Autonomous unloading method and device, electronic equipment and storage medium

Abstract

The invention provides an autonomous unloading method and device, electronic equipment and a storage medium, and relates to the technical field of autonomous unloading, the autonomous unloading method and device are used for unloading from a self-loading and unloading garbage truck to a mobile garbage station, and the self-loading and unloading garbage truck comprises a box body lifting oil cylinder, a tail camera and a scraper mechanism; the method comprises the following steps: acquiring a pressure signal of a box body lifting oil cylinder and image data acquired by a tail camera; determining an estimated value of the weight of garbage in the box body of the self-loading and self-unloading garbage truck based on the pressure signal; identifying a garbage filling state in a garbage hopper of the mobile garbage station based on the image data; an unloading control instruction is generated based on the estimated value and the garbage filling state; and based on the discharging control instruction, a box body lifting oil cylinder is controlled to execute lifting or stopping action, and a scraper mechanism is synchronously controlled to execute opening or closing action, so that automatic discharging is carried out. In the mode, manual intervention is not needed, the single dumping amount can be automatically controlled, garbage overflow is avoided, and the unloading efficiency and the operation safety are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous unloading technology, and in particular to an autonomous unloading method, apparatus, electronic device and storage medium. Background Technology

[0002] Self-loading and unloading garbage trucks are commonly used sanitation vehicles for the collection and transportation of urban household waste. They load garbage through a bin-lifting mechanism and a compression mechanism, and then drive to a transfer station for unloading. Currently, garbage transfer stations typically have multiple mobile garbage stations for temporary garbage storage.

[0003] In related technologies, the unloading method requires operators to manually control the lifting angle of the container and the opening degree of the scraper based on experience, repeatedly dumping the waste into the station. This operation method, which relies on manual judgment, not only requires the driver to frequently adjust the actuator, resulting in high labor intensity and low work efficiency, but also makes it easy for waste to overflow and cause pollution or incomplete dumping because the amount dumped at one time is difficult to control precisely, affecting the normal operation of the transfer station. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an autonomous unloading method, device, electronic equipment and storage medium that can automatically control the amount of material dumped at one time without human intervention, avoid waste overflow, and significantly improve unloading efficiency and operational safety.

[0005] In a first aspect, embodiments of the present invention provide an autonomous unloading method for unloading materials from a self-loading garbage truck to a mobile garbage station. The self-loading garbage truck includes: a container lifting cylinder, a rear camera, and a scraper mechanism. The method includes: acquiring pressure signals from the container lifting cylinder and image data collected by the rear camera; determining an estimated value of the weight of garbage inside the container of the self-loading garbage truck based on the pressure signals; identifying the garbage filling state in the garbage bin of the mobile garbage station based on the image data; generating unloading control commands based on the estimated value and the garbage filling state; controlling the container lifting cylinder to perform lifting or stopping actions based on the unloading control commands, and simultaneously controlling the scraper mechanism to perform opening or closing actions to perform autonomous unloading.

[0006] In a preferred embodiment of the present invention, the above-mentioned estimation of the weight of garbage inside the self-loading garbage truck body based on pressure signals includes: determining the real-time output force of the lifting cylinder of the body in the current lifting state based on the cylinder diameter, rod diameter and lifting angle of the lifting cylinder of the body, combined with the pressure signal; obtaining the center of gravity position parameters of the body at the current lifting angle; establishing the torque balance equation of the body based on the real-time output force and the center of gravity position parameters; and determining the estimated value based on the torque balance equation.

[0007] In a preferred embodiment of the present invention, the above-mentioned identification of the garbage filling status in the garbage bin of the mobile garbage station based on image data includes: extracting the outline region of the garbage bin from the image data; identifying the pixel features of garbage accumulation in the outline region, and comparing the pixel features with the background pixel features of the garbage bin in an empty state to obtain a comparison result; determining the current filling rate of the garbage bin based on the comparison result; and determining the garbage filling status based on the current filling rate and a preset overflow threshold.

[0008] In a preferred embodiment of the present invention, the above-mentioned generation of unloading control instructions based on the estimated value and the waste filling state includes: comparing the estimated value with a preset single unloading weight threshold; if the estimated value reaches the single unloading weight threshold, or the waste filling state is full, then the unloading control instruction is a stop unloading instruction; otherwise, the unloading control instruction is a continue unloading instruction.

[0009] In a preferred embodiment of the present invention, the above-mentioned control scraper mechanism to perform opening or closing actions includes: before the lifting cylinder of the container begins to lift and dump, controlling the scraper mechanism to run to the closed position to block the garbage from flowing out; when the unloading control command is a continue dumping command, controlling the scraper mechanism to run to the open position to allow the garbage to dump out; when the unloading control command is a stop dumping command, controlling the scraper mechanism to run to the closed position, and controlling the lifting cylinder of the container to stop lifting or start lowering.

[0010] In a preferred embodiment of the present invention, the method for setting the single dumping weight threshold includes: pre-obtaining the effective volume of the garbage bin of the mobile garbage station and the average density of the type of garbage to be dumped; determining the maximum single-time holding weight of the garbage bin based on the effective volume and average density; and determining the single dumping weight threshold based on the maximum single-time holding weight and a pre-set safety factor.

[0011] In a preferred embodiment of the present invention, before acquiring the pressure signal of the lifting cylinder of the container and the image data collected by the rear camera, the method further includes: receiving the model identifier of the mobile garbage station to be visited by the user; retrieving the garbage bin volume parameters and recommended dumping control parameters corresponding to the model identifier from a pre-stored database; and setting the single dumping weight threshold and overflow threshold for this unloading operation based on the garbage bin volume parameters and dumping control parameters.

[0012] Secondly, embodiments of the present invention also provide an autonomous unloading device for unloading materials from a self-loading garbage truck to a mobile garbage station. The self-loading garbage truck includes: a container lifting cylinder, a rear camera, and a scraper mechanism. The device includes: a data acquisition module for acquiring pressure signals from the container lifting cylinder and image data collected by the rear camera; an estimation value determination module for determining an estimated value of the weight of garbage inside the container of the self-loading garbage truck based on the pressure signals; a garbage filling state recognition module for recognizing the garbage filling state in the garbage bin of the mobile garbage station based on the image data; an unloading control command generation module for generating unloading control commands based on the estimated values ​​and the garbage filling state; and an autonomous unloading module for controlling the container lifting cylinder to perform lifting or stopping actions based on the unloading control commands, and simultaneously controlling the scraper mechanism to perform opening or closing actions to perform autonomous unloading.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the autonomous unloading method of the first aspect described above.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the autonomous unloading method described in the first aspect.

[0015] The embodiments of the present invention bring the following beneficial effects: This invention provides an autonomous unloading method, apparatus, electronic device, and storage medium. By acquiring pressure signals from the lifting cylinder of the container and image data from a rear-mounted camera, the method estimates the weight of garbage inside the container of a self-loading garbage truck based on the pressure signals. It also identifies the garbage filling status in the garbage bin of a mobile garbage station based on the image data. Based on the estimated weight and the garbage filling status, it generates unloading control commands. These commands control the lifting cylinder to lift or stop, and simultaneously control the scraper mechanism to open or close, thus enabling autonomous unloading. This method requires no manual intervention, automatically controls the amount of garbage dumped at one time, prevents garbage overflow, and significantly improves unloading efficiency and operational safety.

[0016] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0017] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart of an autonomous unloading method provided in an embodiment of the present invention; Figure 2 A flowchart of another autonomous unloading method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an autonomous unloading device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] A self-loading and unloading garbage truck is a special sanitation vehicle used for collecting and transporting urban domestic waste. It consists of a loading carrier, a loading and feeding mechanism, a loading and compression mechanism, an unloading mechanism, a hydraulic system, and an electrical system.

[0022] The self-loading and unloading garbage truck consists of a subframe, container, bin lifting mechanism, compression mechanism, and unloading mechanism. During operation, the bin lifting mechanism collects garbage, which is then compressed towards the rear of the container by a scraper and sliding plate mechanism (collectively called the compression mechanism). This initial compression of the collected, expanded garbage achieves a compression ratio of approximately 3:1, allowing for the loading of more garbage. After garbage collection, unloading begins. Currently used in urban areas, the unloading sites for self-loading and unloading garbage trucks on streets are mostly urban waste transfer stations, which typically house multiple mobile garbage stations. Unlike large landfills, these stations cannot completely empty the garbage in one go; multiple unloading operations are required, involving manual control of the bin's lifting angle and the compression mechanism's opening angle. This is time-consuming, labor-intensive, and prone to spillage if not properly controlled. This autonomous unloading control method effectively frees up the attention of sanitation workers and significantly reduces their workload. Furthermore, through the coordinated operation of the internal components of this control method, the amount of waste during a single dumping can be effectively controlled, preventing waste from being dumped outside the designated area. This also greatly improves the efficiency of sanitation operations.

[0023] Self-loading and unloading garbage trucks are commonly used sanitation vehicles for the collection and transportation of urban household waste. They load garbage through a bin-lifting mechanism and a compression mechanism, and then drive to a transfer station for unloading. Currently, garbage transfer stations typically have multiple mobile garbage stations for temporary garbage storage.

[0024] In related technologies, the unloading method requires operators to manually control the lifting angle of the container and the opening degree of the scraper based on experience, repeatedly dumping the waste into the station. This operation method, which relies on manual judgment, not only requires the driver to frequently adjust the actuator, resulting in high labor intensity and low work efficiency, but also makes it easy for waste to overflow and cause pollution or incomplete dumping because the amount dumped at one time is difficult to control precisely, affecting the normal operation of the transfer station.

[0025] Based on this, the present invention provides an autonomous unloading method, device, electronic equipment, and storage medium. This method acquires pressure signals from the lifting cylinder of the container and image data from a rear-mounted camera. Based on the pressure signals, it estimates the weight of the garbage inside the self-loading garbage truck's container. Based on the image data, it identifies the garbage filling status in the mobile garbage station's hopper. Based on the estimated weight and the garbage filling status, it generates unloading control commands. Based on these commands, it controls the lifting cylinder to lift or stop, and simultaneously controls the scraper mechanism to open or close, thus enabling autonomous unloading. This method requires no manual intervention, automatically controls the amount of garbage dumped at one time, avoids garbage overflow, and significantly improves unloading efficiency and operational safety.

[0026] To facilitate understanding of this embodiment, a detailed description of an autonomous unloading method disclosed in this embodiment of the invention will be provided first.

[0027] Example 1 This invention provides an autonomous unloading method. Figure 1 This is a flowchart illustrating an autonomous unloading method provided in an embodiment of the present invention. The method is used for unloading materials from a self-loading garbage truck to a mobile garbage station. The self-loading garbage truck includes: a container lifting cylinder, a rear camera, and a scraper mechanism. Figure 1 As shown, the autonomous unloading method may include the following steps: Step S101: Obtain the pressure signal from the lifting cylinder of the box and the image data collected by the tail camera.

[0028] Among them, the self-loading and unloading garbage truck is a special sanitation vehicle used for collecting and transporting domestic waste. It is usually composed of a chassis, subframe, container, bin lifting mechanism, compression mechanism (including scraper and sliding plate), and unloading mechanism (container lifting cylinder). Its characteristic is that it can automatically pour the garbage from the garbage bin into the container and perform preliminary compression.

[0029] Mobile garbage stations refer to movable garbage bins or containers placed in urban garbage transfer stations for temporary storage of garbage unloaded from garbage trucks. Once full, they are transferred by large transport vehicles. They typically have standardized volumes and interfaces.

[0030] The container lifting cylinder is a hydraulic actuator installed between the subframe and the container. It tilts the container around the rear hinge point by extending and retracting, thus unloading the waste. Its internal hydraulic pressure is proportional to the load (the weight of the container plus the weight of the waste).

[0031] The pressure signal is a real-time hydraulic pressure value (unit: MPa or bar) collected by pressure sensors installed at the inlet and outlet of the lifting cylinder in the housing, reflecting the load borne by the cylinder.

[0032] Among them, the rear camera is installed at the rear of the garbage truck (such as the upper rear of the container) to monitor the scene behind in real time, especially the garbage bins of the mobile garbage station, providing a data source for image recognition.

[0033] The scraper mechanism, located at the top of the container, consists of a scraper, a sliding plate, and a drive cylinder. It is used to compress the waste and prevent waste from flowing out during unloading. When the scraper opens, the unloading port opens; when the scraper closes, the unloading port closes.

[0034] The image data consists of consecutive frames captured by the rear camera, typically in color or grayscale, containing information about the garbage bin and its surrounding environment.

[0035] The pressure sensor can acquire cylinder pressure at a sampling frequency of 50~100Hz and transmit it to the controller via CAN bus or analog input channel. The camera can be an industrial-grade waterproof camera, transmitting real-time video streams via Ethernet or LVDS interface at a frame rate of 25~30fps.

[0036] For example, the controller reads the pressure value every 10ms, and each image frame is acquired approximately every 33ms. The system performs low-pass filtering on the pressure signal and denoising preprocessing on the image, thus providing real-time and stable raw data for subsequent weight estimation and image recognition.

[0037] Step S102: Determine the estimated weight of the garbage inside the self-loading garbage truck container based on the pressure signal.

[0038] The estimated weight of the waste is calculated by processing the pressure signal to represent the approximate weight (in kg or t) of the waste currently in the bin. It is not a precise measurement, but it reflects the trend of weight change.

[0039] Among them, the hydraulic principle and mechanical model can be used to convert pressure into cylinder output force, and then combined with parameters such as the lifting angle of the container and the position of the center of gravity, the weight of the garbage can be calculated through torque balance.

[0040] For example, if the pressure is 12 MPa at a certain moment, and the cylinder parameters and lifting angle are known, the calculated cylinder output force is 90 kN. Combining this with the container's own weight and center of gravity, the calculated weight of the waste is approximately 3.5 tons. Real-time monitoring of the remaining waste weight inside the container provides a basis for determining whether overloading has occurred or if unloading is complete.

[0041] Step S103: Identify the garbage filling status in the garbage bins of the mobile garbage station based on image data.

[0042] Among them, the garbage filling status is a qualitative or quantitative description of the degree of fullness of the garbage bins in the mobile garbage station, such as empty, half full, overflowing, etc., which is used to determine whether it can continue to receive garbage.

[0043] Among these methods, computer vision algorithms (such as object detection, semantic segmentation, and background subtraction) can be used to analyze images, identify garbage bin areas, and determine their fill levels. This prevents garbage overflow and ensures that the dumping process does not pollute the environment.

[0044] For example, the algorithm detects the boundary of the garbage bin in the image, calculates that the proportion of garbage pixels in the bin is 75%, and combines it with a preset threshold (such as 90%), then determines that the current filling status is not full.

[0045] Step S104: Generate unloading control instructions based on the estimated value and the waste filling status.

[0046] Among them, the unloading control command is a decision signal generated by the vehicle control system based on the weight estimate and filling status, such as continuing to dump or stopping dumping, which is used to drive the actuator to move.

[0047] The controller compares the estimated weight with a preset single-discharge weight threshold and determines whether the filling status is overflowing. If any condition is met, a stop-discharge command is generated; otherwise, a continue-discharge command is generated. The logic is an OR relationship.

[0048] For example, the current estimated value is 3.5 tons, and the threshold is 3.0 tons, which has been reached; however, image recognition shows that the garbage bin is not full. Due to the weight condition triggering the command, the dumping will still stop. This dual-judgment mechanism ensures timely stopping in any possible situation where the limit is exceeded, improving reliability.

[0049] Step S105: Based on the unloading control command, control the lifting cylinder of the box to perform lifting or stopping actions, and simultaneously control the scraper mechanism to perform opening or closing actions, so as to perform autonomous unloading.

[0050] The controller uses a hydraulic multi-way valve to control the extension and retraction of the lifting cylinder of the box, and a solenoid directional valve to control the movement of the scraper cylinder. When the command is to continue tilting, the lifting cylinder continues to rise and the scraper opens; when the command is to stop tilting, the lifting cylinder stops or lowers and the scraper closes. Both operate synchronously and in coordination.

[0051] For example, upon receiving a stop dumping command, the controller first sends a signal to close the scraper, and then stops the lifting cylinder after a 0.5-second delay to prevent residual waste from dripping. This achieves fully automated unloading without manual intervention, improving operational efficiency and safety.

[0052] In practical applications, a self-loading garbage truck, fully loaded with household waste, drives to a municipal waste transfer station. The driver parks the vehicle next to the designated mobile waste station and presses the "automatic unloading" button in the cab. The system automatically starts: the container slowly rises while a camera monitors the status of the garbage hopper, and a pressure sensor monitors the weight in real time. When the weight of the waste in the container decreases to near zero, or when the garbage hopper is full, the system automatically stops lifting, closes the scraper, and then the container falls back down. The entire process requires no driver intervention, and the driver is prompted to leave after unloading is complete.

[0053] Furthermore, to ensure the system's reliability in harsh environments (such as rain, night, and dust), the rear camera can employ infrared illumination and automatic heating defogging functions, and is equipped with windshield wipers. The controller uses automotive-grade chips and has a self-diagnostic function; for example, if a sensor disconnects or the image is lost, it will automatically alarm and stop unloading, switching to manual control. Simultaneously, the system can record unloading data (time, weight, images, etc.) for subsequent analysis and optimization.

[0054] The autonomous unloading method provided in this invention includes an autonomous unloading method, device, electronic equipment, and storage medium. It acquires pressure signals from the lifting cylinder of the container and image data from a rear-mounted camera. Based on the pressure signals, it estimates the weight of the garbage inside the self-loading garbage truck's container. Based on the image data, it identifies the garbage filling status in the mobile garbage station's hopper. Based on the estimated weight and the garbage filling status, it generates unloading control commands. These commands control the lifting cylinder to lift or stop, and simultaneously control the scraper mechanism to open or close, thus enabling autonomous unloading. This method requires no manual intervention, automatically controls the amount of garbage dumped at one time, prevents garbage overflow, and significantly improves unloading efficiency and operational safety.

[0055] Example 2 This invention also provides another autonomous unloading method, which is implemented based on the method described in the above embodiments.

[0056] Figure 2 A flowchart of another autonomous unloading method provided in an embodiment of the present invention is shown below. Figure 2 As shown, the autonomous unloading method may include the following steps: Step S201: Receive the model identifier of the mobile waste station to be visited, input by the user.

[0057] The model identifier is a unique code that identifies the mobile waste station model. It can be numbers, letters, or a QR code / barcode. For example, "MLD-5" or a QR code scan result.

[0058] The system allows drivers to input model codes via a touchscreen or scan QR codes / barcodes on the garbage bins using a handheld barcode scanner, which the system automatically recognizes. Electronic tags can also be read via voice input or radio frequency identification (RFID).

[0059] For example, the driver can use their mobile phone to scan the QR code on the garbage bin, which displays "Model: MLD-5" and transmits it to the vehicle controller via Bluetooth.

[0060] Step S202: Retrieve the garbage bin volume parameters and recommended dumping control parameters corresponding to the model identifier from the pre-stored database.

[0061] The controller can query a local database or a cloud database via 4G / 5G network based on the model identifier to return the volume parameters and recommended control parameters for that model. The database needs to be pre-loaded with information on common models.

[0062] The database consists of structured data stored locally on the vehicle controller or in the cloud, containing parameters for various types of garbage bins, such as effective volume, length, width and height, recommended overflow threshold, recommended safety factor, and maximum lifting angle limit.

[0063] Among them, the garbage bin volume parameters mainly refer to the effective volume, and may also include the bin opening size, depth, etc., which are used for scaling and perspective correction during image recognition.

[0064] Recommended dumping control parameters, in addition to volume, may include: a recommended overflow threshold (e.g., 90% filling rate) for this model, a safety factor (e.g., 0.85), a suggested lifting speed, and a scraper action delay, in order to optimize the unloading effect.

[0065] In practical applications, for new types of waste stations not yet entered into the database, drivers can manually input parameters and save them as new entries for later use. Simultaneously, combined with GPS positioning, the system can automatically identify the current transfer station location and display commonly used models for selection. If multiple models are available for the same transfer station, the system can prompt the driver for confirmation. Furthermore, the database can be updated regularly by downloading the latest parameters from the cloud to ensure accuracy.

[0066] Step S203: Based on the garbage bin volume parameters and dumping control parameters, set the single dumping weight threshold and overflow threshold for this unloading operation.

[0067] The single dumping weight threshold is calculated from the volume parameters and the safety factor.

[0068] The overflow threshold can be read directly from the database or set according to recommended values, such as 90%.

[0069] Step S204: Obtain the pressure signal from the lifting cylinder of the box and the image data collected by the tail camera.

[0070] This step is similar to step S101 above, and will not be described in detail here.

[0071] Step S205: Determine the estimated weight of the garbage inside the self-loading garbage truck container based on the pressure signal.

[0072] Specifically, determining the estimated weight of garbage inside the self-loading garbage truck's container based on pressure signals can include: determining the real-time output force of the container's lifting cylinder in the current lifting state based on the cylinder diameter, rod diameter, and lifting angle of the container's lifting cylinder, combined with the pressure signals; obtaining the center of gravity position parameters of the container at the current lifting angle; establishing the container's torque balance equation based on the real-time output force and center of gravity position parameters; and determining the estimated value based on the torque balance equation.

[0073] The cylinder bore and rod diameter, respectively, are the piston diameter and piston rod diameter of the hydraulic cylinder, determining the effective working area of ​​the cylinder. A larger cylinder bore results in a greater output force under the same pressure. The rod diameter affects the area difference between the rod-side chamber and the rodless chamber.

[0074] The lifting angle is the angle between the lifting box and the horizontal plane, which can be measured directly by an angle sensor installed at the hinge point of the box, or indirectly calculated by the stroke of the hydraulic cylinder. Changes in angle affect the position of the center of gravity and the lever arm.

[0075] The real-time output force is the actual thrust generated by the hydraulic cylinder under the current pressure (generally, oil is injected into the rodless chamber during lifting). The real-time output force F can be calculated using the following formula: F = P × A; where P is the current pressure and A is the area of ​​the rodless chamber: A = π (D / 2). 2 If there is no rod cavity, the area needs to be reduced by the rod cross-sectional area.

[0076] The center of gravity position parameter is the spatial position of the center of gravity of the container (including waste) relative to the lower hinge point of the hydraulic cylinder, usually expressed in polar coordinates (distance, angle). This parameter is related to the container structure, waste distribution, and lifting angle, and is generally obtained through 3D modeling or experimental calibration to obtain a table of center of gravity coordinates at a series of angles.

[0077] The torque balance equation takes the container as the research object, taking the moment about the lower hinge point of the hydraulic cylinder. The torque generated by the output force of the hydraulic cylinder is equal to the sum of the torque generated by the weight of the container and the weight of the garbage. The equation needs to consider the changes of each lever arm with the angle.

[0078] The estimated value is the weight of waste obtained by solving equations. It may have some error due to model simplification, but it is sufficient for control decisions.

[0079] When determining the real-time output force, internal friction and back pressure of the hydraulic cylinder can be considered and corrected.

[0080] Regarding the acquisition of the center of gravity position parameter, the controller has a built-in two-dimensional lookup table that stores the polar coordinates (r, θ) of the center of gravity of the container (including waste) relative to the lower hinge point of the hydraulic cylinder at different lifting angles. Since the distribution of waste may change, it is usually assumed that the center of gravity moves along the longitudinal direction of the container, and is dynamically corrected by real-time weight estimation.

[0081] Among them, the torque balance equation is: ;in, This refers to the real-time output force of the hydraulic cylinder in the current lifting state. The hydraulic cylinder lever arm (requires geometric calculation). The weight of the box is known. The center of gravity lever arm of the box, The weight of the waste is unknown. The center of gravity lever arm for the waste. Hydraulic cylinder lever arm. It can be calculated from the cylinder's installation position and current angle.

[0082] For example, assuming the cylinder lever arm is 1.0m, the container's weight is 2000kg, the container's center of gravity lever arm is 2.2m, the garbage's center of gravity lever arm is 1.8m, and the output force is 8000kgf. Then the equation is: 8000 × 1.0 = 2000 × 2.2 + ×1.8, solving for the solution yields... =(8000-4400) / 1.8=2000kg.

[0083] When determining the estimated value, if there are multiple sets of data (such as multiple measurements at different angles) after obtaining the weight of the waste, the least squares method or Kalman filter can be used to fuse them to improve accuracy.

[0084] In practical applications, to eliminate the effects of cylinder leakage and pressure fluctuations, the system performs moving average filtering on the pressure signal and periodically performs zero-point calibration. Furthermore, considering the potential uneven distribution of waste within the container (such as wet waste deposition), the waste lever arm in the center of gravity position parameter is adjusted. It is not a fixed value, but rather related to the weight and distribution of the waste. Therefore, a multi-angle measurement method can be used: data is collected multiple times at different lifting angles, and simultaneous equations are solved to determine the waste weight and center of gravity position; or a machine learning model can be used to train a pressure-weight mapping relationship to improve the robustness of the estimation.

[0085] Step S206: Identify the garbage filling status in the garbage bins of the mobile garbage station based on image data.

[0086] Specifically, identifying the garbage filling status inside the garbage bin of a mobile garbage station based on image data may include: extracting the outline region of the garbage bin from the image data; identifying the pixel features of garbage accumulation within the outline region and comparing the pixel features with the background pixel features of the garbage bin when it is empty to obtain a comparison result; determining the current filling rate of the garbage bin based on the comparison result; and determining the garbage filling status based on the current filling rate and a pre-set overflow threshold.

[0087] The contour region is the pixel area occupied by the garbage bins of the mobile garbage station in the image, usually represented by a rectangle or polygon. It can be extracted using object detection algorithms (such as YOLO, SSD) or image segmentation techniques.

[0088] Among them, pixel features describe the visual attributes of trash in an image, such as color (RGB values), texture (gradient, LBP), and edges. These features are used to distinguish trash from the background of empty buckets.

[0089] The background pixel features in the empty bin state are image features collected when the garbage bin is empty, serving as a baseline template. These features can be pre-stored or automatically initialized by the system taking an empty bin image before each operation.

[0090] This process involves comparing the features of the current image with those of the background to identify the difference regions (i.e., garbage-covered areas). Common methods include pixel differencing, color histogram matching, and deep learning semantic segmentation.

[0091] The current fill rate is the proportion of garbage filling the garbage bin, usually expressed as an area ratio: number of pixels in the garbage area / total number of pixels in the garbage bin × 100%. If stereo vision or a depth camera is used, the volume fill rate can be estimated.

[0092] The overflow threshold is a preset upper limit for the filling rate. If this value is exceeded, the garbage bin is considered full and dumping should stop. For example, it can be set to 90% or 95%, and adjusted according to the type of garbage and the bin shape.

[0093] Among them, the garbage filling status is a qualitative conclusion drawn from the comparison between the filling rate and the threshold, such as overflowing status (≥ threshold) or not full status (< threshold).

[0094] This can be achieved by using deep learning-based instance segmentation models (such as Mask R-CNN) or traditional image processing methods (such as color segmentation + morphology) to locate the outline region of the garbage bin from camera images. The model needs to be pre-trained to adapt to different lighting conditions, angles, and garbage bin types.

[0095] Within the outline region, pixel-level difference analysis can be performed between the current image and the background image of the garbage dump. A threshold is set to obtain a binarized difference map, where white pixels represent garbage. Alternatively, feature matching can be used, such as calculating the difference between the color histogram of the current region and the background histogram, or a deep learning network can be used to directly output a garbage region segmentation map.

[0096] The area fill rate is obtained by dividing the number of pixels in the garbage bin by the total number of pixels in the bin. If a depth camera is used, the volume fill rate can be estimated by combining the depth information (the 3D model inside the bin needs to be calibrated beforehand).

[0097] In practical applications, to improve recognition robustness, the system can fuse multiple frames of images for temporal smoothing to avoid misjudgment based on a single frame. For example, if four out of five consecutive frames are judged as overflowing, then the overflowing state is finally confirmed. Simultaneously, considering different weather and lighting conditions, image preprocessing parameters (such as exposure and contrast) can be automatically adjusted. For nighttime operations, the camera uses infrared supplementary lighting and employs infrared features for recognition. Furthermore, if there are various garbage bin models, empty bin templates and features for each model can be pre-stored in the database, and the corresponding template can be automatically loaded through model recognition.

[0098] Step S207: Generate unloading control instructions based on the estimated value and the waste filling status.

[0099] Specifically, based on the estimated value and the state of waste filling, a discharge control instruction is generated, which may include: comparing the estimated value with a pre-set single discharge weight threshold; if the estimated value reaches the single discharge weight threshold, or the waste filling state is full, the discharge control instruction is a stop discharge instruction; otherwise, the discharge control instruction is a continue discharge instruction.

[0100] The method for setting the single dumping weight threshold may include: obtaining in advance the effective volume of the garbage bin of the mobile garbage station and the average density of the type of garbage to be dumped; determining the maximum single-time holding weight of the garbage bin based on the effective volume and average density; and determining the single dumping weight threshold based on the maximum single-time holding weight and a pre-set safety factor.

[0101] The effective volume is the maximum volume of garbage that the garbage bin can hold. It is usually provided by the manufacturer or measured on-site, and the unit is m³ or L.

[0102] The average density is the typical density of the transported waste, which varies considerably among different types of waste.

[0103] The maximum single-load capacity is theoretically the maximum weight of garbage that the garbage bin can withstand, which is the effective volume multiplied by the average density. In practice, it may be slightly less than this value due to factors such as the angle of garbage accumulation.

[0104] The safety factor is a coefficient less than 1 (usually between 0.8 and 0.95), used to reserve a safety margin to prevent the garbage bin from overloading or overflowing. For example, a safety factor of 0.9 can be used for light waste and 0.85 for heavy waste.

[0105] Among them, the single dumping weight threshold is the ultimate upper limit of weight used for control, which is the maximum capacity weight multiplied by the safety factor.

[0106] Furthermore, the safety factor can be dynamically adjusted: a low safety factor is used for easily expanding waste (such as paper), while a high safety factor is used for waste with good compaction. The system can record historical unloading data. If the waste bin frequently overflows but the weight does not reach the threshold, the safety factor is automatically increased; conversely, if the weight often exceeds the limit but the bin is not full, the safety factor is decreased. In addition, the density parameter can be adjusted for different seasons. For example, during the rainy season, the water content of waste is high, and the density increases, requiring corresponding adjustment of the threshold.

[0107] The single-discharge weight threshold is the maximum permissible weight for a single dumping, set based on the capacity and density of the mobile waste station's hopper. It is typically slightly less than the theoretical maximum capacity of the hopper, leaving a safety margin. For example, if the hopper capacity is 5 m³ and the waste density is 0.4 t / m³, the theoretical maximum is 2 tons, and the threshold is set at 1.8 tons.

[0108] The stop dumping command is a control signal used to instruct the lifting cylinder to stop rising (or falling), the scraper to close, and to terminate the dumping.

[0109] The "Continue to Discharge" command is a control signal used to instruct the lifting cylinder to continue rising, the scraper to open, and to allow dumping.

[0110] In practical applications, to prevent false triggering caused by instantaneous fluctuations, the system can perform a first-order low-pass filter on the weight estimate and set a comparison hysteresis interval. For example, with a threshold set to 1.8 tons, a stop is triggered when the weight exceeds 1.8 tons, but pouring can only resume when the weight drops below 1.7 tons (if the hopper is not full). For the filling status, continuous multi-frame confirmation is also used. Furthermore, the system can record the reason for each stop (weight exceeding the limit or overflow) for subsequent analysis and optimization.

[0111] Step S208: Based on the unloading control command, control the lifting cylinder of the box to perform lifting or stopping actions, and simultaneously control the scraper mechanism to perform opening or closing actions, so as to perform autonomous unloading.

[0112] Specifically, controlling the scraper mechanism to perform opening or closing actions can include: controlling the scraper mechanism to move to the closed position before the container lifting cylinder starts lifting for dumping, so as to block the garbage from flowing out; when the unloading control command is a continue dumping command, controlling the scraper mechanism to move to the open position to allow the garbage to dump out; when the unloading control command is a stop dumping command, controlling the scraper mechanism to move to the closed position, and controlling the container lifting cylinder to stop lifting or start lowering.

[0113] The closed position is characterized by the scraper moving downwards until it is tightly fitted against the rear of the container, sealing the discharge port and preventing waste from flowing out. This position is typically detected by a limit switch or proximity sensor.

[0114] The opening position is as follows: the scraper is raised upwards to fully open the discharge port, allowing the garbage to slide out by gravity.

[0115] Among them, stopping lifting or starting to lower: When stopping dumping, the lifting cylinder of the container should stop rising further; if necessary, the cylinder can be controlled to slowly lower a certain distance so that the container falls back slightly, reducing the risk of garbage residue leakage.

[0116] In this system, after pressing the automatic unloading button, the system first controls the scraper cylinder to close the scraper. Only after detecting the closed-position signal does it begin to lift the container. This ensures that waste will not accidentally spill out before the container tilts. When a continue unloading command is received, the controller controls the scraper cylinder to retract, opening the scraper. The opening action should typically be smooth to avoid impact. Upon receiving a stop unloading command, the system prioritizes quickly closing the scraper (within approximately 1 second), then stops the lifting cylinder's upward movement, or controls it to slowly descend a small distance (e.g., 5°) to slightly lower the container and reduce waste dripping. If a complete reset is required, it will be lowered in subsequent steps.

[0117] Furthermore, to enhance safety, interlocking logic can be set between the scraper action and the lifting action: lifting is not allowed when the scraper is not fully closed; if an abnormality (such as jamming) is detected during the scraper opening process, the system will immediately stop and trigger an alarm. Simultaneously, the system can be set to different action speeds: a fast mode for scraper closing and a slow mode for opening, to precisely control the unloading volume. When the hydraulic cylinder stops, a hydraulic lock prevents it from sliding down under its own weight.

[0118] Example 3 Corresponding to the above method embodiments, this invention provides an autonomous unloading device. Figure 3 This is a schematic diagram of an autonomous unloading device provided in an embodiment of the present invention. The device is used for unloading materials from a self-loading garbage truck to a mobile garbage station. The self-loading garbage truck includes: a body lifting cylinder, a rear camera, and a scraper mechanism, such as... Figure 3 As shown, the autonomous unloading device may include: The data acquisition module 301 is used to acquire the pressure signal of the lifting cylinder of the box and the image data collected by the tail camera.

[0119] The estimation value determination module 302 is used to determine the estimated weight of garbage inside the container of the self-loading garbage truck based on the pressure signal.

[0120] The garbage filling status recognition module 303 is used to recognize the garbage filling status in the garbage bin of the mobile garbage station based on image data.

[0121] The unloading control command generation module 304 is used to generate unloading control commands based on estimated values ​​and waste filling status.

[0122] The autonomous unloading module 305 is used to control the lifting cylinder of the box to perform lifting or stopping actions based on the unloading control command, and simultaneously control the scraper mechanism to perform opening or closing actions to perform autonomous unloading.

[0123] The autonomous unloading device provided in this invention can acquire pressure signals from the lifting cylinder of the container and image data collected by the rear camera. Based on the pressure signals, it determines an estimated value of the weight of garbage inside the self-loading garbage truck container. Based on the image data, it identifies the garbage filling state in the garbage bin of the mobile garbage station. Based on the estimated value and the garbage filling state, it generates unloading control commands. Based on the unloading control commands, it controls the lifting cylinder of the container to perform lifting or stopping actions, and simultaneously controls the scraper mechanism to perform opening or closing actions, thereby performing autonomous unloading. In this method, no manual intervention is required, the amount of garbage dumped at one time can be automatically controlled, garbage overflow is avoided, and unloading efficiency and operational safety are significantly improved.

[0124] In some embodiments, the estimation value determination module is further configured to determine the real-time output force of the lifting cylinder in the current lifting state based on the cylinder diameter, rod diameter, and lifting angle of the lifting cylinder, combined with the pressure signal; obtain the center of gravity position parameters of the housing at the current lifting angle; establish the torque balance equation of the housing based on the real-time output force and the center of gravity position parameters; and determine the estimated value based on the torque balance equation.

[0125] In some embodiments, the waste filling status recognition module is further configured to extract the contour region of the waste bin from the image data; identify the pixel features of waste accumulation within the contour region, and compare the pixel features with the background pixel features of the waste bin in an empty state to obtain a comparison result; determine the current filling rate of the waste bin based on the comparison result; and determine the waste filling status based on the current filling rate and a preset overflow threshold.

[0126] In some embodiments, the unloading control command generation module is further configured to compare the estimated value with a preset single unloading weight threshold; if the estimated value reaches the single unloading weight threshold, or the waste filling state is full, the unloading control command is a stop unloading command; otherwise, the unloading control command is a continue unloading command.

[0127] In some embodiments, the autonomous unloading module is further configured to control the scraper mechanism to move to the closed position before the container lifting cylinder starts lifting for dumping, so as to block the garbage from flowing out; when the unloading control command is a continue dumping command, control the scraper mechanism to move to the open position to allow the garbage to be dumped; when the unloading control command is a stop dumping command, control the scraper mechanism to move to the closed position and control the container lifting cylinder to stop lifting or start lowering.

[0128] In some embodiments, the unloading control command generation module is further configured to: pre-obtain the effective volume of the garbage bin of the mobile garbage station and the average density of the type of garbage to be dumped; determine the maximum single-time holding weight of the garbage bin based on the effective volume and average density; and determine the single-time unloading weight threshold based on the maximum single-time holding weight and a pre-set safety factor.

[0129] In some embodiments, the data acquisition module is further configured to receive the model identifier of the mobile waste station to be visited by the user; retrieve the waste bin volume parameters and recommended dumping control parameters corresponding to the model identifier from a pre-stored database; and set the single dumping weight threshold and overflow threshold for this unloading operation based on the waste bin volume parameters and dumping control parameters.

[0130] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0131] Example 4 This invention also provides an electronic device for running the above-described autonomous unloading method; see [link to previous document]. Figure 4 The diagram shows the structure of an electronic device, which includes a memory 400 and a processor 401. The memory 400 is used to store one or more computer instructions, which are executed by the processor 401 to realize the above-mentioned autonomous unloading method.

[0132] Furthermore, Figure 4 The electronic device shown also includes a bus 402 and a communication interface 403. The processor 401, the communication interface 403 and the memory 400 are connected via the bus 402.

[0133] The memory 400 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0134] Processor 401 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 401 or by instructions in software form. Processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 400, and processor 401 reads information from memory 400 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0135] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the above-described autonomous unloading method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0136] The computer program product for the autonomous unloading method provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0137] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0138] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0141] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0142] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An autonomous unloading method, characterized in that, For unloading garbage trucks from mobile garbage stations, the self-loading garbage truck includes: a body lifting cylinder, a rear camera, and a scraper mechanism; the method includes: Acquire the pressure signal from the lifting cylinder of the housing and the image data captured by the tail camera; The estimated weight of the garbage inside the self-loading garbage truck container is determined based on the pressure signal. The image data is used to identify the garbage filling status inside the garbage bins of the mobile garbage station; Based on the estimated value and the waste filling status, an unloading control command is generated; Based on the unloading control command, the lifting cylinder of the box is controlled to perform lifting or stopping actions, and the scraper mechanism is simultaneously controlled to perform opening or closing actions to perform autonomous unloading.

2. The method according to claim 1, characterized in that, The step of determining an estimated weight of garbage inside the self-loading garbage truck container based on the pressure signal includes: Based on the cylinder diameter, rod diameter, and lifting angle of the lifting cylinder, and in conjunction with the pressure signal, the real-time output force of the lifting cylinder in the current lifting state is determined. Obtain the center of gravity position parameters of the box body at the current lifting angle; Based on the real-time output force and the center of gravity position parameters, the torque balance equation of the box is established; The estimated value is determined based on the torque balance equation.

3. The method according to claim 2, characterized in that, The step of identifying the garbage filling status in the garbage bins of the mobile garbage station based on the image data includes: Extract the outline region of the garbage bin from the image data; Identify the pixel features of garbage accumulation within the outline area, and compare the pixel features with the background pixel features of the garbage bin when it is empty to obtain the comparison result; The current filling rate of the garbage bin is determined based on the comparison results; The garbage filling status is determined based on the current filling rate and the preset overflow threshold.

4. The method according to claim 3, characterized in that, The step of generating unloading control instructions based on the estimated value and the waste filling status includes: The estimated value is compared with a pre-set single-discharge weight threshold; If the estimated value reaches the single dumping weight threshold, or if the waste filling state is full, then the unloading control command is a stop dumping command; otherwise, the unloading control command is a continue dumping command.

5. The method according to claim 4, characterized in that, The control of the scraper mechanism to perform opening or closing actions includes: Before the lifting cylinder of the container begins to lift and dump, the scraper mechanism is controlled to move to the closed position to prevent the garbage from flowing out; When the unloading control command is the continued unloading command, the scraper mechanism is controlled to move to the open position to allow the waste to be dumped. When the unloading control command is the stop unloading command, the scraper mechanism is controlled to move to the closed position, and the box lifting cylinder is controlled to stop lifting or start lowering.

6. The method according to claim 4, characterized in that, The method for setting the single dumping weight threshold includes: The effective volume of the garbage bins of the mobile garbage station and the average density of the types of garbage to be dumped are obtained in advance; The maximum single-use weight of the garbage bin is determined based on the effective volume and the average density. The single unloading weight threshold is determined based on the maximum single-time capacity and the pre-set safety factor.

7. The method according to claim 4, characterized in that, Before acquiring the pressure signal from the lifting cylinder of the housing and the image data captured by the tail camera, the method further includes: Receives the model identifier of the mobile waste station to be visited, input by the user; Retrieve the garbage bin volume parameters and recommended dumping control parameters corresponding to the model identifier from the pre-stored database; Based on the garbage bin volume parameters and the dumping control parameters, the single dumping weight threshold and the overflow threshold are set for this unloading operation.

8. An autonomous unloading device, characterized in that, For unloading garbage trucks from mobile garbage stations, the self-loading garbage truck includes: a body lifting cylinder, a rear camera, and a scraper mechanism; the device includes: The data acquisition module is used to acquire the pressure signal of the lifting cylinder of the box and the image data collected by the tail camera; The estimation value determination module is used to determine the estimated weight of the garbage inside the self-loading garbage truck container based on the pressure signal. The garbage filling status recognition module is used to identify the garbage filling status inside the garbage bin of the mobile garbage station based on the image data; The unloading control command generation module is used to generate unloading control commands based on the estimated value and the waste filling status. The autonomous unloading module is used to control the lifting cylinder of the box to perform lifting or stopping actions based on the unloading control command, and simultaneously control the scraper mechanism to perform opening or closing actions, so as to perform autonomous unloading.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the autonomous unloading method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the autonomous unloading method according to any one of claims 1 to 7.

Images