Description:FIELD OF INVENTION
[0001] The present disclosure relates to industrial automation systems, and particularly relates to an Artificial Intelligence (AI)-based adaptive cement bag loading system and method configured to dynamically detect truck geometry and automatically adapt loading alignment and bag stacking patterns in cement plant dispatch bays operating under variable logistics conditions.
BACKGROUND
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Cement dispatch operations in industrial plants traditionally depend on mechanical or semi-automatic bag loading systems engineered for fixed truck dimensions and precisely controlled bay alignments. These conventional setups presume uniform vehicle widths, centered positioning, and consistent heights, often relying on static conveyors, flap mechanisms, or basic positioning devices as seen in prior art like unpowered automatic loaders or stacking machines.
[0004] In real-world cement logistics, particularly in diverse industrial ecosystems of developing regions, trucks display substantial variability in geometry, including width variations, misaligned parking, and heights mismatched to legacy bay infrastructure lacking vertical adjustability or expansive clearances. Gate congestion from unscheduled arrivals exacerbates delays, with average truck turnaround times increasing due to manual adjustments, equipment jams in palletizers or conveyors, and weighbridge errors leading to dispatch inaccuracies.
[0005] Legacy systems, such as those using distributing carriages for fixed piling or belt-fed stackers, function deterministically without real-time perception of environmental variances like truck misalignment or dynamic positioning shifts. This results in persistent manual interventions, safety hazards from overloaded operators, inconsistent bag stacking (risking collapses), reduced throughput (e.g., packing line stoppages), and elevated costs from detention penalties.
[0006] Existing systems such as FLSmidth automatic truck loading systems feature mechanical fork-based mechanisms, palletizer-integrated loaders, configurable stacking parameters, and high-throughput mechanical loading. However, they limit adaptability to mechanical/PLC-driven controls, predefined stacking patterns, controlled truck positioning assumptions, absent real-time AI perception-driven trajectory planning, restricted dynamic pallet angle adaptation, and vertical architectures needing sufficient bay height.
[0007] Beumer Group truck loading systems offer high precision palletizers, telescopic loaders, and centralized automation control for efficient bag loading. However, they suffer from infrastructure-heavy deployment, dependency on mechanical alignment fixtures, limited adaptive intelligence at the truck interface, and high installation height requirements.
[0008] Aumund/Bulk Handling mechanical solutions provide bulk material conveying, stacking, and loading/feeding systems for cement dispatch. However, they exhibit absence of integrated robotic pallet loading intelligence, limited perception-driven loading decision capability, and a primary focus on material flow rather than adaptive dispatch robotics.
[0009] Therefore, there remains an unmet need for an intelligent, AI-enabled loading system that dynamically perceives truck geometry via adaptive sensing, autonomously adjusts robotic stacking paths, and optimizes dispatch efficiency without infrastructure overhauls.
[0010] In view of the foregoing challenges, the present disclosure provides a system and method configured to dynamically detect truck geometry and automatically adapt loading alignment and bag stacking patterns in cement plant dispatch bays operating under variable logistics conditions.
[0011] The invention discloses an artificial intelligence based cement bag loading system comprising imaging devices, an AI processing module, an adaptive mechanical loading assembly, alignment control mechanisms, vertical adjustment assemblies, and a safety monitoring subsystem. The system captures visual information of a truck positioned at a dispatch bay and computes geometric parameters including width, height, angular orientation, and lateral offset. Based on computed parameters, the system automatically selects an optimal bag stacking configuration and dynamically aligns the loading assembly with the truck plane. The invention enables operation in legacy plant configurations using a scissor lift based vertical adjustment mechanism, thereby allowing retrofit deployment without extensive civil modifications.
[0012] In comparison with existing systems, the present invention differentiates with perception-driven stacking geometry decisions, automatic truck pose compensation, compact scissor-lift vertical architecture, and adaptive loading under variable bed inclinations. The present invention enables adaptive robotic loading in imperfect real-world dispatch environments, reducing infrastructure dependency. The present invention provides hybrid robotics, machine vision and compact mechanical stacking architecture.
[0013] The innovation protects four major architectural layers simultaneously: AI perception-guided pallet geometry selection, real-time truck pose compensation, compact mechanical stacking via scissor lift, and high-throughput adaptive loading trajectory planning. This multi-layer integration establishes a strong technological moat while enhancing dispatch efficiency, safety, and deployment flexibility in variable industrial environments.
OBJECTS OF THE INVENTION
[0014] It is an object of the present disclosure which provides an AI-based adaptive cement bag loading system and method capable of automatically detecting truck geometry and adjusting loading operations accordingly.
[0015] It is an object of the present disclosure to provide a system to dynamically select bag stacking configurations based on truck width, to align the loading mechanism with truck orientation and lateral displacement, and to enable deployment in legacy plants with minimal civil modification.
[0016] It is an object of the present disclosure to provide an intelligent safety envelope capable of detecting human intrusion and stopping operations and to improve operational safety, throughput, and consistency of bag loading operations.
SUMMARY
[0017] The present disclosure is directed towards an AI-based adaptive cement bag loading system for dynamic truck geometry detection and automated stacking. The system comprising of (a) atleast one camera installed within a loading bay configured to capture a plurality of images of incoming trucks; (b) an Artificial Intelligence integrated central processor configured to: analyze image data from the atleast one camera to determine a plurality of geometric parameters to detect truck geometry, and control operation of the system; (c) an adaptive stacking controller configured to determine a stacking configuration of cement bags based on the detected truck geometry to optimize load stability and maximize utilization; (d) an adaptive loader assembly configured to load cement bags onto the trucks, wherein the adaptive loader assembly including a heavy-duty scissor lift mechanism configured to dynamically adjust loading height and orientation of the loading apparatus according to truck bed elevation while maintaining stable transfer of cement bags; and (e) a safety monitoring subsystem configured to continuously evaluate the loading bay using AI-based human detection.
[0018] In an aspect of the present disclosure, the AI integrated central processor controls the safety monitoring subsystem configured to continuously assess the loading bay via AI-based human detection, and upon detecting human presence in a predefined safety envelope, trigger an immediate controlled shutdown of cement bag loading operations.
[0019] In an aspect of the present disclosure, the AI integrated central processor is configured to determine a plurality of geometric parameters including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline.
[0020] In an aspect of the present disclosure, the AI integrated central processor is configured to employ deep learning models such as deep Convolutional Neural Network architectures including ResNet-101 and Mask R-CNN and PyTorch framework for analyzing the plurality of images of incoming trucks.
[0021] In an aspect of the present disclosure, the AI integrated central processor is configured to employ deep learning models trained on truck geometry datasets to predict and adjust stacking trajectories in real-time.
[0022] In an aspect of the present disclosure, the adaptive stacking controller is configured to determine a stacking configuration comprising either four-bag or six-bag rows.
[0023] In another aspect of the present disclosure, the adaptive loader assembly includes a flexible bag gripper or end effector, a plurality of position sensors and multi-axis motion control to load cement bags effectively.
[0024] In another aspect of the present disclosure, the loader alignment mechanism is configured to dynamically adjust orientation of a loading apparatus to match truck angle and position and compensate for off-center parking conditions without manual intervention.
[0025] The present disclosure is also directed towards method of AI-based adaptive cement bag loading for dynamic truck geometry detection and automated stacking, the method comprising of: capturing a plurality of real-time images of an incoming truck within a loading bay via at least one camera; analyzing the real-time data using an AI integrated processing unit to determine a plurality of geometry parameters of truck including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline; generating an adaptive stacking plan by the AI integrated processing unit based on detected truck geometry and cement bag dimensions; adjusting orientation of a loading apparatus by a heavy-duty scissor lift mechanism based on detected truck geometry and cement bag dimensions; simultaneously adjusting loading height of the loading apparatus by the heavy-duty scissor lift mechanism according to truck bed elevation; and controlling a loader to pick cement bags from a supply and autonomously stack them onto the truck per the adaptive plan.
[0026] One should appreciate that although the present disclosure has been explained with respect to a defined set of functional modules, any other module or set of modules can be added/deleted/modified/combined and any such changes in architecture/construction of the proposed system are completely within the scope of the present disclosure. Each module can also be fragmented into one or more functional sub-modules, all of which are also completely within the scope of the present disclosure.
[0027] Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.
BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings are included to provide a further understanding of the present disclosure, and is incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0029] FIG. 1 illustrates schematic overview of the AI-based intelligent cement bag loading system including imaging devices, AI integrated processing unit, adaptive loader assembly, vertical adjustment mechanism, and safety monitoring subsystem.
[0030] FIG. 2 illustrates representative loading patterns for truck configurations, demonstrating dynamic four-bag and six-bag row selection.
[0031] FIG. 3 illustrates system configurations for (a) legacy plants incorporating a heavy-duty scissor lift vertical adjustment mechanism and (b) new plant installations (present invention) incorporating an up-down vertical motion mechanism integrated with streamlined truck flow.
DETAILED DESCRIPTION
[0032] Aspects of the present disclosure relate to AI-based adaptive cement bag loading system and method for dynamic truck geometry detection and automated stacking.
[0033] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0034] Each of the appended claims defines a separate invention, which for infringement purposes is recognized as including equivalents to the various elements or limitations specified in the claims. Depending on the context, all references below to the "invention" may in some cases refer to certain specific embodiments only. In other cases it will be recognized that references to the "invention" will refer to subject matter recited in one or more, but not necessarily all, of the claims.
[0035] If the specification states a component or feature “may”, “can”, “could”, or “might” be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic. Various terms as used herein are shown below. To the extent a term used in a claim is not defined below, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0036] The present disclosure relates to an AI-based adaptive cement bag loading system and method for dynamic truck geometry detection and automated stacking. The system comprising of (a) atleast one camera installed within a loading bay configured to capture a plurality of images of incoming trucks; (b) an Artificial Intelligence integrated central processor configured to: analyze image data from the atleast one camera to determine a plurality of geometric parameters to detect truck geometry, and control operation of the system; (c) an adaptive stacking controller configured to determine a stacking configuration of cement bags based on the detected truck geometry to optimize load stability and maximize utilization; (d) an adaptive loader assembly configured to load cement bags onto the trucks, wherein the adaptive loader assembly including a heavy-duty scissor lift mechanism configured to dynamically adjust loading height and orientation of the loading apparatus according to truck bed elevation while maintaining stable transfer of cement bags; and (e) a safety monitoring subsystem configured to continuously evaluate the loading bay using AI-based human detection. Figure 1 illustrates a schematic overview of AI-based intelligent cement truck bag loading system.
[0037] The method of AI-based adaptive cement bag loading for dynamic truck geometry detection and automated stacking, comprising of: capturing a plurality of real-time images of an incoming truck within a loading bay via at least one camera; analyzing the real-time data using an AI integrated processing unit to determine a plurality of geometry parameters of truck including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline; generating an adaptive stacking plan by the AI integrated processing unit based on detected truck geometry and cement bag dimensions; adjusting orientation of a loading apparatus by a heavy-duty scissor lift mechanism based on detected truck geometry and cement bag dimensions; simultaneously adjusting loading height of the loading apparatus by the heavy-duty scissor lift mechanism according to truck bed elevation; and controlling a loader to pick cement bags from a supply and autonomously stack them onto the truck per the adaptive plan.
[0038] In an embodiment of the present disclosure, the AI integrated central processor controls the safety monitoring subsystem configured to continuously assess the loading bay via AI-based human detection, and upon detecting human presence in a predefined safety envelope, trigger an immediate controlled shutdown of cement bag loading operations.
[0039] In an embodiment of the present disclosure, the AI integrated central processor is configured to determine a plurality of geometric parameters including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline.
[0040] In an embodiment of the present disclosure, the AI integrated central processor is configured to employ deep learning models such as deep Convolutional Neural Network architectures including ResNet-101 and Mask R-CNN and PyTorch framework for analyzing the plurality of images of incoming trucks.
[0041] In an embodiment of the present disclosure, the AI integrated central processor is configured to employ deep learning models trained on truck geometry datasets to predict and adjust stacking trajectories in real-time.
[0042] In an embodiment of the present disclosure, the adaptive stacking controller is configured to determine a stacking configuration comprising either four-bag or six-bag rows.
[0043] In an embodiment of the present disclosure, the adaptive loader assembly includes a flexible bag gripper or end effector, a plurality of position sensors and multi-axis motion control to load cement bags effectively.
[0044] In another embodiment of the present disclosure, the loader alignment mechanism is configured to dynamically adjust orientation of a loading apparatus to match truck angle and position and compensate for off-center parking conditions without manual intervention.
[0045] The invention comprises one or more cameras installed within a loading bay configured to capture images of incoming trucks. The captured images are processed by an artificial intelligence module trained to detect truck boundaries and determine geometric parameters. The AI module estimates truck width, height, angular orientation relative to the loading axis, and lateral displacement from the bay centerline. An adaptive stacking controller determines a stacking configuration comprising either four-bag or six-bag rows based on detected truck geometry to optimize load stability and maximize utilization. A loader alignment mechanism dynamically adjusts orientation of the loading apparatus to match truck angle and position. The system compensates for off-center parking conditions without manual intervention.
[0046] For legacy plant deployments lacking vertical motion capability, a heavy-duty scissor lift mechanism adjusts loading height according to truck bed elevation while maintaining stable transfer of cement bags. A safety monitoring subsystem continuously evaluates the loading zone using AI-based human detection. Upon detecting human presence within a predefined safety envelope, the system executes an immediate controlled shutdown. The system is designed to operate reliably in dusty cement environments and under variable lighting conditions.

KEY ASPECTS OF THE INVENTION
1. Adaptive Pallet Geometry Control
[0047] The system dynamically determines pallet loading configuration between four-bag row and six-bag row stacking patterns based on real-time estimation of truck bed usable width using machine vision. Unlike conventional systems where stacking pattern is pre-programmed or operator selected, the present invention performs:
• perception driven configuration selection
• dispatch optimization based on real geometry
• automatic compensation for truck variation
This enables improved space utilization and higher loading throughput.
2. Vision Based Lateral Truck Pose Compensation
[0048] The invention incorporates a camera based truck pose estimation module configured to determine lateral truck offset (Y-axis deviation) relative to loading bay reference frame. Robotic trajectory is automatically corrected to align pallet placement without requiring:
• mechanical centering guides
• truck wheel stoppers
• driver precision parking
This enables robust operation under real industrial dispatch conditions.
3. Truck Bed Inclination Adaptive Loading Angle
[0049] The system estimates truck bed pitch angle and adjusts pallet loading trajectory and placement angle accordingly. This protects:
• stack stability under inclined loading surfaces
• robotic kinematic planning under gravity effects
• pallet placement safety
Conventional systems assume flat truck beds or rely on manual correction.
4. Compact Vertical Stacking Mechanism Using Scissor Lift
[0050] The invention replaces conventional telescopic mast or telescopic conveyor Z-axis loading systems with a multi-stage scissor lift mechanism capable of:
• stacking up to six bag layers on inclined beds
• stacking up to ten bag layers on flat beds
• operating in low height loading bays
Mechanical advantages include:
• reduced installation height requirement
• improved stiffness during high throughput loading
• simplified structural design
• improved retrofitting feasibility
5. High Throughput Stability Architecture
[0051] The coordinated design of:
• scissor lift geometry
• pallet manipulation trajectory
• perception feedback loop
enables loading throughput of approximately 50 bags per minute, significantly exceeding manual loading rates (~35 bags per minute), while maintaining stack integrity.
6. Retrofittable Low Bay Deployment Innovation
[0052] The loading system is deployable in existing dispatch bays with limited vertical clearance, eliminating the need for civil reconstruction or elevated structural platforms typically required by telescopic loaders.
7. AI Assisted Dispatch Optimization Layer
[0053] Stacking configuration, loading trajectory and cycle timing are optimized simultaneously using perception data and dispatch logic, creating a closed loop perception-decision-actuation architecture.

ADVANTAGES OF THE INVENTION
[0054] Advantages of invention includes:
• Dynamic adaptability: AI detects truck geometry variations in real-time for autonomous adjustments, eliminating manual work
• Compact deployment: Scissor-lift fits low-height bays, cutting retrofit costs vs. tall loaders
• Superior safety: AI human detection triggers instant shutdowns, minimizing accidents in busy zones
• High efficiency: Perception-optimized trajectories enable thousands of bags/hour with stable stacking
• Operational flexibility: Handles misalignments and inclinations for diverse fleets without fixtures
[0055] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
, Claims:We Claim:
1. An AI-based adaptive cement bag loading system for dynamic truck geometry detection and automated stacking, the system comprising of:
a) atleast one camera installed within a loading bay configured to capture a plurality of images of incoming trucks;
b) an Artificial Intelligence integrated central processor configured to:
analyze image data from the atleast one camera to determine a plurality of geometric parameters to detect truck geometry, and
control operation of the system;
c) an adaptive stacking controller configured to determine a stacking configuration of cement bags based on the detected truck geometry to optimize load stability and maximize utilization;
d) an adaptive loader assembly configured to load cement bags onto the trucks, wherein the adaptive loader assembly including a heavy-duty scissor lift mechanism configured to dynamically adjust loading height and orientation of the loading apparatus according to truck bed elevation while maintaining stable transfer of cement bags; and
e) a safety monitoring subsystem configured to continuously evaluate the loading bay using AI-based human detection.
2. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the AI integrated central processor controls the safety monitoring subsystem configured to continuously assess the loading bay via AI-based human detection, and upon detecting human presence in a predefined safety envelope, trigger an immediate controlled shutdown of cement bag loading operations.
3. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the AI integrated central processor is configured to determine a plurality of geometric parameters including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline.
4. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the AI integrated central processor is configured to employ deep learning models such as deep Convolutional Neural Network architectures including ResNet-101 and Mask R-CNN and PyTorch framework for analyzing the plurality of images of incoming trucks.
5. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the AI integrated central processor is configured to employ deep learning models trained on truck geometry datasets to predict and adjust stacking trajectories in real-time.
6. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the adaptive stacking controller is configured to determine a stacking configuration comprising either four-bag or six-bag rows.
7. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the adaptive loader assembly includes a flexible bag gripper or end effector, a plurality of position sensors and multi-axis motion control to load cement bags effectively.
8. The AI-based adaptive cement bag loading system as claimed in claim 1, wherein the heavy-duty scissor lift mechanism is configured to dynamically adjust orientation of a loading apparatus to match truck angle and position and compensate for off-center parking conditions without manual intervention.
9. A method of AI-based adaptive cement bag loading for dynamic truck geometry detection and automated stacking, the method comprising of:
capturing a plurality of real-time images of an incoming truck within a loading bay via at least one camera;
analyzing the real-time data using an AI integrated processing unit to determine a plurality of geometry parameters of truck including truck width, height, angular orientation relative to the loading axis, and lateral displacement from loading bay centerline;
generating an adaptive stacking plan by the AI integrated processing unit based on detected truck geometry and cement bag dimensions;
adjusting orientation of a loading apparatus by a heavy-duty scissor lift mechanism based on detected truck geometry and cement bag dimensions;
simultaneously adjusting loading height of the loading apparatus by the heavy-duty scissor lift mechanism according to truck bed elevation; and
controlling a loader to pick cement bags from a supply and autonomously stack them onto the truck per the adaptive plan.
10. The method as claimed in claim 9, wherein the analyzing the real-time data using an AI integrated processing unit utilizing pre-trained AI models such as deep Convolutional Neural Network architectures including ResNet-101 and Mask R-CNN and PyTorch framework.