supply images of the at least one healthcare supply positioned on the inspection chamber;

obtaining, by one or more hardware processors through a data obtaining subsystem, positional data associated with the one or more robotic manipulators and the predefined storage chambers, color data and depth data from the one or more manipulator image capturing units and the one or more inspection image capturing units, the multi-perspective healthcare supply images and orientation data from the one or more inspection image capturing units, storage chamber metadata associated with a plurality of storage chambers, and pressure sensor data associated with the one or more end-effectors;

generating, by the one or more hardware processors through a manipulator triggering subsystem, a control command to trigger the one or more actuators for providing the motion to the one or more robotic manipulators based on the positional data, the color data and the depth data to reach towards the at least one healthcare supply in the input container;

operating, by the one or more hardware processors through an end-effector actuation subsystem, the one or more end-effectors based on the pressure sensor data to perform gripping of the at least one healthcare supply from the input container and the inspection chamber, and releasing the at least one healthcare supply in the inspection chamber and the predefined storage chambers;

processing, by the one or more hardware processors through a data extraction subsystem with one or more artificial intelligence (AI) models, the multi-perspective healthcare supply images to extract the healthcare supply metadata;

modifying, by the one or more hardware processors through the manipulator triggering subsystem, the control command based on the orientation data to change an orientation of the at least one healthcare supply using the one or more robotic manipulators, to capture additional multi-perspective healthcare supply images if the multi-perspective healthcare supply images are inadequate to extract the healthcare supply metadata;

mapping, by the one or more hardware processors through a data mapping subsystem, the extracted healthcare supply metadata with the storage chamber metadata associated with the plurality of storage chambers to determine the predefined storage chambers to receive the at least one healthcare supply;

operating, by the one or more hardware processors through a chamber actuating subsystem, the chamber positioning mechanism to actuate the predefined storage chambers into the access position for receiving the at least one healthcare supply based on mapping analysis performed by the data mapping subsystem, between the extracted healthcare supply metadata and the storage chamber metadata;

generating, by the one or more hardware processors through the manipulator triggering subsystem, the control command to trigger the one or more actuators; and

providing, by the one or more hardware processors through the manipulator triggering subsystem, the motion to the one or more robotic manipulators based on the positional data associated with the predefined storage chambers to release the at least one healthcare supply into the predefined storage chambers to categorize the unsegregated healthcare supplies.

15 . The method of claim 14 , further comprises:

generating, through a user interface, user-defined sorting rules to map the storage chamber metadata with a unique chamber identifier associated with each storage chamber of the plurality of storage chambers,

the storage chamber metadata comprises at least one of: a healthcare supply name, a dosage strength, a lot number, an expiry date, a manufacturer identifier, a barcode value, a quick response (QR) code value, and a healthcare supply category identifier.

16 . The method of claim 14 , further comprises:

processing, by the one or more hardware processors through the manipulator triggering subsystem, the positional data using a mathematical representation model to determine a current location of the one or more robotic manipulators;

processing, by the one or more hardware processors through the manipulator triggering subsystem, the color data and the depth data using a vision-based object detection model associated with the one or more artificial intelligence (AI) models to determine a target location of the at least one healthcare supply within the input container; and

generating, by the one or more hardware processors through the manipulator triggering subsystem, the control command by computing a motion trajectory from the current location to the target location using a motion planning model associated with the one or more artificial intelligence (AI) models, the motion planning model comprising at least one of: an inverse kinematics solver, a trajectory optimization model, and a reinforcement learning-based motion policy.

17 . The method of claim 14 , further comprises:

processing, by the one or more hardware processors through the end-effector actuation subsystem, the pressure sensor data by monitoring one of: vacuum levels in the suction-based gripper and gripping force in the mechanical gripper to compare the monitored one of: the vacuum levels and the gripping force against predefined threshold values to verify successful gripping and releasing of the at least one healthcare supply; and

modifying, by the one or more hardware processors through the end-effector actuation subsystem, the control command to initiate one of: a re-grasp sequence and a repositioning sequence based on:

the pressure sensor data indicating one of: an ineffective gripping and releasing; and

comparative analysis between one of: the vacuum levels and the gripping force against the predefined threshold values,

the predefined threshold values generated based on historical pressure sensor data associated with gripping of the unsegregated healthcare supplies.

18 . The method of claim 14 , wherein the one or more artificial intelligence (AI) models in the data extraction subsystem comprises at least one of:

an image segmentation model trained to segment label region on the multi-perspective healthcare supply images from nearby packaging information;

an object detection model trained to localize alphanumeric text within the segmented label regions to extract the healthcare supply metadata;

an optical character recognition (OCR) model trained to extract the alphanumeric text from the multi-perspective healthcare supply images;

a barcode or quick response (QR) code recognition model to decode machine-readable identifiers for extracting the healthcare supply metadata;

a vision-language model configured to interpret at least one of: textual features and visual features in combination to extract the healthcare supply metadata; and

a unit-count estimation model configured to identify healthcare supply boundaries within the multi-perspective healthcare supply images for generating healthcare supply count data based on the identified healthcare supply boundaries.

19 . The method of claim 14 , further comprises:

performing, by the one or more hardware processors through the data mapping subsystem, the mapping by comparing the extracted healthcare supply metadata against the storage chamber metadata using at least one of: direct string-matching procedure, barcode matching procedure, quick response (QR) code matching procedure, numerical matching procedure, and fuzzy logic-based matching procedure of textual data; and

assigning, by the one or more hardware processors through the data mapping subsystem, the at least one healthcare supply to a default storage chamber within the plurality of storage chambers designated for unrecognized healthcare supplies if metadata correlation is absent between the extracted healthcare supply metadata and the storage chamber metadata; and

assigning, by the one or more hardware processors through the data mapping subsystem, the at least one healthcare supply to a trash storage chamber within the plurality of storage chambers if the extracted healthcare supply metadata indicates the at least one healthcare supply is one of: expired, damaged, excluded from restocking based on supply characteristics, and nominal consumed.

20 . A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to perform operations for categorizing unsegregated healthcare supplies into predefined storage chambers using healthcare supply metadata, the operations comprising:

obtaining positional data associated with one or more robotic manipulators and the predefined storage chambers, color data and depth data from one or more manipulator image capturing units and one or more inspection image capturing units, multi-perspective healthcare supply images and orientation data from the one or more inspection image capturing units, storage chamber metadata associated with a plurality of storage chambers, and pressure sensor data associated with one or more end-effectors;

generating a control command to trigger one or more actuators for providing motion to the one or more robotic manipulators based on the positional data, the color data and the depth data to reach towards at least one healthcare supply within the unsegregated healthcare supplies in an input container;

operating the one or more end-effectors based on the pressure sensor data to perform gripping of the at least one healthcare supply from the input container and an inspection chamber, and releasing the at least one healthcare supply in the inspection chamber and the predefined storage chambers within the plurality of storage chambers;

processing with one or more artificial intelligence (AI) models the multi-perspective healthcare supply images to extract the healthcare supply metadata;

modifying the control command based on the orientation data to change an orientation of the at least one healthcare supply using the one or more robotic manipulators, to capture additional multi-perspective healthcare supply images if the multi-perspective healthcare supply images are inadequate to extract the healthcare supply metadata;

mapping the extracted healthcare supply metadata with the storage chamber metadata associated with the plurality of storage chambers to determine the predefined storage chambers to receive the at least one healthcare supply;

operating the chamber positioning mechanism to actuate the predefined storage chambers into an access position for receiving the at least one healthcare supply based on mapping analysis between the extracted healthcare supply metadata and the storage chamber metadata;

generating the control command to trigger the one or more actuators; and

providing the motion to the one or more robotic manipulators based on the positional data associated with the predefined storage chambers to release the at least one healthcare supply into the predefined storage chambers to categorize the unsegregated healthcare supplies.