Methods, devices and equipment for automatic waste sorting by robots

Abstract

This application provides a method, apparatus, and equipment for automatic garbage sorting by a robot, relating to the field of robotics. The method includes: determining the robot's initial travel route by combining the robot's position, the position of each piece of garbage, and the location where each piece of garbage is disposed of; acquiring the robot's remaining garbage storage space and the characteristics of each piece of garbage; adjusting the initial travel route based on the robot's remaining garbage storage space and the characteristics of each piece of garbage to generate the robot's target travel route; acquiring dynamic obstacle information within the target area; and adjusting the target travel route based on the dynamic obstacle information to generate the robot's final travel route, so that the robot processes each piece of garbage within the target area according to the final travel route. The technical effect of this application is: automatically collecting garbage scattered in various locations, achieving comprehensive garbage classification and collection.

Description

Technical Field

[0001] This application relates to the field of robotics technology, specifically to a method, apparatus, and equipment for an automatic sorting robot for household waste. Background Technology

[0002] With the accelerating pace of urbanization, the amount of urban household waste is constantly increasing. Traditional manual waste collection and sorting methods are inefficient and prone to errors, and can no longer meet the needs of modern urban household waste management.

[0003] Currently, some intelligent waste management equipment has emerged on the market, such as waste sorting and recycling machines and waste sorting bins. These devices have improved the efficiency and accuracy of household waste sorting to some extent. However, most of these devices are stationary and cannot actively search for and collect waste scattered in various locations, thus failing to achieve comprehensive waste sorting and collection.

[0004] Therefore, there is an urgent need for an intelligent and autonomous method for collecting and sorting household waste to solve the above problems. Summary of the Invention

[0005] This application provides a method, apparatus, and equipment for automatically sorting household waste using a robot, which is used to automatically collect waste scattered in various locations, thereby achieving comprehensive waste sorting and collection.

[0006] In a first aspect, this application provides a method for an automatic garbage sorting robot, the method comprising: acquiring the position of a robot within a target area, the positions of multiple types of garbage within the target area, and the disposal location of each type of garbage; formulating an initial driving route for the robot based on the robot's position, the positions of each type of garbage, and the disposal location of each type of garbage; acquiring the robot's remaining garbage storage space and the garbage characteristics of each type of garbage; adjusting the initial driving route according to the robot's remaining garbage storage space and the garbage characteristics of each type of garbage to generate a target driving route for the robot; acquiring dynamic obstacle information within the target area, adjusting the target driving route according to the dynamic obstacle information to generate a final driving route for the robot, so that the robot processes each type of garbage within the target area according to the final driving route.

[0007] By adopting the above technical solution and comprehensively considering robot location, waste location, disposal location, remaining storage space, waste characteristics, and dynamic obstacle information, highly efficient and intelligent automatic waste sorting by a waste management robot is achieved. First, by acquiring the location information of the robot and waste within the target area, as well as the waste disposal location, an initial travel route is formulated, providing the robot with a basic working path. Then, considering the robot's remaining waste storage space and the characteristics of each type of waste, the initial route is adjusted to generate a more reasonable target travel route, avoiding frequent back-and-forth trips due to insufficient storage space during operation, thus improving waste collection efficiency. Finally, by acquiring dynamic obstacle information and adjusting the route accordingly, a final travel route is generated, enabling the robot to flexibly cope with complex and changing urban environments, effectively avoiding collision risks and ensuring operational safety. This multi-level, dynamically optimized route planning method not only improves the efficiency and accuracy of waste collection but also enhances the robot's adaptability and operational stability in real-world environments, thereby achieving automatic collection of waste scattered throughout the target area and realizing comprehensive waste classification and collection.

[0008] Optionally, the step of determining the robot's initial travel route by combining the robot's position, the position of each piece of trash, and the placement location of each piece of trash includes: calculating the distance from the robot to each piece of trash and the distance between each piece of trash based on the robot's position and the position of each piece of trash; determining the order in which the robot processes each piece of trash in sequence based on the distance from the robot to each piece of trash and the distance between each piece of trash, thus obtaining the robot's initial processing sequence; and planning the path for the robot to move between each piece of trash based on the initial processing sequence and the placement location of each piece of trash, thus generating the robot's initial travel route.

[0009] By employing the aforementioned technical solution, the distances from the robot to each piece of trash and the distances between the trash pieces are calculated, providing fundamental data support for route planning. Subsequently, based on this distance information, the order in which the robot processes each piece of trash is determined, forming an initial processing sequence. This helps optimize trash collection efficiency and reduce unnecessary back-and-forth trips. Finally, combining the initial processing sequence and the placement location of each piece of trash, the specific path the robot takes as it moves between the trash pieces is planned, generating the final initial travel route. This method not only considers optimizing the order of trash collection but also incorporates trash placement into route planning, thus achieving a complete workflow that balances collection and placement. Through this comprehensive route planning method, the robot can complete trash collection and placement tasks along the optimal path, significantly improving work efficiency, reducing unnecessary energy consumption, and enhancing the coherence and coordination of the entire waste management process. This initial travel route planning lays a solid foundation for subsequent route optimization, contributing to more intelligent and efficient urban waste management.

[0010] Optionally, the waste characteristics include waste type and waste volume. The step of adjusting the initial travel route based on the robot's remaining waste storage space and the waste characteristics of each type of waste to generate the robot's target travel route includes: determining, based on the waste type of each type of waste, a target waste that needs to be prioritized for processing; adjusting the initial travel route based on the location and placement location of the target waste to generate the robot's first travel route; determining, based on the robot's remaining waste storage space and the waste volume of each type of waste, whether the robot's remaining waste storage space meets the processing requirements when processing each type of waste according to the first travel route; if the robot's remaining waste storage space meets the processing requirements, then the first travel route is used as the robot's target travel route; if the robot's remaining waste storage space does not meet the processing requirements, then the first travel route is adjusted to generate the robot's target travel route.

[0011] By adopting the above technical solution, the system prioritizes the processing of waste based on its type, enabling the robot to handle important or urgent waste first, thus improving the timeliness and importance management of waste disposal. Secondly, the initial travel route is adjusted based on the location and placement of the target waste to generate a first travel route, ensuring efficient processing of priority waste. Next, by determining whether the robot's remaining waste storage space meets the processing requirements, the system can pre-assess the feasibility of the route, preventing the robot from interrupting its work due to insufficient storage space. Finally, based on the assessment results, the first travel route is adopted as the target travel route, or a new target travel route is generated through further adjustments. This dynamic adjustment mechanism ensures that the robot always operates on the optimal route, meeting both waste priority requirements and fully utilizing the robot's storage space, thereby improving overall work efficiency.

[0012] Optionally, if the remaining waste storage space of the robot does not meet the processing requirements, adjusting the first driving route to generate a target driving route for the robot includes: obtaining the amount of waste that the robot can process; selecting a corresponding amount of waste as waste to be processed from the first driving route based on the amount of waste that the robot can process; adjusting the first driving route based on the location of the waste to be processed and the placement location of the waste to be processed to generate a second driving route for the robot; and using the second driving route as the target driving route for the robot.

[0013] By adopting the above technical solution, the system can accurately assess the robot's actual processing capacity by obtaining the amount of waste it can handle, and thus select an appropriate amount of waste as the waste to be processed in the first travel route. This capacity-based selection method ensures that the robot can make full use of its storage space in each operation, avoiding situations of insufficient storage space or excessive idleness. Secondly, the first travel route is adjusted according to the location and disposal location of the waste to be processed, generating a second travel route. This adjustment takes into account the spatial distribution characteristics of the waste, enabling the robot to complete the collection and disposal of a limited amount of waste along an optimized path. Finally, the second travel route is determined as the robot's target travel route, ensuring that the entire processing process satisfies the robot's storage capacity limitations while guaranteeing the rationality and efficiency of the route. This dynamic adjustment mechanism not only improves the robot's working efficiency but also enhances the system's adaptability and reliability. Through this method, the robot can maximize its processing capacity within a limited storage space, while avoiding the problem of frequent back-and-forth trips due to insufficient storage space, significantly improving the overall waste processing efficiency.

[0014] Optionally, the dynamic obstacle information includes position, speed, and direction of movement. Acquiring the dynamic obstacle information within the target area and adjusting the target driving route based on the dynamic obstacle information to generate the robot's final driving route includes: predicting the position and time of the robot's encounter with the dynamic obstacle during its journey along the target driving route, based on the obstacle's position, speed, and direction of movement; and adjusting the target driving route based on the position and time to obtain the robot's final driving route.

[0015] By employing the aforementioned technical solution, and utilizing detailed information about dynamic obstacles, including their location, speed, and direction of movement, the system accurately predicts the possible encounter locations and times between the robot and these obstacles. This prediction mechanism enables the system to identify potential collision risks in advance, providing crucial information for route adjustments. Secondly, based on the predicted encounter locations and times, the system makes targeted adjustments to the target route, generating the final route. This route optimization based on dynamic information not only improves the robot's safety in complex environments but also ensures the continuity and efficiency of the waste collection process. By adapting to environmental changes in real time, the robot can flexibly avoid moving obstacles, reducing unnecessary stops and detours, thereby maintaining high work efficiency. This dynamic path planning method significantly enhances the robot's adaptability and operational stability in urban environments, effectively solving the problem of fixed routes being easily affected by environmental changes. Simultaneously, it provides the robot with greater operational space, enabling it to maximize the completion of waste collection tasks while ensuring safety.

[0016] Optionally, predicting the location and time of the robot's encounter with the dynamic obstacle during its journey along the target route, based on the obstacle's location, speed, and direction of movement, includes: acquiring the robot's speed; calculating the estimated time for the robot to reach each target point on the target route based on the robot's speed and the target route; calculating the location of the dynamic obstacle at different time points based on the obstacle's location, speed, and direction of movement; determining whether the robot's location coincides with or is less than a preset safety distance at any given time point, based on the estimated time for the robot to reach each target point on the target route and the dynamic obstacle's location at different time points; and if the robot's location coincides with or is less than the preset safety distance at a first time point, then determining that location and the first time point as the location and time of the robot's encounter with the dynamic obstacle.

[0017] By employing the aforementioned technical solution, and by acquiring the robot's moving speed and combining it with the target travel route, the system can accurately calculate the estimated time for the robot to reach each target point on the route, laying a temporal foundation for subsequent collision risk assessment. Simultaneously, based on the position, speed, and direction of movement of dynamic obstacles, the system can predict the obstacle's position at different times, providing necessary information for spatial risk assessment. By comparing the positions of the robot and dynamic obstacles at various times, the system can determine whether there is overlap or a distance less than a preset safety distance, thereby accurately identifying potential collision risk points. When a collision risk is detected between the robot and a dynamic obstacle at a specific time, the system can determine the corresponding position and time as encounter parameters. This multi-dimensional, high-precision prediction method not only improves the accuracy of collision risk assessment but also provides specific spatiotemporal references for subsequent route adjustments. Through this method, the robot can identify and avoid potential hazards in advance, significantly improving safety and work efficiency in complex dynamic environments. Furthermore, by considering a preset safety distance, the system can also provide sufficient buffer space for the robot's movement, further enhancing the safety and stability of the entire waste collection process.

[0018] Optionally, after generating the robot's final travel route, the method further includes: monitoring the robot's operating status, the waste distribution change information within the target area, and the robot's current position; optimizing the final travel route based on the robot's current position, the robot's operating status, and the waste distribution change information, and generating the robot's dynamic travel route.

[0019] By adopting the above technical solutions and monitoring the robot's operational status, the system can promptly grasp the robot's working capabilities and efficiency, providing crucial reference for route optimization. Simultaneously, real-time monitoring of changes in waste distribution within the target area enables the system to quickly respond to environmental changes and adjust collection strategies accordingly. Furthermore, by continuously tracking the robot's current location, the system can evaluate route execution in real time, providing precise spatial information for dynamic adjustments. Based on this real-time data, the system can continuously optimize the final travel route, generating a dynamic route that better reflects the current situation. This dynamic optimization mechanism allows the robot to flexibly respond to various unforeseen circumstances, such as new waste, environmental changes, or changes in its own state, thereby maintaining high efficiency. Through continuous route optimization, the robot can consistently complete waste collection tasks along the optimal path, significantly improving overall work efficiency and resource utilization.

[0020] Secondly, this application provides an automatic garbage sorting device for household waste robots. The device includes: a first acquisition module, a combination module, a second acquisition module, a first adjustment module, and a second adjustment module. The first acquisition module is used to acquire the position of the robot within a target area, the positions of multiple types of garbage within the target area, and the disposal positions of each type of garbage. The combination module is used to combine the robot's position, the positions of each type of garbage, and the disposal positions of each type of garbage to formulate an initial travel route for the robot. The second acquisition module is used to acquire the robot's remaining garbage storage space and the garbage characteristics of each type of garbage. The first adjustment module is used to adjust the initial travel route based on the robot's remaining garbage storage space and the garbage characteristics of each type of garbage to generate a target travel route for the robot. The second adjustment module is used to acquire dynamic obstacle information within the target area and adjust the target travel route based on the dynamic obstacle information to generate a final travel route for the robot, so that the robot processes each type of garbage within the target area according to the final travel route.

[0021] Thirdly, this application provides an electronic device that adopts the following technical solution: it 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 used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-described methods for automatically sorting garbage by a household waste robot.

[0022] Fourthly, this application provides a computer-readable storage medium that employs the following technical solution: storing a computer program capable of being loaded by a processor and executing any of the above-mentioned methods for automatically sorting garbage by a household waste robot.

[0023] In summary, this application includes at least one of the following beneficial technical effects:

[0024] By comprehensively considering robot location, waste location, disposal location, remaining storage space, waste characteristics, and dynamic obstacle information, a highly efficient and intelligent automated waste sorting system for household waste has been achieved. First, by acquiring the location information of the robot and waste within the target area, as well as the waste disposal location, an initial travel route is formulated, providing the robot with a basic working path. Then, considering the robot's remaining waste storage space and the characteristics of each type of waste, the initial route is adjusted to generate a more reasonable target travel route, avoiding frequent back-and-forth trips due to insufficient storage space during operation, thus improving waste collection efficiency. Finally, by acquiring dynamic obstacle information and adjusting the route accordingly, a final travel route is generated, enabling the robot to flexibly cope with complex and changing urban environments, effectively avoiding collision risks and ensuring operational safety. This multi-level, dynamically optimized route planning method not only improves the efficiency and accuracy of waste collection but also enhances the robot's adaptability and operational stability in real-world environments, thereby achieving the automated collection of waste scattered throughout the target area, realizing comprehensive waste sorting and collection. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a method for automatically sorting household waste using a robot, as provided in an embodiment of this application.

[0026] Figure 2 This is a schematic diagram of the structure of an automatic garbage sorting device for household waste provided in an embodiment of this application;

[0027] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] Explanation of reference numerals in the attached figures: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. Detailed Implementation

[0029] To enable those skilled in the art 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 with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

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

[0031] Figure 1 This is a flowchart illustrating a method for automatically sorting household waste using a robot, as provided in an embodiment of this application. Figure 1 As shown, the method includes S101-S105:

[0032] S101, obtain the location of the robot within the target area, the location of multiple pieces of garbage within the target area, and the disposal location of each piece of garbage.

[0033] In this embodiment, the target area can be a variety of different environments, depending on the application scenario of the waste sorting robot. The target area typically refers to a specific area where waste sorting is required, and may include, but is not limited to, the following: Indoor environments: such as the interior spaces of public buildings like office buildings, shopping malls, schools, and hospitals; Outdoor environments: such as open public areas like parks, squares, and pedestrian streets; Community environments: including public areas of residential communities, such as roads and green spaces within the community; Industrial parks: such as public places in factories and warehouses; Transportation hubs: such as train stations, airports, and subway stations, areas with high pedestrian traffic; Tourist attractions: such as scenic spots and theme parks, areas with concentrated tourist populations.

[0034] In one example, the robot's real-time location coordinates are obtained by installing a GPS positioning module on the robot or combining it with indoor positioning technologies (such as UWB, Bluetooth beacons, etc.). For the locations of multiple pieces of trash within the target area, computer vision technology can be used, with cameras installed on the robot, to detect and locate the trash through image recognition algorithms. Simultaneously, deep learning models can be used to classify the trash to determine the disposal location for each piece. The disposal locations for each piece of trash are typically pre-defined fixed points, and this information can be stored in the robot's database.

[0035] In acquiring this information, the robot may need to conduct an initial survey within the target area to comprehensively collect data. To improve efficiency, SLAM (Simultaneous Localization and Mapping) technology can be used, enabling the robot to simultaneously perform localization and build an environmental map during movement. This not only acquires the necessary location information but also generates a detailed environmental map, providing a reference for subsequent path planning.

[0036] The purpose of acquiring this information is to enable the robot to fully understand its working environment and task objectives. Robot location information is used to determine the starting point, waste location information is used to determine the target points that need to be processed, and disposal location information is used to plan the destination of waste disposal. These data collectively constitute the fundamental elements of robot route planning.

[0037] By accurately acquiring this location information, the efficiency and accuracy of robots can be significantly improved. For example, robots can calculate the optimal path based on their own location and the location of each piece of waste, avoiding unnecessary repetitive travel; based on the waste's classification and corresponding disposal location, robots can rationally arrange the processing order, reducing the number of trips; at the same time, accurate location information also helps robots navigate precisely in complex environments, avoid obstacles, and complete waste sorting tasks safely and efficiently.

[0038] S102, combining the robot's position, the position of each piece of trash, and the placement location of each piece of trash, formulates the robot's initial driving route.

[0039] In one example, the process of determining the initial travel route first involves calculating the distance from the robot to each piece of trash and the distance between the trash pieces. This can be achieved through simple coordinate calculations; however, considering practical considerations, it may be necessary to combine map information of the target area to calculate the actual walkable distance.

[0040] Next, based on this distance data, the system needs to determine the order in which the robot processes each piece of trash, forming an initial processing sequence. The simplest method is to select the nearest unprocessed piece of trash to the current location as the next target. While this method may not be optimal, it can quickly generate a feasible processing order and is easy to implement and adjust.

[0041] After determining the initial processing sequence, the system needs to plan the robot's specific path between each piece of trash, taking into account their placement locations. This step requires considering factors such as the terrain features of the target area and potential static obstacles. The system can utilize pre-stored map information to plan a path between each pair of points that avoids known obstacles.

[0042] Based on the above embodiments, as an optional implementation method, in S102, the initial travel route of the robot is formulated by combining the robot's position, the position of each piece of trash, and the placement position of each piece of trash, specifically including S201-S203:

[0043] S201, based on the robot's position and the positions of each piece of trash, calculate the distance from the robot to each piece of trash and the distance between each piece of trash.

[0044] S202, combining the distance from the robot to each piece of trash and the distance between each piece of trash, determine the order in which the robot processes each piece of trash, and obtain the robot's initial processing sequence.

[0045] In one example, the system acquires the robot's current location and the location information of all unprocessed waste within the target area. This information can be obtained through a monitoring system within the area or the robot's own positioning system. Next, the system calculates the straight-line distance from the robot to each waste point, as well as the distances between all waste points. This distance data forms a complete distance matrix, providing the foundation for subsequent path planning.

[0046] With this distance matrix, various algorithms can be applied to determine the optimal processing order. A common approach is to use an improved nearest neighbor algorithm. The basic idea of ​​this algorithm is to select the next garbage point closest to the current position as the target each time. However, a simple nearest neighbor algorithm may lead to suboptimal solutions, so some optimization strategies can be introduced. For example, when selecting the next target, not only the nearest point at the current position should be considered, but also the impact of selecting that point on the overall path length. The system can further optimize the initial sequence through methods such as local search or simulated annealing.

[0047] In practical applications, other factors need to be considered to refine the initial processing sequence. For example, some types of waste may have a higher processing priority, such as perishable or hazardous waste; some areas may have time constraints and need to be cleaned up within a specific time period. The system will integrate these constraints into the sequence generation process to ensure that the generated initial processing sequence takes into account both distance factors and the needs of actual operation.

[0048] The initial processing sequence obtained through this method can typically significantly improve the efficiency of waste collection. For example, in an area containing 50 waste collection points, an optimized processing sequence may reduce the total travel distance by about 30% compared to a random order or a simple order from nearest to farthest. This not only means that the robot can complete the task faster, but also means reduced energy consumption and equipment wear and tear.

[0049] More importantly, this initial processing sequence provides a solid foundation for subsequent real-time adjustments. In practice, the environment may change, new garbage may appear, or some planned garbage points may have already been manually cleaned. With this initial sequence, the system can make more efficient local adjustments without having to recalculate the entire path each time.

[0050] S203, combining the initial processing sequence and the placement location of each piece of waste, plans the path for the robot to move between the pieces of waste and generates the robot's initial driving route.

[0051] In one example, considering that different types of waste have different disposal locations, the robot must also take into account these locations when processing waste according to the initial processing sequence in S202. Different types of waste correspond to different disposal locations. If the disposal location is far away, the initial processing sequence may need to be adjusted to optimize the robot's movement path and improve overall efficiency.

[0052] Suppose that in a community, there are the following types of waste and their corresponding disposal locations: General household waste (G1, G4, G7): disposed of in trash cans near each building in the community; Recyclables (G2, G5, G8): disposed of at the community recycling station; Bulky waste (G3, G6): disposed of at the designated bulky waste temporary storage point in the community; Kitchen waste (G9, G10): disposed of at the dedicated kitchen waste treatment station.

[0053] The initial processing sequence generated in step S202 is:

[0054] G1>G2>G3>G4>G5>G6>G7>G8>G9>G10; In step S203, the system considers the specific placement location of each type of waste and optimizes the robot's movement path accordingly. The optimization process is as follows:

[0055] First, the system identifies the types of waste that can be centrally processed: recyclables (G2, G5, G8) can be centrally disposed of at recycling stations; bulky waste (G3, G6) can be centrally disposed of at bulky waste temporary storage points; and kitchen waste (G9, G10) can be centrally disposed of at kitchen waste treatment stations.

[0056] The system then rearranges the processing order to minimize the number of robot trips: Recyclable waste is processed in a centralized manner: G2 > G5 > G8; bulky waste is processed in a centralized manner: G3 > G6; and kitchen waste is processed in a centralized manner: G9 > G10. Considering that general household waste (G1, G4, G7) is scattered around various buildings, the system attempts to intersperse its processing with other waste processing areas to optimize the overall path.

[0057] Based on the above considerations, the system may generate the following optimized processing sequence:

[0058] G1>G2>G5>G8>G4>G3>G6>G7>G9>G10.

[0059] The corresponding optimized movement path may be as follows: Move from the starting point to the building where G1 is located to process general household waste; move to the recycling station to process recyclables from G2, G5, and G8 in sequence; pass through the building where G4 is located to process general household waste; move to the bulky waste temporary storage point to process G3 and G6; process general household waste from G7 on the return journey; and finally move to the kitchen waste treatment station to process G9 and G10.

[0060] This optimized path takes into account the different disposal locations of various types of waste, significantly reducing the number of round trips and the total travel distance for the robot. For example, what used to require three trips to the recycling station (to process G2, G5, and G8 respectively) can now be completed in a single trip. Similarly, bulky waste and kitchen waste are now processed in a single centralized process.

[0061] This optimization reduces the total travel distance and significantly improves waste collection efficiency. At the same time, it also reduces the number of times the robot travels within the community, minimizing disruption to residents' daily lives.

[0062] S103, obtain the robot's remaining garbage storage space and the garbage characteristics of each piece of garbage.

[0063] In one example, it's necessary to monitor the robot's remaining waste storage space in real time. This can be achieved by installing weight or volume sensors inside the robot's storage compartment. These sensors continuously monitor the weight or volume of waste currently in the compartment, thus calculating the remaining storage space. This information is crucial for developing subsequent waste collection strategies, as it determines how much waste the robot can collect before returning to the drop-off point.

[0064] Simultaneously, the system needs to acquire the characteristics of each type of waste. These characteristics may include the type of waste (e.g., recyclable, non-recyclable, hazardous waste), estimated weight, volume, and other information. This information can be obtained through cameras within the target area combined with image recognition technology. The system can utilize a pre-trained machine learning model to analyze the captured waste images, thereby identifying the type of waste. Weight and volume estimations can be made based on the size and shape of the waste in the image, combined with pre-defined reference data.

[0065] The purpose of acquiring this information is to enable the system to plan the waste collection sequence more intelligently. For example, when the robot has limited remaining storage space, the system can prioritize collecting smaller pieces of waste to maximize the use of the remaining space. Alternatively, the system can adjust the collection sequence based on the type of waste to ensure that different types of waste are not mixed, facilitating subsequent sorting and processing.

[0066] Furthermore, understanding the characteristics of waste can help robots prepare for collection tasks. For example, for heavier waste, the robot may need to adjust the force of its robotic arm; for waste with unusual shapes, it may need to adjust its grasping strategy. This advance preparation can improve the success rate and efficiency of waste collection.

[0067] S104: Based on the robot's remaining waste storage space and the characteristics of each piece of waste, adjust the initial driving route and generate the robot's target driving route.

[0068] In one example, adjusting the initial route first requires considering the robot's remaining trash storage space. The system assesses the amount of trash the robot can collect before needing to return to the trash drop-off point based on the remaining space. This assessment directly impacts the route adjustment. For instance, if the remaining space is small, the system might prioritize collecting a small amount of trash near the current location before heading to the drop-off point to empty the storage space, rather than continuing a long distance along the initial route.

[0069] Meanwhile, the characteristics of each type of waste are also an important basis for route adjustment. The system considers factors such as the type, weight, and volume of the waste. For larger or heavier waste, the system may adjust its position in the collection sequence to ensure that the robot processes it when there is sufficient storage space. In addition, the system will optimize the route according to the type of waste, processing similar types of waste together as much as possible and reducing the number of times the robot travels between different collection points.

[0070] In actual adjustment, the system may employ dynamic programming. It continuously calculates and updates the optimal next target point based on the current remaining storage space and the characteristics of the surrounding waste. This dynamic adjustment method enables the robot to respond more flexibly to changes in the working environment, such as sudden large amounts of waste or a sharp reduction in storage space.

[0071] The adjusted target route will contain more detailed information. In addition to indicating the robot's movement path, it will also indicate the processing order at each waste collection point, the expected storage space usage, and plans for possible return trips to the collection point. This detailed information can guide the robot to perform tasks more efficiently and also provides a basis for possible real-time adjustments.

[0072] Based on the above embodiments, as an optional implementation, in S104, the waste characteristics include waste type and waste volume. The initial travel route is adjusted according to the robot's remaining waste storage space and the waste characteristics of each piece of waste. The generation of the robot's target travel route specifically includes S401-S404:

[0073] S401, based on the type of each type of waste, determine the target waste that needs to be prioritized for treatment among multiple types of waste.

[0074] In one example, the system acquires information about the type of each piece of waste to be processed. This information may come from previous waste identification steps or pre-defined waste sorting data. The system then sorts these wastes according to pre-set priority rules. These priority rules may be based on multiple factors, such as the rate of decomposition, environmental impact, and recycling value. For example, easily perishable organic waste may be given a higher priority because it may produce odors and attract pests; hazardous waste such as batteries or chemicals may also have a high priority to prevent potential environmental pollution; and recyclables may be assigned different priorities based on their recycling value.

[0075] The system also considers the quantity and distribution of waste when determining priorities. If a certain type of high-priority waste is scarce and scattered, the system may weigh processing efficiency and choose to process the more abundant or concentrated medium-priority waste first. This dynamic adjustment avoids efficiency losses caused by frequent long-distance robot movements.

[0076] S402, based on the location of the target waste and the location where the target waste is disposed of, adjusts the initial driving route to generate the robot's first driving route.

[0077] In one example, when implementing step S402, the system first needs to integrate several key pieces of information: the priority list of target waste determined in step S401, the initial driving route generated in step S203, the specific location of each target waste, and its corresponding disposal location. Based on this information, a series of adjustments and optimizations are made to the initial driving route.

[0078] In practice, the system will first attempt to incorporate priority waste into the existing initial route. If a high-priority waste location is far from the initial route, the system will assess the costs and benefits of deviating from the initial route to process that waste. If the benefits outweigh the costs, the system will adjust the route accordingly. Simultaneously, the system will also consider the waste disposal location, designing a route that efficiently connects the waste location and the disposal location.

[0079] During this process, the system may employ optimization algorithms, such as nearest neighbor algorithms or genetic algorithms, to find the optimal route adjustment scheme. These algorithms consider multiple factors, including distance, time cost, and energy consumption, to balance processing priorities and overall efficiency.

[0080] S403, based on the robot's remaining waste storage space and the volume of each piece of waste, determine whether the robot's remaining waste storage space meets the processing requirements when the robot processes each piece of waste according to the first driving route.

[0081] In one example, two key data points need to be obtained: the robot's remaining waste storage space and the volume of waste at each waste point along the first travel route. The robot's remaining storage space can be monitored in real time by sensors, while the volume of each piece of waste may come from previous waste identification steps or estimated data. Next, the system will simulate the robot's waste collection process according to the order of the first travel route, calculating the remaining storage space at each step. If the robot cannot complete the processing of all waste along the current first travel route, for example, if there is insufficient storage space when processing a certain piece of waste.

[0082] This proactive assessment and simulation significantly improves the reliability and efficiency of the waste collection system. First, it prevents robots from being forced to interrupt their tasks due to insufficient storage space during actual operation. Such interruptions not only reduce efficiency but can also lead to some waste not being processed in a timely manner, causing environmental problems. Second, this step provides the system with an opportunity to adjust its strategy promptly. For example, in step S404, the system might adjust its route, returning to the waste processing station to empty the storage space after processing G4, before processing G5.

[0083] S404, if the robot's remaining waste storage space meets the processing requirements, then the first driving route is taken as the robot's target driving route; if the robot's remaining waste storage space does not meet the processing requirements, then the first driving route is adjusted to generate the robot's target driving route.

[0084] In one example, if the determination in step S403 indicates that the robot's remaining garbage storage space is insufficient to complete all garbage collection tasks on the first travel route, the system will initiate a route adjustment process. The purpose of this process is to generate a new target travel route, enabling the robot to complete the garbage collection tasks as efficiently as possible under the constraints of storage space.

[0085] For example, continuing the case from step S403, the system might generate the following new route:

[0086] G1>G2>G3>G4>Return to processing station to clear>G5;

[0087] This adjustment ensures the robot has sufficient storage space before processing G5. In some cases, the system may more aggressively adjust its route, such as postponing some non-priority waste collection points to the next round to ensure high-priority waste is processed promptly.

[0088] G1>G3>Return to processing station to clear>G2>G4>G5;

[0089] This dynamic adjustment capability ensures the feasibility of waste collection tasks and avoids task interruptions due to insufficient storage space. This not only improves system reliability but also prevents environmental problems that may be caused by waste accumulation. Secondly, by intelligently adjusting routes, the system can maximize the robot's work efficiency even with limited storage space. For example, by rationally scheduling the return to the processing station, unnecessary round trips can be minimized, thereby saving time and energy.

[0090] Based on the above embodiments, as an optional implementation, in S404, if the robot's remaining waste storage space does not meet the processing requirements, the first driving route is adjusted, and the target driving route of the robot is generated, specifically including S4001-S4003:

[0091] S4001, obtain the amount of garbage that the robot can process, and select the corresponding amount of garbage from the first driving route as garbage to be processed based on the amount of garbage that the robot can process.

[0092] In one example, the system determines the amount of trash the robot can handle. This amount may be influenced by several factors, such as the robot's remaining trash storage space, battery life, and estimated working time. Let's assume that calculations show the system determines the robot can currently handle a maximum of 5 pieces of trash.

[0093] Once this quantity is obtained, the system selects a corresponding number of trash items from the first driving route generated in step S402 as pending waste, i.e., waste that will not be processed temporarily. This selection process needs to consider multiple factors, including the priority of the waste (from the result of step S401), the location of the waste, and the volume of the waste. The system will attempt to select the most suitable combination of waste items as pending waste while ensuring that high-priority waste is processed in a timely manner.

[0094] Suppose the first travel route includes the following garbage collection points: G1 (high priority), G2 (medium priority), G3 (high priority), G4 (low priority), G5 (medium priority), G6 (high priority), and G7 (low priority). If the robot can handle 5 garbage collection points, the system might select G4 and G7 as the garbage to be processed. This selection considers both the priority of the garbage and ensures that the robot can handle the most important garbage.

[0095] S4002, based on the location of the waste to be processed and the location where the waste is disposed of, adjust the first driving route to generate the robot's second driving route.

[0096] In one example, when implementing step S4002, the system first considers the locations of the unprocessed waste identified in S4001. These locations represent waste points that can be temporarily skipped in the current task. Simultaneously, the system also needs to consider the disposal locations of this unprocessed waste, typically waste treatment plants or transfer stations. Based on this information, the system uses various path optimization algorithms, such as genetic algorithms, ant colony algorithms, or heuristic algorithms, to adjust the initial route generated in step S4002. During the adjustment process, the system avoids unprocessed waste points, optimizes path length, considers the location of waste treatment plants, and balances task priorities.

[0097] For example, suppose the first travel route is: Start > G1 > G2 > G3 > G4 > G5 > G6 > G7 > Processing Station, where G4 and G7 are identified as waste to be processed by S4001. Then, S4002 might generate the following second travel route: Start > G1 > G3 > G2 > G5 > G6 > Processing Station. This new route avoids G4 and G7 and may also optimize the access order of other points to reduce the total travel distance.

[0098] S4003, the second driving route is taken as the target driving route of the robot.

[0099] S105: Obtain dynamic obstacle information within the target area, adjust the target driving route based on the dynamic obstacle information, and generate the robot's final driving route so that the robot can process each piece of garbage within the target area according to the final driving route.

[0100] In one example, obtaining information about dynamic obstacles relies primarily on a specialized monitoring system installed within the target area. This system may include devices such as high-definition cameras, infrared sensors, and laser scanners, strategically deployed throughout the area to provide comprehensive environmental monitoring. These devices are capable of capturing all dynamic changes within the area in real time, including dynamic obstacles such as pedestrians, moving vehicles, or other moving objects.

[0101] The central control system continuously processes the data transmitted from these monitoring devices, using computer vision and target tracking algorithms to identify and track dynamic obstacles. The system constructs a real-time updated environmental map containing information such as the location, direction of movement, and speed of dynamic obstacles. This centralized environmental perception method provides more comprehensive and accurate environmental information compared to methods relying on the robot's own sensors, especially when dealing with large areas or multiple robots working collaboratively.

[0102] Based on the acquired dynamic obstacle information, the central control system needs to adjust the previously generated target driving route. This process involves real-time path planning and obstacle avoidance strategies. The system assesses whether there are potential collision risks on the current route. If a risk is detected, the system calculates a new path to bypass the obstacle. This may involve commanding the robot to temporarily change its direction of travel, slow down and wait for the obstacle to pass, or completely replan a new path.

[0103] During the adjustment process, the system not only needs to avoid current obstacles but also predict their possible trajectories to prevent collisions at some point in the future. This predictive planning enables smoother robot movement and reduces unnecessary pauses and changes in direction.

[0104] Furthermore, route adjustment needs to balance safety and efficiency. While safety is the primary consideration, the system will also strive to find a route that avoids obstacles without excessively increasing travel distance. This may involve quickly evaluating and comparing multiple possible paths to select an optimal compromise.

[0105] Through these adjustments, the system ultimately generates the robot's final route. This route not only includes the waste collection plan from the original target route but also incorporates strategies for adapting to the dynamic environment. The central control system continuously sends updated route information and control commands to the robot, guiding it to efficiently complete the waste disposal task while ensuring safety.

[0106] For example, a garbage collection robot was originally planned to start from the northwest corner of the area, proceed in a straight line for 300 meters along the main pedestrian street, and then turn right into a small square to collect garbage. However, as the robot began its movement, the monitoring system detected a group of about 20 tourists slowly moving about 150 meters from the planned route, while a temporary street performance attracting a large audience was taking place near the small square. The central control system quickly processed this information, predicting that the robot might be blocked by the crowd at the 150-meter mark if it continued as planned, and would be unable to work effectively once it reached the small square. Therefore, the system immediately adjusted the robot's route, instructing it to deviate 50 meters eastward, bypassing the main pedestrian street, and proceeding along a parallel path with less traffic. As the robot approached the small square, the system noticed that the street performance was still ongoing, so it further adjusted the route, instructing the robot to temporarily skip this area and proceed to a quieter area to the east for garbage collection. At the same time, the system discovered that several garbage bins near the robot's new route were nearly overflowing. Although these garbage bins were not originally planned, in order to improve overall efficiency, the system decided to have the robot handle these garbage bins along its route. While the robot is performing a new task, the system continuously monitors the entire area. When it detects that the crowd in the small square is starting to disperse, it updates the robot's route again and arranges for it to return to the small square after completing the current task.

[0107] Based on the above embodiments, as an optional implementation, in S105, the dynamic obstacle information includes position, movement speed, and movement direction. Acquiring dynamic obstacle information within the target area and adjusting the target driving route based on the dynamic obstacle information to generate the robot's final driving route specifically includes S501-S502:

[0108] S501 predicts the location and time when the robot will encounter the dynamic obstacle during its journey along the target route, based on the obstacle's position, speed, and direction of movement.

[0109] In one example, the system first needs to acquire and process real-time environmental data, including information from the robot's own sensors (such as LiDAR, cameras, and ultrasonic sensors) and information from potential external data sources (such as traffic monitoring systems and IoT devices). The system uses this data to build a dynamic model of the current environment, identifying and tracking surrounding dynamic obstacles, such as pedestrians, vehicles, or other moving objects. For each identified dynamic obstacle, the system records its current position, estimates its speed, and predicts its possible direction of movement. Simultaneously, the system analyzes the robot's target route, including predetermined waypoints, estimated speeds, and turning plans. Based on this information, the system predicts the future trajectories of the robot and each dynamic obstacle. By comparing these predicted trajectories, the system can calculate potential meeting points and meeting times.

[0110] For example, if the system detects a pedestrian moving east at a speed of 0.5 m / s, while the robot plans to move north at a speed of 1 m / s, the system will calculate that they may meet at a specific coordinate point in 30 seconds.

[0111] Based on the above embodiments, as an optional implementation, in S501, predicting the position and time point at which the robot encounters the dynamic obstacle during its journey along the target route, based on the obstacle's position, speed, and direction of movement, specifically includes:

[0112] The robot's moving speed is obtained. Based on the robot's moving speed and the target travel route, the estimated time for the robot to reach each target point on the target travel route is calculated. Based on the position, moving speed, and moving direction of the dynamic obstacle, the position of the dynamic obstacle at different time points is calculated. Based on the estimated time for the robot to reach each target point on the target travel route and the position of the dynamic obstacle at different time points, it is determined whether the position of the robot coincides with the position of the dynamic obstacle at any time point or the distance is less than a preset safety distance. If the position of the robot coincides with the position of the dynamic obstacle at the first time point or the distance is less than the preset safety distance, then this position and the first time point are determined as the position and time point where the robot meets the dynamic obstacle.

[0113] In one example, the robot's moving speed is acquired, data which may come from the robot's internal sensors or control system. Then, based on the robot's speed and the planned target route, the system calculates the estimated time for the robot to reach each target point on the route. This step uses basic physical motion formulas, considering the route length, the robot's speed, and possible acceleration and deceleration processes, to assign an estimated arrival time to each target point. Simultaneously, based on the initial position, speed, and direction of dynamic obstacles, the system uses similar motion formulas or more complex prediction models (such as Kalman filters) to calculate the positions of the dynamic obstacles at different time points. This process may need to consider factors such as the obstacle's acceleration and turning ability to improve prediction accuracy.

[0114] Next, the system compares the robot's predicted position with the predicted position of the dynamic obstacle on a timeline. At each time point, the system calculates the distance between the robot and the obstacle to determine if there is any overlap or if the distance is less than a preset safety distance. This preset safety distance is a key parameter, determined based on factors such as the robot's size, stopping distance, and operating environment. If the system detects that at a certain time point (referred to as the first time point) the distance between the robot and the obstacle is less than the safety distance, it marks that location and time point as a potential encounter point.

[0115] S502 adjusts the target driving route based on the location and time point to obtain the robot's final driving route.

[0116] In one example, the system comprehensively analyzes the predicted data provided in step S501, including potential collision points, encounter times, and the motion characteristics of dynamic obstacles. Simultaneously, the system needs to consider factors such as the robot's current state, task priority, and energy level. Based on this information, the system employs complex path planning algorithms, such as dynamic windowing or sampling-based path planning methods, to dynamically adjust the target travel route. During the adjustment process, the system weighs multiple objectives, including avoiding collisions, minimizing travel distance, optimizing energy use, and ensuring task completion time.

[0117] For example, if S501 predicts a possible encounter with a fast-moving vehicle at an intersection in 30 seconds, S502 might choose to slightly slow down or change its route to avoid this potential hazard. Alternatively, if a section of road is predicted to be heavily populated with pedestrians during a specific time period, the system might choose a slightly longer but safer alternative route.

[0118] After generating the robot's final travel route, the following is also included:

[0119] Monitor the robot's operating status, changes in waste distribution within the target area, and the robot's current location; based on the robot's current location, operating status, and waste distribution changes, optimize the final travel route and generate the robot's dynamic travel route.

[0120] In one example, the system first continuously monitors three key factors: the robot's operational status, changes in the distribution of waste within the target area, and the robot's current location. The robot's operational status includes information such as its battery level, work efficiency, and whether it has encountered any malfunctions; this data can be obtained through the robot's internal sensors and control system.

[0121] Information on changes in waste distribution within the target area may come from multiple sources, such as real-time reporting systems, environmental monitoring sensor networks, or feedback from other robots. The robot's current location is precisely obtained via GPS or other positioning systems. The system utilizes this real-time data, combined with the previously generated final route, and employs intelligent algorithms (such as dynamic programming and reinforcement learning) to optimize the route.

[0122] For example, if a sudden surge of trash is detected in an area, the system may adjust its route to prioritize that area for the robot. Alternatively, if the robot's battery level is lower than expected, the system may replan its route to reach the charging station faster. Or, if a minor malfunction is detected in a robot's function, the system may adjust its route to avoid tasks requiring that function. This dynamic optimization process is continuous; the system constantly updates and adjusts its route based on the latest information, generating dynamic driving routes.

[0123] In one embodiment of the present invention, after completing waste collection, the waste robot needs to transport the waste to a sorting line for further processing. However, directly transporting all the waste to the sorting line may cause equipment damage or reduce processing efficiency. To solve this problem, the robot of the present invention performs pre-sorting before transporting the waste to the sorting line.

[0124] Specifically, the robot first identifies and sorts out large, non-recyclable materials and materials that may damage the sorting equipment. This step relies on the robot's vision system and a material database. The robot's vision system scans each piece of waste and compares the scan results with a pre-stored material database. If the material is identified as belonging to either of these two special categories, the robot will store it separately in a dedicated container instead of sending it to the sorting line.

[0125] This pre-sorting operation serves two purposes: first, it effectively prevents materials that could damage the sorting equipment from entering the production line, thereby extending the equipment's lifespan and reducing maintenance costs; second, by removing large, non-recyclable materials that the production line cannot handle, it significantly improves the efficiency of subsequent sorting processes.

[0126] After pre-sorting, the robot transports the remaining waste to the sorting line. Notably, the robot of this invention possesses unique adaptive capabilities while operating on the sorting line. Equipped with an advanced motion control system and a flexible robotic arm, the robot can adjust its position and movements in real time based on the waste being grasped. Specifically, the robot continuously monitors the distribution and movement of waste on the line using a vision system, adjusting its speed and position as needed to maintain optimal operating positioning. Simultaneously, the robot's robotic arm dynamically adjusts its grasping posture and force based on the shape, size, and location of different types of waste.

[0127] This adaptive capability brings significant benefits. First, it greatly improves sorting efficiency and accuracy because the robot can always maintain optimal working condition; second, it enhances the system's flexibility, enabling the robot to handle various types and conditions of waste; finally, this intelligent operation method also reduces the need for human intervention, further reducing labor costs.

[0128] Through the above measures, the waste management robot of this invention can not only efficiently complete the collection and preliminary sorting of waste, but also ensure the safe operation and efficient processing of the sorting line. This intelligent waste management method greatly improves the efficiency and reliability of the entire waste management system, providing strong technical support for the intelligent management of urban household waste.

[0129] Based on the above method, this application also discloses an automatic garbage sorting device for household waste robots, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an automatic waste sorting device for household waste robots provided in an embodiment of this application. The device includes: a first acquisition module, a connecting module, a second acquisition module, a first adjustment module, and a second adjustment module; wherein,

[0130] The first acquisition module is used to acquire the robot's position within the target area, the positions of multiple pieces of trash within the target area, and the disposal locations of each piece of trash. The combination module is used to combine the robot's position, the positions of each piece of trash, and the disposal locations of each piece of trash to formulate the robot's initial travel route. The second acquisition module is used to acquire the robot's remaining trash storage space and the characteristics of each piece of trash. The first adjustment module is used to adjust the initial travel route based on the robot's remaining trash storage space and the characteristics of each piece of trash to generate the robot's target travel route. The second adjustment module is used to acquire dynamic obstacle information within the target area, adjust the target travel route based on the dynamic obstacle information, and generate the robot's final travel route so that the robot processes each piece of trash within the target area according to the final travel route.

[0131] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0132] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0133] The communication bus 1002 is used to realize the connection and communication between these components.

[0134] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0135] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0136] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0137] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 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 touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 3 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for an automatic waste sorting method using a household waste robot.

[0138] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 1001 can be used to call an application program stored in the memory 1005 for an automatic garbage sorting method of a household waste robot. When executed by one or more processors, the electronic device performs one or more of the methods described in the above embodiments.

[0139] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0140] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0141] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some service interfaces; indirect couplings or communication connections between devices or units may be electrical or other forms.

[0143] 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.

[0144] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0145] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a memory 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 application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0146] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for automatically sorting household waste using a robot, the method comprising: The location of the robot within the target area, the location of multiple pieces of trash within the target area, and the disposal location of each piece of trash are obtained. Based on the robot's position, the positions of each piece of trash, and the placement location of each piece of trash, an initial travel route for the robot is determined, including: calculating the distance from the robot to each piece of trash and the distance between each piece of trash based on the robot's position and the positions of each piece of trash; determining the order in which the robot processes each piece of trash, based on the distance from the robot to each piece of trash and the distance between each piece of trash, to obtain the robot's initial processing sequence; and planning the path for the robot to move between each piece of trash, based on the initial processing sequence and the placement location of each piece of trash, to generate the robot's initial travel route. Obtain the remaining waste storage space of the robot and the waste characteristics of each piece of waste; The waste characteristics include waste type and waste volume. Based on the robot's remaining waste storage space and the waste characteristics of each type of waste, the initial travel route is adjusted to generate the robot's target travel route. This includes: determining the target waste that needs to be prioritized for processing from among the multiple types of waste based on the waste type; adjusting the initial travel route based on the location and placement location of the target waste to generate the robot's first travel route; determining whether the robot's remaining waste storage space meets the processing requirements when processing each type of waste according to the first travel route based on the robot's remaining waste storage space and the waste volume of each type of waste; if the robot's remaining waste storage space meets the processing requirements, then the first travel route is taken as the robot's target travel route. If the robot's remaining waste storage space does not meet the processing requirements, the first driving route is adjusted to generate a target driving route for the robot, including: obtaining the amount of waste that the robot can process; selecting a corresponding amount of waste as waste to be processed from the first driving route based on the amount of waste that the robot can process; adjusting the first driving route based on the location of the waste to be processed and the placement location of the waste to be processed to generate a second driving route for the robot; and using the second driving route as the target driving route for the robot. The process involves acquiring dynamic obstacle information within the target area, including the obstacle's position, speed, and direction of movement. Based on this information, the target driving route is adjusted to generate the robot's final driving route. This includes: predicting the location and time of the robot's encounter with the dynamic obstacle during its journey along the target driving route, based on the obstacle's position, speed, and direction of movement. This includes: acquiring the robot's speed; calculating the estimated time for the robot to reach each target point on the target driving route based on the robot's speed and the target driving route; and calculating the time for the dynamic obstacle to encounter the obstacle at its location, speed, and direction of movement. The robot's position at different time points is determined based on the estimated time for the robot to reach each target point on the target travel route and the position of the dynamic obstacle at different time points. It is then determined whether the robot's position coincides with or is less than a preset safety distance from the position of the dynamic obstacle at any given time point. If the robot's position coincides with or is less than the preset safety distance from the position of the dynamic obstacle at a first time point, this position and the first time point are determined as the position and time point at which the robot encounters the dynamic obstacle. Based on the position and time point, the target travel route is adjusted to obtain the robot's final travel route, so that the robot processes the garbage within the target area according to the final travel route.

2. The automatic garbage sorting method using a garbage robot according to claim 1, characterized in that, After generating the robot's final travel route, the process also includes: Monitor the robot's operating status, the changes in the distribution of garbage within the target area, and the robot's current location; Based on the robot's current position, its operating status, and the information on changes in waste distribution, the final travel route is optimized, and a dynamic travel route for the robot is generated.

3. A robotic automatic waste sorting device for household waste, characterized in that, The device includes: a first acquisition module, a combination module, a second acquisition module, a first adjustment module, and a second adjustment module; wherein, The first acquisition module is used to acquire the position of the robot in the target area, the position of multiple pieces of garbage in the target area, and the placement position of each piece of garbage; The combining module is used to combine the robot's position, the position of each piece of trash, and the placement position of each piece of trash to formulate the robot's initial travel route, including: calculating the distance from the robot to each piece of trash and the distance between each piece of trash based on the robot's position and the position of each piece of trash; determining the order in which the robot processes each piece of trash in sequence based on the distance from the robot to each piece of trash and the distance between each piece of trash, to obtain the robot's initial processing sequence; and planning the path for the robot to move between each piece of trash based on the initial processing sequence and the placement position of each piece of trash, to generate the robot's initial travel route. The second acquisition module is used to acquire the remaining garbage storage space of the robot and the garbage characteristics of each piece of garbage; The first adjustment module is used to adjust the initial travel route based on the robot's remaining waste storage space and the waste characteristics of each type of waste, and to generate a target travel route for the robot. This includes: determining, based on the waste type of each type of waste, a target waste that needs to be prioritized for processing; adjusting the initial travel route based on the location and placement location of the target waste to generate a first travel route for the robot; and determining, based on the robot's remaining waste storage space and the waste volume of each type of waste, whether the robot's remaining waste storage space is sufficient to process each type of waste according to the first travel route. The robot's remaining waste storage space meets the processing requirements; if the remaining waste storage space does not meet the processing requirements, the first driving route is used as the robot's target driving route. This includes: obtaining the amount of waste the robot can process; selecting a corresponding amount of waste from the first driving route as waste to be processed based on the amount of waste the robot can process; adjusting the first driving route based on the location of the waste to be processed and the location where the waste is disposed of, to generate a second driving route for the robot; and using the second driving route as the robot's target driving route. The second adjustment module is used to acquire dynamic obstacle information within the target area, the dynamic obstacle information including position, speed, and direction of movement. Based on the dynamic obstacle information, it adjusts the target driving route to generate the robot's final driving route, including: predicting the position and time of the robot encountering the dynamic obstacle during its journey along the target driving route based on the position, speed, and direction of movement of the dynamic obstacle; acquiring the robot's speed; calculating the estimated time for the robot to reach each target point on the target driving route based on the robot's speed and the target driving route; and calculating the estimated time for the robot to reach each target point on the target driving route based on the position, speed, and direction of movement of the dynamic obstacle. The robot determines the positions of dynamic obstacles at different times; based on the estimated time for the robot to reach each target point on the target travel route and the positions of the dynamic obstacles at different times, it determines whether the position of the robot coincides with the position of the dynamic obstacle at any time point or the distance is less than a preset safety distance; if the position of the robot coincides with the position of the dynamic obstacle at a first time point or the distance is less than the preset safety distance, then the position and the first time point are determined as the position and time point where the robot meets the dynamic obstacle; based on the position and time point, the target travel route is adjusted to obtain the final travel route of the robot; so that the robot processes each piece of garbage in the target area according to the final travel route.

4. An electronic device, characterized in that, The device 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 used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-2.

Images