Sanitation equipment path planning method, device, equipment and medium

Abstract

According to the environmental sanitation equipment path planning method, device, equipment and medium, a plurality of environmental sanitation equipment and a plurality of garbage disposal stations in a specific geographic area jointly form an environmental sanitation distributed network, and each environmental sanitation equipment stores information of a current node where the environmental sanitation equipment is located and information of neighbor nodes adjacent to the environmental sanitation equipment. The environmental sanitation equipment path planning method comprises the following steps: selecting a target garbage disposal station closest to environmental sanitation equipment; and simulating an ant colony by using an ant colony optimization algorithm ACO to select a next node from all neighbor nodes, and searching an optimal path from the environmental sanitation equipment to the target garbage disposal station through iterative optimization.

Description

Technical Field

[0001] This application is applied to the environmental sanitation field, and specifically relates to a path planning method, device, equipment and medium for environmental sanitation equipment. Background Technique

[0002] In the environmental sanitation field, the ad-hoc network technology is widely used in the communication of equipment such as garbage collection trucks and cleaning robots. These devices move in the city and need to exchange location information and status data in real time. The ad-hoc network technology enables these devices to achieve interconnection through a wireless communication network without the support of fixed infrastructure. For example, garbage collection trucks need to adjust their routes according to real-time data to collect garbage along the most optimized paths, while cleaning robots need to coordinate their operations to avoid repeated cleaning or missed areas. Existing ad-hoc routing selection algorithms often rely on a central server for routing management, which limits the scalability and stability of the network; the central server becomes a single point of failure of the network, and once a failure occurs, the communication of the entire network will be affected. In addition, the computing and storage capabilities of the central server also limit the expansion of the network and are difficult to meet the needs of large-scale device access and data exchange. In the urban environment, due to the interference of factors such as buildings and terrain, the stability and coverage of wireless signals are limited, further exacerbating the complexity of routing selection.

[0003] The main defect of the existing technology lies in its strong dependence on the central server, which not only limits the scalability of the network, but also affects the stability and robustness of the network. In the environmental sanitation field, there are a large number of devices and the operating environment is complex and changeable. The dynamic nature of the network requires the routing selection algorithm to be able to quickly adapt to changes in the network topology and achieve efficient data transmission. However, centralized routing selection algorithms often react slowly when faced with rapid increases or decreases in network nodes and fluctuations in link quality, and are difficult to adjust routing strategies in a timely manner, resulting in low data transmission efficiency and even communication interruptions. In addition, the computing and storage capabilities of the central server also limit the expansion of the network and are difficult to meet the needs of large-scale device access and data exchange. Summary of the Invention

[0004] To solve these problems, this solution proposes a path planning method, device, equipment and medium for environmental sanitation equipment.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, this application provides a path planning method for environmental sanitation equipment. A plurality of environmental sanitation equipment and a plurality of garbage treatment stations in a specific geographical area jointly form an environmental sanitation distributed network. Each environmental sanitation equipment stores its own current node information and the information of its adjacent neighbor nodes. The path planning method for environmental sanitation equipment includes:

[0007] Select the target waste treatment station closest to the sanitation equipment;

[0008] Use the Ant Colony Optimization algorithm ACO to simulate the ant colony to select the next node from all neighbor nodes. After iterative optimization, find the optimal path for the sanitation equipment to reach the target waste treatment station.

[0009] Preferably, the node information includes: the ID of the node calculated by the SHA-1 algorithm based on the GPS address of the node.

[0010] Preferably, the steps for the sanitation equipment to use the Ant Colony Optimization algorithm ACO to simulate the ant colony to select the next node from all neighbor nodes and find the optimal path to the target waste treatment station after iterative optimization include:

[0011] Calculate the probability that ant m selects the next node j from the current node i according to the following formula

[0012]

[0013] Where represents the pheromone concentration from the current node i to the next node j of ant m, n = 1, 2, 3....n; represents the heuristic information from the current node i to the next node j of ant m, α is the pheromone importance parameter, β is the heuristic information importance parameter, Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni;

[0014] represents traversing all neighbor nodes k and calculating the sum of the path weights from the current node i to each neighbor node k of ant m;

[0015] Take the node with the highest probability as the next node for ant m to move;

[0016] Take the next node with the most selections among the n ants as the next node for the sanitation equipment to move;

[0017] Repeat the behavior simulation and pheromone update of the ants until the maximum number of iterations is reached, and take the message passing path with the most ants as the best path.

[0018] Preferably, the steps for pheromone update include:

[0019] Update the pheromone according to the following formula:

[0020]

[0021] Where τ ij(t + 1) is the pheromone concentration from the current node i to the next node j at the (t + 1)-th moment, τ ij (t) is the pheromone concentration from the current node i to the next node j at the t-th moment, and ρ is the pheromone evaporation rate; is the pheromone increment during the process of ant m moving from the current node i to the next node j, which is calculated by the formula:

[0022]

[0023] where L is the total length of the path taken by ant m, and Q is the pheromone enhancement constant.

[0024] Preferably, the path planning method for sanitation equipment includes:

[0025] When a self-fault of the sanitation vehicle or a fault in the surrounding link is detected, the Dijkstra algorithm is called to recalculate the shortest path to the target waste treatment station.

[0026] Preferably, the path planning method for sanitation equipment includes:

[0027] When the load of the target waste treatment station exceeds the preset load, the pheromone concentration of all paths passing through the target waste treatment station is increased by a preset percentage.

[0028] On the other hand, the present application also provides a path planning device for sanitation equipment. A plurality of sanitation equipment and a plurality of waste treatment stations in a specific geographical area jointly form a sanitation distributed network. The current node information of each sanitation equipment and the information of its adjacent neighbor nodes are stored in each sanitation equipment. The path planning device for sanitation equipment includes:

[0029] A selection module for selecting the target waste treatment station closest to the sanitation equipment;

[0030] A path optimization module for using the ant colony optimization algorithm ACO to simulate the ant colony to select the next node from all neighbor nodes, and through iterative optimization, find the optimal path for the sanitation equipment to reach the target waste treatment station.

[0031] Preferably, the path optimization module includes:

[0032] A probability calculation unit for calculating the probability of ant m selecting the next node j from the current node i according to the following formula

[0033]

[0034] where, represents the pheromone concentration from ant m from the current node i to the next node j, and n = 1, 2, 3....n; [[ID=...]] It represents the heuristic information for ant m to move from the current node i to the next node j. α is the pheromone importance parameter, β is the heuristic information importance parameter, and Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni;

[0035] It represents traversing all neighbor nodes k and calculating the comprehensive path weight for ant m to move from the current node i to each neighbor node k;

[0036] The ant node selection unit is used to take the node with the highest probability as the next node for ant m to move;

[0037] The sanitation equipment node selection unit is used to take the next node with the most selections among n ants as the next node for the sanitation equipment to move;

[0038] The path generation unit is used to repeatedly execute the behavior simulation of ants and pheromone update until the maximum number of iterations is reached, and take the message passing path with the most ants as the optimal path.

[0039] On the other hand, the present application also provides a control device, which is characterized by including a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps of the above-mentioned sanitation equipment path planning method.

[0040] On the other hand, the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, it implements the steps of the above-mentioned sanitation equipment path planning method.

[0041] The beneficial effects of the present invention are as follows:

[0042] The DHT technology eliminates the dependence on the central server by distributing storage node information and routing information, improving the robustness and scalability of the network. The ACO algorithm simulates the foraging behavior of ants and finds the optimal path through the dynamic adjustment of pheromones, enhancing the self-adaptability and self-healing ability of the network. Combining these two technologies aims to build a decentralized, efficient, and stable ad hoc network routing selection system to meet the requirements of high dynamicity and high reliability in the sanitation field. Through this innovative routing selection mechanism, the communication efficiency and operation coordination ability of sanitation equipment can be significantly improved, providing technical support for the sustainable development of smart cities. Description of the Drawings

[0043] Figure 1 It is a schematic flow chart of the sanitation equipment path planning method in the embodiments of the present application. Detailed Embodiments

[0044] For the convenience of those skilled in the art, the following further describes and explains the present invention patent through the accompanying drawings. The description is relatively detailed and complete, but it should not be construed as a limitation on the scope of the present invention patent. Obvious deformations and replacement forms of the following examples are all within the protection scope of this patent.

[0045] Referring to Figure 1 , the embodiment of the present application provides a path planning method for sanitation equipment. A plurality of sanitation equipment and a plurality of garbage treatment stations in a specific geographical area jointly constitute a sanitation distributed network. Each sanitation equipment stores its own current node information and the information of its adjacent neighbor nodes. The path planning method for sanitation equipment includes:

[0046] Select the target garbage treatment station closest to the sanitation equipment;

[0047] Use the ant colony optimization algorithm ACO to simulate the ant colony to select the next node from all neighbor nodes. After iterative optimization, find the optimal path for the sanitation equipment to reach the target garbage treatment station.

[0048] In an urban area, there are multiple sanitation equipment (such as garbage collection trucks) and multiple garbage treatment stations.

[0049] These equipment and treatment stations jointly constitute a sanitation distributed network. Each sanitation equipment is equipped with a GPS positioning system, which can obtain its own position information in real time, and stores its own current node information and the information of its adjacent neighbor nodes. The purpose of this method is to select the nearest target garbage treatment station and use the ant colony optimization algorithm (ACO) to find the optimal path to reach the target garbage treatment station, so as to improve the operation efficiency of the sanitation equipment and the rationality of path planning.

[0050] The steps S1 of selecting the nearest target garbage treatment station include:

[0051] S11, the sanitation equipment obtains the current accurate position information through its own GPS positioning system;

[0052] S12, obtain the position information of all garbage treatment stations from the network; this information can be obtained through a pre-stored database or real-time communication;

[0053] S13, calculate the straight-line distance (or other distance metrics, such as Manhattan distance) from the current position of the sanitation equipment to each garbage treatment station;

[0054] S14, select the garbage treatment station with the shortest distance as the target node; if there are multiple garbage treatment stations with the same distance, any one can be selected or selected according to other priority rules (such as processing capacity, current load, etc.).

[0055] In this embodiment, step S2 of using the ant colony optimization algorithm (ACO) to find the optimal path includes:

[0056] Step S21: Initialize the algorithm parameters, specifically including:

[0057] Pheromone concentration: Assign an initial pheromone concentration value to each edge in the sanitation distributed network (i.e., the connection between each pair of adjacent nodes). This value can be the same initial value, such as 1.0.

[0058] Heuristic information: Calculate the heuristic information for each edge, usually the reciprocal of the length (distance) of the edge.

[0059] For example, if the length of the edge is d, the heuristic information is 1 / d.

[0060] Algorithm parameters: Set the pheromone importance parameter α, the heuristic information importance parameter β, the pheromone evaporation rate ρ, and the pheromone enhancement constant Q. These parameters can be adjusted according to actual needs to optimize the algorithm performance.

[0061] Number of ants and number of iterations: Determine the number of ants n participating in the path search and the maximum number of iterations T.

[0062] Step s22: Ant path selection, specifically including:

[0063] ο For each ant m, starting from the current node where the sanitation equipment is located, select the next node according to the following probability formula:

[0064] ο

[0065] Where, represents the pheromone concentration of ant m from the current node i to the next node j, n = 1, 2, 3....n; represents the heuristic information of ant m from the current node i to the next node j, α is the pheromone importance parameter, β is the heuristic information importance parameter, Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni;

[0066] Each ant selects the next node in turn according to the above probability formula until it reaches the target waste treatment station, forming a complete path.

[0067] Step S23: Path evaluation and pheromone update, specifically including:

[0068] Evaluate the path formed by each ant and calculate the total length L of the path.

[0069] Update the pheromone concentration on the path according to the path length. The pheromone update formula is:

[0070]

[0071] Among them, τ ij (t + 1) is the pheromone concentration from the current node i to the next node j at the (t + 1)-th moment, and τ ij (t) is the pheromone concentration from the current node i to the next node j at the t-th moment, and ρ is the pheromone evaporation rate; is the pheromone increment during the process of ant m moving from the current node i to the next node j, and is calculated by the formula:

[0072]

[0073] where L is the length from the current node i to the next node j, and Q is the pheromone enhancement constant.

[0074] Repeat the above path selection and pheromone update process until the maximum number of iterations T is reached.

[0075] Step S24: Determine the optimal path, specifically including:

[0076] After all iterations are completed, select the shortest path among the paths passed by the ants as the optimal path. Send the optimal path to the sanitation equipment to guide it to drive to the target garbage disposal station along this path.

[0077] In this embodiment, the path planning method for the sanitation equipment includes: S3, when detecting a self-fault of the sanitation vehicle or a fault in the surrounding link, call the Dijkstra algorithm to recalculate the shortest path to the target garbage disposal station.

[0078] The sanitation vehicle is equipped with a self-diagnosis system that can monitor the vehicle status in real time. Once a fault is detected, the fault type and time are immediately recorded.

[0079] The sanitation vehicle monitors the link status with surrounding nodes (other sanitation vehicles or garbage disposal stations) by sending detection signals (such as ping). If the detection fails continuously for multiple times, it is considered that the link has a fault.

[0080] The sanitation vehicle sends the initially detected fault information to the central control system for further confirmation by the system.

[0081] Once the fault is confirmed, the central control system notifies the fault information to all relevant sanitation vehicles so that they can update their respective path planning.

[0082] The central control system or the sanitation vehicle constructs a graph model according to the latest network topology information (including faulty nodes and links), where the nodes represent sanitation vehicles, garbage disposal stations, etc., the edges represent the paths between them, and the weights of the edges represent the lengths of the paths or the estimated driving times.

[0083] Call the Dijkstra algorithm to calculate the shortest path from the current position of the sanitation vehicle to the nearest waste treatment station. The Dijkstra algorithm is a greedy algorithm that gradually constructs the shortest path to the target node by continuously selecting the current shortest path.

[0084] Send the newly calculated shortest path to the sanitation vehicle and guide it to drive according to the new path.

[0085] After receiving the new path, the sanitation vehicle adjusts its driving direction and travels along the newly calculated shortest path to the target waste treatment station.

[0086] Through the above step S3, the sanitation vehicle can quickly respond and re-plan the path when there is a fault in itself or the surrounding links, thereby reducing the impact of the fault on the sanitation operation and improving the continuity and efficiency of the operation. At the same time, this method also improves the robustness and reliability of the sanitation system, ensuring the stable operation of urban environmental sanitation management.

[0087] During the driving process, the sanitation vehicle continues to monitor its own state and the link state to ensure the feasibility of the path and trigger the path recalculation again when necessary.

[0088] In this embodiment, the path planning method for sanitation equipment includes:

[0089] S4, when the load of the target waste treatment station exceeds the preset load, increase the pheromone concentration of all paths passing through the target waste treatment station by a preset percentage.

[0090] The sanitation management system monitors the load conditions of each waste treatment station in real time, including the amount of waste waiting to be processed, the processing speed, available resources, etc.

[0091] Set a preset load threshold for each waste treatment station, and trigger the load balancing mechanism when the actual load exceeds this threshold.

[0092] When it is detected that the load of the target waste treatment station exceeds the preset threshold, the system evaluates the pheromone concentration that needs to be adjusted.

[0093] According to the load situation and historical data, determine a preset percentage for increasing the pheromone concentration of all paths passing through the target waste treatment station.

[0094] For each path leading to the target waste treatment station, increase the pheromone concentration according to the preset percentage. The increase in pheromone concentration can be calculated by the following formula:

[0095]

[0096] Where is the adjusted pheromone concentration, is the pheromone concentration before adjustment.

[0097] After updating the pheromone concentrations of all relevant paths, these new pheromone values will be used in the path selection of the next round of the ant colony optimization algorithm.

[0098] Due to the increase in pheromone concentration, the ants in the ant colony algorithm will be more inclined to choose these adjusted paths when selecting paths, thus dispersing the vehicles arriving at the target waste treatment station and reducing its load. The system continuously monitors the load situation of the waste treatment station and dynamically adjusts the pheromone concentration according to real-time data to achieve continuous load balancing.

[0099] Relying on this step S4, the sanitation management system can effectively balance the load of the waste treatment station. By dynamically adjusting the pheromone concentration, it guides the sanitation vehicles to choose paths with lower loads, avoiding the overall operation efficiency being affected by some overloaded waste treatment stations. This method improves the flexibility and response speed of sanitation operations, ensuring the efficient operation of urban environmental sanitation management.

[0100] Next, a specific example is used to illustrate the above method.

[0101] In a sanitation self-organizing network in a certain city, a sanitation self-organizing network system based on the distributed hash table (DHT) and ant colony optimization (ACO) algorithms is deployed. This sanitation self-organizing network system consists of 30 mobile garbage collection vehicles and 20 fixed waste treatment stations, covering an area of 100 square kilometers in the city. Each node is equipped with a GPS positioning system, and its GPS coordinates are used to generate a unique hash value as its identity in the DHT network. Among them, the aforementioned mobile garbage collection vehicles and fixed garbage collection stations are all called a node.

[0102] For example, the GPS coordinates of mobile garbage collection vehicle 1 are (39.9, 116.3), and a 160-bit ID is obtained through SHA-1 hashing. Using the asli library in Pyton, the SHA-1 hashing calculation can be easily implemented. After performing the hashing calculation, the 160-bit ID generated according to the GPS coordinates (39.9, 116.3) of mobile garbage collection vehicle 1 is: 7a89de01234567890ade1234567890ade12345678.

[0103] For each node, the information of its neighbor nodes is stored in the DHT module. In this embodiment, the neighbor nodes refer to the N neighbor nodes with the shortest distance to the current node. For example: Assume that each node stores the information of the 5 other nodes with the shortest distance to itself.

[0104] When the sanitation ad-hoc network system is initialized, the initial pheromone concentration of all paths is set to 0.1, and the pheromone evaporation rate is set to 0.8, which means that every time unit passes, the pheromone concentration will be reduced to 80% of the original. By releasing 50 ants, each ant representing a data packet, they start from the garbage collection vehicle and search for the optimal path to reach the nearest garbage disposal station.

[0105] Taking garbage collection vehicle 1 as an example, it needs to send data to the nearest garbage disposal station. Ant 1 starts from garbage collection vehicle 1 and evaluates the pheromone concentration and distance to its neighbor nodes. Suppose the pheromone concentration from garbage collection vehicle 1 to garbage collection vehicle 2 for Ant 1 is 0.15, and the distance is 0.5 kilometers; the pheromone concentration to garbage disposal station 1 is 0.1, and the distance is 1.2 kilometers. The probability P(1,2) for Ant 1 to select the next node from node 1 is calculated as follows:

[0106]

[0107] Ant 1 selects path 1-2 or 1-garbage disposal station 1 according to this probability P(1,2). After selecting path 1-2, Ant 1 continues to move forward and finally reaches garbage disposal station 1. The purpose of path evaluation is to determine the efficiency and effectiveness of this path. The path evaluation criteria can be path length, delay, or energy consumption. For example, the total length of path 1-2-garbage disposal station 1 is 1.5 kilometers, the delay is 0.05 seconds, and the energy consumption is 0.03 units.

[0108] The purpose of pheromone update is to strengthen good paths and weaken bad paths. After Ant 1 walks on path 1-2, it releases pheromone according to the path evaluation result. If the path evaluation result is good, the pheromone increases; if the result is bad, the pheromone decreases. The pheromone update formula is:

[0109] τ 1-2 (t + 1)=(1 - ρ)·τ 1-2 (t)+Δτ 1-2

[0110] Among them, ρ is the pheromone evaporation rate of 0.8, and Δτ 1-2 is the amount of pheromone released by Ant 1 on path 1-2, assumed to be 0.05 (based on the path evaluation result). In this way, the pheromone concentration of path 1-2 is updated to 0.12 + 0.05 = 0.17.

[0111] The purpose of the self-healing mechanism is to quickly recalculate the routing when a node or link in the network fails, so as to restore network connectivity. Suppose waste treatment station 1 fails. After the system detects it, the self-healing mechanism is immediately activated. The system uses the Dijkstra algorithm to recalculate the shortest path from garbage truck 1 to other waste treatment stations. Suppose the new path is 1-3-4-waste treatment station 2.

[0112] Load balancing can ensure that the data traffic in the network is evenly distributed, avoiding overloading of certain nodes. Suppose the load of waste treatment station 1 exceeds 80%. The system will increase the pheromone concentration passing through waste treatment station 1 by 10% to encourage ants to choose other paths and reduce the load on waste treatment station 1. For example, if the pheromone concentration of waste treatment station 1 is 0.3, it becomes 0.33 after the increase.

[0113] In this way, we can build a decentralized, highly self-adaptive and self-healing ad-hoc network routing system to meet the requirements of the sanitation field for high dynamicity and high reliability. In this system, the dynamic adjustment of pheromone simulates the process of ants finding food paths in nature. Through the evaporation and enhancement of pheromone, the algorithm can guide data packets to choose the optimal path and quickly adapt when the network structure changes, ensuring the stability and efficiency of the network. This bio-inspired algorithm provides an effective solution for solving complex network problems, especially in dynamic and uncertain environments, such as the sanitation network where real-time data exchange and high-efficiency operation scheduling are required. Through continuous pheromone update and path evaluation, the system can learn and optimize routing strategies, thereby improving the performance and reliability of the entire network.

[0114] This solution innovatively combines Distributed Hash Table (DHT) and Ant Colony Optimization (ACO) technologies, bringing significant improvements and benefits to the routing selection of ad-hoc networks in the sanitation field. The following is a detailed description of the specific beneficial effects of this solution:

[0115] 1) Enhance the self-adaptability and self-healing ability of the network and improve the robustness of the network:

[0116] Using DHT technology, each node in the network can independently store and retrieve routing information without relying on a central server. This decentralized feature enables the network to quickly adapt when facing the dynamic addition and departure of nodes, automatically reorganize the routing, and thus improve the self-adaptability of the network.

[0117] Combined with the ACO algorithm, the network can simulate the foraging behavior of ants and find the optimal path through the dynamic change of pheromone. When a node or link in the network fails, the ACO algorithm can quickly detect and recalculate the routing, realizing the self-healing of the network, thus greatly enhancing the robustness of the network.

[0118] 2) Achieve load balancing and improve the utilization rate of network resources:

[0119] The load balancing module in this solution can dynamically adjust the pheromone concentration according to the real-time monitored network status, guide the traffic distribution, avoid the performance degradation of some nodes due to overload, and ensure the effective utilization of idle nodes.

[0120] Through this intelligent traffic management, network resources are more reasonably allocated, the throughput and efficiency of the entire network are improved, and communication delays and data losses caused by node overload are reduced.

[0121] 3) Reduce the dependence on the central server and lower the risk of central failure:

[0122] Traditional ad hoc networks rely on the central server for routing management and data forwarding. Once the central server fails, the communication of the entire network will be severely affected. This solution realizes the distributed storage and processing of routing information through DHT technology, eliminating the risk of single-point failure.

[0123] This decentralized architecture not only improves the stability of the network but also reduces the maintenance cost because there is no longer a need for a powerful central server to support the network operation.

[0124] 4) Improve the communication efficiency of sanitation equipment and optimize operation scheduling and execution:

[0125] This solution reduces the data transmission delay and improves the communication efficiency by optimizing the route selection. This is crucial for sanitation equipment that requires real-time data exchange, such as garbage collection trucks and cleaning robots.

[0126] The efficient communication network makes the operation scheduling of sanitation equipment more flexible and precise, and the operation execution more coordinated, thus improving the overall operation efficiency and the quality of urban cleaning services.

[0127] In summary, this solution not only improves the technical performance of the ad hoc network in the sanitation field but also provides strong technical support for the sustainable development of smart cities. By improving the stability, scalability, and communication efficiency of the network, this solution provides a solid foundation for the intelligence and automation of sanitation operations, contributing to the construction of a cleaner, more efficient, and smarter urban environment.

[0128] The embodiment of this application also provides a path planning device for sanitation equipment. A plurality of sanitation equipment and a plurality of garbage disposal stations in a specific geographical area jointly constitute a sanitation distributed network. Each sanitation equipment stores its own current node information and the information of its adjacent neighbor nodes. The path planning device for sanitation equipment includes:

[0129] A selection module is used to select a target garbage disposal station closest to the sanitation equipment;

[0130] The path optimization module is used to use the ant colony optimization algorithm ACO to simulate the ant colony to select the next node from all neighboring nodes, and through iterative optimization, find the optimal path for sanitation equipment to reach the target garbage treatment station.

[0131] Among them, the path optimization module includes:

[0132] The probability calculation unit is used to calculate the probability of ant m selecting the next node j from the current node i according to the following formula:

[0133]

[0134] in, represents the pheromone concentration of ant m from the current node i to the next node j, n = 1, 2, 3....n; represents the heuristic information of ant m from the current node i to the next node j, α is the pheromone importance parameter, β is the heuristic information importance parameter, Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni;

[0135] It means traversing all neighbor nodes k and calculating the comprehensive path weight of ant m from the current node i to each neighbor node k;

[0136] Ant node selection unit, used to convert the probability The highest node is the next node for ant m to move to;

[0137] The sanitation equipment node selection unit is used to select the next node that is most selected among the n ants as the next node for the sanitation equipment to move to;

[0138] The path generation unit is used to repeatedly perform ant behavior simulation and pheromone update until the maximum number of iterations is met, and the path with the most ants passing messages is taken as the optimal path.

[0139] An embodiment of the present application also provides a control device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the above-mentioned sanitation equipment path planning method are implemented.

[0140] An embodiment of the present application also provides a readable storage medium, which stores a program or instruction. When the program or instruction is executed by a processor, the steps of the above-mentioned sanitation equipment path planning method are implemented.

[0141] It should be noted that the various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0142] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0143] It should also be noted that in this text, the orientation or positional relationships indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. This is for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, relational terms such as "first" and "second" are used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations, nor can they be construed as indicating or implying relative importance. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements does not include those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or terminal device comprising the element.

[0144] The technical solutions provided by the present invention have been introduced in detail above. Specific examples are used herein to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only for helping to understand the present invention, and the content of this specification should not be construed as a limitation to the present invention. At the same time, for those of ordinary skill in the art, based on the present invention, there will be various forms of changes in the specific implementation manners and application scopes. It is not necessary and impossible to enumerate all the implementation manners here, and the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. A path planning method for sanitation equipment, characterized in that, A number of sanitation equipment and a number of waste treatment stations in a specific geographical area jointly constitute a sanitation distributed network. Each sanitation equipment stores its own current node information and the information of its adjacent neighbor nodes. The sanitation equipment path planning method includes: Select the target waste treatment station closest to the sanitation equipment; Use the Ant Colony Optimization (ACO) algorithm to simulate the ant colony to select the next node from all neighbor nodes. After iterative optimization, find the optimal path for the sanitation equipment to reach the target waste treatment station.

2. The path planning method for environmental sanitation equipment according to claim 1, characterized in that The node information includes: the ID of the node calculated by using the SHA-1 algorithm based on the GPS address of the node.

3. The path planning method for environmental sanitation equipment according to claim 1, characterized in that, The steps for the sanitation equipment to use the Ant Colony Optimization (ACO) algorithm to simulate the ant colony to select the next node from all neighbor nodes and find the optimal path for the sanitation equipment to reach the target waste treatment station after iterative optimization include: Calculate the probability that ant m selects the next node j from the current node i according to the following formula Among them, represents the pheromone concentration of ant m from the current node i to the next node j, where n = 1, 2, 3....n; represents the heuristic information of ant m from the current node i to the next node j. α is the pheromone importance parameter, β is the heuristic information importance parameter, and Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni; Indicates traversing all neighbor nodes k and calculating the sum of the path weights from the current node i to each neighbor node k for ant m; The probability The node with the highest probability is used as the next node for the movement of ant m; Take the next node with the most selections among the n ants as the next node for the movement of the sanitation equipment; Repeat the behavior simulation and pheromone update of the ants until the maximum number of iterations is met, and take the message passing path with the most ants as the best path.

4. The path planning method for environmental sanitation equipment according to claim 3, characterized in that, The steps for pheromone update include: Among them, τ ij (t + 1) is the pheromone concentration from the current node i to the next node j at the (t + 1)-th moment, and τ ij (t) is the pheromone concentration from the current node i to the next node j at the t-th moment, and ρ is the pheromone evaporation rate; is the increase in pheromone during the process of ant m moving from the current node i to the next node j, through the formula: Calculate, where L is the total length of the path walked by ant m, and Q is the pheromone enhancement constant.

5. The path planning method for environmental sanitation equipment according to claim 1, wherein The sanitation equipment path planning method includes: When a self-fault of the sanitation vehicle or a fault in the surrounding link is detected, call the Dijkstra algorithm to recalculate the shortest path to the target waste treatment station.

6. The path planning method for environmental sanitation equipment according to claim 1, wherein, The sanitation equipment path planning method includes: When the load of the target waste treatment station exceeds the preset load, increase the pheromone concentration of all paths passing through the target waste treatment station by a preset percentage.

7. A path planning device for environmental sanitation equipment, characterized in that, A number of sanitation equipment and a number of waste treatment stations in a specific geographical area jointly constitute a sanitation distributed network. Each sanitation equipment stores its own current node information and the information of its adjacent neighbor nodes. The sanitation equipment path planning device includes: A selection module for selecting the target waste treatment station closest to the sanitation equipment; A path optimization module for using the Ant Colony Optimization (ACO) algorithm to simulate the ant colony to select the next node from all neighbor nodes and find the optimal path for the sanitation equipment to reach the target waste treatment station after iterative optimization.

8. The path planning device for environmental sanitation equipment according to claim 7, characterized in that The path optimization module includes: A probability calculation unit, which is used to calculate the probability that ant m selects the next node j from the current node i according to the following formula Among them, represents the pheromone concentration of ant m from the current node i to the next node j, where n = 1, 2, 3....n; represents the heuristic information of ant m from the current node i to the next node j. α is the pheromone importance parameter, β is the heuristic information importance parameter, and Ni is the set of all neighbor nodes of the current node i; k is an index variable used to traverse all neighbor nodes Ni; It means to traverse all neighbor nodes k and calculate the sum of the path weights from the current node i to each neighbor node k for ant m. An ant node selection unit is used to take the node with the highest probability as the next node for the movement of ant m; A sanitation equipment node selection unit for taking the next node with the most selections among the n ants as the next node for the movement of the sanitation equipment; A path generation unit for repeating the behavior simulation and pheromone update of the ants until the maximum number of iterations is met, and taking the message passing path with the most ants as the best path.

9. A control device, characterized in that, It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps of the sanitation equipment path planning method according to any one of claims 1 to 6.

10. A readable storage medium, characterized in that, The program or instruction is stored on the readable storage medium. When the program or instruction is executed by the processor, it implements the steps of the sanitation equipment path planning method according to any one of claims 1 to 6.

Images