Mechanical arm and conveyor belt cooperative control planning method for intelligent garbage sorting

Abstract

The invention relates to the technical field of intelligent garbage treatment and automatic sorting, and discloses a mechanical arm and conveyor belt cooperative control planning method for intelligent garbage sorting, and the method comprises the following steps: controlling a conveyor belt to convey garbage to a garbage bag breaking device at a set speed for bag breaking treatment, and controlling the conveyor belt to decelerate or pause until the garbage bag breaking treatment is completed; and the conveying belt is controlled to convey the garbage to the metal detection device for metal detection, the garbage type is recognized, the garbage grabbing mode and path are determined, and the garbage is grabbed and conveyed to a designated garbage can in a classified mode. The technical scheme of cooperative control of the mechanical arm and the conveying belt is adopted, and the efficient and accurate garbage sorting effect is achieved; compared with a sorting system independently depending on a mechanical arm or a conveying belt in the prior art, through the synergistic effect of the mechanical arm and the conveying belt, the garbage sorting process is smoother, and the problem that the treatment efficiency is low due to system asynchronism is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent garbage disposal and automated sorting, and in particular to a method for collaborative control planning of a robotic arm and a conveyor belt for intelligent garbage sorting. Background Art

[0002] With the acceleration of urbanization, garbage disposal has become an important issue in environmental protection and resource recycling. Traditional garbage sorting methods rely on manual operation or simple mechanical sorting equipment, which are not only inefficient but also have large errors. In recent years, intelligent garbage sorting technology has gradually emerged, especially in industrial large-scale garbage recycling and treatment, automated and intelligent garbage sorting systems have shown great potential.

[0003] The existing intelligent garbage sorting system mainly relies on visual recognition technology combined with robotic arm grabbing technology to achieve garbage classification and processing. The visual recognition module uses a camera or sensor to shoot the garbage and perform image analysis to identify the type of garbage. Then, the robotic arm grabs the garbage based on the recognition results and puts it into the designated recycling unit.

[0004] However, most existing intelligent garbage sorting technologies rely on fixed-speed conveyor belts, which are difficult to dynamically adjust according to the actual weight and size of the garbage, which easily leads to delayed sorting of heavy objects and misclassification of light objects. They also rely on two-dimensional visual recognition technology, which makes it difficult to accurately obtain the three-dimensional spatial information of the garbage, which makes it easy for the robot arm to deviate during the grasping process, and the sorting robot arm and conveyor belt often operate independently, resulting in the system being difficult to adapt and adjust in time when the type of garbage changes. Therefore, the present invention provides a collaborative control planning method for a robot arm and a conveyor belt for intelligent garbage sorting to solve the shortcomings of the prior art. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a collaborative control planning method for a robotic arm and a conveyor belt for intelligent garbage sorting, which solves the problem that the existing garbage sorting robotic arm and conveyor belt often operate independently, making it difficult to make timely adaptive adjustments when the type of garbage changes.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting, comprising the following steps: When the sensor detects that the initial garbage is dumped on the conveyor belt, the conveyor belt is controlled to convey the garbage to the garbage bag breaking device at a set speed for bag breaking processing; When the garbage is transported to the bag breaking device, the conveyor belt is controlled to slow down or pause until the garbage bag is broken; After the garbage bags are broken and the garbage is spread out, the conveyor belt is controlled to convey the garbage to the metal detection device for metal detection; After metal detection is completed, the conveyor belt is controlled to transport the garbage to the visual recognition area, and a 3D camera is used to reconstruct the garbage in three dimensions, identify the type of garbage, and determine the garbage grabbing method and path; The robot arm is controlled to grab the garbage and transfer the classified garbage to the designated garbage bin according to the garbage grabbing method and path determined by the recognition results.

[0007] Preferably, the speed control of the conveyor belt comprises the following steps: The weight of the garbage dumped on the conveyor belt is detected in real time by the weight sensor; Determine whether the weight exceeds the set threshold. If so, reduce the conveyor belt speed to the set slow speed. If not, run at the basic conveyor belt speed. During the garbage transportation process, the speed of the conveyor belt is dynamically adjusted based on the speed sensor data at both ends of the conveyor belt.

[0008] Preferably, the deceleration or pause control of the conveyor belt comprises the following steps: The conveyor belt monitors whether the garbage reaches the bag breaking area through the sensor of the bag breaking device; When the garbage reaches the bag breaking area, the conveyor belt automatically switches to deceleration mode until the bag breaking device detects that the garbage has been broken; After the garbage bags are broken, the conveyor belt returns to the set speed and continues to transport.

[0009] Preferably, the three-dimensional reconstruction of the garbage using a 3D camera comprises the following steps: The 3D camera is used to collect multi-view images of the garbage, and the multi-view image reconstruction algorithm is used to extract the three-dimensional feature points of the garbage; Classify the garbage feature images using a deep learning model, where the deep learning model is a ResNet50 or MobileNet model; In the process of image feature extraction, the attention mechanism is combined to extract features from the salient areas of the garbage feature image; Based on the recognition results, the grabbing method and path for each type of garbage are calculated.

[0010] Preferably, the identification of the types of garbage includes the following steps: Use 3D cameras to image garbage from multiple perspectives, and extract features from garbage images based on deep learning algorithms to extract the geometric shape, color, texture, and material characteristics of the garbage; Combining the convolutional neural network model with the support vector machine classification method, the garbage types are classified and the garbage grabbing points and optimal placement locations are calculated; Adjust the robot’s target grabbing strategy based on the identified garbage category, including selecting the appropriate adsorption, clamping or grabbing mode; After the garbage is sorted, the optimal path of the robotic arm is calculated, and the grasping trajectory is optimized in combination with the obstacle avoidance algorithm.

[0011] Preferably, the grabbing and delivering of the robot arm comprises the following steps: The robotic arm automatically adjusts the gripping force based on the type of garbage identified by the 3D camera; Dynamically adjust the rotation angle, gripping point and gripping force of the robot arm for garbage of different shapes and materials; The grasping trajectory of the robotic arm adopts the shortest path planning method based on the Dijkstra algorithm and combines it with the dynamic obstacle avoidance algorithm to optimize the grasping path.

[0012] Preferably, the Dijkstra algorithm establishes a distance graph between the starting position of the robot arm and the target grasping point, calculates the shortest path from the starting point to the end point based on the weights between the nodes, and dynamically adjusts the path; during the calculation process, the rotation angle of the robot arm, the grasping posture and the obstacle avoidance requirements are taken into account.

[0013] Preferably, the convolutional neural network model is used to extract deep features of garbage images, including edge features, color distribution, texture patterns and geometric forms, and perform feature learning through multi-layer convolution, pooling and fully connected layers.

[0014] Preferably, the support vector machine classification method is used to classify garbage types based on high-dimensional features extracted by a convolutional neural network model, map garbage to different categories based on a hyperplane classification strategy, and optimize classification boundaries.

[0015] It also provides a robot arm and conveyor belt collaborative control planning system for intelligent garbage sorting, including the following modules: Weight detection module, used to detect the weight information of garbage after it is put in; A conveyor belt control module is used to dynamically adjust the conveyor belt speed according to the detected information; The visual recognition module includes a 3D camera and recognition system, which is used to photograph and reconstruct the garbage on the conveyor belt in three dimensions, identify the type of garbage, and determine the grabbing method and path; The robotic arm control module is used to control the robotic arm to complete garbage grabbing and classified delivery according to the results of garbage identification by the visual recognition module; The control module is used to receive and process data from each module to complete the coordinated control of the garbage sorting process.

[0016] The present invention provides a method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting. It has the following beneficial effects: 1. The present invention adopts a technical solution of coordinated control of a robotic arm and a conveyor belt to achieve efficient and accurate garbage sorting effects. Compared with the sorting system in the prior art that relies solely on a robotic arm or a conveyor belt, the present invention makes the garbage sorting process smoother through the synergy of the two, reducing the problem of low processing efficiency caused by system asynchrony.

[0017] 2. The present invention ensures the accuracy of garbage classification and the real-time processing through a weight detection module and a control strategy for real-time dynamic adjustment of the conveyor belt speed. Compared with traditional garbage disposal solutions, the system can adjust the processing speed in time according to the weight of the garbage, avoiding delays in the processing of heavy objects and greatly improving the overall processing efficiency.

[0018] 3. By combining 3D visual recognition with intelligent robotic arm control, the present invention can accurately identify and grab garbage in different forms. Compared with the prior art, this solution has significantly improved recognition accuracy and grasping flexibility, especially in the processing of complex forms of garbage, avoiding the recognition errors and grasping difficulties existing in traditional technologies.

[0019] 4. The present invention coordinates various subsystems in real time through the control module, automatically adjusts the working status, and ensures the intelligent and adaptive adjustment of the garbage sorting process; compared with the traditional fixed process control scheme, the control module can optimize the sorting strategy according to real-time feedback, improves the system's adaptability and intelligence level, thereby effectively improving the overall efficiency of garbage disposal. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the method steps of the present invention; Figure 2 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Please see attached Figure 1 , an embodiment of the present invention provides a method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting, comprising the following steps: S1, when the sensor detects that the initial garbage is dumped on the conveyor belt, the conveyor belt is controlled to convey the garbage to the garbage bag breaking device at a set speed for bag breaking; S2. When the garbage is transported to the bag breaking device, the conveyor belt is controlled to slow down or pause until the garbage bag breaking process is completed; S3. After the garbage bags are broken and the garbage is spread out, the conveyor belt is controlled to convey the garbage to the metal detection device for metal detection, and the speed of the conveyor belt is controlled according to the working state of the metal detection device and the current speed of the conveyor belt; S4. After completing the metal detection, the conveyor belt is controlled to transport the garbage to the visual recognition area, and the 3D camera is used to reconstruct the garbage in three dimensions, identify the type of garbage, and determine the garbage grabbing method and path; S5. Control the robot arm to grab the garbage and transfer the classified garbage to the designated garbage bin according to the garbage grabbing method and path determined by the recognition result.

[0023] For step S1, in this embodiment, during the intelligent garbage sorting process, the system needs to effectively detect the entry status of the initial garbage, and control the conveyor belt to transport the garbage to the bag breaking device for pre-processing at a set speed. This process is not only related to the smooth progress of the garbage sorting process, but also affects the accuracy of subsequent identification and grasping. In general, the state of the initial garbage is more complicated and may appear in the form of bagged, loose or piled. Therefore, for different types of garbage states, the operating parameters of the conveyor belt need to be reasonably adjusted to ensure the effectiveness of the bag breaking process. In one possible implementation method, the system detects the characteristics of the initial garbage based on multi-sensor fusion technology, combines the conveyor belt dynamics model, and optimizes the conveying speed so that the garbage can be fully processed in the bag breaking area.

[0024] In this embodiment, the system first uses the sensor array to detect the garbage entry state. As an option, a weight sensor (such as a strain gauge sensor) can be used to make a preliminary judgment on the garbage mass. Specifically, when the garbage is dumped onto the conveyor belt, the instantaneous mass change measured by the sensor can be used to determine the density distribution of the garbage. Assume that the conveyor belt carrying mass in the initial state of the system is , the total mass change after dumping the garbage is: ; in, is the change in the mass of the conveyor belt, represents the total mass on the conveyor belt at the current moment, is the quality of the conveyor belt at the initial moment. In general, the system can set a quality threshold ,like , it is determined that the garbage has been successfully put in, triggering the conveyor belt start signal.

[0025] In one possible implementation, in addition to quality detection, the system also uses optical sensors and infrared ranging modules to identify the geometric dimensions of the garbage. Specifically, the system uses LiDAR to scan the three-dimensional shape of the garbage and obtain the height of the garbage. and area , and determine the garbage filling degree based on the following calculation formula: ; in, is the density of garbage, is the area of ​​garbage, is the height of the garbage, is the effective conveying area of ​​the conveyor belt. , it means that the garbage density is high and the conveying speed needs to be appropriately reduced to ensure the processing effect of the bag breaking device.

[0026] In some embodiments, the system can also combine RGB-Depth (RGB-D) cameras for further morphological analysis. As an option, a deep learning model (such as MobileNet) can be used to classify the shape characteristics of garbage and distinguish between bagged garbage and bulk garbage. When bagged garbage is detected, the system can introduce a speed regulation mechanism into the conveyor belt control algorithm and adopt an exponential decay speed control strategy, namely: ; in, For current time The transmission speed, is the maximum initial transmission speed, is the attenuation coefficient, This is the base of the natural logarithm. In this way, when the garbage approaches the bag breaking device, the speed can be gradually reduced to improve the bag breaking efficiency.

[0027] In another possible implementation, in order to ensure that the garbage does not roll or accumulate during the conveying process, the conveyor belt adopts dynamic acceleration compensation control and achieves stable conveying through the PID (proportional-integral-differential) control algorithm. Assume that the desired speed of the conveyor belt is , the real-time measured transmission speed is , then the velocity error is defined as: ; The PID control calculation is as follows: ; in, is the speed error, is the expected speed, is the actual speed, , and are proportional, integral and differential gain parameters respectively, is the output value of the conveyor belt controller, represents the duration of the control process, is the time variable in the integral operation, is the speed error The derivative with respect to time. Through PID control, the conveyor belt can dynamically adjust the running speed according to the garbage load, avoiding the problem of uneven transportation caused by garbage accumulation.

[0028] In some embodiments, the surface material of the conveyor belt can be a non-slip coating with a high friction coefficient to improve the stability of garbage transportation. As an option, a polyurethane (PU) material or a rubber composite material can be used, whose static friction coefficient is Usually greater than 0.8, it can effectively prevent garbage from slipping due to inertia. In addition, in some scenarios, the conveyor belt can also be integrated with a lateral guide device to correct the position of larger-sized garbage so that it can enter the bag breaking area more evenly.

[0029] In another possible implementation, in order to further optimize the operation status of the conveyor belt, the system can predict and adaptively adjust the blockages that occur during the garbage transportation process based on intelligent learning algorithms. Specifically, the system can record the operation data of the conveyor belt and use recursive neural networks (RNN) to analyze the historical transportation conditions, predict the possible garbage accumulation points in advance, and then adjust the transmission speed or change the garbage arrangement in advance in the next round of transportation to reduce the probability of blockage.

[0030] In some embodiments, the control unit of the conveyor belt can be linked with the host computer system so that the transmission data can be updated to the central processing unit (CPU) in real time. As an option, the Modbus TCP / IP communication protocol can be used to achieve remote monitoring and adjustment of the conveyor belt speed and garbage status data so as to maintain stable operation under complex working conditions.

[0031] For step S2, in this embodiment, during the garbage transportation process, in order to ensure that the garbage can be fully processed in the bag breaking device, the system needs to accurately control the running state of the conveyor belt so that it can be appropriately slowed down or paused when the garbage reaches the bag breaking device to ensure the stability of the bag breaking process. In general, the efficiency of garbage bag breaking processing is affected by factors such as the shape of the garbage, the material of the bag, and the amount of garbage put in. Therefore, in the control strategy of slowing down or pausing the conveyor belt, it is necessary to combine real-time detection data to adjust the running state of the conveyor belt to match the working rhythm of the bag breaking device. In one possible implementation, the system determines the movement mode of the conveyor belt based on garbage position detection, morphology analysis, and the load state of the bag breaking device, so that the garbage enters the bag breaking area in the best state.

[0032] In this embodiment, the system first needs to determine whether the garbage has reached the bag breaking device. As an option, a laser distance sensor can be used to monitor the movement trajectory of the garbage. Specifically, a group of laser distance sensors are arranged in the area of ​​the conveyor belt near the bag breaking device to measure the front position of the garbage. The entrance position of the bag breaking device Distance : ; in, Current location for garbage The entrance position of the bag breaking device The distance between.

[0033] In general, the system sets a critical distance ,when When the garbage is in the bag breaking device, the conveyor belt is triggered to slow down or pause control logic to ensure that the garbage can enter the bag breaking device stably.

[0034] In a possible implementation, the deceleration process of the conveyor belt can adopt a staged speed regulation strategy. Specifically, when the garbage approaches the bag breaking device, the conveyor belt is first decelerated at a linear decay speed, so that the garbage slowly enters the bag breaking area to prevent the garbage from being scattered due to inertial impact. Assume that the initial speed of the conveyor belt is , the final target speed of the deceleration section is , then the speed control function of the conveyor belt can be expressed as: ; in, Conveyor belt in time The speed of is the initial speed of the conveyor belt (the speed before deceleration), is a deceleration parameter, and its size can be dynamically adjusted according to the density, shape and processing capacity of the garbage bag breaking device. In some embodiments, if the garbage bag is large or the filling density is high, the system can increase To speed up the deceleration process and prevent the garbage from being displaced or offset when entering the bag breaking device.

[0035] As an option, the system can further pause the conveyor belt when the garbage completely enters the bag breaking device to ensure the smooth progress of the bag breaking process.

[0036] Specifically, the system can detect the working status of the bag breaking device through pressure sensors or image recognition technology. For example, a contact pressure sensor can be set at the entrance of the bag breaking device. When it detects that the garbage has a stable contact force on the device, When the system determines that the garbage has entered the bag breaking state, the conveyor belt will stop running until the bag breaking is completed.

[0037] In some embodiments, in order to improve the stability of the bag breaking process, the system can also dynamically adjust the pause time of the conveyor belt in combination with the load status of the bag breaking device. As a possible implementation method, the system detects the load status of the bag breaking device through motor power monitoring. If the power consumption of the bag breaking device is Exceeding the set threshold , it means that the garbage is still in the process of breaking the bag, and the system keeps the conveyor belt in a paused state to prevent the garbage from being transported away before the bag is completely broken. And the duration exceeds the set time When the bag is broken, the system determines that the bag is broken and resumes the conveyor belt operation.

[0038] In another possible implementation, the system can further optimize the conveyor belt pause strategy by combining visual recognition. Specifically, an industrial camera can be used to monitor the broken bag status of the garbage in real time. If it is detected that the garbage bag has been completely torn and the internal garbage has been dispersed, the control system sends a resume operation instruction to the conveyor belt. As an option, the system can use a deep learning model (such as YOLO or ResNet) to process the image data to accurately determine the bag breaking completion status, thereby improving the system's automation and processing efficiency.

[0039] In some embodiments, in order to prevent the accumulation of garbage during the pause process, the system can also be combined with a vibration mechanism or a lateral guide device to slightly vibrate or guide the garbage during the pause of the conveyor belt, so that the garbage is more evenly distributed in the working area of ​​the bag breaking device, thereby improving the bag breaking effect. As a possible implementation method, the vibration mechanism can be driven by an eccentric wheel motor, and when the conveyor belt is paused, low-amplitude vibration is periodically applied to make the garbage bag easier to handle by the bag breaking device.

[0040] For step S3, in this embodiment, after the garbage enters the bag breaking device and completes the preliminary processing, the system needs to further classify and identify the garbage after the bag is broken. At this time, the garbage that has been preliminarily sorted and processed usually has different shapes, colors, sizes and other characteristics. It is necessary to use image recognition technology and machine vision systems, combined with artificial intelligence algorithms, to classify the garbage more accurately. In the aforementioned steps, the system accurately controls the transportation and processing status of the garbage through sensor data and control algorithms to ensure that the garbage stably enters the bag breaking area and is effectively processed. In the next step, the system further identifies and classifies the garbage through high-resolution cameras or multispectral sensors to ensure that subsequent classification operations can be accurately performed.

[0041] In this embodiment, the system uses a camera array set behind the bag breaking device to collect real-time images of the garbage after the bag is broken. As an option, an industrial-grade CCD camera can be used in combination with an infrared sensor to collect the appearance characteristics of the garbage in multiple dimensions. Specifically, the camera captures the external information of the garbage based on the intensity and color difference of the reflected light, generates an RGB image and a depth image, and enhances the contrast of the image through image preprocessing technology, making the garbage features in the image more prominent.

[0042] In some embodiments, the system can analyze the collected images in conjunction with a convolutional neural network (CNN) to automatically identify the types of garbage. Specifically, the CNN model extracts feature information of garbage from the image through multi-layer convolution and pooling operations, and classifies the garbage in conjunction with a pre-trained classification model. For example, when different types of garbage such as metal, plastic, and paper are detected in the image, the system automatically classifies and marks them. At this point, the output result of the CNN model can be expressed as: ; in, Represents the classification result, is the input image, is the classification function in the CNN model.

[0043] As an option, during the garbage classification process, the system can also combine the transfer learning method of deep learning, and use the transfer learning technology to enable the classification model to be adaptively adjusted according to different scenarios. Specifically, the system can use a pre-trained model and fine-tune it according to the actual garbage characteristics to adapt to the garbage identification needs in different environments. One advantage of transfer learning is that it can quickly improve the accuracy of the model, especially when the garbage types are diverse and change rapidly.

[0044] In another possible implementation, in addition to visual recognition technology, the system can also combine spectral analysis technology to further determine the garbage material. Specifically, by installing near-infrared sensors on the conveyor belt, the material of the garbage can be accurately identified. For example, by measuring the absorption characteristics of garbage in the near-infrared band, the system can determine whether the garbage is plastic, metal or paper, and further refine the classification standards.

[0045] In some embodiments, the system can also introduce a two-dimensional laser scanner or a three-dimensional laser radar (LiDAR) based on visual recognition technology to perform three-dimensional reconstruction of the garbage to help determine the shape and volume of the garbage. Specifically, the system scans the outer contour of the garbage and combines it with known geometric features of the object to infer its possible physical properties and provide a basis for subsequent processing.

[0046] In some scenarios, the system can also use sensor data fusion technology to comprehensively consider the input data from different sensors and further optimize the accuracy and stability of garbage classification through algorithms such as Kalman filters. For example, by fusing the data of multiple sensors (such as visual sensors, infrared sensors, and ultrasonic sensors) through Kalman filters, high-precision garbage classification and identification can be achieved in a variety of environments.

[0047] In another possible implementation, the system can combine intelligent feedback control mechanisms to adjust the classification strategy in real time according to the classification results during the garbage classification process. For example, when the system identifies that the proportion of a certain type of garbage is too high, the system can adjust the working parameters of the classification equipment (such as wind power, screening speed, etc.) to optimize the classification effect and ensure classification efficiency and accuracy.

[0048] For step S4, in this embodiment, after visual recognition and classification, the next step is to actually process the garbage according to the classification results, including placing it in a suitable recycling container or starting further processing procedures. This step involves processing operations based on the classification results, which is crucial to improving resource recovery efficiency and achieving effective garbage classification. In order to ensure the accuracy and efficiency of the processing, the core task of this step is to allocate different types of garbage to corresponding processing devices or storage areas through a precise control system based on the classification results of the garbage. In general, the classified garbage will be processed in different ways according to the type. For example, recyclables, non-recyclables, hazardous materials, etc. will be sent to their respective processing units for follow-up work. In order to ensure the smooth progress of this process, the system needs to adopt high-precision control algorithms and processing mechanisms.

[0049] The system distributes different types of garbage through an automated sorting device based on the classification information obtained in the previous steps. As an option, the sorting device can use an airflow sorting system or a robotic arm, depending on the type and characteristics of the garbage. For light recyclables, such as plastic bottles and paper, the system can blow them to the corresponding recycling bins through airflow. Specifically, the system adjusts the strength of the airflow through an airflow pressure control valve. When light garbage is detected, the force of the airflow is increased. It can be controlled by the following formula: ; in, is the force of the airflow, is the aerodynamic constant, is the cross-sectional area of ​​the object, is the pressure difference between the airflow and the garbage. The size of the bin ensures that lightweight items are accurately distributed to the recycling bin.

[0050] For heavier garbage, such as metal and glass bottles, the system uses a robotic arm sorting system to handle them. Specifically, the robotic arm uses a visual recognition system to identify the characteristics of the target garbage and activates the precise grasping function. To achieve this process, the robotic arm combines a force feedback control system to monitor the grasping force of the object in real time. and gripping position to avoid damaging the garbage or causing it to lose control. The gripping force control can be adjusted by the following formula: ; in, To monitor the grasping force of an object in real time, is the adjustment constant of the grasping force, By adjusting the gripping force in real time according to the change in the displacement of the object, the system can efficiently and safely classify heavy objects and place them in the appropriate storage area.

[0051] In another possible implementation, the system can also be combined with vibration screening technology for processing, which is particularly suitable for crushed materials or finer garbage. Specifically, the system uses an electric vibrator to make the surface of the garbage vibrate periodically, causing the items to naturally separate according to weight or size. By precisely controlling the vibration frequency and amplitude, the system can classify the garbage in a shorter time, thereby improving processing efficiency.

[0052] In some embodiments, the system can also intelligently adjust the sorting method based on the characteristics of the garbage, for example, dynamically select the appropriate sorting equipment according to the material properties, shape characteristics and weight distribution of the object. At this time, the system combines deep learning algorithms to intelligently analyze the identified garbage categories and automatically select the appropriate sorting equipment and methods. For example, some complex forms of garbage such as cartons may require a combination of robotic arm grabbing and airflow blowing to complete the sorting.

[0053] In another embodiment, in order to achieve more efficient garbage disposal, the system can also optimize the sorting process in real time through an information feedback mechanism. Specifically, the system monitors the working status and efficiency of each sorting device in real time through a sensor network, and adjusts the sorting strategy based on real-time data. When the recycling efficiency of a certain type of garbage is lower than expected, the system will automatically optimize the equipment parameters or adjust the sorting process, thereby improving the overall efficiency of the entire system.

[0054] For step S5, in this embodiment, it is ensured that each type of garbage is accurately processed in its corresponding processing unit to avoid confusion, misallocation or omission. In general, subsequent processing may include mechanical processing, thermal processing, compression processing or chemical processing, and different processing methods are performed according to the type of garbage. In order to ensure the efficiency and sustainability of this process, the system needs to provide accurate control mechanisms and real-time feedback to monitor the garbage processing status and adjust the processing method.

[0055] In this embodiment, the system monitors the processing status of garbage in real time through a sensor network set on each processing unit. As an option, the system can use a variety of sensors such as temperature and humidity sensors, pressure sensors or gas detection sensors to detect environmental parameters during the processing process. Specifically, when the garbage enters the processing unit, the sensor will measure its important parameters such as temperature, humidity, compression rate, etc. in real time to determine the progress of garbage processing and whether the processing method needs to be adjusted. At this time, the system will adjust the working status of the processing unit according to the data collected by the sensor to ensure the stability of the processing process.

[0056] For example, when processing wet garbage (such as kitchen waste), the system can use the humidity measured by the humidity sensor to To adjust the compression rate and drying time of wet garbage. Greater than a set value , the system will automatically start the heating device to shorten the garbage drying time to reduce the impact of moisture on subsequent processing links during wet garbage treatment. Specifically, the humidity threshold Set by the following formula: ; in, is the humidity measured by the humidity sensor, Indicates the quality of water in the garbage. is the total mass of garbage.

[0057] In another possible implementation, if the process involves metal waste or plastic and other hard materials, the system can compress the waste through a mechanical compression device to further reduce the volume of waste generated after processing. Exceeding the preset threshold When the system stops the compression process automatically, it can avoid excessive compression of garbage or equipment damage. Specifically, the compression force control can be carried out by the following formula: ; in, is the compression force detected by the pressure sensor, is the stiffness constant of the compression device, is the change in displacement of the object.

[0058] As an option, for waste in the thermal treatment process, the system can ensure that the treatment temperature is maintained within an appropriate range through a temperature control system. For example, during the pyrolysis process, the system monitors the temperature of the waste treatment unit in real time through a temperature sensor to ensure that it fluctuates within the set temperature range. Exceeding the maximum safe temperature , the system will automatically reduce the heat source output to prevent overheating from causing uneven processing or equipment failure.

[0059] In addition, in order to improve the level of intelligent processing, the system can also combine machine learning models to adaptively adjust the garbage processing process. For example, based on historical data, the system can predict the problems that may arise during the processing of different types of garbage and optimize the processing process in advance. Specifically, the machine learning model can be trained based on the real-time data fed back by the sensor and predict the changing trend of garbage processing in the next few seconds or minutes, so as to adjust the operation strategy of the processing equipment.

[0060] In some embodiments, the system can optimize the operation of the processing unit through a dynamic optimization control algorithm. For example, through a reinforcement learning algorithm, the system can continuously adjust the processing parameters according to the real-time feedback of the garbage processing to achieve long-term optimization of the garbage processing.

[0061] The robot arm and conveyor belt collaborative control planning system for intelligent garbage sorting described below and the robot arm and conveyor belt collaborative control planning method for intelligent garbage sorting described above can be referenced to each other.

[0062] Please see attached Figure 2 The present invention also provides a robot arm and conveyor belt collaborative control planning system for intelligent garbage sorting, including the following modules: The weight detection module is used to detect the weight information of the garbage after it is put in. The weight of each material is measured in real time through the weighing sensor set on the conveyor belt. Weight information is of great significance for determining the type of garbage and determining the subsequent treatment method. For example, heavier items may belong to metal or glass, while lighter items may be plastic or paper. In some embodiments, the system can also combine the relationship between weight and object size to further improve the accuracy of classification. The output information of this module is transmitted to the conveyor belt control module and the robotic arm control module to adjust the sorting strategy in real time.

[0063] The conveyor belt control module is used to dynamically adjust the conveyor belt speed according to the detected information. Generally, if the weight detects a heavier object, the conveyor belt speed will be appropriately slowed down to give the robot enough time to complete the grabbing action; for light garbage, the conveyor belt speed can be increased to improve the overall processing efficiency. As an option, this module can accurately control the conveyor belt speed according to real-time data through the PID control algorithm to ensure the smooth operation of the system and the accuracy of garbage grabbing.

[0064] The visual recognition module, including a 3D camera and recognition system, is used to photograph and reconstruct the garbage on the conveyor belt in three dimensions, identify the type of garbage and determine the grasping method and path. The 3D camera can obtain the three-dimensional shape and spatial position of the garbage, and provide more accurate grasping path information for the robotic arm. Specifically, the visual recognition module uses an image processing algorithm to extract features of each item, and combines it with a deep learning model to identify its category (such as plastic, paper, metal, etc.). In addition, the system will determine the posture and path required for the robotic arm to grasp the garbage based on the shape and characteristics of the garbage. The module can also update the spatial position of the garbage in real time through the visual positioning system to ensure grasping accuracy.

[0065] The robot arm control module is used to control the robot arm to complete the garbage grabbing and classified delivery according to the results of the garbage recognition module. Specifically, the robot arm control module first selects a suitable grabbing method according to the category and characteristics of the object, such as using a clamp or suction cup to grab, and selects a suitable path for irregularly shaped objects. The robot arm accurately performs the grabbing task through force feedback control and path planning algorithms. In some embodiments, the robot arm can also adjust the grabbing force according to the feedback information to ensure the stability and safety of the grabbing action.

[0066] The control module is used to receive and process the data of each module, complete the coordinated control of the garbage sorting process, and realize the effective transmission and feedback of information by coordinating the visual recognition module, weight detection module, conveyor belt control module and robotic arm control module. The control module adjusts the system operating parameters according to the real-time data of each module through real-time optimization algorithm to ensure the efficiency and stability of the entire garbage sorting process. Specifically, the control module can dynamically adjust the processing strategy according to the different characteristics of the garbage. For example, during the garbage identification process, if special items (such as batteries, dangerous goods, etc.) are identified, the system can change the processing process in time to ensure safety.

[0067] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, which will not be repeated here.

[0068] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A robot arm and conveyor belt collaborative control planning method for intelligent garbage sorting, characterized in that: The following steps are involved: When the sensor detects that the initial garbage is dumped on the conveyor belt, the conveyor belt is controlled to convey the garbage to the garbage bag breaking device at a set speed for bag breaking; When the garbage is transported to the bag breaking device, the conveyor belt is controlled to slow down or pause until the garbage bag is broken; After the garbage bags are broken and the garbage is spread out, the conveyor belt is controlled to convey the garbage to the metal detection device for metal detection; After metal detection is completed, the conveyor belt is controlled to transport the garbage to the visual recognition area, and a 3D camera is used to reconstruct the garbage in three dimensions, identify the type of garbage, and determine the garbage grabbing method and path; The robot arm is controlled to grab the garbage and transfer the classified garbage to the designated garbage bin according to the garbage grabbing method and path determined by the recognition results.

2. The method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 1 is characterized in that: The speed control of the conveyor belt comprises the following steps: The weight of the garbage dumped on the conveyor belt is detected in real time by the weight sensor; Determine whether the weight exceeds the set threshold. If so, reduce the conveyor belt speed to the set slow speed. If not, run at the basic conveyor belt speed. During the garbage transportation process, the speed of the conveyor belt is dynamically adjusted based on the speed sensor data at both ends of the conveyor belt.

3. The method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 1 is characterized in that: The deceleration or pause control of the conveyor belt comprises the following steps: The conveyor belt monitors whether the garbage reaches the bag breaking area through the sensor of the bag breaking device; When the garbage reaches the bag breaking area, the conveyor belt automatically switches to deceleration mode until the bag breaking device detects that the garbage has been broken; After the garbage bags are broken, the conveyor belt returns to the set speed and continues to transport.

4. The method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 1 is characterized in that: The three-dimensional reconstruction of the garbage using a 3D camera comprises the following steps: The 3D camera is used to collect multi-view images of the garbage, and the multi-view image reconstruction algorithm is used to extract the three-dimensional feature points of the garbage; Classify the garbage feature images using a deep learning model, where the deep learning model is a ResNet50 or MobileNet model; In the process of image feature extraction, the attention mechanism is combined to extract features from the salient areas of the garbage feature image; Based on the recognition results, the grabbing method and path for each type of garbage are calculated.

5. The method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 1 is characterized in that: The identification of the garbage types includes the following steps: Use 3D cameras to image garbage from multiple perspectives, and extract features from garbage images based on deep learning algorithms to extract the geometric shape, color, texture, and material characteristics of the garbage; Combining the convolutional neural network model with the support vector machine classification method, the garbage types are classified and the garbage grabbing points and optimal placement locations are calculated; Adjust the robot’s target grabbing strategy based on the identified garbage category, including selecting the appropriate adsorption, clamping or grabbing mode; After the garbage is sorted, the optimal path of the robotic arm is calculated, and the grasping trajectory is optimized in combination with the obstacle avoidance algorithm.

6. The method for coordinated control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 1, characterized in that: The grabbing and delivery of the robotic arm includes the following steps: The robotic arm automatically adjusts the gripping force based on the type of garbage identified by the 3D camera; Dynamically adjust the rotation angle, gripping point and gripping force of the robot arm for garbage of different shapes and materials; The grasping trajectory of the robotic arm adopts the shortest path planning method based on the Dijkstra algorithm and combines it with the dynamic obstacle avoidance algorithm to optimize the grasping path.

7. The method for coordinated control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 6 is characterized in that: The Dijkstra algorithm establishes a distance graph between the starting position of the robot and the target grasping point, calculates the shortest path from the starting point to the end point based on the weights between the nodes, and dynamically adjusts the path; during the calculation process, the rotation angle, grasping posture and obstacle avoidance requirements of the robot are taken into account.

8. The method for collaborative control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 5 is characterized in that: The convolutional neural network model is used to extract deep features of garbage images, including edge features, color distribution, texture patterns and geometric forms, and perform feature learning through multi-layer convolution, pooling and fully connected layers.

9. The method for coordinated control planning of a robot arm and a conveyor belt for intelligent garbage sorting according to claim 5, characterized in that: The support vector machine classification method is used to classify garbage types based on high-dimensional features extracted by a convolutional neural network model, map garbage to different categories based on a hyperplane classification strategy, and optimize classification boundaries.

10. A robot arm and conveyor belt coordinated control planning system for intelligent garbage sorting, applied to a robot arm and conveyor belt coordinated control planning method for intelligent garbage sorting as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Weight detection module, used to detect the weight information of garbage after it is put in; A conveyor belt control module is used to dynamically adjust the conveyor belt speed according to the detected information; The visual recognition module includes a 3D camera and recognition system, which is used to photograph and reconstruct the garbage on the conveyor belt in three dimensions, identify the type of garbage, and determine the grabbing method and path; The robot arm control module is used to control the robot arm to complete the garbage grabbing and classification according to the result of garbage recognition by the visual recognition module; The control module is used to receive and process data from each module to complete the coordinated control of the garbage sorting process.

Images