Carrying method and system of heavy-load intelligent stacking robot

Abstract

The invention discloses a carrying method and system of a heavy-load intelligent stacking robot. The moving path of the heavy-load intelligent stacking robot is constructed according to the transfer path of an object to be carried, the spatial position of the heavy-load intelligent stacking robot and the motion dimension of the heavy-load intelligent stacking robot. Based on the distribution position of the dynamic obstacle relative to the moving path, the moving speed of the heavy-load intelligent stacking robot and the load state of the heavy-load intelligent stacking robot, intelligent regulation and control of the heavy-load intelligent stacking robot in the moving process are triggered, and dynamic management and control of the heavy-load intelligent stacking robot on the to-be-carried object in the moving process are guaranteed. Therefore, the in-place storage system of the to-be-carried object is determined according to the stress state of the to-be-carried object, the moving state of the heavy-load intelligent stacking robot and the position form of the target position of the to-be-carried object, so that the heavy-load intelligent stacking robot can integrally control the to-be-carried object on the moving level and the in-place level.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy-load intelligent stacking robots, and in particular to a handling method and system of a heavy-load intelligent stacking robot. Background Art

[0002] With the development of science and technology, heavy-loaded intelligent stacking robots are gradually applied to people's lives, and are used to transport objects to be transported in indoor spaces. The objects to be transported are wafer components, chip components or accessories, etc., which are not restricted here. In the prior art, the heavy-loaded intelligent stacking robot moves along a preset moving path, and does not take into account dynamic obstacles and the load status of the heavy-loaded intelligent stacking robot, which affects the dynamic control of the heavy-loaded intelligent stacking robot over the objects during movement, and cannot achieve the overall control of the heavy-loaded intelligent stacking robot over the objects at the moving level and the in-place level. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a handling method and system for a heavy-load intelligent stacking robot.

[0004] An embodiment of the present invention provides a handling method for a heavy-loaded intelligent stacking robot, comprising: in an indoor space, collecting the approach distance of the heavy-loaded intelligent stacking robot relative to an object to be transported; triggering the heavy-loaded intelligent stacking robot to clamp the object to be transported step by step according to the approach distance; determining a transfer path for the object to be transported based on a current position of the object to be transported and a target position of the object to be transported; constructing a moving path for the heavy-loaded intelligent stacking robot according to the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot; determining the distribution position of dynamic obstacles relative to the moving path according to the moving path of the heavy-loaded intelligent stacking robot, a spatial distribution map of the indoor space and a dynamic video, and triggering intelligent regulation of the heavy-loaded intelligent stacking robot during movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-loaded intelligent stacking robot and the load state of the heavy-loaded intelligent stacking robot; collecting the stress state of the object to be transported, and determining an in-place storage system for the object to be transported according to the stress state of the object to be transported, the moving state of the heavy-loaded intelligent stacking robot and the position shape of the target position of the object to be transported.

[0005] An embodiment of the present invention provides a handling system of a heavy-load intelligent stacking robot, the handling system of the heavy-load intelligent stacking robot is applied to the handling method of the heavy-load intelligent stacking robot, and the handling system of the heavy-load intelligent stacking robot comprises: A collection module is used to collect the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported in the indoor space; A clamping module, used for triggering the heavy-duty intelligent stacking robot to clamp the object step by step according to the approach distance; A transfer path module, used to determine a transfer path of the object to be transported based on the current position of the object to be transported and the target position of the object to be transported; A moving path module, used to construct a moving path of the heavy-load intelligent stacking robot according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the motion dimension of the heavy-load intelligent stacking robot; An intelligent control module is used to determine the distribution position of dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space and the dynamic video, and trigger the intelligent control of the heavy-load intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot and the load state of the heavy-load intelligent stacking robot; The positioning storage module is used to collect the stress state of the objects to be transported, and determine the in-place storage system of the objects to be transported according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported.

[0006] In an embodiment of the present invention, through the method in the embodiment of the present invention, in an indoor space, the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported is collected; the step-by-step clamping of the heavy-loaded intelligent stacking robot on the object to be transported is triggered according to the approach distance; the transfer path of the object to be transported is determined based on the current position of the object to be transported and the target position of the object to be transported; the moving path of the heavy-loaded intelligent stacking robot is constructed according to the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, which is compatible with the overall consideration of the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, realizes multi-dimensional control of the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, and ensures the accuracy of the moving path of the heavy-loaded intelligent stacking robot.

[0007] Furthermore, the distribution positions of dynamic obstacles relative to the moving path are determined according to the moving path of the heavy-loaded intelligent stacking robot, the spatial distribution map of the indoor space and the dynamic video, and the intelligent regulation of the heavy-loaded intelligent stacking robot during the movement is triggered based on the distribution positions of the dynamic obstacles relative to the moving path, the moving speed of the heavy-loaded intelligent stacking robot and the load status of the heavy-loaded intelligent stacking robot, thereby ensuring the dynamic control of the heavy-loaded intelligent stacking robot over the transported objects during the movement.

[0008] Therefore, the stress state of the objects to be transported is collected, and the storage system for the objects to be transported is determined according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported. This enables the objects to be transported to be controlled when they are driven by the heavy-load intelligent stacking robot and enter the target position of the objects to be transported, thereby ensuring the accuracy of the storage system for the objects to be transported, so that the heavy-load intelligent stacking robot can perform overall control over the objects to be transported at the moving level and the positioning level. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of an application scenario of a handling method of a heavy-load intelligent stacking robot in one embodiment; Figure 2 is a schematic flow chart of a handling method of a heavy-load intelligent stacking robot in an embodiment of the present invention; Figure 3 Schematic diagram of the structure of the handling system of the heavy-load intelligent stacking robot in an embodiment of the present invention; Figure 4 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0011] Embodiment 1

[0012] The handling method of the heavy-load intelligent stacking robot provided in this application can be applied to Figure 1 In the application environment shown, the computer 102 communicates with the server 104 through the network. The computer 102 can be, but is not limited to, various personal computers, servers, and heavy-duty intelligent stacking robots, and the server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

[0013] Embodiment 2

[0014] See also Figures 1 to 4 A method for handling a heavy-loaded intelligent stacking robot is applied to a handling scenario of a heavy-loaded intelligent stacking robot; the method for handling a heavy-loaded intelligent stacking robot comprises: Step S11: In the indoor space, collecting the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported; Step S12: triggering the heavy-duty intelligent stacking robot to clamp the object step by step according to the approach distance; Step S13: determining a transfer path of the object to be transported based on the current position of the object to be transported and the target position of the object to be transported; Step S14: constructing a moving path of the heavy-load intelligent stacking robot according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the movement dimension of the heavy-load intelligent stacking robot; Step S15: determining the distribution position of the dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space, and the dynamic video, and triggering the intelligent regulation of the heavy-load intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot; Step S16: collecting the stress state of the objects to be transported, and determining the in-place storage system for the objects to be transported according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot, and the position shape of the target position of the objects to be transported.

[0015] In step S11, in the indoor space, the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported is collected; In the specific implementation process of the present invention, the specific steps are: S111: Collect the location of the indoor space; S112: triggering real-time monitoring of the indoor space according to the position of the indoor space; S113: In the indoor space, the location of the heavy-load intelligent stacking robot and the location of the object to be transported are collected; S114: determining a relative distance between the heavy-load intelligent stacking robot and the object to be transported according to the location of the heavy-load intelligent stacking robot and the location of the object to be transported; S115: If the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is less than a preset distance, the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is used to determine the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported, and the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported is collected.

[0016] In an embodiment of the present application, the position of the indoor space is collected; and real-time monitoring of the indoor space is triggered according to the position of the indoor space.

[0017] Specifically, the indoor space is controlled and the location of the indoor space is determined so as to locate the indoor space and monitor the indoor space in real time, thereby dynamically controlling the interior of the indoor space. This usually involves the use of cameras, sensors or other monitoring equipment to monitor dynamic changes in the indoor space in real time.

[0018] Optionally, in large warehouses, heavy-duty intelligent stacking robots need to be deployed to carry objects to be transported. In order to monitor and manage these robots, we first deployed Wi-Fi positioning base stations in various corners and key locations of the warehouse. These base stations are connected to the warehouse management system and can receive and send the location information of the heavy-duty intelligent stacking robots in real time. High-definition cameras and infrared sensors are also installed at key locations. These cameras are connected to the warehouse management system and can monitor the situation inside the warehouse in real time. When the heavy-duty intelligent stacking robot moves in the warehouse, the management system will adjust the monitoring range of the camera in real time according to its location information to ensure that the robot is always under monitoring.

[0019] Furthermore, in the indoor space, the location of the heavy-load intelligent stacking robot and the location of the object to be transported are collected; and the relative distance between the heavy-load intelligent stacking robot and the object to be transported is determined according to the location of the heavy-load intelligent stacking robot and the location of the object to be transported.

[0020] At this time, the location of the heavy-loaded intelligent stacking robot and the location of the objects to be transported are introduced. For the collection of the location of the heavy-loaded intelligent stacking robot, the heavy-loaded intelligent stacking robot is usually equipped with a positioning system, such as GPS (differential GPS or indoor GPS technology may be used in outdoor or special indoor environments), Wi-Fi positioning, Bluetooth positioning, UWB (ultra-wideband) positioning, RFID (radio frequency identification) positioning or visual SLAM (simultaneous localization and mapping), etc.; for the collection of the location of the objects to be transported, positioning tags (such as RFID tags, Bluetooth beacons, etc.) are installed on the objects to be transported. When the heavy-loaded intelligent stacking robot or a fixed reader approaches, the tag information can be read to determine the location of the objects to be transported.

[0021] Optionally, in a large automated warehouse, the heavy-duty intelligent stacking robot is equipped with a UWB positioning system, which can send the location of the heavy-duty intelligent stacking robot to the warehouse management system in real time. At the same time, an RFID tag is installed on the object to be transported. When the heavy-duty intelligent stacking robot approaches the shelf and is ready to transport the object to be transported, it uses its built-in RFID reader to read the tag information to determine the location of the object to be transported.

[0022] After collecting the location of the heavy-load intelligent stacking robot and the location of the object to be transported, the next step is to calculate the relative distance between them based on this information. Specifically, the location of the heavy-load intelligent stacking robot and the location of the object to be transported are expressed in coordinate form (such as x, y coordinates on a two-dimensional plane or x, y, z coordinates in three-dimensional space), and the Euclidean distance formula is used to calculate the relative distance between the heavy-load intelligent stacking robot and the object to be transported. If necessary, other factors such as path obstacles, the robot's mobility (such as turning radius, maximum climbing ability, etc.) and the size and weight of the object to be transported can also be considered to estimate the actual movable distance or adjust the path planning.

[0023] Therefore, if the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is less than the preset distance, the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is used to determine the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported, and the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported is collected.

[0024] At this time, a preset distance is introduced, which is determined based on factors such as the operating range, safety distance and handling efficiency of the heavy-load intelligent stacking robot. For example, the preset distance is 2 meters, which means that when the distance between the heavy-load intelligent stacking robot and the object to be transported is less than 2 meters, the robot is considered to be in a close state.

[0025] Specifically, the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is compared with a preset distance, and the approach process of the heavy-loaded intelligent stacking robot relative to the object to be transported is controlled, so as to further refine the movement of the heavy-loaded intelligent stacking robot.

[0026] When the relative distance between the heavy-duty intelligent stacking robot and the object to be transported is less than the preset distance, the relative distance is regarded as the approach distance of the heavy-duty intelligent stacking robot relative to the object to be transported. Based on this approach distance data, the robot's handling operation instructions, handling speed or path planning are further triggered to ensure the safety and efficiency of the handling process. For example, if the approach distance continues to decrease and is lower than a certain safety threshold (such as 0.5 meters), an emergency stop instruction is triggered to prevent a collision between the robot and the object to be transported.

[0027] In step S12, the heavy-duty intelligent stacking robot is triggered to clamp the object to be transported step by step according to the approach distance; In the specific implementation process of the present invention, the specific steps are: S121: Acquire the approach distance and collect the outer contour of the object to be transported; S122: Determine the shape of the object to be transported according to the outer contour of the object to be transported; S123: Interact with the layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-load intelligent stacking robot; S124: Matching the corresponding clamping system based on the interaction of the layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-duty intelligent stacking robot; S125: Determine a table of approach distance-clamping force relationships according to the traversal of the clamping system; S126: Determine the clamping force of the heavy-load intelligent stacking robot on the object to be transported based on the approach distance-clamping force relationship table and the approach distance, and the clamping force increases step by step as the approach distance decreases, so that the heavy-load intelligent stacking robot clamps the object to be transported step by step.

[0028] In an embodiment of the present application, the approach distance is acquired, and the outer contour of the object to be transported is collected; and the shape of the object to be transported is determined according to the outer contour of the object to be transported.

[0029] The approach distance is obtained by measuring the actual distance between the heavy-load intelligent stacking robot and the object to be transported, that is, the approach distance, in real time through a built-in sensor (such as an ultrasonic sensor, a laser rangefinder or an infrared sensor).

[0030] While obtaining the approach distance, start the visual sensor (such as a camera), laser scanner or depth camera and other equipment to perform an all-round scan of the object to be transported, so as to capture the three-dimensional shape, size and possible surface features of the object to be transported, thereby generating an accurate representation of the outer contour of the object to be transported.

[0031] The outer contour of the object to be transported is introduced, and the outer contour of the object to be transported is recognized and analyzed. By comparing with the preset morphological database or using the morphological recognition algorithm, the specific shape of the object to be transported, such as a rectangle, cylinder, irregular shape, etc., is identified. In addition to recognizing the shape, the system will also extract the key features of the object to be transported, such as size (length, width, height), surface area, volume, and possible fragile parts (such as fragile edges, recessed areas, etc.).

[0032] Specifically, after scanning and generating the three-dimensional outer contour of the box to be transported, the system uses an image processing algorithm to analyze it. By comparing it with a preset morphology database, the system recognizes that the box to be transported is in the shape of a cuboid.

[0033] Furthermore, the system extracts the key features of the box to be transported, including its length of 1.2 meters, width of 0.8 meters, height of 0.6 meters, and no obvious fragile parts. This information will be used for subsequent transport decisions and action planning to ensure the safety and efficiency of the transport process.

[0034] At the same time, the layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-load intelligent stacking robot are interacted with; the corresponding clamping system is matched based on the interaction of the layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-load intelligent stacking robot.

[0035] At this point, the layout style of the indoor space, the form of the objects to be transported, and the model of the heavy-load intelligent stacking robot are introduced. According to the layout style of the indoor space, information about the layout style of the indoor space is collected, which may include the size and shape of the space, shelf layout, aisle width, obstacle location, etc. Then, the morphological information of the objects to be transported is obtained, such as size, shape, weight, material, and possible special handling requirements (such as fragile, requiring specific angles for handling, etc.), and then the model information of the heavy-load intelligent stacking robot is understood, which includes the robot's arm length, grasping ability, moving speed, programmability, etc.

[0036] The layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-load intelligent stacking robot are input into the corresponding decision-making model. The decision-making module is responsible for integrating and interactively analyzing this information and predicting the possibility and effect of different transport solutions.

[0037] According to the handling scheme generated above and the capabilities of the heavy-load intelligent stacking robot, the most suitable clamping mechanism or tool is selected from the preset clamping system library. The selection of the clamping system may be based on a variety of factors, such as the shape and size of the object to be transported, the stability requirements during the handling process, the robot's grasping method and accessibility, etc.; once the clamping system is selected, the system may also need to adjust its parameters to ensure a perfect match with the object to be transported. These parameters may include clamping force, location of clamping point, working mode of the clamping mechanism, etc.

[0038] Specifically, based on the interaction results, a clamping system suitable for large rectangular objects to be transported was selected, which has a wide clamping arm and adjustable clamping force. The parameters of the clamping system were further adjusted to ensure that the clamping arm can firmly clamp the object box to be transported without damaging its surface. The clamping force was set to moderate to maintain stability during transportation while avoiding excessive clamping to cause unnecessary pressure.

[0039] Furthermore, a proximity distance-clamping force relationship table is determined according to the traversal of the clamping system.

[0040] Specifically, a clamping system is introduced and specifically defined. At this point, a comprehensive analysis of the clamping system requires understanding the performance of the clamping system at different approach distances, especially the change in clamping force. The analysis of the clamping system may involve simulation experiments, actual tests, or consulting the technical documentation of the clamping system to obtain accurate data on the relationship between clamping force and approach distance.

[0041] During the traversal process, data about the clamping force at different approach distances are collected. These data may exist in the form of discrete points, each of which represents a specific approach distance and the corresponding clamping force. These data are processed, and interpolation algorithms or other mathematical methods may be used to smooth the data points to obtain a continuous approach distance-clamping force relationship curve, and then a approach distance-clamping force relationship table is formulated. This table is usually listed in discrete approach distance intervals, and each interval corresponds to a recommended clamping force value.

[0042] Optionally, based on the processed data, a table of approach distance-clamping force relationship is formulated. For example, the following relationship is set: When the approach distance is 2 meters, the clamping force is 20% (light contact, ready to adjust the position); When the approach distance is 1 meter, the clamping force increases to 50% (stable clamping, start moving); When the approach distance is 0.5 meters, the clamping force reaches 80% (tight clamping to ensure safe handling).

[0043] Furthermore, the clamping force of the heavy-loaded intelligent stacking robot on the object to be transported is determined based on the approach distance-clamping force relationship table and the approach distance. The clamping force increases step by step as the approach distance decreases, so that the heavy-loaded intelligent stacking robot clamps the object to be transported step by step.

[0044] Specifically, a table of approach distance-clamping force relationship and approach distance is introduced, and the table of approach distance-clamping force relationship and approach distance are matched, so as to output the corresponding clamping force based on the table of approach distance-clamping force relationship, and the heavy-duty intelligent stacking robot adjusts the working state of its clamping mechanism according to the clamping force value found to achieve the required clamping force. This usually involves controlling the motor, pneumatic or hydraulic device of the clamping mechanism of the heavy-duty intelligent stacking robot to change the clamping degree of the clamping claw.

[0045] As the heavy-duty intelligent stacking robot gradually approaches the object to be transported, the approach distance keeps shrinking, and the heavy-duty intelligent stacking robot will gradually increase the clamping force according to the approach distance-clamping force relationship table. This step-by-step clamping method helps ensure stability and safety during the handling process, and avoids damage to the object to be transported or the robot itself caused by sudden clamping actions. During the entire handling process, the heavy-duty intelligent stacking robot may continuously monitor the changes in clamping force and approach distance, and make fine adjustments as needed.

[0046] Optionally, as the heavy-duty intelligent stacking robot continues to approach the box to be transported, the approach distance is gradually reduced to 1.5 meters, 1 meter, and 0.5 meters. At each stage, the heavy-duty intelligent stacking robot will gradually increase the clamping force according to the approach distance-clamping force relationship table until it reaches 90% of the clamping force required for safe handling.

[0047] In step S13, a transfer path of the object to be transported is determined based on the current position of the object to be transported and the target position of the object to be transported; In the specific implementation process of the present invention, the specific steps are: S131: Collect the current position of the object to be transported; S132: Determine a target position of the object to be transported based on the object to be transported and the indoor space; S133: determining a height difference according to a current position of the object to be transported and a target position of the object to be transported; S134: Determine a height transport system based on the height difference and the spatial style of the indoor space; S135: Determine a transfer path for the object to be transported according to the height transport system, the current position of the object to be transported, the horizontal distance between the target position of the object to be transported, and the path planning system corresponding to the indoor space.

[0048] In the embodiment of the present application, the current position of the object to be transported is collected; and the target position of the object to be transported is determined based on the object to be transported and the indoor space.

[0049] Specifically, the current position of the objects to be transported is introduced, and the current position of the objects to be transported is specifically limited. At the same time, the objects to be transported and the indoor space interact. At this time, the properties of the objects to be transported are understood in detail, including their size, weight, material, and whether special treatment is required (such as fragile, toxic, etc.). At the same time, a comprehensive analysis of the indoor space is conducted, including layout, obstacles, aisle width, shelf height, lighting conditions, etc.

[0050] Optionally, an interaction result is output based on the interaction between the object to be transported and the indoor space. The interaction result may be a data set of the object to be transported. The data set of the object to be transported is input into a positioning learning model of the indoor space, and a target position of the object to be transported is output based on the positioning learning model.

[0051] For the training of the positioning learning model, the collected data of the objects to be transported and the indoor space are cleaned, integrated and standardized to improve the training efficiency and accuracy of the model. Key features related to positioning are extracted from the data, such as the size and weight of the objects to be transported, the layout of the indoor space and the location of obstacles, etc. The positioning learning model is trained using machine learning or deep learning algorithms, combined with historical data and real-time data. The goal of the model is to predict the target location of the objects to be transported in the indoor space based on the input data set of the objects to be transported.

[0052] Furthermore, a height difference is determined according to a current position of the object to be transported and a target position of the object to be transported; and a height transport system is determined based on the height difference and a spatial style of the indoor space.

[0053] At this time, the current position of the object to be transported and the target position of the object to be transported are introduced, the current position of the object to be transported and the target position of the object to be transported are controlled, and the height of the current position is compared with the height of the target position to obtain the height difference.

[0054] Alternatively, assume that in a multi-storey warehouse, the object to be transported is currently located at a shelf on the second floor, at a height of 3 meters (relative to the ground on the first floor). The target location is a specific area on the third floor, at a height of 6 meters (relative to the ground on the first floor). Through measurement and calculation, it is concluded that the object to be transported needs to rise 3 meters from the current location to reach the target location.

[0055] At the same time, the height difference and the spatial style of the interior space are introduced. The spatial style of the interior space refers to the overall atmosphere and characteristics displayed by the interior environment. The spatial style of the interior space includes rectangular style, circular style, etc., which are not limited here.

[0056] Optionally, collect data on handling systems under different height differences and different spatial styles, including the type, size, handling efficiency, energy consumption, etc. of handling equipment. At the same time, collect specific parameters of indoor spaces, such as height, area, shape, layout, etc., and extract key features from the collected data, such as the adaptability of handling equipment, space utilization, handling efficiency, etc. For indoor spaces, extract features such as height difference, spatial style, and plane layout. At the same time, use machine learning algorithms (such as neural networks, etc.) to build a model, use the extracted features as input, and the performance of the handling system (such as efficiency, energy consumption, etc.) as output. Use historical data to train the model, adjust the model parameters to improve the prediction accuracy, output the corresponding system learning model, and output the height handling system according to the system learning model.

[0057] Furthermore, the transfer path of the object to be transported is determined according to the height transport system, the current position of the object to be transported, the horizontal distance between the target position of the object to be transported, and the path planning system corresponding to the indoor space.

[0058] Specifically, a height handling system, a horizontal distance between the current position of the object to be transported and the target position of the object to be transported, and a path planning system corresponding to the indoor space are introduced. The horizontal distance between the current position of the object to be transported and the target position of the object to be transported refers to the distance required for the object to be transported to move from the current position to the target position on the horizontal plane. The path planning system corresponding to the indoor space refers to a set of rules and strategies for guiding the heavy-loaded intelligent stacking robot to move safely and efficiently in the indoor space based on factors such as the layout of the indoor space, obstacles, characteristics of the handling equipment and handling requirements.

[0059] The path planning system corresponding to the indoor space usually considers the following factors: Heavy-load intelligent stacking robot: the main handling equipment.

[0060] Obstacles: Identify and mark fixed obstacles (such as walls, columns) and mobile obstacles (such as other handling equipment, people) in indoor spaces.

[0061] Aisle width: Ensure the minimum aisle width that handling equipment can pass through to avoid collision or obstruction.

[0062] Ground conditions: Consider factors such as ground flatness, load-bearing capacity, and whether it is slippery to ensure the stability and safety of the handling equipment.

[0063] Safety regulations: Comply with indoor safety regulations and signs, such as emergency exits, fire escapes, etc.

[0064] Combined with the height transport system, horizontal distance and indoor space path planning system, the optimal transfer path for the objects to be transported is calculated. At this time, the path planning model is collected, the height transport system, horizontal distance and indoor space path planning system are input into the path planning model, and the optimal transfer path for the objects to be transported is output based on the path planning model.

[0065] For the training of the path planning model, collect the structural data of the indoor space, including shelf layout, channel width, obstacle location, etc., collect the performance data of the height handling system, such as the lifting range, moving speed, and turning ability of the heavy-duty intelligent stacking robot, and collect the data of historical handling tasks, including the location of the objects to be transported, the target location, and the transfer path. Extract key features from the collected data, such as the height, weight, and shape of the objects to be transported, extract the layout features of the indoor space, such as the channel direction, obstacle distribution, etc., and extract the performance features of the heavy-duty intelligent stacking robot, such as moving speed and turning radius. Finally, use machine learning algorithms (such as reinforcement learning, deep learning, etc.) to build a path planning model, using the extracted features as input and the optimal transfer path of the objects to be transported as output. Optionally, use historical data to train the model and adjust the model parameters to improve the prediction accuracy.

[0066] S14: constructing a moving path of the heavy-load intelligent stacking robot according to the transfer path of the object to be transported, the spatial position of the heavy-load intelligent stacking robot, and the movement dimension of the heavy-load intelligent stacking robot; In the specific implementation process of the present invention, the specific steps are: S141: Obtaining a transfer path for the object to be transported; S142: determining a plurality of path nodes according to a transfer path of the object to be transported, a moving range of the heavy-load intelligent stacking robot, and a spatial layout of the indoor space; S143: Associating a plurality of path nodes, the spatial position of the heavy-load intelligent stacking robot, and the motion dimension of the heavy-load intelligent stacking robot; S144: Perform multiple interactions on multiple path nodes, the spatial position of the heavy-loaded intelligent stacking robot, and the movement dimensions of the heavy-loaded intelligent stacking robot, and determine and construct a moving path of the heavy-loaded intelligent stacking robot based on the multiple interactions of the multiple path nodes, the spatial position of the heavy-loaded intelligent stacking robot, and the movement dimensions of the heavy-loaded intelligent stacking robot.

[0067] At this time, the transfer path of the objects to be transported is obtained; and a plurality of path nodes are determined according to the transfer path of the objects to be transported, the moving range of the heavy-load intelligent stacking robot, and the spatial layout of the indoor space.

[0068] A transfer path for the objects to be transported is introduced, and the transfer path for the objects to be transported, the moving range of the heavy-load intelligent stacking robot, and the spatial layout of the indoor space are interacted with, fully considering the transfer path for the objects to be transported, the moving range of the heavy-load intelligent stacking robot, and the spatial layout of the indoor space.

[0069] Regarding the moving range of the heavy-duty intelligent stacking robot, the heavy-duty intelligent stacking robot has specific moving capabilities, including maximum moving speed, turning radius, lifting height, etc. Regarding the spatial layout of the indoor space, the spatial layout of the indoor space includes the location and size of shelves, passages, obstacles (such as columns, equipment, etc.). These factors will affect the robot's moving path. For example, narrow passages may limit the robot's turning and moving speed, while tall shelves require the robot to have sufficient lifting capabilities.

[0070] Optionally, a path planning algorithm is used to generate possible paths. The path planning algorithm takes into account the robot's mobility, spatial layout, and any known obstacles. On the generated path, the system determines multiple path nodes based on the robot's characteristics and spatial layout. Multiple path nodes may be points where the robot needs to stop, turn, or adjust its speed, or they may be key points to avoid obstacles or narrow passages. They are compatible with the overall consideration of the transfer path of the objects to be transported, the moving range of the heavy-loaded intelligent stacking robot, and the spatial layout of the indoor space, and realize multi-dimensional control of the transfer path of the objects to be transported, the moving range of the heavy-loaded intelligent stacking robot, and the spatial layout of the indoor space.

[0071] Furthermore, multiple path nodes, spatial positions of the heavy-load intelligent stacking robot, and movement dimensions of the heavy-load intelligent stacking robot are associated.

[0072] At this time, multiple path nodes, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot are introduced. Regarding the spatial position of the heavy-loaded intelligent stacking robot, the spatial position of the heavy-loaded intelligent stacking robot refers to the position of the heavy-loaded intelligent stacking robot in the indoor space. The motion dimension of the heavy-loaded intelligent stacking robot includes the robot's moving speed, turning angle, lifting height, etc. These dimensions jointly determine the motion state and trajectory of the heavy-loaded intelligent stacking robot in space.

[0073] Optionally, a heavy-duty intelligent stacking robot needs to move a batch of objects to be transported from the storage area to the outbound area. The warehouse layout includes multiple shelves, passages, and obstacles, and multiple path nodes are introduced. The starting node is the stacking location of the objects to be transported in the storage area. The intermediate node 1 is the turning point to bypass the obstacle. The intermediate node 2 is the stop point before the lifting shelf. The end node is the stacking location of the objects to be transported in the outbound area.

[0074] The heavy-loaded intelligent stacking robot obtains its own position information in real time through laser radar and visual cameras. At the starting node, the heavy-loaded intelligent stacking robot confirms that it is located at the stacking position of the objects to be transported in the storage area. At this time, at the starting node, the heavy-loaded intelligent stacking robot starts to accelerate and prepare to enter the transportation state. At the intermediate node 1, the heavy-loaded intelligent stacking robot adjusts the steering angle to bypass obstacles. At the intermediate node 2, the heavy-loaded intelligent stacking robot lowers the lifting arm, grabs the objects to be transported, and lifts the lifting arm to an appropriate height. At the end node, the heavy-loaded intelligent stacking robot slows down and accurately locates the stacking position of the objects to be transported in the storage area, and puts down the objects to be transported.

[0075] Furthermore, multiple interactions are performed on multiple path nodes, the spatial positions of the heavy-loaded intelligent stacking robot, and the movement dimensions of the heavy-loaded intelligent stacking robot, and the moving path of the heavy-loaded intelligent stacking robot is determined based on the multiple interactions of the multiple path nodes, the spatial positions of the heavy-loaded intelligent stacking robot, and the movement dimensions of the heavy-loaded intelligent stacking robot.

[0076] At this time, multiple interactions of multiple path nodes, the spatial positions of the heavy-loaded intelligent stacking robot, and the motion dimensions of the heavy-loaded intelligent stacking robot are introduced, covering the interactions of multiple path nodes and the spatial positions of the heavy-loaded intelligent stacking robot, the interactions of multiple path nodes and the motion dimensions of the heavy-loaded intelligent stacking robot, and the spatial positions of the heavy-loaded intelligent stacking robot and the motion dimensions of the heavy-loaded intelligent stacking robot.

[0077] For the interaction of multiple path nodes and the spatial position of the heavy-duty intelligent stacking robot, it is necessary to determine the specific spatial position of each path node. The heavy-duty intelligent stacking robot will match the preset path nodes according to its current spatial position to determine which node it is near or which position segment between nodes. The heavy-duty intelligent stacking robot can accurately know its position in space, as well as the distance and direction to the next path node.

[0078] For the interaction of multiple path nodes and the motion dimensions of the heavy-duty intelligent stacking robot, each path node contains specific motion instructions, which determine the motion dimensions of the heavy-duty intelligent stacking robot at that node, such as speed, steering angle, lifting height, etc. The heavy-duty intelligent stacking robot will adjust its own motion state according to the instructions of the current node. The robot can accelerate, decelerate, turn, lift, etc. according to the instructions to ensure the accuracy and safety of the motion trajectory.

[0079] In view of the interaction between the spatial position of the heavy-loaded intelligent stacking robot and the movement dimension of the heavy-loaded intelligent stacking robot, the heavy-loaded intelligent stacking robot will adjust the movement dimension in real time according to the changes in its own spatial position during movement. For example, when the heavy-loaded intelligent stacking robot approaches an obstacle, it will automatically slow down and adjust the steering angle to avoid collision. The heavy-loaded intelligent stacking robot can adjust its movement state in real time according to environmental changes to ensure stable and safe movement in complex environments.

[0080] Furthermore, in the model learning method, a reinforcement learning algorithm can be used to train the heavy-duty intelligent stacking robot for path planning. Reinforcement learning is a method of learning strategies by interacting with the environment. The heavy-duty intelligent stacking robot learns how to select the optimal path node according to different spatial positions and motion dimensions through continuous trial and error.

[0081] In reinforcement learning, the current spatial position and motion dimension of the heavy-loaded intelligent stacking robot are defined as the state, and the selection of the next path node is defined as the action. The heavy-loaded intelligent stacking robot selects an action based on the current state and observes the result (i.e., the next state and reward). The reward function is used to evaluate the quality of the action selected by the heavy-loaded intelligent stacking robot. In path planning, the reward function can be designed as a reward for reaching the target node, a reward for avoiding obstacles, and a penalty for moving distance. Through continuous iteration and optimization of strategies, the heavy-loaded intelligent stacking robot can learn how to select the optimal action in different states, thereby building an efficient moving path.

[0082] Therefore, the overall consideration of the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot and the movement dimension of the heavy-load intelligent stacking robot is compatible, and the multi-dimensional control of the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot and the movement dimension of the heavy-load intelligent stacking robot is realized, ensuring the accuracy of the moving path of the heavy-load intelligent stacking robot.

[0083] S15: determining the distribution position of the dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space, and the dynamic video, and triggering the intelligent control of the heavy-load intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot; In the specific implementation process of the present invention, the specific steps are: S151: Obtaining the moving path of the heavy-load intelligent stacking robot; S152: Determine a first position feature based on the moving path of the heavy-load intelligent stacking robot and the spatial distribution map of the indoor space; determine a second position feature based on the moving path of the heavy-load intelligent stacking robot and the dynamic video; S153: Determine the distribution position of the dynamic obstacle relative to the moving path according to the first position feature, the second position feature and the current position of each obstacle; S154: Obtaining the distribution position of the dynamic obstacles relative to the moving path; S155: collecting an intelligent control model, and inputting the distribution position of the dynamic obstacle relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot into the intelligent control model; S156: Outputting corresponding intelligent instructions based on the intelligent control model, and triggering intelligent control of the heavy-load intelligent stacking robot during the movement according to the intelligent instructions.

[0084] At this time, the moving path of the heavy-loaded intelligent stacking robot is obtained; the first position feature is determined based on the moving path of the heavy-loaded intelligent stacking robot and the spatial distribution map of the indoor space; and the second position feature is determined based on the moving path of the heavy-loaded intelligent stacking robot and the dynamic video.

[0085] Specifically, the first position feature and the second position feature are introduced to facilitate subsequent control of the first position feature and the second position feature.

[0086] In the first position feature, it involves matching the moving path with the spatial distribution map of the indoor space to determine the specific position of the heavy-loaded intelligent stacking robot in the space. By comparing the moving path of the heavy-loaded intelligent stacking robot with the spatial distribution map, the position characteristics of the heavy-loaded intelligent stacking robot at different time points can be determined, such as which static obstacles it is approaching, which area it is in, etc.; Optionally, in the above-mentioned warehouse, the calculated optimal path is matched with the spatial distribution map of the warehouse. Assuming that the heavy-loaded intelligent stacking robot approaches a wall during its movement, then this position feature is "approaching the wall"; In the second position feature, it involves using dynamic video information to determine the position feature of the heavy-duty intelligent stacking robot. Dynamic video can provide real-time obstacle information, such as personnel, other moving vehicles, etc. By analyzing dynamic video, the relative position of the heavy-duty intelligent stacking robot at different time points can be determined, such as the distance to surrounding objects, relative speed, etc. In the above warehouse, through the dynamic video captured by the surveillance camera, it is found that a worker is walking along the predetermined path of the heavy-duty intelligent stacking robot. By analyzing the video, the relative position and relative speed of the heavy-duty intelligent stacking robot and the worker can be determined, thereby obtaining the second position feature, such as "the worker is walking 5 meters ahead at a speed of about 1m / s."

[0087] Furthermore, the distribution positions of the dynamic obstacles relative to the moving path are determined according to the first position feature, the second position feature and the current position of each obstacle.

[0088] Specifically, the first position feature, the second position feature and the current position of each obstacle are introduced, and the first position feature, the second position feature and the current position of each obstacle are comprehensively analyzed. Through comparative analysis, the specific position of dynamic obstacles (such as personnel, other moving vehicles) relative to the moving path can be determined, such as whether they are on the path, the distance from the path, etc. This helps to evaluate the impact of dynamic obstacles on the movement of the heavy-load intelligent stacking robot and take corresponding obstacle avoidance measures.

[0089] Optionally, in combination with the above example, based on the first position feature "close to the wall" and the second position feature "the worker is walking 5 meters ahead at a speed of about 1m / s", as well as the current position information of the worker, it can be determined that the distribution position of the worker relative to the moving path is "on the path, 5 meters away from the heavy-load intelligent stacking robot". This means that the heavy-load intelligent stacking robot needs to take obstacle avoidance measures, such as slowing down or changing the path, to avoid collision with the worker.

[0090] Therefore, the distribution position of dynamic obstacles relative to the moving path is obtained; the intelligent control model is acquired, and the distribution position of dynamic obstacles relative to the moving path, the moving speed of the heavy-loaded intelligent stacking robot, and the load state of the heavy-loaded intelligent stacking robot are input into the intelligent control model.

[0091] Optionally, the intelligent control model is a preset learning model, which is usually based on machine learning or deep learning algorithms and can output optimal control instructions based on multiple parameters such as input dynamic obstacle information, robot movement speed, load status, etc. The intelligent control model may include multiple sub-modules such as a path planning module, an obstacle avoidance strategy module, and a speed control module, each of which is responsible for processing specific tasks.

[0092] For the training of the intelligent control model, the heavy-duty intelligent stacking robot needs to follow a preset path from shelf A to delivery port B. There may be dynamic obstacles (such as workers or other mobile devices) on the path. By collecting data on the location of dynamic obstacles, robot movement speed, and load status, and performing preprocessing and feature engineering, we select a neural network model for training. During the training process, we use the gradient descent algorithm to minimize the loss function and find the optimal learning rate and regularization coefficient through grid search. Finally, we use the test set to evaluate the model and obtain a high accuracy and recall rate to output the intelligent control model.

[0093] At this time, data about dynamic obstacles, the moving speed and load status of heavy-loaded intelligent stacking robots are collected from actual scenarios. The data should cover a variety of scenarios to ensure the generalization ability of the model. The collected data is cleaned to remove noise and outliers, and the preprocessed data is output. The preprocessed data is divided into training set, validation set and test set. The training set is used to update the model parameters, the validation set is used to evaluate the model performance and adjust the hyperparameters, and the test set is used to finally evaluate the generalization ability of the model. The model is trained using the training set, and the loss function is minimized through iterative optimization algorithms (such as gradient descent). The performance of the model, such as loss value and accuracy, is monitored during the training process. Grid search, random search or Bayesian optimization methods are used to find the optimal hyperparameter combination. The performance of the model under different hyperparameter combinations is evaluated on the validation set to output the intelligent control model.

[0094] The distribution of dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load status of the heavy-load intelligent stacking robot are passed as input parameters to the intelligent control model. The intelligent control model will analyze and calculate based on these input parameters, and then output the optimal control instructions, such as changing the path, slowing down to avoid obstacles, pausing movement, etc.

[0095] At the same time, the corresponding intelligent instructions are output based on the intelligent control model, and the intelligent control of the heavy-loaded intelligent stacking robot during the movement is triggered according to the intelligent instructions.

[0096] At this point, the intelligent control model first receives real-time data from the heavy-duty intelligent stacking robot and its surrounding environment. These data include but are not limited to the position, speed, and direction of dynamic obstacles, the robot's current position, speed, acceleration, and load status. The intelligent control model uses machine learning or deep learning algorithms to calculate and analyze the input data. After calculation and analysis, the model outputs specific intelligent instructions to guide the next action of the heavy-duty intelligent stacking robot.

[0097] Specifically, the control system of the heavy-duty intelligent stacking robot receives and analyzes the instructions from the intelligent control model. According to the analyzed instructions, the robot starts to perform the corresponding intelligent control actions. The model will dynamically adjust according to the real-time feedback data to ensure the accuracy and effectiveness of the control instructions. For example, if the position of an obstacle changes, the model will immediately update the instructions to guide the robot to perform new obstacle avoidance actions.

[0098] S16: collecting the stress state of the object to be transported, and determining the in-place storage system of the object to be transported according to the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot, and the position shape of the target position of the object to be transported; In the specific implementation process of the present invention, the specific steps are: S161: collecting a real-time image of the object to be transported based on the positioning monitoring of the object to be transported; S162: determining the stress state of the object to be transported according to the real-time image of the object to be transported, the shape of the object to be transported, and the clamping force of the heavy-load intelligent stacking robot on the object to be transported, so as to collect the stress state of the object to be transported; S163: collecting movement signals of the heavy-load intelligent stacking robot, and determining a plurality of movement parameters of the heavy-load intelligent stacking robot according to the movement signals of the heavy-load intelligent stacking robot; S164: Determine the movement state of the heavy-load intelligent stacking robot according to multiple movement parameters of the heavy-load intelligent stacking robot; S165: multiple interactions are performed on the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot, and the position and shape of the target position of the object to be transported; S166: Determine the in-place storage system for the object to be transported according to multiple interactions of the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot, and the position shape of the target position of the object to be transported.

[0099] At this time, based on the positioning monitoring of the object to be transported, a real-time image of the object to be transported is collected; the stress state of the object to be transported is determined according to the real-time image of the object to be transported, the shape of the object to be transported, and the clamping force of the heavy-duty intelligent stacking robot on the object to be transported, so as to collect the stress state of the object to be transported; Specifically, cameras, infrared sensors, laser rangefinders and other devices are usually used to locate and monitor the objects to be transported. These devices can capture the location information of the objects to be transported in real time, and the camera is the main device for collecting real-time images. It is usually installed in a fixed position of the heavy-duty intelligent stacking robot, such as the end of the robotic arm or a corner of the vehicle body. When the heavy-duty intelligent stacking robot approaches the objects to be transported, the camera will start and capture the real-time image of the objects to be transported. The collected real-time image may need to undergo some pre-processing, such as denoising, contrast enhancement, etc., to improve the accuracy of subsequent analysis.

[0100] The collected real-time images are analyzed to identify the outline, size and other information of the objects to be transported. This can be achieved through image processing technologies such as edge detection and shape matching. In addition to image analysis, the physical form of the objects to be transported, such as weight, texture, fragility, etc., needs to be considered. This information can usually be pre-entered in the warehouse management system. When the heavy-duty intelligent stacking robot clamps the objects to be transported, it will monitor the clamping force through one or more force sensors. These sensors can provide real-time feedback on the size of the clamping force, thereby helping to determine the stress state of the objects to be transported. Combined with the results of image analysis, morphological considerations and clamping force monitoring, the stress state of the objects to be transported can be comprehensively judged. For example, if the object to be transported is fragile and the clamping force is too large, it can be judged that it is in a potential state of excessive force.

[0101] Specifically, when the robot approaches the box of glass products, the camera on it begins to capture real-time images. These images show the box outline, size, and stacking stability of the glass products. By analyzing the real-time images, the robot recognizes that the box of glass products is fragile and of moderate size. At the same time, the weight information of the box of glass products is obtained from the warehouse management system. When the robot is ready to clamp the box of glass products, its force sensor begins to monitor the clamping force. In order to ensure that the glass products are not damaged, the robot will adjust the clamping force to a safe range. Combining the results of image analysis, morphological considerations, and clamping force monitoring, the robot determines that the box of glass products is in a safe stress state.

[0102] At the same time, the movement signal of the heavy-loaded intelligent stacking robot is collected, and multiple movement parameters of the heavy-loaded intelligent stacking robot are determined according to the movement signal of the heavy-loaded intelligent stacking robot; and the movement state of the heavy-loaded intelligent stacking robot is determined according to the multiple movement parameters of the heavy-loaded intelligent stacking robot.

[0103] Specifically, the mobile signal of the heavy-loaded intelligent stacking robot was introduced, and the signal preprocessing was performed on the mobile signal of the heavy-loaded intelligent stacking robot, including filtering and denoising, to improve the accuracy of the data. The signal processing algorithm was used to extract the robot's movement parameters, such as position, speed, acceleration, moving direction, etc., from the preprocessed signal.

[0104] The robot's movement state is analyzed based on the extracted movement parameters. During the state analysis, the robot's movement state can also be detected for abnormalities. At this time, the speed parameter can be used to determine whether the robot is moving, the acceleration parameter can be used to determine whether the robot is accelerating or decelerating, and the position parameter can be used to determine whether the robot is moving on the predetermined track. If the speed parameter changes suddenly and drastically, it may mean that the robot has encountered an obstacle or a fault.

[0105] Furthermore, multiple interactions are performed on the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot, and the position shape of the target position of the objects to be transported; and the in-place storage system for the objects to be transported is determined based on the multiple interactions of the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot, and the position shape of the target position of the objects to be transported.

[0106] At this time, multiple interactions of the stress state of the objects to be transported, the moving state of the heavy-loaded intelligent stacking robot and the positional morphology of the target position of the objects to be transported are introduced, covering the interaction of the stress state of the objects to be transported and the moving state of the heavy-loaded intelligent stacking robot, the interaction of the stress state of the objects to be transported and the positional morphology of the target position of the objects to be transported, and the interaction of the moving state of the heavy-loaded intelligent stacking robot and the positional morphology of the target position of the objects to be transported.

[0107] In view of the interaction between the stress state of the object to be transported and the movement state of the heavy-duty intelligent stacking robot, when the weight or center of gravity of the object to be transported exceeds the normal handling range of the robot, the robot needs to adjust its movement strategy. Real-time monitoring of the stress state can help the robot to promptly detect potential handling risks and take corresponding preventive measures. At the same time, the robot's movement state (such as acceleration, deceleration, turning radius, etc.) will directly affect the stress state of the object to be transported. For example, rapid acceleration or deceleration may cause the object to be transported to shake or tilt. Therefore, the robot needs to dynamically adjust its movement strategy according to the stress state information of the object to be transported to reduce the adverse effects on the object to be transported.

[0108] Regarding the interaction between the stress state of the object to be transported and the positional shape of the target location of the object to be transported, information such as the weight, shape and center of gravity position of the object to be transported will affect its stability and safety when placed at the target location. The positional shape of the target location (such as the shelf height, the load-bearing capacity of the shelf, the size and shape of the storage space, etc.) will also affect the stress state of the object to be transported. Therefore, when selecting the target location, it is necessary to comprehensively consider the stress state of the object to be transported and the positional shape of the target location to ensure the smooth progress of the transportation process.

[0109] Regarding the interaction between the movement state of the heavy-load intelligent stacking robot and the positional shape of the target position of the objects to be transported, the movement state of the heavy-load intelligent stacking robot (such as speed, acceleration, steering ability, etc.) will affect its efficiency and accuracy in reaching the target position. The positional shape of the target position will also affect the robot's movement strategy. Therefore, the robot needs to dynamically adjust its movement strategy according to the positional shape information of the target position to ensure the smooth progress of the handling process.

[0110] In practical applications, the multiple interactions between the stress state of the objects to be transported, the movement state of the heavy-duty intelligent stacking robot, and the position and shape of the target position of the objects to be transported are interrelated and influence each other. Therefore, when planning the transport task, it is necessary to comprehensively consider the interaction between these three factors and optimize them. For example, advanced algorithms and technical means (such as machine learning, path planning algorithms, etc.) can be used to intelligently plan and schedule the transport tasks to achieve the optimization of multiple interactions. At the same time, real-time monitoring and feedback mechanisms can be used to timely discover and deal with potential transport risks to ensure the safety and efficiency of the transport process.

[0111] Finally, the storage system for objects to be transported refers to a comprehensive system that ensures that the objects to be transported can be stored safely, efficiently and orderly at the designated location, covering the properties of the objects to be transported, the capabilities of the heavy-duty intelligent stacking robot, and the location and shape of the target location.

[0112] At this time, based on the properties of the objects to be transported, determine the weight, size, shape and center of gravity of the objects to be transported, and evaluate the forces that the objects to be transported may be subjected to during the transportation process, such as gravity, inertia, etc. At the same time, consider factors such as the material, fragility, and corrosiveness of the objects to be transported, which may affect the storage method and transportation strategy.

[0113] Regarding the capabilities of the heavy-load intelligent stacking robot, understand the robot's maximum handling weight, moving speed, acceleration, steering ability, etc., determine the robot's energy consumption, stability and maintenance requirements in different states. At the same time, consider whether the robot has functions such as automatic navigation, obstacle avoidance, and path planning, and evaluate the robot's integration capabilities with the warehouse management system to achieve automated handling and storage.

[0114] According to the location and shape of the target location, measure the size, height, load-bearing capacity of the storage area, determine the type, number of layers, spacing and access method of the storage shelves, consider the relative position relationship between the storage area and the entrances and exits, passages, and other equipment, and evaluate the safety, convenience and scalability of the storage area.

[0115] For the in-place storage system, a detailed transportation plan is formulated according to the properties of the objects to be transported, the capabilities of the robot, and the location and shape of the target location, including factors such as the transportation route, transportation time, and transportation method. The transportation task is carried out according to the transportation plan, and the objects to be transported are placed safely and accurately at the target location. The force state, robot movement state, and changes in storage position during the transportation process are monitored in real time, and the storage system is adjusted and optimized according to the actual situation during the transportation process.

[0116] Therefore, the control of the objects to be transported entering the target position of the objects to be transported is achieved under the drive of the heavy-load intelligent stacking robot, which ensures the accuracy of the storage system for the objects to be transported, so that the heavy-load intelligent stacking robot can perform overall control of the objects to be transported at the moving level and the in-place level.

[0117] In an embodiment of the present invention, through the method in the embodiment of the present invention, in an indoor space, the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported is collected; the step-by-step clamping of the heavy-loaded intelligent stacking robot on the object to be transported is triggered according to the approach distance; the transfer path of the object to be transported is determined based on the current position of the object to be transported and the target position of the object to be transported; the moving path of the heavy-loaded intelligent stacking robot is constructed according to the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, which is compatible with the overall consideration of the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, realizes multi-dimensional control of the transfer path of the object to be transported, the spatial position of the heavy-loaded intelligent stacking robot and the motion dimension of the heavy-loaded intelligent stacking robot, and ensures the accuracy of the moving path of the heavy-loaded intelligent stacking robot.

[0118] Furthermore, the distribution positions of dynamic obstacles relative to the moving path are determined according to the moving path of the heavy-loaded intelligent stacking robot, the spatial distribution map of the indoor space and the dynamic video, and the intelligent regulation of the heavy-loaded intelligent stacking robot during the movement is triggered based on the distribution positions of the dynamic obstacles relative to the moving path, the moving speed of the heavy-loaded intelligent stacking robot and the load status of the heavy-loaded intelligent stacking robot, thereby ensuring the dynamic control of the heavy-loaded intelligent stacking robot over the transported objects during the movement.

[0119] Therefore, the stress state of the objects to be transported is collected, and the storage system for the objects to be transported is determined according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported. This enables the objects to be transported to be controlled when they are driven by the heavy-load intelligent stacking robot and enter the target position of the objects to be transported, thereby ensuring the accuracy of the storage system for the objects to be transported, so that the heavy-load intelligent stacking robot can perform overall control over the objects to be transported at the moving level and the positioning level.

[0120] Embodiment 3

[0121] See also Figure 3 , Figure 3 It is a schematic diagram of the structural composition of the handling system of the heavy-load intelligent stacking robot in an embodiment of the present invention.

[0122] like Figure 3 As shown, a handling system of a heavy-load intelligent stacking robot, the handling system of the heavy-load intelligent stacking robot comprises: The acquisition module 21 is used to acquire the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported in the indoor space; A clamping module 22, used for triggering the heavy-duty intelligent stacking robot to clamp the object to be transported step by step according to the approach distance; A transfer path module 23, for determining a transfer path of the object to be transported based on the current position of the object to be transported and the target position of the object to be transported; A moving path module 24, used to construct a moving path of the heavy-load intelligent stacking robot according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the movement dimension of the heavy-load intelligent stacking robot; The intelligent control module 25 is used to determine the distribution position of the dynamic obstacles relative to the moving path according to the moving path of the heavy-loaded intelligent stacking robot, the spatial distribution map of the indoor space and the dynamic video, and trigger the intelligent control of the heavy-loaded intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-loaded intelligent stacking robot and the load state of the heavy-loaded intelligent stacking robot; The positioning storage module 26 is used to collect the stress state of the objects to be transported, and determine the in-place storage system of the objects to be transported according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported.

[0123] Embodiment 4

[0124] In this embodiment, an electronic device is provided. Its internal structure diagram can be shown as follows: Figure 4As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and the non-volatile storage medium is deployed with a database, which is used to store user behavior data and user portraits. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with other electronic devices that deploy application software. When the computer program is executed by the processor, a low-altitude patrol method of a drone is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0125] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for handling a heavy-load intelligent stacking robot, characterized in that: include: In indoor space, collect the approach distance of the heavy-load intelligent stacking robot relative to the objects to be transported; The heavy-duty intelligent stacking robot is triggered to clamp the objects to be transported step by step according to the approach distance; Determine a transfer path for the object to be transported based on the current position of the object to be transported and the target position of the object to be transported; Constructing a moving path of the heavy-load intelligent stacking robot according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the motion dimension of the heavy-load intelligent stacking robot; Determine the distribution position of dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space, and the dynamic video, and trigger the intelligent regulation of the heavy-load intelligent stacking robot during movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load status of the heavy-load intelligent stacking robot; The stress state of the objects to be transported is collected, and the in-place storage system of the objects to be transported is determined according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported.

2. The handling method of the heavy-load intelligent stacking robot according to claim 1, characterized in that: The method of collecting the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported in the indoor space includes: Collect the location of the indoor space; Trigger real-time monitoring of indoor spaces based on their location; In the indoor space, collect the location of the heavy-load intelligent stacking robot and the location of the objects to be transported; Determine the relative distance between the heavy-load intelligent stacking robot and the object to be transported according to the location of the heavy-load intelligent stacking robot and the location of the object to be transported; If the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is less than the preset distance, the relative distance between the heavy-loaded intelligent stacking robot and the object to be transported is used to determine the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported, and the approach distance of the heavy-loaded intelligent stacking robot relative to the object to be transported is collected.

3. The handling method of the heavy-load intelligent stacking robot according to claim 2, characterized in that: The step of triggering the heavy-load intelligent stacking robot to clamp the object to be transported step by step according to the approach distance includes: Obtain the approach distance and collect the outer contour of the object to be transported; Determine the shape of the object to be transported according to its outer contour; Interact with the layout style of the indoor space, the shape of the objects to be transported, and the model of the heavy-load intelligent stacking robot; Match the corresponding clamping system based on the layout style of the indoor space, the shape of the objects to be transported and the interaction of the model of the heavy-duty intelligent stacking robot; Determine the approach distance-clamping force relationship table according to the traversal of the clamping system; The clamping force of the heavy-loaded intelligent stacking robot on the object to be transported is determined based on the approach distance-clamping force relationship table and the approach distance. The clamping force increases step by step as the approach distance decreases, so that the heavy-loaded intelligent stacking robot clamps the object step by step.

4. The method for handling a heavy-load intelligent stacking robot according to claim 3, characterized in that: The step of determining the transfer path of the object to be transported based on the current position of the object to be transported and the target position of the object to be transported includes: Collect the current location of the object to be transported; Determine the target location of the object to be transported based on the object to be transported and the indoor space; Determine the height difference based on the current position of the object to be transported and the target position of the object to be transported; Determine the height transport system based on the height difference and the spatial style of the interior space; The transfer path of the object to be transported is determined according to the height transport system, the current position of the object to be transported, the horizontal distance between the target position of the object to be transported, and the path planning system corresponding to the indoor space.

5. The method for handling a heavy-load intelligent stacking robot according to any one of claims 1 to 4, characterized in that: The moving path of the heavy-load intelligent stacking robot is constructed according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the movement dimension of the heavy-load intelligent stacking robot, including: Obtain the transfer path of the object to be transported; Determine multiple path nodes according to the transfer path of the objects to be transported, the moving range of the heavy-load intelligent stacking robot, and the spatial layout of the indoor space; Associating multiple path nodes, the spatial positions of the heavy-load intelligent stacking robot, and the motion dimensions of the heavy-load intelligent stacking robot; Multiple interactions are performed on multiple path nodes, the spatial positions of the heavy-load intelligent stacking robot, and the motion dimensions of the heavy-load intelligent stacking robot, and the moving path of the heavy-load intelligent stacking robot is determined and constructed based on the multiple interactions of the multiple path nodes, the spatial positions of the heavy-load intelligent stacking robot, and the motion dimensions of the heavy-load intelligent stacking robot.

6. The method for transporting a heavy-load intelligent stacking robot according to claim 5, characterized in that: The method of determining the distribution position of the dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space, and the dynamic video, and triggering the intelligent regulation of the heavy-load intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot, includes: Obtain the moving path of the heavy-load intelligent stacking robot; Determine the first position feature based on the moving path of the heavy-load intelligent stacking robot and the spatial distribution map of the indoor space; determine the second position feature based on the moving path of the heavy-load intelligent stacking robot and the dynamic video; The distribution positions of the dynamic obstacles relative to the moving path are determined according to the first position feature, the second position feature and the current position of each obstacle.

7. The method for transporting a heavy-load intelligent stacking robot according to claim 6, characterized in that: The method further includes determining the distribution position of dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space, and the dynamic video, and triggering the intelligent regulation of the heavy-load intelligent stacking robot during the moving process based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot. Obtain the distribution position of dynamic obstacles relative to the moving path; Collecting the intelligent control model, and inputting the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot, and the load state of the heavy-load intelligent stacking robot into the intelligent control model; Based on the intelligent control model, the corresponding intelligent instructions are output, and the intelligent control of the heavy-load intelligent stacking robot during the movement is triggered according to the intelligent instructions.

8. The method for transporting a heavy-load intelligent stacking robot according to claim 7, characterized in that: The method of collecting the stress state of the object to be transported and determining the in-place storage system of the object to be transported according to the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the object to be transported includes: Based on the positioning monitoring of the object to be transported, a real-time image of the object to be transported is collected; The stress state of the object to be transported is determined according to the real-time image of the object to be transported, the shape of the object to be transported and the clamping force of the heavy-load intelligent stacking robot on the object to be transported, so as to collect the stress state of the object to be transported.

9. The method for transporting a heavy-load intelligent stacking robot according to claim 8, characterized in that: The collecting of the stress state of the object to be transported and determining the in-place storage system of the object to be transported according to the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the object to be transported also include: Collecting movement signals of the heavy-load intelligent stacking robot, and determining a plurality of movement parameters of the heavy-load intelligent stacking robot according to the movement signals of the heavy-load intelligent stacking robot; Determine the moving state of the heavy-load intelligent stacking robot according to multiple moving parameters of the heavy-load intelligent stacking robot; Multiple interactions are performed on the stress state of the object to be transported, the moving state of the heavy-load intelligent stacking robot, and the position and shape of the target position of the object to be transported; The in-place storage system for the objects to be transported is determined based on multiple interactions of the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot, and the position and shape of the target position of the objects to be transported.

10. A handling system for a heavy-load intelligent stacking robot, characterized in that: The handling system of the heavy-load intelligent stacking robot is applied to the handling method of the heavy-load intelligent stacking robot as claimed in any one of claims 1 to 9, and the handling system of the heavy-load intelligent stacking robot comprises: A collection module is used to collect the approach distance of the heavy-load intelligent stacking robot relative to the object to be transported in the indoor space; A clamping module, used for triggering the heavy-duty intelligent stacking robot to clamp the object step by step according to the approach distance; A transfer path module, used to determine a transfer path of the object to be transported based on the current position of the object to be transported and the target position of the object to be transported; A moving path module, used to construct a moving path of the heavy-load intelligent stacking robot according to the transfer path of the objects to be transported, the spatial position of the heavy-load intelligent stacking robot, and the motion dimension of the heavy-load intelligent stacking robot; An intelligent control module is used to determine the distribution position of dynamic obstacles relative to the moving path according to the moving path of the heavy-load intelligent stacking robot, the spatial distribution map of the indoor space and the dynamic video, and trigger the intelligent control of the heavy-load intelligent stacking robot during the movement based on the distribution position of the dynamic obstacles relative to the moving path, the moving speed of the heavy-load intelligent stacking robot and the load state of the heavy-load intelligent stacking robot; The positioning storage module is used to collect the stress state of the objects to be transported, and determine the in-place storage system of the objects to be transported according to the stress state of the objects to be transported, the moving state of the heavy-load intelligent stacking robot and the position shape of the target position of the objects to be transported.

Images