Cargo transport management apparatus and method

Abstract

The present application relates to a kind of goods transport management device and method, it is related to goods transport management technical field, device includes processing unit, image acquisition equipment and weight monitoring equipment, image acquisition equipment gathers the geometric characteristic of goods, mark information feature and destination feature;Weight monitoring equipment gathers the gravity change characteristic of goods;Processing unit determines the test mode of goods according to the geometric characteristic of goods, mark information feature, and determines the first handling mode of grabbing goods according to the test information obtained based on test mode, according to the destination feature in the handling process based on first handling mode, the change of the geometric characteristic of goods and / or gravity change characteristic determines the second handling mode of unloading goods;Wherein, processing unit is adjusted to the first transport route of pre-setting according to first handling mode and geometric characteristic to form the second transport route of transporting goods in the way of dynamically adjusting the gravity change characteristic of goods and / or handling feature.

Description

Technical Field

[0001] This invention relates to the field of cargo transportation management technology, and in particular to a cargo transportation management device and method. Background Technology

[0002] In modern logistics systems, large warehouses are key hubs for cargo transportation, and their operational efficiency directly impacts the smoothness and economic benefits of the global supply chain. However, existing cargo transportation management systems have significant shortcomings in handling non-standard sized goods, mainly in the following aspects: Limitations of fixed transport routes: Currently, many warehouses rely on pre-set fixed transport routes to guide the handling of goods. This method may be efficient and feasible for goods with uniform specifications and dimensions, but it becomes difficult to handle goods with special dimensions or those that exceed the standard. Because these special goods cannot adapt to standardized transport processes, overall transport efficiency is hampered.

[0003] Inefficiency and Risks of Manual Transportation: To address the aforementioned problems, manual transportation is necessary to handle these specially sized goods. While manual transportation can flexibly handle various complex situations, it is less efficient, more costly, and poses significant safety risks compared to mechanized and automated transportation. Moving these special goods is not only physically demanding for workers, but improper handling can easily lead to damage to the goods or injury to personnel.

[0004] Difficulties in adjusting goods during transport: Even with manual adjustments during transit, the space and time for such adjustments are extremely limited in the cramped or crowded warehouse environment. In such cases, the placement and adjustment of goods require extremely high precision; even the slightest mistake can lead to transport delays or damage.

[0005] Therefore, existing transportation management systems lack the ability to identify, plan, and adjust for special cargo. On the one hand, the system struggles to identify and classify cargo of different sizes and specifications in real time; on the other hand, the system is insufficient in optimizing transportation routes and methods for special cargo, making it difficult to meet the flexibility and personalized needs of cargo transportation.

[0006] For example, Chinese patent application CN116986195A discloses an automated warehouse control method and system based on Internet of Things (IoT) technology, applied to an IoT warehouse including multiple storage boxes, each including multiple storage cabinets; the system includes: a data acquisition module, including multiple cabinet monitoring terminals, used to collect cabinet information; the data acquisition module is also used to acquire images of goods in the target area; a warehouse management module is used to identify the images of goods, determine the type of goods, and determine a first transportation strategy; it is also used to determine a first target storage cabinet from multiple storage boxes for storing goods corresponding to a storage request; the warehouse management module is also used to receive a goods retrieval request, determine a second target storage cabinet containing the goods corresponding to the goods retrieval request; and it is also used to determine a second transportation strategy based on the type of goods corresponding to the goods retrieval request. The defects of this patent in terms of goods transportation include: (1) Non-standard shaped goods may be difficult to be grasped and handled by standardized handling tools due to their unique shape, size, or weight distribution. If the automated system lacks a flexible or adaptable grasping mechanism, it may not be able to safely or effectively handle these goods. (2) For irregularly shaped goods, the system may not fully consider the actual storage needs of the goods when determining its primary target storage locker. For example, it may require additional space to avoid compression and deformation, or a specific placement method to maintain stability. This may lead to improper use of storage space or damage to the goods. (3) During the goods retrieval process, non-standard goods may require special handling strategies or tools to ensure safe unloading. If the system cannot accurately adjust its secondary transportation strategy according to the specific shape and weight distribution of the goods, the unloading process may face problems of inefficiency and high risk.

[0007] Therefore, there is an urgent need to optimize existing warehouse cargo transportation management systems, especially to improve their flexibility and efficiency in handling goods of special dimensions.

[0008] Furthermore, on the one hand, there are differences in understanding among those skilled in the art; on the other hand, the applicant studied a large number of documents and patents when making this invention, but due to space limitations, not all details and contents were listed in detail. However, this does not mean that the present invention does not possess the features of these prior art. On the contrary, the present invention already possesses all the features of the prior art, and the applicant reserves the right to add relevant prior art to the background art. Summary of the Invention

[0009] Existing technologies for transporting non-standard sized or irregular goods using transport robots present numerous problems. Current systems have significant shortcomings in managing the transport of non-standard sized goods. First, the fixed transport routes used in most warehouses are inefficient when handling oversized or special goods because these goods are unsuitable for standardized transport processes, limiting transport efficiency and effectiveness. Second, while manual transport methods for these goods are flexible, they are inefficient, costly, and pose significant safety hazards. Workers face high labor intensity when handling special goods and are prone to accidents due to operational errors. Finally, even with manual adjustments during transport, the narrow and crowded warehouse environment limits the possibility of such adjustments, increasing the risk of damage and transport delays. In conclusion, to improve overall logistics efficiency, these problems in the management of non-standard goods transport need to be addressed.

[0010] To improve efficiency in cargo handling and transportation, existing technologies have developed solutions that adjust transportation methods based on the actual state of the cargo by detecting different cargo parameters. For example, Chinese patent document CN112987739A discloses a method for an AGV (Automated Guided Vehicle) robot to move under different load conditions, including the following steps: product gripping, detection of the object's center of gravity, detection of the object's volume, the transported goods being positioned entirely on a moving platform, the transported goods being partially positioned outside the moving platform, and the end of the transport. The AGV robot performs three-dimensional imaging processing on the transported goods using a camera. After the three-dimensional imaging processing, a weighing unit weighs the transported goods. A central computing unit analyzes the shape and weight of the transported goods to calculate the coordinates of the center of gravity. A center of gravity detection device checks and verifies the center of gravity of the transported goods, ensuring that the center of gravity of the transported goods is placed on the robot's moving platform in the lowest possible state. Finally, a limiting unit fixes the transported goods in place. This technical solution can detect and verify the center of gravity coordinates of the transported goods. By comparing the combined data of the goods' mass and center of gravity, it adjusts the acceleration and maximum speed of the mobile platform accordingly. This effectively prevents goods from tipping over during transport due to an excessively high center of gravity or excessive mass, making the transport robot safer and more efficient. However, this technical solution uses a uniform gripping method for all goods, ignoring the specific transport requirements of each item. It cannot adjust the gripping method according to the actual transport requirements of the goods, thus posing a risk of damage due to inaccuracies in the actual transport conditions. Furthermore, the parameters adjusted according to the differences in the center of gravity of different transported goods in this technical solution only involve the speed parameters of the mobile platform and do not involve the adjustment of the actual transport route. It is understandable that once the transport posture of the goods changes, its accessibility and efficiency through a specific route may also be affected. The road conditions of the specific route will also affect the frequency of adjustment of the actual operating parameters of the transport robot. For example, when the goods need to be transported in a lateral posture, the original narrow passage transport route will not be able to meet the actual transport requirements. Multiple adjustments to the transport posture are required to achieve smooth transport of the goods, which in turn leads to a reduction in the overall transport efficiency of the goods.

[0011] To address the shortcomings of existing technologies, this invention provides a cargo transportation management device, comprising a processing unit, an image acquisition device, and a weight monitoring device. The image acquisition device is used to acquire the geometric features, marking information features, and destination features of the cargo; the weight monitoring device is used to acquire the center of gravity change features of the cargo; the processing unit is used to determine a test mode for the cargo based on its geometric features and marking information features, and to determine a first handling mode for grasping the cargo based on test information obtained from the test mode, and to determine a second handling mode for unloading the cargo based on the destination features, changes in the geometric features of the cargo, and / or center of gravity change features during the handling process based on the first handling mode; wherein, the processing unit generates a first transportation route and predicts the virtual center of gravity change features of the cargo based on the first handling mode, geometric features, and center of gravity change features; during the handling process, the operating parameters of the transportation robot are dynamically adjusted based on the deviation between the cargo's center of gravity change features and the virtual center of gravity change features to maintain the stability of the cargo.

[0012] Unlike existing technologies, the cargo transportation management device of the present invention can, on the one hand, determine the cargo gripping parameters based on the actual geometric characteristics of the cargo and the marking information characteristics reflecting the cargo handling requirements, and after gripping the cargo, determine a second handling mode for unloading the cargo based on the destination characteristics of the cargo, changes in the cargo's geometric characteristics, and / or changes in the center of gravity; on the other hand, the cargo transportation management device can also dynamically adjust the operating parameters of the transportation robot during the handling process based on the deviation between the changes in the cargo's center of gravity and the changes in the virtual center of gravity. Based on the above distinguishing technical features, the problems to be solved by the present invention may include: how to determine the corresponding handling posture based on the actual physical parameters and handling requirements of different cargoes, and how to adjust the operating parameters of the transportation robot based on the adjusted cargo handling posture, so as to improve the stability and efficiency of cargo transportation.

[0013] Specifically, the advantages of the present invention include: (1) Enhanced adaptability: By collecting the geometric features, marking information features and destination features of the cargo, the device can handle cargo of various sizes and shapes, including non-standard sized cargo, thereby overcoming the limitations of the prior art in handling special cargo.

[0014] (2) Improve transportation efficiency: The processing unit can determine the most suitable handling mode based on the characteristics of the goods and generate the best transportation route. This not only improves handling efficiency but also reduces the need for manual intervention and optimizes the entire transportation process.

[0015] (3) Ensuring cargo stability and safety: The application of weight monitoring equipment enables real-time monitoring of cargo stability throughout the transportation process. By tracking changes in the cargo's center of gravity in real time and comparing them with predicted virtual center of gravity change characteristics, the processing unit can dynamically adjust the operating parameters of the transport robot to ensure cargo stability during transportation and reduce the risk of cargo damage.

[0016] (4) Flexibility and dynamic adjustment capability: This technical solution allows for dynamic adjustment of transportation strategies during cargo handling, especially when faced with changes in the internal environment of the warehouse or unexpected changes in cargo during handling, it can make rapid adjustments to maintain transportation efficiency and cargo safety.

[0017] (5) Reduce labor costs and safety risks: By using automated processing and handling modes, the reliance on manual handling is reduced, thereby reducing safety risks and labor costs caused by manual operation, while improving work efficiency and safety.

[0018] According to a preferred embodiment, the processing unit communicates with the transport robot via wired or wireless means and controls the operating parameters of the transport robot. During transportation, if the dynamic adjustment frequency of the transport robot exceeds a frequency threshold and the destination is not approached, the processing unit optimizes the first transport route into a second transport route based on the road condition characteristics and turning characteristics of the preset transport route. Unlike the prior art, the processing unit of the present invention can optimize the actual transport route based on the frequency of dynamic adjustment of the transport robot's operating parameters during transportation. Based on the above-mentioned distinguishing technical features, the problem to be solved by the present invention may include: how to optimize the transport route according to the operating state of the transport robot under the actual transport route, so as to reduce the number of times the transport robot dynamically adjusts, thereby achieving a more flexible and efficient transport route planning process. Specifically, the road condition characteristics and turning characteristics of different transport routes are different, which leads to different numbers of times the transport robot adjusts its operating parameters on different transport routes. Excessive adjustments will lead to increased energy consumption and mechanical wear. Therefore, this invention optimizes the transportation route when the dynamic adjustment frequency of the transportation robot on the current route exceeds a frequency threshold. This optimization includes alternative paths that bypass temporary obstacles and smoother turning paths, thereby reducing the dynamic adjustment frequency of the transportation robot and decreasing energy consumption and mechanical wear. This invention enables more flexible and efficient transportation route planning. Through communication with the transportation robot, the processing unit can dynamically adjust the transportation route based on actual road conditions and turning situations. Especially when the transportation robot's adjustment frequency is high and the destination is far away, this technology can prevent goods from being damaged or slipping due to excessive vibration or instability, while also avoiding potential delays and obstacles, thus improving overall transportation efficiency and time management.

[0019] According to a preferred embodiment, the processing unit is further configured to determine a test mode for the cargo based on geometric features, marking information features, weight distribution features, and center of gravity change features. The test mode includes gripping points, gripping methods, gripping force, and placement patterns. This enhances the flexibility and accuracy of the transport robot in handling different cargo, improving the safety and efficiency of handling operations. Such personalized handling modes help reduce the probability of cargo damage during handling.

[0020] According to a preferred embodiment, the processing unit is further configured to: generate at least one placement scheme involving the stacking order and placement posture of the transportable goods based on the test information of each goods received in the test mode when at least two goods are being tested; and adjust the placement scheme based on a second transport route and a dynamic adjustment scheme for the goods to form a first handling mode for orderly grasping of goods. This invention can dynamically adjust these schemes according to actual transport conditions. This allows for the rational stacking of goods and avoids damage to goods, while also improving the transport efficiency of transporting multiple goods at once, thereby enhancing the overall efficiency of the goods transport process.

[0021] According to a preferred embodiment, the processing unit is further configured to: adjust the operating parameters of the transport robot based on destination characteristics, changes in the geometric features of the goods, and / or changes in the center of gravity during the handling of goods in a first handling mode; and construct an operating parameter model corresponding to the changes in the geometric features and / or changes in the center of gravity of each type of goods, so as to directly retrieve the operating parameters when the transport robot transports the same type of goods. This allows the transport robot to quickly retrieve existing operating parameter models when facing the same type of goods, improving the working efficiency of the transport robot and reducing the time consumed during handling.

[0022] According to a preferred embodiment, the processing unit is further configured to: when an image acquisition device acquires an image of the unloading position at the destination, read the unloading position features of the destination, and determine the unloading speed and handling angle based on the destination features, changes in the geometric features of the goods, changes in the center of gravity, and the unloading position features during the handling process based on the first handling mode, thereby forming a second handling mode. The processing unit can accurately calculate the optimal unloading speed and angle based on the image information of the unloading position, combined with the characteristics of the goods and handling conditions. This invention not only ensures the safety of the goods during the unloading process but also improves the efficiency of the unloading operation and optimizes the entire handling process.

[0023] According to a preferred embodiment, during the process of the transport robot performing a gripping test on goods in a test mode, the processing unit adjusts the gripping parameters and gripping angle of the transport robot based on the characteristics of the goods' center of gravity change fed back by the weight monitoring device, in order to prevent the goods from falling. The processing unit adjusts the gripping parameters and gripping angle in real time to cope with possible changes in the center of gravity of the goods during handling, effectively preventing the goods from falling or being damaged. This real-time adjustment mechanism ensures the efficiency and safety of goods handling.

[0024] According to a preferred embodiment, a weight monitoring device is mounted on the gripping assembly of a transport robot. Based on an initial three-dimensional image of the goods acquired by an image acquisition device, a processing unit generates a first gripping scheme to be executed by the transport robot. During the process of the transport robot adjusting the shape of the goods based on the first gripping scheme, the processing unit receives information including: geometric features and marking information features of the goods acquired by the image acquisition device, and weight distribution features and center of gravity change features of the goods acquired by the weight monitoring device. By optimizing the gripping operation, this invention can improve the accuracy and efficiency of the gripping operation and reduce the time spent on adjustments and retries.

[0025] This invention provides a cargo transportation management method from a second aspect. The method includes: collecting geometric features, marking information features, and destination features of cargo; collecting the center of gravity features and their changes of the cargo; determining a test mode for the cargo based on the geometric features and marking information features, and determining a first handling mode for grasping the cargo based on the test information obtained based on the test mode; determining a second handling mode for unloading the cargo based on the destination features, changes in the geometric features of the cargo, and / or changes in the center of gravity during the handling process based on the first handling mode; wherein, a pre-set first transportation route is adjusted according to the first handling mode and geometric features to form a second transportation route for transporting the cargo in a manner that dynamically adjusts the changes in the center of gravity of the cargo and / or the handling features. This invention achieves dynamic and adaptive transportation route planning. By considering changes in the center of gravity and geometric features of the cargo during transportation, as well as the dynamic adjustment frequency of the transportation robot, this invention can optimize the preset transportation route based on road conditions and turning characteristics before approaching the destination, thereby improving transportation efficiency and adaptability.

[0026] According to a preferred embodiment, the method further includes: during transportation, when the dynamic adjustment frequency of the transportation robot is greater than a frequency threshold and the destination is not approached, optimizing the first transportation route into a second transportation route based on the road condition characteristics and turning characteristics of the preset transportation route.

[0027] This invention optimizes transportation routes to adapt to real-time changing environments. The method optimizes transportation routes under specific conditions (such as when the dynamic adjustment frequency of the transport robot exceeds a certain threshold), ensuring maximum transportation efficiency while reducing unnecessary delays, thus enhancing the flexibility and responsiveness of the transportation process. Attached Figure Description

[0028] Figure 1 This is a schematic diagram showing the connection relationship of the hardware modules of the cargo transportation management device provided by the present invention; Figure 2 This is a schematic diagram illustrating an application scenario of the cargo transportation management device provided by the present invention; Figure 3 This is a schematic diagram of a cargo transportation management device provided by the present invention, depicting a cargo loading scenario. Figure 4 This is a schematic diagram of different transportation routes of the cargo transportation management device provided by the present invention; Figure 5 This is a logical schematic diagram of the processing unit of the cargo transportation management device provided by the present invention; Figure 6 This is a flowchart illustrating the cargo transportation management method provided by the present invention.

[0029] List of reference numerals 100: Processing unit; 200: Image acquisition device; 300: Weight monitoring device; 400: Transport robot; 410: Cargo platform; 500: First transport route; 600: Second transport route; 700: Cargo; 710: Marking information feature; 720: Location of cargo; 730: Destination. Detailed Implementation

[0030] The following is a detailed explanation with reference to the accompanying drawings.

[0031] In existing technologies, transport robots 400 face numerous problems in transporting non-standard sized or irregular goods 700. Current systems have significant shortcomings in managing the transport of non-standard sized goods 700. First, the fixed transport routes used in most warehouses are inefficient when handling oversized or special goods 700 because these special goods 700 are unsuitable for standardized transport processes, limiting transport efficiency and effectiveness. Second, while manual transport methods for handling such goods 700 are flexible, they are inefficient, costly, and pose significant safety hazards. Workers face high labor intensity when handling special goods 700 and are prone to accidents due to operational errors. Finally, even with manual adjustments during transport, the narrow and crowded warehouse environment limits the possibility of adjustments, increasing the risk of damage to goods 700 and transport delays. In summary, to improve overall logistics efficiency, these problems in the management of non-standard goods transport need to be addressed.

[0032] This invention provides a cargo transportation management device and method, particularly a cargo transportation management device and method for non-standard sized cargo. This invention can also provide a transportation robot 400 applying the cargo transportation management method of this invention. This invention can also provide a cargo transportation strategy generation model. This invention can also provide a server, which is communicatively connected to the transportation robot 400 and provides cargo transportation strategies to the transportation robot 400.

[0033] In this invention, the processing unit 100 communicates with the transport robot 400 via wired or wireless means. The image acquisition device 200 and the weight monitoring device 300 are mounted on the robotic arm (or gripping assembly) of the transport robot 400 to effectively collect the geometric features and center of gravity changes of the cargo 700 during transport. The image acquisition device 200 is positioned to capture the cargo 700 and its markings from all directions. The weight monitoring device 300 is mounted on the robotic arm or gripping assembly of the transport robot 400, and is used by the processing unit 100 or the weight monitoring device 300 itself to calculate the collected pressure data as center of gravity data, thereby monitoring the center of gravity changes of the cargo 700 in real time.

[0034] The processing unit 100 is equipped with an artificial intelligence model, which is used to process and analyze information such as geometric features, marking information features, test mode of cargo 700, first handling mode, second handling mode, destination features, and transportation route, so that the transport robot 400 can transport non-standard sized cargo 700 in a stable manner.

[0035] Non-standard sized goods 700 generally include goods with irregular packaging, unstable center of gravity, and variable shape. The packaging of non-standard sized goods 700 may contain objects with uneven weight distribution, such as plants, animals, or partially filled fluids, which cannot be arbitrarily thrown, dropped, or crushed like industrial products. These objects cannot withstand severe collisions or compression, nor can they withstand violent vibrations; therefore, manual handling is generally required, resulting in low handling efficiency. Mechanical robots can perform intelligent handling using the cargo transportation management device of this invention, preventing damage to non-standard sized goods 700 and improving transportation efficiency.

[0036] The transport robot 400 is a mechanical device that performs cargo handling tasks and can automate handling operations according to the instructions of the processing unit 100. It is typically equipped with a platform 410, a robotic arm or gripper for grasping and handling goods 700, and can automatically adjust the grasping method, handling speed, and handling route under the control of the processing unit 100. The transport robot 400 is also equipped with a sensor system to monitor its operating status and surrounding environment in real time, ensuring efficient and safe handling operations.

[0037] For example, the transport robot 400 includes a wheeled base. A platform 410 is positioned above the base for placing goods. The platform 410 is designed to support the expected weight of the goods and may have a smooth surface or a surface with anti-slip material. It can be fixed or adjustable to facilitate loading and unloading of goods. A robotic arm is typically attached to the base and can move in multiple degrees of freedom to achieve different positions and postures. The robotic arm may be articulated, mimicking the structure of a human arm, or other types such as SCARA arms, designed for high speed and precision. A robotic hand is attached to the end of the robotic arm for grasping and moving goods. The robotic hand may have multiple fingers, similar to a human hand, or may be a suction cup, gripper, or other component designed specifically for grasping specific items. Weight distribution feature acquisition devices are integrated into the robotic hand, which may include pressure sensors, strain gauges, or other types of sensors capable of measuring and recording the weight distribution data of the goods as they are grasped. These sensors are connected to each finger or gripping point on the robotic hand to ensure that changes in weight distribution can be monitored in real time during goods handling. The transport robot 400 is equipped with an internal control system, including a microprocessor and electronic hardware, which manages all mechanical components and sensors. This control system is also responsible for processing data collected by the weight distribution feature acquisition device and adjusting the gripping force of the robotic arm and the movement of the robotic arm based on this data to ensure that the cargo 700 is transported stably and safely.

[0038] The image acquisition device 200 is a high-precision camera used to capture the appearance features, markings, and destination characteristics of the cargo 700. It can acquire high-definition image or video data, providing accurate visual information to the processing unit 100. Through analysis and processing of the image data, the processing unit 100 can identify information such as the type, size, and optimal gripping point of the cargo 700, thereby determining the most suitable handling mode.

[0039] Labeling information is typically printed on packaging boxes and includes textual information and warning signs. Warning signs include textual information such as "Fragile," "Keep Dry," "Handle with Handle," "Do Not Open with Knife," "Keep Away from Magnets," and "Do Not Stack," as well as graphic symbols. Labeling information is related to the safety of the goods and therefore must be captured visually. Labeling information also includes stacking height, load weight / height, "Do Not Stack," weight symbols (indicating the weight of the packaging including the product), images of two people lifting a box, "Do Not Use Forklifts," and "Static Discharge" warnings. An image of two people lifting a box indicates that the goods are too heavy for one person; it is not a weight indicator.

[0040] The weight monitoring device 300 is a dedicated sensor system, including, for example, several pressure sensors. These pressure sensors are positioned on the side of the gripper of the transport robot 400 that contacts the cargo 700, and are used to monitor and collect pressure or weight changes in the cargo 700 during handling in real time. When the center of gravity of the cargo 700 is unstable, its weight changes frequently, causing changes in the pressure at the contact points of the various pressure sensors. Based on the pressure data from each pressure sensor, the weight monitoring device 300 can accurately measure the weight distribution and weight data of the cargo 700 and transmit this data to the processing unit 100. If the weight monitoring device 300 is equipped with a microprocessor or utilizes the integrated dedicated chip of the transport robot 400 for calculations, it can determine the center of gravity of the cargo 700 based on the pressure data from each pressure sensor at a given moment and a preset algorithm. When the center of gravity changes, the weight monitoring device 300 can collect the changes in the center of gravity of the cargo 700. Alternatively, the weight monitoring device 300 can send the data on the changes in the center of gravity to the processing unit 100. The processing unit 100 uses this data on changes in the center of gravity to adjust the handling method and operating parameters of the transport robot 400 to ensure the safety of the goods 700 during transportation and unloading.

[0041] Destination characteristics: These include the location of the destination and the characteristics of the unloading location. Unloading location characteristics refer to the set of information used to describe specific attributes of the unloading site during the unloading process. These characteristics include spatial layout, such as the size, shape, and obstacle location of the unloading area; ground conditions, such as flatness, coefficient of friction, and stability; lighting conditions, which affect the imaging quality of the image acquisition device 200; environmental factors, such as temperature and humidity, which may affect cargo storage or equipment performance; safety requirements, ensuring that operations comply with safety regulations; and the specific coordinates and height of the cargo placement point. Using these characteristics, the processing unit 100 can accurately calculate the unloading speed and angle, thereby optimizing the unloading operation and ensuring that the cargo 700 is unloaded safely and efficiently.

[0042] The principles of this invention include: like Figure 2 and Figure 3 As shown, during the handling of cargo 700, the image acquisition device 200 acquires the geometric features, marking information features 710, and destination features of cargo 700. This information is transmitted to the processing unit 100, which uses this feature data to determine the test mode of cargo 700. This test mode includes the gripping point, gripping method, gripping force, and placement shape. Based on the test information obtained from the test mode, the processing unit 100 determines the first handling mode of the transport robot 400, which covers how to grip and handle cargo 700. During the gripping test of cargo 700 by the transport robot 400, the processing unit 100 adjusts the gripping parameters and gripping angle based on the center of gravity change characteristics fed back by the weight monitoring device 300 to ensure the safety and stability of cargo 700 during the handling process.

[0043] Furthermore, the processing unit 100 generates a first transport route 500 based on the geometric features and center of gravity change characteristics of the cargo 700, and predicts the virtual center of gravity change characteristics of the cargo 700. During the handling process, the weight monitoring device 300 collects the weight change information of the cargo 700 in real time and transmits this information back to the processing unit 100. The processing unit 100 calculates the center of gravity change characteristics based on the real-time weight change characteristics, and dynamically adjusts the operating parameters of the transport robot 400 based on the deviation between the center of gravity change characteristics and the virtual center of gravity change characteristics to maintain the stability of the cargo 700.

[0044] When the dynamic adjustment frequency of the transport robot 400 exceeds a set threshold, the processing unit 100 optimizes the first transport route 500 into a second transport route 600 based on the road condition and turning characteristics of the preset transport route. When testing at least two goods 700, the processing unit 100 generates a placement scheme involving the stacking order and orientation of the transportable goods 700 based on the test information of each goods 700, and adjusts the placement scheme according to the second transport route 600 and the dynamic adjustment scheme of the goods 700. Finally, the processing unit 100 also adjusts the unloading speed and handling angle based on changes in the geometric features and center of gravity of the goods 700, as well as the unloading position characteristics of the destination 730, forming a second handling mode.

[0045] To address the shortcomings of existing technologies, this invention provides a cargo transportation management device, such as... Figure 1 As shown, it includes a processing unit 100, an image acquisition device 200, and a weight monitoring device 300. The cargo transportation management device of the present invention executes the cargo transportation management method of the present invention.

[0046] Image acquisition device 200 is used to acquire geometric features, marking information features 710, and destination features of cargo 700. Weight monitoring device 300 is used to acquire weight change features and center of gravity change features of cargo 700. Processing unit 100 is used to determine a test mode for cargo 700 based on its geometric features and marking information features 710, and to determine a first handling mode for grasping cargo 700 based on test information obtained based on the test mode. It also determines a second handling mode for unloading cargo 700 based on destination features, changes in geometric features, and / or center of gravity change features during handling in the first handling mode. Processing unit 100 generates a first transport route 500 and predicts the virtual center of gravity change features of cargo 700 based on the first handling mode, geometric features, and center of gravity change features. During handling, the operating parameters of transport robot 400 are dynamically adjusted based on the deviation between the actual center of gravity change features and the virtual center of gravity change features of cargo 700 to maintain the stability of cargo 700.

[0047] The advantages of this invention include: (1) Enhanced adaptability: By collecting the geometric features, marking information features 710 and destination features of cargo 700, the device is able to handle cargo 700 of various sizes and shapes, including non-standard sized cargo 700, thereby overcoming the limitations of the prior art in handling special cargo 700.

[0048] (2) Improve transportation efficiency: The processing unit 100 can determine the most suitable handling mode based on the characteristics of the goods 700 and generate the best transportation route. This not only improves handling efficiency but also reduces the need for manual intervention and optimizes the entire transportation process.

[0049] (3) Ensuring the stability and safety of cargo 700: The application of weight monitoring equipment 300 enables real-time monitoring of the stability of cargo 700 throughout the transportation process. By tracking the changes in the center of gravity of cargo 700 in real time and comparing them with the predicted virtual center of gravity change characteristics, processing unit 100 can dynamically adjust the operating parameters of transport robot 400 to ensure the stability of cargo 700 during transportation and reduce the risk of damage to cargo 700.

[0050] (4) Flexibility and dynamic adjustment capability: This technical solution allows for dynamic adjustment of transportation strategies during the handling of goods 700. In particular, it can make rapid adjustments when faced with changes in the internal environment of the warehouse or unexpected changes in goods 700 during handling, so as to maintain transportation efficiency and cargo safety.

[0051] (5) Reduce labor costs and safety risks: By using automated processing and handling modes, the reliance on manual handling is reduced, thereby reducing safety risks and labor costs caused by manual operation, while improving work efficiency and safety.

[0052] According to a preferred embodiment, the processing unit 100 is communicatively connected to the transport robot 400 via wired or wireless means and controls the operating parameters of the transport robot 400. During transport, if the dynamic adjustment frequency of the transport robot 400 exceeds a frequency threshold and it has not yet approached the destination 730, such as... Figure 4 In the scenario shown, the processing unit 100 optimizes the first transportation route 500 into the second transportation route 600 based on the road condition characteristics and turning characteristics of the preset transportation route.

[0053] Specifically, the processing unit 100 includes a data processing module, a path planning algorithm module, and a decision-making module. The data processing module receives and parses sensor data from the transport robot 400, then transmits the processed data to the path planning algorithm module. The path planning algorithm module dynamically adjusts the transport route based on a preset route, real-time road conditions, and turning characteristics. When the dynamic adjustment frequency of the transport robot 400 exceeds a threshold and it is not approaching its destination, the path planning algorithm module optimizes the first transport route 500 into a second transport route 600. The path planning algorithm module then transmits the second transport route 600 to the decision-making module. The decision-making module evaluates the path planning results and decides whether to send control commands to the transport robot 400. If route optimization is deemed necessary, the decision-making module sends commands to the transport robot 400 via communication software to adjust its operating parameters. Throughout this process, the data processing module ensures data flow and state synchronization between the various software modules.

[0054] For example, the frequency threshold is no more than 5 adjustments per minute. The frequency threshold is not fixed and can be adjusted as needed. Road condition characteristics include ground smoothness, obstacle distribution, and the number of people. Turning characteristics involve turning radius, speed limits, and stability requirements during turns. The first transport route 500 is preset, and its selection by the decision module considers the shortest path and conventional obstacle avoidance strategies. When the dynamic adjustment frequency of the transport robot 400 exceeds the set threshold, and there is still a certain distance to the destination 730, the decision module in the processing unit 100 will initiate an optimization program. The path planning algorithm module analyzes the current road condition and turning characteristics, considering factors such as temporarily stacked goods and areas under maintenance, and uses advanced path planning algorithms, such as A... The algorithm, or Dijkstra's algorithm, combined with a machine learning model, predicts future road condition changes and optimizes the first transportation route 500 into a second transportation route 600. The second transportation route 600 may include alternative routes that bypass temporary obstacles and smoother turning routes to reduce energy consumption and mechanical wear.

[0055] The processing unit 100 sends the second transportation route 600 to the transportation robot 400, guiding it to adjust its route. The transportation robot 400 performs its tasks according to the new route and continuously provides feedback on its performance to the processing unit 100. The processing unit 100 evaluates the optimization effect based on the feedback data and prepares for the next route adjustment.

[0056] This invention enables more flexible and efficient transportation route planning. Through communication with the transportation robot 400, the processing unit 100 can dynamically adjust the transportation route based on actual road conditions and turning situations. Especially when the transportation robot 400 adjusts frequently and is far from the destination 730, this technology can prevent the goods 700 from being damaged or slipping due to excessive vibration or instability, while also avoiding potential delays and obstacles, thereby improving overall transportation efficiency and time management.

[0057] According to a preferred embodiment, such as Figure 3 In the scenario shown, the processing unit 100 (determined by its decision module) determines the test mode of the cargo 700 based on geometric features, marking information features 710, weight distribution features, and center of gravity change features. The test mode includes the gripping point, gripping method, gripping force, and placement shape.

[0058] The decision module determines the test mode for cargo 700 by analyzing the following characteristics: Geometric features: ,in This represents the nth geometric attribute.

[0059] Logo information characteristics: ,in This represents the k-th flag information.

[0060] Weight distribution characteristics: ,in Indicates the first Weight distribution points.

[0061] Characteristics of center of gravity changes: ,in Indicates the first A state of change in the center of gravity.

[0062] Test pattern T consists of the following elements: Catch point: ,in Indicates the first One crawl point.

[0063] Fetching method: ,in Indicates the first One crawling method.

[0064] Scraping strength: ,in Indicates the first The intensity of the capture.

[0065] Placement: ,in Indicates the first Each arrangement.

[0066] Therefore, test mode It can be represented as: 。

[0067] The decision module in processing unit 100 determines the most suitable [factor] by comprehensively analyzing G, M, D, and C. To ensure the safe and efficient handling of cargo 700.

[0068] Preferably, the gripping point Scraping methods , grasping strength and placement Based on pre-entered empirical data, the decision module determines the grasping point when geometric features, marker information feature 710, weight distribution features, and center of gravity change features are determined. Scraping methods , grasping strength and placement Specific information. This invention provides a sample of empirical data.

[0069] Table 1: Sample of empirical data for test modes.

[0070]

[0071] Table 1 provides a simplified sample of empirical data. In actual transportation, due to the varied forms of non-standard goods such as water bags, the empirical data tables will be more numerous and complex.

[0072] This invention enhances the flexibility and accuracy of the transport robot 400 in handling different goods 700 by determining the testing mode, thereby improving the safety and effectiveness of handling operations. This personalized handling mode helps reduce the probability of damage to goods 700 during handling.

[0073] Preferably, the processing unit 100 is equipped with a center of gravity prediction model for virtual center of gravity change characteristics. The center of gravity prediction model is preferably a deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a graph neural network (GNN). Preferably, the center of gravity prediction model can be set on a dedicated integrated chip within the weight monitoring device 300 to determine the center of gravity change characteristics of the cargo 700, thereby reducing the data processing load of the processing unit 100.

[0074] A large number of non-standard sized goods 700 were selected, and their center of gravity change characteristics were collected as data samples during transportation under various road conditions. The data samples were then input into a deep learning model for training. Preferably, the data samples included not only center of gravity change characteristics but also the weight and shape data of the goods 700.

[0075] The following description uses a flexible, non-full water bag as a sample of non-standard sized goods 700. Even when the water bag is placed in a regular cargo box, the goods remain unstable during transportation due to the water bag's swaying and frequent changes in its center of gravity. Therefore, the transport robot 400 needs to properly grip the water bag and its packaging box according to the control instructions or gripping scheme sent by the processing unit 100, so that the water bag can be transported and the non-standard sized goods 700 can be prevented from tipping over or falling off during transportation.

[0076] The data samples include the shape, internal liquid distribution, and temperature data of the water bag in a static state. Deformation data and deformation functions of the fluid under various external forces are input into the deep learning model. Data on the external forces experienced by the transport robot 400 while carrying goods of similar weight to the water bag on the first transport route 500 are also input into the deep learning model. The deep learning model learns and determines the fluid morphology under various road conditions based on the external force data, deformation data, and deformation functions. The deep learning model calculates the center of gravity of the water bag based on a pre-input geometric algorithm for the center of gravity and the fluid morphology. As the water morphology inside the water bag continuously changes, the deep learning model also continuously calculates the center of gravity of the water bag and its change characteristics. After training with a large number of data samples, the deep learning model forms a center of gravity prediction model. The center of gravity prediction model is used to simulate the change characteristics of the center of gravity based on the transport route information.

[0077] Preferably, the center of gravity prediction model also actively constructs a loss function. The center of gravity prediction model includes a formula for the loss function. When the transport robot 400 carries the water bag along the first transport route 500 according to the test mode, the center of gravity prediction model continuously receives external force data, weight distribution characteristics, and image data of the water bag's shape fed back by the transport robot 400, enabling the model to calculate the actual center of gravity change characteristics. The center of gravity prediction model compares the virtual center of gravity change characteristics with the actual center of gravity change characteristics, inputting the differences in various parameters into the formula of the loss function to correct the loss function. When the transport robot 400 transports the water bag again, the center of gravity prediction model can optimize the virtual center of gravity change characteristics based on the loss function.

[0078] Preferably, the processing unit 100 receives data on the overall geometry of the transport robot 400, the action data for grasping goods, and the data on the safe center of gravity range. The center of gravity prediction model calculates the center of gravity of the transport robot 400 in real time based on the overall geometry of the transport robot 400 and the data on the action data for grasping goods. The center of gravity prediction model also performs a fitting calculation based on the real-time center of gravity of the non-standard sized goods 700 and the center of gravity of the transport robot 400 to obtain the overall center of gravity. When the overall center of gravity of the transport robot 400 and the non-standard sized goods 700 approaches the critical value of the safe center of gravity range, the center of gravity prediction model sends information to the control model in the processing unit 100 so that the control model can generate posture adjustment parameters for the transport robot 400 to avoid the transport robot 400 tipping over due to center of gravity shift. According to a preferred embodiment, as... Figure 3In the scenario shown, when at least two goods 700 are being tested, the processing unit 100 generates at least one placement scheme involving the stacking order and placement posture of the transportable goods 700 based on the test information of each goods 700 received in the test mode. The placement scheme is adjusted based on the second transport route 600 and the dynamic adjustment scheme of the goods 700 to form a first handling mode for orderly grasping of goods 700.

[0079] When processing at least two goods 700 for testing, the processing unit 100 performs the following steps: (1) Receive test information from each cargo 700, denoted as T i , where i=1,2,...,n, and n is the quantity of goods.

[0080] (2) Based on test information Generate at least one placement scheme, S j Where j = 1, 2, ..., m, and m is the number of placement schemes. Each placement scheme S j Including stacking order and placement posture, it can be represented as: S j =(O j ,P j Among them, O j Indicates the stacking order, P j Indicate the placement posture.

[0081] (3) Based on the dynamic adjustment plan for the second transportation route 600 and cargo 700, the placement plan S is adjusted. j Adjustments were made to form the first handling pattern for orderly grabbing of goods 700, denoted as B. k Let k = 1, 2, ..., l be the number of transport modes. The adjustment process can be represented as: .

[0082] Where R represents the second transportation route 600, and D represents the dynamic adjustment plan.

[0083] Finally, the processing unit 100 outputs the adjusted transport mode. This guides the orderly grabbing and handling of 700 cargo items.

[0084] This invention can dynamically adjust these schemes according to actual transportation conditions. This allows for the rational stacking of goods 700 and prevents them from being crushed, while also improving the transportation efficiency of transporting multiple goods 700 at once, thereby enhancing the overall efficiency of the goods 700 transportation process.

[0085] According to a preferred embodiment, such as Figure 5As shown, during the process of transporting goods 700 based on the first transport mode, the processing unit 100 adjusts the operating parameters of the transport robot 400 based on the destination characteristics, changes in the geometric features of the goods 700 and / or changes in the center of gravity, and constructs an operating parameter model corresponding to the changes in the geometric features and / or changes in the center of gravity of each goods 700, so as to directly retrieve the operating parameters when the transport robot 400 transports the same goods 700.

[0086] First, define a specific sample value for each parameter: Destination characteristics: Assuming destination characteristics include coordinate location and temperature conditions, they are expressed as: ,in These are the three-dimensional spatial coordinates of the destination 730, and The temperature at the destination is 730. As an example, let... ={(50,75,30),22}.

[0087] Changes in the geometric features of cargo 700 ( ): Considering variations in the length, width, and height of the goods, As an example, let =(2,-1,0) means that the length increased by 2 units, the width decreased by 1 unit, and the height remained unchanged.

[0088] Characteristics of center of gravity change (ΔC): Assuming that the change of the center of gravity can be represented by the offset of the three axes, As an example, let =(0.5,-0.5,0) indicates that the center of gravity has shifted by 0.5 units in the X-axis direction, shifted by 0.5 units in the Y-axis direction, and remained unchanged in the Z-axis direction.

[0089] Initial running parameters ( This may include velocity v, acceleration a, and stability parameters s, for example As an example, let ={5,1,0.75}.

[0090] Adjustment function: This function adjusts the runtime parameters based on changes in destination features, geometric features, and center of gravity. Assuming this function simply adjusts each parameter linearly, it can be written as: .

[0091] in and To adjust the coefficient. As an example, we can take... .

[0092] Running parameter model ( ): This refers to a model that determines operating parameters based on geometric and center-of-gravity variation characteristics. As a simple example, we can assume that the operating parameter model is a linear model that maps these variations to adjusted parameters:

[0093] in And the x-mapping coefficient. You can choose... =(0.1,0,-0.1) and χ=(0.05,-0.05,0).

[0094] Using these sample values, calculate the adjusted operating parameters:

[0095] Running parameter model The output is:

[0096] Therefore, the adjusted operating parameters are: speed 7.45 m / s and acceleration 1.8 m / s². 2 The stability parameter remains at 0.75.

[0097] Therefore, when transporting the same goods 700, the transport robot 400 can directly obtain its operating parameters through the following methods: .

[0098] This ensures that the transport robot 400 can effectively adapt to changes in the characteristics of the cargo 700 and the different requirements of the destination.

[0099] This allows the transport robot 400 to quickly retrieve existing operating parameter models when facing the same type of goods 700, improving the working efficiency of the transport robot 400 and reducing the time consumed during handling.

[0100] According to a preferred embodiment, such as Figure 5 As shown, when the image acquisition device 200 acquires an image of the unloading position of the destination 730, the processing unit 100 reads the unloading position features of the destination 730 and determines the unloading speed and handling angle based on the destination features, changes in the geometric features of the cargo 700, changes in the center of gravity, and unloading position features during the handling process based on the first handling mode, thereby forming a second handling mode.

[0101] When the image acquisition device 200 acquires an image of the unloading location at the destination 730, the processing unit 100 performs the following steps: (1) Read the unloading location characteristics of destination 730, denoted as Q. d .

[0102] (2) Destination characteristics based on the first transport mode The changes in the geometric features of cargo 700 (ΔG), the changes in the center of gravity (ΔC), and the unloading position (Q) are all considered. d Determine the unloading speed. and carrying angle This process can be represented as a function: ( , )=G( ,ΔG,ΔC, )。 Assuming the function is a simple linear combination, it can be defined as follows: = + ΔG+ ΔC+

[0103] θ d =β 1 D f +β 2 ΔG+β 3 ΔC+β 4 Q d in and These are weighting coefficients. As an example, we can take... .

[0104] As an example, let ={(50,75,30),22}; ΔG=(2,-1,0); ΔC=(0.5,-0.5,0); Q d ={(52,76,31),5}. Substituting these sample data into the above formula, the unloading speed can be calculated. and carrying angle .

[0105] The processing unit 100 can accurately calculate the optimal unloading speed and angle based on the image information of the unloading location, combined with the characteristics of the cargo 700 and the handling conditions. This invention not only ensures the safety of the cargo 700 during the unloading process but also improves the efficiency of the unloading operation and optimizes the entire handling process.

[0106] According to a preferred embodiment, during the process of the transport robot 400 performing a gripping test on the cargo 700 based on the test mode, the processing unit 100 calculates the center of gravity change characteristics based on the weight change characteristics of the cargo 700 fed back by the weight monitoring device 300, and adjusts the gripping parameters and gripping angle of the transport robot 400 to prevent the cargo 700 from falling.

[0107] The processing unit 100 adjusts the gripping parameters and gripping angle in real time to cope with possible changes in the center of gravity of the goods 700 during handling, effectively preventing the goods 700 from falling or being damaged. This real-time adjustment mechanism ensures the efficiency and safety of handling the goods 700.

[0108] According to a preferred embodiment, a weight monitoring device 300 is mounted on the gripping assembly of a transport robot 400. Based on an initial three-dimensional image of the cargo 700 acquired by an image acquisition device 200, a processing unit 100 generates a first gripping scheme to be executed by the transport robot 400. During the process of the transport robot 400 adjusting the shape of the cargo 700 based on the first gripping scheme, the information received by the processing unit 100 includes: geometric features and marking information features 710 of the cargo 700 acquired by the image acquisition device 200, and weight distribution features or center of gravity change features of the cargo 700 acquired by the weight monitoring device 300. By optimizing the gripping operation, this invention can improve the accuracy and efficiency of the gripping operation and reduce the time spent on adjustments and retrying.

[0109] This invention provides a cargo transportation management method, such as... Figure 6 As shown, the method includes: S1: Collect the geometric features, marking information features 710, and destination features of cargo 700.

[0110] S2: Collect the center of gravity change characteristics of cargo 700.

[0111] S3: Determine the test mode of cargo 700 based on the geometric features and marking information features 710 of cargo 700.

[0112] S31: Determine the test mode of cargo 700 based on geometric features, marking information features 710, weight distribution features, and center of gravity change features.

[0113] S32: During the process of the transport robot 400 performing a gripping test on the cargo 700 based on the test mode, the processing unit 100 adjusts the gripping parameters and gripping angle of the transport robot 400 based on the center of gravity change characteristics of the cargo 700 fed back by the weight monitoring device 300, so as to prevent the cargo 700 from falling.

[0114] Based on the initial 3D image of the cargo 700 acquired by the image acquisition device 200, a first gripping scheme is generated and executed by the transport robot 400. During the process of the transport robot 400 adjusting the shape of the cargo 700 based on the first gripping scheme, the processing unit 100 receives information including: geometric features and marking information features 710 of the cargo 700 acquired by the image acquisition device 200, and weight distribution features and center of gravity change features of the cargo 700 acquired by the weight monitoring device 300. If, during the execution of the first gripping scheme, the processing unit 100 determines, based on the received information, that the cargo 700 has not been successfully gripped, or that the cargo 700 shows a tendency to fall after gripping, then the processing unit 100 adjusts the first gripping scheme to a second gripping scheme.

[0115] S4: Determine the first handling mode for grabbing cargo 700 based on the test information obtained from the test mode.

[0116] According to a preferred embodiment, when testing at least two goods 700, at least one placement scheme involving the stacking order and placement posture of the transportable goods 700 is generated based on the test information of each goods 700 received in the test mode. The placement scheme is adjusted based on the second transport route 600 and the dynamic adjustment scheme of the goods 700 to form a first handling mode for orderly grasping of goods 700.

[0117] S5: Based on the destination characteristics and the location of the goods 720, retrieve the first transportation route 500.

[0118] S6: Transport goods 700 according to the first handling mode and the first transportation route 500.

[0119] During the handling of goods 700 based on the first handling mode, the operating parameters of the transport robot 400 are adjusted based on the destination characteristics, changes in the geometric features of the goods 700, and / or changes in the center of gravity. An operating parameter model corresponding to the changes in the geometric features and / or changes in the center of gravity of each goods 700 is constructed so that the operating parameters can be directly retrieved when the transport robot 400 transports the same goods 700.

[0120] The steps of the present invention further include steps S7 and S8.

[0121] S7: Adjust the pre-set first transport route 500 according to the first handling mode and geometric characteristics to form a second transport route 600 that transports the goods 700 in a way that dynamically adjusts the center of gravity change characteristics and / or handling characteristics of the goods 700.

[0122] S71: During transportation, if the dynamic adjustment frequency of the transportation robot 400 is greater than the frequency threshold and it is not close to the destination, the first transportation route 500 is optimized into the second transportation route 600 based on the road condition characteristics and turning characteristics of the preset transportation route.

[0123] This invention optimizes transportation routes to adapt to real-time changing environments. The method optimizes transportation routes under specific conditions, such as when the dynamic adjustment frequency of the transport robot 400 exceeds a certain threshold, ensuring maximum transportation efficiency while reducing unnecessary delays and enhancing the flexibility and responsiveness of the transportation process.

[0124] S8: Determine the second handling mode for unloading cargo 700 based on the destination characteristics, changes in the geometric characteristics of cargo 700, and / or changes in the center of gravity during the handling process based on the first handling mode.

[0125] When the image acquisition device 200 acquires an image of the unloading position at the destination, the unloading position features of the destination 730 are read. Based on the destination features, changes in the geometric features of the cargo 700, changes in the center of gravity, and the unloading position features during the handling process based on the first handling mode, the unloading speed and handling angle are determined, thereby forming a second handling mode.

[0126] This invention enables dynamic and adaptive transportation route planning. By considering changes in the center of gravity and geometric features of the cargo 700 during transportation, as well as the dynamic adjustment frequency of the transportation robot 400, this invention can optimize the preset transportation route based on road conditions and turning characteristics even before approaching the destination 730, thereby improving transportation efficiency and adaptability.

[0127] It should be noted that the specific embodiments described above are exemplary. Those skilled in the art can devise various solutions inspired by the disclosure of this invention, and these solutions all fall within the scope of this invention and its protection. Those skilled in the art should understand that this specification and its accompanying drawings are illustrative and not intended to limit the scope of the claims. The scope of protection of this invention is defined by the claims and their equivalents. This specification contains multiple inventive concepts; phrases such as "preferredly" and "according to a preferred embodiment" indicate that the corresponding paragraph discloses an independent concept. The applicant reserves the right to file divisional applications based on each inventive concept.

Claims

1. A cargo transportation management device, characterized in that, include: Image acquisition device (200): Acquires geometric features, marking information features (710), and destination features of goods (700); Weight monitoring device (300): Collects the center of gravity change characteristics of the cargo (700); Processing unit (100): Determines a test mode for the cargo (700) based on the geometric features and the marking information features (710) of the cargo (700), and determines a first handling mode for grasping the cargo (700) based on the test information obtained based on the test mode, and determines a second handling mode for unloading the cargo (700) based on the destination features, the changes in the geometric features of the cargo (700) and / or the changes in the center of gravity during the handling process based on the first handling mode; The processing unit (100) generates a first transport route (500) based on the first transport mode, the geometric features and the center of gravity change features, and predicts the virtual center of gravity change features of the goods (700). During the transport process, the operating parameters of the transport robot (400) are dynamically adjusted based on the deviation between the center of gravity change features of the goods (700) and the virtual center of gravity change features to maintain the stability of the goods (700). The processing unit (100) communicates with the transport robot (400) via wired or wireless means and controls the operating parameters of the transport robot (400). During transportation, if the dynamic adjustment frequency of the transport robot (400) is greater than the frequency threshold and it is not close to the destination (730), the processing unit (100) optimizes the first transport route (500) into a second transport route (600) based on the road condition characteristics and turning characteristics of the preset transport route.

2. The cargo transportation management device according to claim 1, characterized in that, The processing unit (100) is further configured to: The test mode of the cargo (700) is determined based on the geometric features, the marking information features (710), the weight distribution features, and the center of gravity change features. The test modes include gripping point, gripping method, gripping force, and placement pattern.

3. The cargo transportation management device according to claim 2, characterized in that, The processing unit (100) is further configured to: When testing at least two of the goods (700), at least one placement scheme involving the stacking order and placement posture of the transportable goods is generated based on the test information of each of the goods (700) received in the test mode. The placement scheme is adjusted based on the dynamic adjustment scheme of the second transport route (600) and the goods (700) to form the first handling mode of orderly grabbing the goods (700).

4. The cargo transportation management device according to any one of claims 1 to 3, characterized in that, The processing unit (100) is further configured to: During the process of transporting the goods (700) based on the first transport mode, the operating parameters of the transport robot (400) are adjusted based on the destination characteristics, changes in the geometric features of the goods (700), and / or changes in the center of gravity, and an operating parameter model corresponding to the changes in the geometric features and / or changes in the center of gravity of each of the goods (700) is constructed. The operating parameters can be directly retrieved when the transport robot (400) transports the same goods (700).

5. The cargo transportation management device according to any one of claims 1 to 3, characterized in that, The processing unit (100) is further configured to: When the image acquisition device (200) acquires an image of the unloading location at the destination (730), the unloading location feature in the destination features is read. Based on the destination characteristics, the changes in the geometric characteristics of the goods (700), the changes in the center of gravity, and the unloading position characteristics during the first handling mode, the unloading speed and handling angle are determined, thereby forming the second handling mode.

6. The cargo transportation management device according to any one of claims 1 to 3, characterized in that, During the process of the transport robot (400) performing a gripping test on the cargo (700) based on the test mode, the processing unit (100) adjusts the gripping parameters and gripping angle of the transport robot (400) based on the center of gravity change characteristics of the cargo (700) fed back by the weight monitoring device (300) in order to prevent the cargo (700) from falling.

7. The cargo transportation management device according to any one of claims 1 to 3, characterized in that, The weight monitoring device (300) is mounted on the gripping assembly of the transport robot (400). Based on the initial three-dimensional image of the cargo (700) acquired by the image acquisition device (200), the processing unit (100) generates a first gripping scheme to be executed by the transport robot (400). During the process of the transport robot (400) adjusting the shape of the goods (700) based on the first gripping scheme, the information received by the processing unit (100) includes: The geometric features and marking information features (710) of the cargo (700) acquired by the image acquisition device (200), and the weight distribution features and center of gravity change features of the cargo (700) acquired by the weight monitoring device (300).

8. A method for managing cargo transportation, characterized in that, The method includes: Collect the geometric features, marking information features (710), and destination features of the goods (700); Collect the center of gravity change characteristics of the cargo (700); The test mode of the cargo (700) is determined based on the geometric features and the marking information features (710) of the cargo (700), and a first handling mode for grasping the cargo (700) is determined based on the test information obtained based on the test mode. A second handling mode for unloading the cargo (700) is determined based on the destination features, the changes in the geometric features of the cargo (700) and / or the changes in the center of gravity during the handling process based on the first handling mode. The first transport route (500) is adjusted according to the first handling mode and the geometric features to form a second transport route (600) that transports the goods (700) in a manner that dynamically adjusts the center of gravity change features and / or handling features of the goods (700). The method further includes: During transportation, if the dynamic adjustment frequency of the transport robot (400) is greater than the frequency threshold and it is not close to the destination (730), the first transport route (500) is optimized into the second transport route (600) based on the road condition characteristics and turning characteristics of the preset transport route.

Images