Control method and device for autonomously movable outdoor garbage can

Abstract

The invention provides a control method and device for an autonomously movable outdoor garbage can, and relates to the field of data processing. In the method, a cleaning instruction input by a user is responded, and the cleaning instruction comprises a to-be-cleaned position; acquiring the current position of the garbage can; determining a first scheduling path according to the current position and the to-be-cleaned position; obtaining an influence factor of the first scheduling path, wherein the influence factor comprises a road condition and a pedestrian flow rate; inputting the influence factor into a preset control model to obtain a second scheduling path; and sending a control instruction to the garbage can to control the garbage can to go to the to-be-cleaned position for cleaning according to the second scheduling path. By implementing the technical scheme provided by the invention, the cleaning efficiency is conveniently improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a control method and device for an autonomously movable outdoor trash can. Background Art

[0002] In the current closed park management, trash cans are important environmental sanitation facilities, and their layout and management are directly related to the cleanliness and beauty of the park.

[0003] At present, in the existing technology, the garbage cans in closed parks are usually fixed in a certain location. Although this method is convenient for residents and visitors to put out garbage to a certain extent, it also brings a series of problems. The fixed location of the garbage can requires regular maintenance and cleaning by a dedicated person, which undoubtedly increases the manpower cost of park management and leads to low cleaning efficiency.

[0004] Therefore, there is an urgent need for a control method and device for an autonomously movable outdoor trash can. Summary of the invention

[0005] The present application provides a control method and device for an autonomously movable outdoor trash can, which is convenient for improving cleaning efficiency.

[0006] In a first aspect of the present application, a control method for an autonomously movable outdoor trash can is provided, the method comprising: responding to a cleaning instruction input by a user, the cleaning instruction comprising a position to be cleaned; obtaining the current position of the trash can; determining a first scheduling path based on the current position and the position to be cleaned; obtaining influencing factors of the first scheduling path, the influencing factors comprising road conditions and pedestrian flow; inputting the influencing factors into a preset control model to obtain a second scheduling path; and sending a control instruction to the trash can to control the trash can to go to the position to be cleaned for cleaning along the second scheduling path.

[0007] By adopting the above technical solution, the system can quickly respond to the user's cleaning instructions and work according to the location to be cleaned specified by the user. This personalized service method meets the user's immediate needs for cleaning a specific area. The system first determines the first scheduling path from the current location of the trash can to the location to be cleaned. Subsequently, by considering influencing factors such as road conditions and pedestrian flow, the system can further optimize the path planning and select a more reasonable and efficient second scheduling path. This helps to reduce unnecessary driving time and resource consumption. The system can adapt to different road conditions and pedestrian flow. Through intelligent path planning and optimization, the trash can can go to the location to be cleaned more quickly and accurately for cleaning. This can not only improve cleaning efficiency, but also reduce the workload of cleaning staff and reduce labor costs. The intelligent trash can management system can provide users with more convenient and efficient cleaning services. Users can trigger cleaning tasks with simple instructions without having to go in person or wait for cleaning staff. This way of improving user experience helps to increase user satisfaction with park management services. Through intelligent path planning and optimization, the system can avoid unnecessary driving and empty driving, thereby reducing energy consumption and resource waste, and facilitating improved cleaning efficiency.

[0008] Optionally, before responding to the cleaning instruction input by the user, the method also includes: receiving image data sent by a sensor device; determining a basic feature map corresponding to the image data based on the image data; performing multi-scale feature extraction on the basic feature map based on a multi-scale channel attention mechanism to obtain a multi-scale feature map; obtaining a salient area of ​​the image data based on the multi-scale feature map; calculating a similarity value between the salient area and a preset area to be cleaned, wherein the preset area to be cleaned is determined by an image to be cleaned; if it is determined that the similarity value is greater than or equal to a preset similarity threshold, displaying a prompt message, wherein the prompt message is used to prompt the user that the position corresponding to the image data needs to be cleaned.

[0009] By adopting the above technical solution, the system can automatically receive image data sent by the sensor device and extract key features in the image through image processing technology. This greatly reduces the need for manual inspection and identification and improves the automation level of cleaning work. Using the multi-scale channel attention mechanism to extract multi-scale features from the basic feature map means that the system can capture information of different scales in the image. This helps to identify salient areas more accurately, because cleaning needs may involve objects or areas of different sizes. Based on the multi-scale feature map, the system can determine the salient areas in the image. These areas are usually more prominent than the background and more likely to need cleaning. This salient area detection improves the pertinence and accuracy of the cleaning task. By calculating the similarity value between the salient area and the preset area to be cleaned, the system can determine whether the current image contains an area that needs to be cleaned. If the similarity reaches or exceeds the preset threshold, the system will display a prompt message to remind the user to clean. This timely prompt helps users respond quickly and handle cleaning needs. Since the system can automatically identify and locate the area that needs to be cleaned, users do not need to spend a lot of time searching and judging. This greatly improves the efficiency of cleaning work and reduces unnecessary labor and time waste. By providing timely prompts and accurate cleaning guidance, the system can enhance the user's experience. Users can complete cleaning tasks more conveniently while enjoying the convenience and comfort brought by intelligent services.

[0010] Optionally, determining a first scheduling path based on the current position and the position to be cleaned specifically includes: calculating a current area based on the current position, wherein a circular area is drawn with the coordinate point corresponding to the current position as the center and a radius of a preset length to obtain the current area, and the preset length is determined according to the volume of the trash can; calculating an area to be cleaned based on the position to be cleaned, wherein the area to be cleaned includes a garbage contour corresponding to the position to be cleaned; acquiring a real-time moving direction of the trash can; and determining a scheduling path between the current area and the contour corresponding to the area to be cleaned based on the real-time moving direction to obtain the first scheduling path.

[0011] By adopting the above technical solution, the system can accurately define an impact range by taking the current position of the trash can as the center and setting a circular area of ​​a preset length as the current area. This approach not only takes into account the physical size of the trash can, but also provides a reasonable boundary for its movement and cleaning work. The area to be cleaned is determined based on the location to be cleaned and its corresponding garbage contour. This means that the system not only knows the target point of cleaning, but also can identify the pollution range around the point, thereby ensuring the thoroughness of cleaning. It is an efficient and intelligent approach to obtain the real-time moving direction of the trash can and determine the scheduling path based on this information. This can reduce unnecessary turns and detours and improve cleaning efficiency. Determining the scheduling path based on the real-time moving direction and the contour of the area to be cleaned means that the system can generate a path that fits the actual cleaning needs. This path takes into account both the current state of the trash can and the specific conditions of the area to be cleaned, thereby ensuring the effectiveness and efficiency of the cleaning work. Through the above steps, the system can generate a scheduling path that is both reasonable and efficient. This can not only reduce cleaning time, but also reduce cleaning costs and improve the efficiency of the entire cleaning work.

[0012] Optionally, obtaining the influencing factor of the first scheduling path specifically includes: obtaining original image data sent by a target monitoring device, wherein the target monitoring device is located on the first scheduling path; preprocessing the original image data to obtain classified image data, wherein the preprocessing includes denoising, filtering, feature extraction and normalization; and obtaining the influencing factor based on the classified image data.

[0013] By adopting the above technical solution, the system can perceive the environmental conditions on the first scheduling path in real time by acquiring the original image data sent by the target monitoring device. This is crucial to ensure the smooth progress of cleaning work, because different environmental conditions may require different cleaning strategies. Preprocessing the original image data, including denoising, filtering, feature extraction and normalization, can significantly improve the accuracy of subsequent analysis. Denoising and filtering can eliminate interference information in the image, feature extraction can highlight key information, and normalization makes data from different sources or different time points comparable. Based on the preprocessed classified image data, the system can extract the influencing factors on the first scheduling path. By considering these influencing factors, the system can optimize the scheduling path, avoid congestion or dangerous areas, and improve cleaning efficiency. At the same time, it can also reduce the risk of damage to cleaning equipment or safety accidents caused by environmental factors. These influencing factors extracted based on image data can provide support for the system's intelligent decision-making. For example, if the system detects a large flow of people on a certain section of the path, it may choose to avoid the area or adjust the cleaning time to reduce interference with pedestrians.

[0014] Optionally, obtaining the influencing factor based on the classified image data specifically includes: performing corner detection on the classified image data to obtain shape feature data; performing contour extraction on the shape feature data to obtain edge contour data; performing feature encoding on the edge contour data to obtain concrete feature data, the concrete feature data including potholes, obstacles and biological entities; obtaining the road condition based on the potholes and the obstacles; and calculating the pedestrian flow based on the biological entities.

[0015] By adopting the above technical solution, the system can identify key points and shape features in the image through corner point detection. These features are crucial for subsequent contour extraction and feature encoding because they represent the basic structure and morphology of objects in the image. Based on the shape feature data obtained by corner point detection, the system can further extract the edge contour of the object. These edge contour data can more accurately depict the actual boundaries of objects in the image, providing a basis for subsequent feature encoding and classification. Feature encoding is performed on the edge contour data to convert abstract contour information into specific, quantifiable, figurative feature data. These figurative feature data include potholes, obstacles, and biological entities, which directly reflect the actual conditions on the dispatch path. Based on the figurative feature data of potholes and obstacles, the system can evaluate the road conditions on the dispatch path. This information is of great significance for determining the driving speed of cleaning equipment, avoiding potential risks, etc., and can ensure the smooth progress of cleaning work. By identifying and analyzing the figurative feature data of biological entities, the system can calculate the flow of people on the dispatch path. The flow of people is an important parameter for evaluating the congestion of the dispatch path and determining the optimal cleaning time, which can help the system avoid cleaning during peak hours and reduce interference with human activities.

[0016] Optionally, the inputting the influencing factor into the preset control model to obtain the second scheduling path specifically includes: obtaining the smooth probability corresponding to the first scheduling path based on the correspondence between the influencing factor and the smooth probability, the preset control model pre-stores the corresponding relationship, and the smooth probability is calculated based on the historical smooth probability corresponding to the historical scheduling path; if it is determined that the smooth probability is less than a preset probability threshold, then performing path correction on the first scheduling path to obtain the second scheduling path, and the smooth probability of the second scheduling path is greater than the smooth probability corresponding to the first scheduling path.

[0017] By adopting the above technical solution, the system uses the smooth probability as a key indicator for selecting a dispatching path. The smooth probability is calculated based on the historical smooth probability corresponding to the historical dispatching path, which means that the system can use past experience to predict the smoothness of the current or future path. This decision-making method based on historical data is more reliable and effective. When the smooth probability of the first dispatching path is lower than the preset probability threshold, the system will immediately make a path correction and generate a second dispatching path. This real-time correction can ensure that the system always selects a path with higher smoothness, thereby improving the efficiency and safety of cleaning work. By selecting a dispatching path with higher smoothness, the system can reduce waiting time and obstacle interference during the cleaning process, and provide users with more efficient and smooth cleaning services. This helps to improve user satisfaction and experience. Selecting a path with higher smoothness means that the cleaning equipment can reach the destination and complete the cleaning task faster. This reduces unnecessary delays and detours, and improves the overall efficiency of the cleaning work. Driving on a path with lower smoothness may increase the risk of wear and tear and failure of the cleaning equipment. By selecting a path with higher smoothness, the system can reduce these risks and extend the service life of the equipment.

[0018] Optionally, the cleaning instruction also includes a target scheduling path, and the method also includes: sending a target control instruction to the trash can to control the trash can to go to the location to be cleaned for cleaning according to the target scheduling path, and the target scheduling path passes through multiple locations to be cleaned, and the target scheduling path is determined by the user planning.

[0019] By adopting the above technical solution, users are allowed to plan the target scheduling path by themselves, so that the cleaning work is more in line with the actual needs of users. Users can customize the best scheduling path according to the specific conditions of the cleaning area, such as the degree of dirtiness, the distribution of obstacles, etc. Through the target scheduling path planned by the user, it can be ensured that the trash can can be cleaned according to the optimal route, reducing unnecessary detours and duplication of work, thereby improving cleaning efficiency. Users can adjust the target scheduling path at any time as needed to adapt to different cleaning needs. Although the target scheduling path is planned by the user, the entire cleaning process is still controlled by the intelligent system. The system can automatically adjust the moving speed, cleaning method and other parameters of the trash can according to the path provided by the user to realize intelligent cleaning operations. By allowing users to plan the target scheduling path, the system can better meet the personalized needs of users and provide more intimate and convenient cleaning services. This can not only improve user satisfaction, but also enhance users' trust and dependence on the intelligent cleaning system. Once the user plans the target scheduling path and sends the target control instruction, the trash can can automatically clean according to the path without the need for continuous monitoring and intervention by the user. This lowers the user's usage threshold and makes cleaning work easier and simpler.

[0020] In a second aspect of the present application, a control device for an autonomously movable outdoor trash can is provided, the control device comprising an acquisition module and a processing module, wherein the acquisition module is used to respond to a cleaning instruction input by a user, the cleaning instruction comprising a position to be cleaned; the acquisition module is also used to acquire the current position of the trash can; the processing module is used to determine a first scheduling path based on the current position and the position to be cleaned; the acquisition module is also used to acquire influencing factors of the first scheduling path, the influencing factors comprising road conditions and pedestrian flow; the processing module is also used to input the influencing factors into a preset control model to obtain a second scheduling path; the processing module is also used to send a control instruction to the trash can to control the trash can to go to the position to be cleaned for cleaning along the second scheduling path.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The system can quickly respond to the user's cleaning instructions and work according to the location to be cleaned specified by the user. This personalized service method meets the user's immediate needs for cleaning a specific area. The system first determines the first dispatching path from the current location of the trash can to the location to be cleaned. Then, by considering influencing factors such as road conditions and pedestrian flow, the system can further optimize the path planning and select a more reasonable and efficient second dispatching path. This helps to reduce unnecessary driving time and resource consumption. The system can adapt to different road conditions and pedestrian flow. Through intelligent path planning and optimization, the trash can can go to the location to be cleaned more quickly and accurately for cleaning. This can not only improve cleaning efficiency, but also reduce the workload of cleaning staff and reduce labor costs. The intelligent trash can management system can provide users with more convenient and efficient cleaning services. Users can trigger cleaning tasks with simple instructions without having to go in person or wait for cleaning staff. This way of improving user experience helps to increase user satisfaction with park management services. Through intelligent path planning and optimization, the system can avoid unnecessary driving and empty driving, thereby reducing energy consumption and resource waste, and facilitating improved cleaning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a control method for an autonomously movable outdoor trash can provided in an embodiment of the present application.

[0025] Figure 2 Another flowchart diagram of a method for controlling an autonomously movable outdoor trash can provided in an embodiment of the present application.

[0026] Figure 3 A schematic diagram of a module of a control device for an autonomously movable outdoor trash can provided in an embodiment of the present application.

[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0032] In the current closed park management, trash cans are key facilities for maintaining environmental sanitation, and their layout and management play a vital role in keeping the park clean and beautiful.

[0033] However, under existing technical conditions, garbage cans in closed parks are often fixed in specific locations. Although this practice simplifies the steps for residents and visitors to put out garbage, it also highlights some significant problems. The fixed location of the garbage cans requires frequent maintenance and cleaning by park managers, which undoubtedly increases the manpower investment of park management and also affects the efficiency of cleaning work.

[0034] In order to solve the above technical problems, the present application provides a control method for an autonomously movable outdoor trash can. Figure 1 , Figure 1 This is a flow chart of a control method for an autonomously movable outdoor trash can provided in an embodiment of the present application. The control method is applied to a server and includes steps S110 to S160, which are as follows: S110 , responding to a cleaning instruction input by a user, where the cleaning instruction includes a location to be cleaned.

[0035] Specifically, the server is the central device that processes user requests and sends instructions to the autonomous mobile outdoor trash can. It may be a cloud server, a server in a local area network, or other forms of computing devices. The user (may be a cleaner, property manager, or ordinary user) sends a cleaning instruction to the server in some way (such as a mobile phone application, web interface, touch screen, etc.). This instruction usually contains the specific tasks or actions that the trash can needs to perform. An autonomous mobile outdoor trash can is an outdoor trash can with autonomous mobility, which can receive instructions from the server and move and clean according to these instructions. It is usually equipped with GPS positioning, sensors, motors, cleaning tools and other equipment and components. The location to be cleaned is a specific place or area that the user specifies to the trash can and needs to be cleaned. It can be a corner in a closed park, an area in a garage, or any other place that needs to be cleaned.

[0036] In one possible implementation, before responding to a cleaning instruction input by a user, image data sent by a sensor device is received; a basic feature map corresponding to the image data is determined based on the image data; based on a multi-scale channel attention mechanism, multi-scale features are extracted from the basic feature map to obtain a multi-scale feature map; based on the multi-scale feature map, a salient area of ​​the image data is obtained; a similarity value between the salient area and a preset area to be cleaned is calculated, where the preset area to be cleaned is determined by an image to be cleaned; if it is determined that the similarity value is greater than or equal to a preset similarity threshold, a prompt message is displayed, where the prompt message is used to prompt the user that the position corresponding to the image data needs to be cleaned.

[0037] Specifically, before performing the cleaning task, the server first receives image data from a sensor device (such as a camera). These image data reflect the current state of the cleaning environment. The server processes the received image data, extracts its basic features, and generates one or more basic feature maps. These basic feature maps describe the basic structure and information in the image. Based on the multi-scale channel attention mechanism, the server performs multi-scale feature extraction on the basic feature map. This means that the server can extract features in the image at different scales to capture information at different scales. The channel attention mechanism helps the server identify which channels (i.e., which features) are more important in the image, so as to pay more attention to these important features. Based on the multi-scale feature map, the server determines the salient areas in the image. These salient areas may be stains, garbage, or other objects that need to be cleaned. The server has a preset model or template of the area to be cleaned, which describes the image features that need to be cleaned. The server compares the salient area with the preset area to be cleaned and calculates the similarity value between them. The higher the similarity value, the more similar the salient area is to the preset area to be cleaned, and the more likely it is to be an area that needs to be cleaned. If the similarity value is greater than or equal to the preset similarity threshold, the server will display a prompt message to the user. This prompt information is used to inform the user that the position corresponding to the image data needs to be cleaned.

[0038] For example, in a closed park, such as a university campus or an industrial park, multiple autonomously movable outdoor trash cans are deployed. These trash cans not only have basic garbage storage functions, but can also move autonomously according to the garbage distribution in the park so as to collect and clean up garbage more efficiently. Sensor devices are used to collect image data in the park in real time, which reflects the garbage distribution around the trash cans. The server processes the received image data, extracts basic features in the image, and generates basic feature maps. These basic feature maps describe the basic structure and information in the image, such as color, shape, texture, etc. Based on the multi-scale channel attention mechanism, the server performs multi-scale feature extraction on the basic feature map. This means analyzing the image at different scales to identify garbage of different sizes and distribution patterns. The channel attention mechanism helps the server focus on feature channels that are more important for garbage recognition, thereby improving recognition accuracy. Based on the multi-scale feature map, the server can identify the salient areas in the image, that is, the areas where garbage is concentrated. The server compares the identified salient areas with the preset templates and calculates the similarity value between them. If the similarity value exceeds the preset threshold, the trash can will determine that the area is a garbage area that needs to be cleaned.

[0039] S120: Get the current position of the trash can.

[0040] Specifically, autonomous mobile outdoor trash cans are equipped with some form of positioning technology, such as GPS (Global Positioning System), Wi-Fi positioning, Bluetooth positioning, RFID (Radio Frequency Identification) or other similar positioning methods. These technologies enable the trash can to determine its position in the environment. Once the trash can determines its position, it will send this location information to the server through some communication protocol (such as Wi-Fi, 4G / 5G, LoRa, etc.). This usually involves the encoding, packaging and transmission of data. The server needs to have an interface or API (Application Programming Interface) that can receive location information from the trash can. When the server receives the location data, it decodes and parses it to obtain the precise location of the trash can. The server may further process and analyze the received location data, such as associating it with other data (such as cleaning instructions, trash can status, etc.), or storing it in a database for subsequent query and analysis. After the server obtains the current location of the trash can, it can perform various operations based on this location information, such as sending cleaning instructions to the trash can, optimizing the scheduling path, and performing real-time monitoring and alarming.

[0041] S130: Determine a first scheduling path according to the current position and the position to be cleaned.

[0042] Specifically, a map data is usually stored in the server, which can describe the terrain, roads, obstacles and other information in the cleaning area in detail. Map data is crucial for path planning because it provides the server with spatial layout information in the cleaning area. The server uses one or more path planning algorithms to determine the first scheduling path. These algorithms usually consider multiple factors, such as distance, time, obstacles, road conditions, etc., to find an optimal path. Common path planning algorithms include Dijkstra algorithm, A* algorithm, genetic algorithm, etc. The server uses the current position of the trash can and the user-specified location to be cleaned as the starting point and end point of the path planning. These two location information are crucial for determining the first scheduling path. Based on the map data and path planning algorithm, the server calculates the optimal path from the current position of the trash can to the location to be cleaned, that is, the first scheduling path. This path takes into account various factors, such as the shortest distance, the shortest time, and avoiding obstacles.

[0043] In a possible implementation, a first scheduling path is determined based on the current position and the position to be cleaned, specifically including: based on the current position, calculating the current area, wherein a circular area is drawn with the coordinate point corresponding to the current position as the center and a radius of a preset length to obtain the current area, and the preset length is determined according to the volume of the trash can; based on the position to be cleaned, the area to be cleaned is calculated, wherein the area to be cleaned includes the garbage contour corresponding to the position to be cleaned; obtaining the real-time moving direction of the trash can; and based on the real-time moving direction, determining the scheduling path between the current area and the contour corresponding to the area to be cleaned to obtain the first scheduling path.

[0044] Specifically, the server draws a circular area with the current position of the trash can as the center and the preset length as the radius. This area is called the "current area". A larger trash can may require more space to rotate or perform other cleaning operations, so the preset length will increase accordingly. The server determines an area to be cleaned based on the position to be cleaned. This area not only includes the location point to be cleaned, but also the garbage outline of the location point. This means that the server takes into account the actual shape and size of the garbage to ensure that the scheduling path can cover the entire garbage area. When determining the scheduling path, the server also considers the real-time moving direction of the trash can. This is because the trash can may have moved in one direction. If the new scheduling path differs too much from the current moving direction, it may cause unnecessary turns and waste time. Based on the real-time moving direction, the server determines a scheduling path from the current area to the outline of the area to be cleaned. This path takes into account the current position, real-time moving direction, volume size and garbage outline of the area to be cleaned of the trash can to ensure that the scheduling path is both efficient and accurate. Among them, the area to be cleaned is preferably a rectangular area.

[0045] For example, assume that in an intelligent cleaning system, the server manages multiple autonomously movable outdoor trash cans and performs cleaning tasks in a park. There is a can that has just been discarded on the motorway of the park. The user specifies the location of the can as the location to be cleaned through the system interface. The trash can is currently located in a corner of the park. The server uses this location as the center of the circle and determines a circular area with a radius of 2 meters as the current area based on the volume of the trash can (assuming it is a medium-sized trash can). The server determines the location of the can specified by the user, and considering the outline of the can (that is, its actual shape and size), demarcates an area to be cleaned that includes the can and a small area around it. At this time, the trash can is moving towards the center of the area to be cleaned. The server obtains the real-time moving direction of the trash can and uses it as a reference factor for determining the scheduling path. Based on the real-time moving direction, the server determines a scheduling path from the current area (the current location of the trash can and its surrounding area) to the area to be cleaned (the can and its surrounding area). This path takes into account the current position of the trash can, its real-time moving direction, its size, and the outline of the can, ensuring that the trash can can be efficiently and accurately moved to the location of the can and cleaned.

[0046] S140: Obtain influencing factors of the first scheduling path, where the influencing factors include road conditions and passenger flow.

[0047] Specifically, road conditions refer to the road conditions on the dispatching path, such as the flatness of the road surface, whether there are obstacles, whether there are potholes or water accumulation, etc. These factors will directly affect the moving speed and cleaning efficiency of the trash can. The server will obtain real-time or historical road condition data, such as through sensor networks, video surveillance or third-party data sources. When planning the dispatching path, the server will avoid choosing paths with poor road conditions to reduce the difficulties and risks that the trash can may encounter during the movement. The flow of people refers to the density and flow of people on the dispatching path. Areas with high flow of people may cause inconvenience to the movement and cleaning of the trash can, such as the need to avoid pedestrians and wait for pedestrians to pass. The server will obtain real-time or predicted flow of people data, such as through camera monitoring, mobile positioning data or historical statistical data. When planning the dispatching path, the server will try to avoid cleaning during peak flow hours or high flow density areas to reduce interference with pedestrians and ensure safety.

[0048] In a possible implementation, obtaining the influencing factor of the first scheduling path specifically includes: obtaining original image data sent by a target monitoring device, where the target monitoring device is located on the first scheduling path; preprocessing the original image data to obtain classified image data, wherein the preprocessing includes denoising, filtering, feature extraction, and normalization; and obtaining the influencing factor based on the classified image data.

[0049] Specifically, the server obtains raw image data from target monitoring devices located on the first dispatch path. These monitoring devices may be cameras or other visual sensors that can capture image information on the dispatch path in real time. A series of preprocessing operations are performed on the acquired raw image data to improve image quality and extract key features. These preprocessing steps generally include: eliminating noise in the image, such as random pixels, stripes, etc., to improve image clarity; using filters to smooth the image or emphasize certain features in the image, such as edge detection filters; extracting key features related to road conditions and pedestrian flow from the image, such as road surface flatness, obstacle locations, number of pedestrians, etc.; converting image data or feature values ​​to the same scale or range for subsequent analysis and comparison. Based on the preprocessed classified image data, the server can analyze various influencing factors related to the first dispatch path. For example, by analyzing the texture and color of the road image, it can be determined whether the road condition is good; by analyzing the number and density of pedestrians or vehicles in the image, the size of the pedestrian flow can be estimated.

[0050] For example, suppose an intelligent cleaning system is planning a first dispatching path from point A to point B, and a camera is installed on the path as a target monitoring device. The camera captures images on the dispatching path in real time and sends these raw image data to the server. These images may contain roads, pedestrians, vehicles, and other elements that may affect the cleaning process. The server preprocesses the received raw images. First, through denoising, the noise caused by factors such as weather and light in the image is eliminated; then, the image is smoothed and the edge features are enhanced using a filter; then, through the feature extraction algorithm, key elements such as the road surface, obstacles, and pedestrians are identified from the image; finally, the extracted features are normalized for subsequent analysis. The server analyzes the influencing factors related to the first dispatching path based on the preprocessed classified image data. For example, by analyzing the color and texture changes of the road surface image, it is judged that there may be some uneven areas on the road surface; by analyzing the number and distribution of pedestrians and vehicles, it is estimated that the flow of people on the current path is large. Based on this information, the server can determine whether this dispatching path is suitable for the current cleaning operation, or whether the dispatching path needs to be adjusted to avoid unfavorable factors.

[0051] In one possible implementation, an influencing factor is obtained based on the classified image data, specifically including: performing corner detection on the classified image data to obtain shape feature data; performing contour extraction on the shape feature data to obtain edge contour data; performing feature encoding on the edge contour data to obtain concrete feature data, the concrete feature data includes potholes, obstacles and biological entities; obtaining road conditions based on potholes and obstacles; and calculating pedestrian flow based on biological entities.

[0052] Specifically, corner detection is a commonly used technique in computer vision, which is used to detect corners in an image (usually points with the largest local intensity changes). These corners are very important for describing the shape and structure of objects in the image. Here, by performing corner detection on the classified image data, feature data describing the shape of the object in the image can be obtained. These data can reflect information such as the flatness of the road surface and the presence of obstacles. Contour extraction is the process of identifying and extracting the boundaries of objects in an image. These boundaries or contours provide important information about the shape, size and position of the object. After obtaining the shape feature data, further contour extraction can obtain more accurate edge contour data. These data are very useful for identifying potholes, obstacles, etc. Feature encoding is the process of converting the extracted feature data into a format or representation that can be understood by a computer. Here, feature encoding is performed on the edge contour data to obtain concrete feature data. These concrete feature data include potholes, obstacles, and biological entities (such as pedestrians, vehicles, etc.). These data directly reflect the actual condition of the road and information about the flow of people. According to the information about potholes and obstacles in the concrete feature data, the condition of the road can be evaluated. For example, the number and size of potholes on the road can reflect the smoothness of the road surface; the location and type of obstacles can affect the choice of dispatching paths. Based on the biological entity information in the concrete feature data, the size of the flow of people can be estimated. For example, by analyzing the number and density of pedestrians or vehicles in the image, the size of the flow of people can be determined. This is very useful for planning dispatching paths that avoid peak hours.

[0053] S150: Input the influencing factors into a preset control model to obtain a second scheduling path.

[0054] Specifically, the server passes the previously acquired and processed influencing factors (such as road conditions, pedestrian flow, etc.) as input data to a preset control model. This control model is designed in advance and configured in the server. It can calculate a new and optimized scheduling path based on the input influencing factors, namely the second scheduling path. The preset control model is a complex neural network model, which contains various rules and logics for making decisions or predictions based on the input data. In an embodiment of the present application, the role of the preset control model is to re-plan or adjust the scheduling path according to actual environmental factors such as road conditions and pedestrian flow to ensure the efficiency, safety and smoothness of the cleaning process.

[0055] S160: Send a control instruction to the trash can to control the trash can to go to the location to be cleaned for cleaning according to the second scheduling path.

[0056] Specifically, after the server calculates the second dispatch path, it will generate corresponding control instructions based on the specific information of this path (such as the starting point, end point, waypoints, speed, etc.). These control instructions are usually a series of digital signals or codes that can be recognized and parsed by the control system of the trash can. The server sends these control instructions to the trash can through the communication network to ensure that the trash can can accurately receive and execute these instructions.

[0057] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a control method for an autonomous movable outdoor trash can provided in an embodiment of the present application. Input the influencing factor into the preset control model to obtain a second scheduling path, specifically including steps S210 to S220: S210, based on the corresponding relationship between the influencing factor and the smooth probability, obtain the smooth probability corresponding to the first scheduling path, the preset control model pre-stores the corresponding relationship, and the smooth probability is calculated based on the historical smooth probability corresponding to the historical scheduling path; S220, if it is determined that the smooth probability is less than the preset probability threshold, then correct the first scheduling path to obtain a second scheduling path, and the smooth probability of the second scheduling path is greater than the smooth probability corresponding to the first scheduling path.

[0058] Specifically, the smooth probability is an indicator to measure whether the dispatching path is unobstructed. This probability is calculated based on influencing factors (such as road conditions and passenger flow). The corresponding relationship between the influencing factors and the smooth probability is pre-stored in the preset control model. This corresponding relationship may be obtained through historical data analysis, for example, what is the smooth probability of the dispatching path under certain specific road conditions and passenger flow. According to the currently acquired influencing factors, using this corresponding relationship, the smooth probability of the first dispatching path can be calculated. This smooth probability is calculated based on the historical smooth probability corresponding to the historical dispatching path, that is, it takes into account the smoothness of the path under similar environmental conditions. Next, the server will determine whether the smooth probability of the first dispatching path is less than a preset probability threshold. This threshold is a standard used to determine whether the current path is smooth enough and whether it needs to be corrected. If the smooth probability is less than the preset probability threshold, it means that the first dispatching path may not be smooth enough and will be greatly affected by road conditions or passenger flow. At this time, the server will correct the first dispatching path. The purpose of path correction is to find a smoother dispatching path, that is, the second dispatching path. The smooth probability of this new path should be greater than the original first dispatching path.

[0059] For example, suppose that outdoor cleaning work needs to be carried out in a large industrial park. There are multiple areas in the park, such as main roads, warehouse areas, office areas, etc. The flow of people and vehicles in these areas will be different at different times of the day. At the same time, weather conditions (such as rain, snow, strong winds, etc.) will also affect the cleaning work. Multiple monitoring devices are installed in the park to capture real-time images. After processing these images, multiple factors that affect the cleaning work can be obtained, such as the flow of people, the flow of vehicles, road conditions (such as water accumulation, fallen leaves, etc.), weather conditions, etc. When the preset probability threshold set by the server is 70%, since the smooth probability of the first dispatching path (60%) is less than this threshold, the server determines that this path may not be smooth enough. Therefore, the server begins to correct the first dispatching path. It may choose to avoid the main road that is under maintenance and has a large flow of people, and choose another relatively smooth path. After correction, the server obtains the second dispatching path, and its smooth probability increases to 80%, which is significantly higher than the smooth probability of the first dispatching path.

[0060] In a possible implementation, before the influencing factors are input into the preset control model to obtain the second dispatch path, the preset control model is trained, specifically including: first, a large amount of historical dispatch path data is collected, including detailed information of each path (such as path length, coverage area, etc.), road conditions (such as road surface flatness, obstacles, etc.), influencing factors such as pedestrian flow, and the smooth probability or actual cleaning effect of each path. The collected data is cleaned and preprocessed, including removing outliers, filling missing values, standardizing or normalizing features, etc., to ensure the quality and consistency of the data. The preprocessed data set is divided into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the performance of the model. According to the characteristics of the problem and the situation of the data, a suitable machine learning algorithm or deep learning model is selected as the preset control model. For example, a model based on a neural network can be selected because the neural network performs well in processing complex nonlinear relationships. According to the type of influencing factor, features related to the probability of smooth dispatch path are extracted and constructed. These features may include quantitative indicators of road conditions (such as road roughness, obstacle density, etc.), statistical data of pedestrian flow (such as peak hour pedestrian flow, average pedestrian flow, etc.), etc. Use the training set to train the selected model.

[0061] During the training process, the model learns how to map the influencing factors to the unblocked probability of the dispatch path. The model parameters can be iteratively updated using optimization algorithms such as gradient descent to minimize the loss function (such as mean square error, cross entropy, etc.) to improve the prediction accuracy of the model. The trained model is evaluated using the validation set to calculate the performance indicators of the model (such as accuracy, recall, F1 value, etc.). Based on the evaluation results, the model parameters are adjusted, including adjusting hyperparameters such as learning rate, batch size, number of iterations, and selecting or adjusting the loss function, etc., to further improve the performance of the model. When the model training is completed, the trained model is saved for subsequent use. The model is deployed to the actual application, receiving the influencing factor data in real time and outputting the adjusted dispatch path. In the actual application, new data is continuously collected and used to update and optimize the model. This can be achieved by regularly retraining the model and using online learning algorithms. Monitor the performance of the model and adjust the model parameters or structure as needed to adapt to changes in the environment and new requirements.

[0062] In a possible implementation, the cleaning instruction also includes a target scheduling path, and the method also includes: sending a target control instruction to the trash can to control the trash can to go to the location to be cleaned for cleaning according to the target scheduling path, the target scheduling path passes through multiple locations to be cleaned, and the target scheduling path is determined by user planning.

[0063] Specifically, in some cases, users may want to plan the dispatch path according to their own needs or preferences, rather than relying entirely on the system's automatic planning. In this case, users can manually plan the target dispatch path through the system's user interface (such as mobile applications, web pages, etc.). The target dispatch path usually includes a starting point, multiple locations to be cleaned (which may be specific areas, landmarks, or buildings, etc.), and the direction and order of the path. Users can select or add locations to be cleaned according to actual conditions, and adjust the direction of the path to form a dispatch path that meets their needs. When the user completes the planning of the target dispatch path, the system will generate corresponding target control instructions based on the user's planning results. These instructions contain detailed information about the target dispatch path, such as the starting point, the location to be cleaned, the direction of the path, etc. The server will send the target control instructions to the specified trash can to ensure that the trash can can accurately clean according to the target dispatch path planned by the user. After receiving the target control instruction, the trash can will parse the instruction and extract the information of the target dispatch path. Then, it will adjust its own navigation system and motion control system based on this information to ensure that it can go to each location to be cleaned according to the target dispatch path for cleaning. During the execution process, the trash can may encounter various obstacles or changes in road conditions, but it will rely on its own perception system and obstacle avoidance algorithm to cope with these challenges and ensure that the task can be completed safely and efficiently.

[0064] The present application also provides a control device for an autonomously movable outdoor trash can, referring to Figure 3 , Figure 3 A module schematic diagram of a control device for an autonomously movable outdoor trash can provided in an embodiment of the present application, wherein the control device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 responds to a cleaning instruction input by a user, and the cleaning instruction includes a position to be cleaned; the acquisition module 31 acquires the current position of the trash can; the processing module 32 determines a first scheduling path according to the current position and the position to be cleaned; the acquisition module 31 acquires influencing factors of the first scheduling path, and the influencing factors include road conditions and pedestrian flow; the processing module 32 inputs the influencing factors into a preset control model to obtain a second scheduling path; the processing module 32 sends a control instruction to the trash can to control the trash can to go to the position to be cleaned for cleaning along the second scheduling path.

[0065] In a possible embodiment, before responding to the cleaning instruction input by the user, the processing module 32 further includes: the acquisition module 31 receives the image data sent by the sensor device; the processing module 32 determines the basic feature map corresponding to the image data based on the image data; the processing module 32 performs multi-scale feature extraction on the basic feature map based on the multi-scale channel attention mechanism to obtain the multi-scale feature map; the processing module 32 obtains the salient area of ​​the image data based on the multi-scale feature map; the processing module 32 calculates the similarity value between the salient area and the preset area to be cleaned, and the preset area to be cleaned is determined by the image to be cleaned; if the processing module 32 determines that the similarity value is greater than or equal to the preset similarity threshold, it displays a prompt message, and the prompt message is used to prompt the user that the position corresponding to the image data needs to be cleaned.

[0066] In a possible implementation, a first scheduling path is determined based on the current position and the position to be cleaned, specifically including: the processing module 32 calculates the current area based on the current position, wherein a circular area is drawn with the coordinate point corresponding to the current position as the center and a radius of a preset length to obtain the current area, and the preset length is determined according to the volume of the trash can; the processing module 32 calculates the area to be cleaned based on the position to be cleaned, wherein the area to be cleaned includes the garbage contour corresponding to the position to be cleaned; the acquisition module 31 acquires the real-time moving direction of the trash can; the processing module 32 determines the scheduling path between the current area and the contour corresponding to the area to be cleaned based on the real-time moving direction, and obtains the first scheduling path.

[0067] In a possible implementation, obtaining the influencing factor of the first scheduling path specifically includes: an acquisition module 31 obtains original image data sent by a target monitoring device, where the target monitoring device is located on the first scheduling path; a processing module 32 preprocesses the original image data to obtain classified image data, wherein the preprocessing includes denoising, filtering, feature extraction, and normalization; and the processing module 32 obtains the influencing factor based on the classified image data.

[0068] In a possible implementation, the processing module 32 obtains the influencing factors based on the classified image data, specifically including: the processing module 32 performs corner detection on the classified image data to obtain shape feature data; the processing module 32 performs contour extraction on the shape feature data to obtain edge contour data; the processing module 32 performs feature encoding on the edge contour data to obtain concrete feature data, and the concrete feature data includes potholes, obstacles and biological entities; the processing module 32 obtains the road condition based on the potholes and obstacles; the processing module 32 calculates the pedestrian flow based on the biological entities.

[0069] In a possible implementation, the processing module 32 inputs the influencing factor into the preset control model to obtain a second scheduling path, specifically including: the processing module 32 obtains the smooth probability corresponding to the first scheduling path based on the correspondence between the influencing factor and the smooth probability, the preset control model pre-stores the corresponding relationship, and the smooth probability is calculated based on the historical smooth probability corresponding to the historical scheduling path; if the processing module 32 determines that the smooth probability is less than the preset probability threshold, the first scheduling path is corrected to obtain a second scheduling path, and the smooth probability of the second scheduling path is greater than the smooth probability corresponding to the first scheduling path.

[0070] In a possible implementation, the cleaning instruction also includes a target scheduling path. The processing module 32 sends a target control instruction to the trash can to control the trash can to go to the location to be cleaned according to the target scheduling path for cleaning. The target scheduling path passes through multiple locations to be cleaned, and the target scheduling path is determined by user planning.

[0071] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0072] The present application also provides an electronic device, referring to Figure 4 , Figure 4The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0073] The communication bus 42 is used to realize the connection and communication between these components.

[0074] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0075] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0076] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0077] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a method for controlling an autonomous movable outdoor trash can.

[0078] exist Figure 4 In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program stored in the memory 45 for a control method for an autonomously movable outdoor trash can. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0080] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0081] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0086] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A control method for an autonomously movable outdoor trash can, characterized in that: The method comprises: responding to a cleaning instruction input by a user, the cleaning instruction including a location to be cleaned; Get the current position of the trash can; Determining a first scheduling path according to the current position and the position to be cleaned; Acquire influencing factors of the first scheduling path, where the influencing factors include road conditions and passenger flow; Inputting the influencing factors into a preset control model to obtain a second scheduling path; A control instruction is sent to the trash can to control the trash can to go to the location to be cleaned for cleaning according to the second scheduling path.

2. The control method of the autonomous movable outdoor trash can according to claim 1, characterized in that: Before responding to the cleaning instruction input by the user, the method further includes: receiving image data sent by the sensor device; Determine, according to the image data, a basic feature map corresponding to the image data; Based on the multi-scale channel attention mechanism, multi-scale feature extraction is performed on the basic feature map to obtain a multi-scale feature map; Obtaining a salient region of the image data according to the multi-scale feature map; Calculating a similarity value between the salient area and a preset area to be cleaned, wherein the preset area to be cleaned is determined by an image to be cleaned; If it is determined that the similarity value is greater than or equal to a preset similarity threshold, a prompt message is displayed, where the prompt message is used to prompt the user to clean the position corresponding to the image data.

3. The control method of the autonomous movable outdoor trash can according to claim 1, characterized in that: The determining of a first scheduling path according to the current position and the position to be cleaned specifically includes: The current area is calculated based on the current position, wherein a circular area is drawn with the coordinate point corresponding to the current position as the center and a radius of a preset length to obtain the current area, and the preset length is determined according to the volume of the trash can; According to the position to be cleaned, an area to be cleaned is calculated, wherein the area to be cleaned includes a garbage contour corresponding to the position to be cleaned; Obtaining the real-time moving direction of the trash can; According to the real-time moving direction, a scheduling path between the current area and the contour corresponding to the area to be cleaned is determined to obtain the first scheduling path.

4. The control method of the autonomous movable outdoor trash can according to claim 1, characterized in that: The obtaining the influencing factor of the first scheduling path specifically includes: Acquire original image data sent by a target monitoring device, where the target monitoring device is located on the first scheduling path; Preprocessing the original image data to obtain classified image data, wherein the preprocessing includes denoising, filtering, feature extraction and normalization; The impact factor is obtained according to the classified image data.

5. The control method of the autonomous movable outdoor trash can according to claim 4, characterized in that: The obtaining the influencing factor according to the classified image data specifically includes: Performing corner point detection on the classified image data to obtain shape feature data; Perform contour extraction on the shape feature data to obtain edge contour data; Performing feature encoding on the edge contour data to obtain concrete feature data, wherein the concrete feature data includes road potholes, obstacles, and biological entities; Based on the road potholes and the obstacles, obtaining the road condition; The human flow is calculated based on the biological entity.

6. The control method of the autonomous movable outdoor trash can according to claim 1, characterized in that: The step of inputting the influencing factors into a preset control model to obtain a second scheduling path specifically includes: Based on the corresponding relationship between the influencing factor and the smooth probability, the smooth probability corresponding to the first scheduling path is obtained, the corresponding relationship is pre-stored in the preset control model, and the smooth probability is calculated based on the historical smooth probability corresponding to the historical scheduling path; If it is determined that the smooth traffic probability is less than the preset probability threshold, the first scheduling path is corrected to obtain the second scheduling path, and the smooth traffic probability of the second scheduling path is greater than the smooth traffic probability corresponding to the first scheduling path.

7. The control method of the autonomous movable outdoor trash can according to claim 1, characterized in that: The cleaning instruction also includes a target scheduling path, and the method further includes: A target control instruction is sent to the trash can to control the trash can to go to the to-be-cleaned location for cleaning according to the target scheduling path, wherein the target scheduling path passes through a plurality of the to-be-cleaned locations, and the target scheduling path is determined by the user planning.

8. A control device for an autonomously movable outdoor trash can, characterized in that: The control device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to respond to a cleaning instruction input by a user, wherein the cleaning instruction includes a position to be cleaned; The acquisition module (31) is also used to acquire the current position of the trash can; The processing module (32) is used to determine a first scheduling path according to the current position and the position to be cleaned; The acquisition module (31) is further used to acquire the influencing factors of the first scheduling path, wherein the influencing factors include road conditions and passenger flow; The processing module (32) is further used to input the influencing factor into a preset control model to obtain a second scheduling path; The processing module (32) is further used to send a control instruction to the trash can to control the trash can to move to the location to be cleaned for cleaning according to the second scheduling path.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the 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 instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images