System and method for dynamically optimizing transport route of hook arm garbage truck

Abstract

The invention belongs to the technical field of garbage collection and transportation, and particularly relates to a hook arm garbage collection and transportation vehicle transportation route dynamic optimization system and method, the loading state of a garbage can is monitored through a sensor, and a collection and transportation instruction is automatically triggered when a preset threshold value is reached, so that garbage overflow is avoided, and meanwhile invalid scheduling is reduced. The intelligent scheduling system combines reinforcement learning and a Transform architecture, can comprehensively analyze real-time road condition information, dynamically calculates an optimal driving path, and timely adjusts the path according to traffic changes. Meanwhile, the system achieves cooperative scheduling of full-load vehicles and empty-box vehicles, ensures efficient connection of all links, effectively improves the response speed and execution efficiency of the clearance task, reduces the vehicle empty driving rate and energy consumption, achieves intelligent and fine management of the garbage clearance process, and improves the efficiency of the clearance task. The problem of low efficiency caused by information lag and fixed path in a traditional scheduling mode is solved.

Description

Technical Field

[0001] This invention belongs to the field of waste collection and transportation technology, specifically relating to a dynamic optimization system and method for the transportation route of a hooklift waste collection vehicle. Background Technology

[0002] In traditional waste collection operations, the scheduling of hooklift garbage trucks relies heavily on manual experience or fixed schedules, lacking real-time monitoring of garbage bin loading status. Existing technologies typically employ a timed collection method, where trucks travel to various garbage bin locations according to a pre-set schedule. While simple to operate, this method suffers from significant efficiency bottlenecks in practice. For example, in areas with high garbage volumes, overflowing bins and environmental pollution may occur; conversely, in areas with lower garbage volumes, trucks still operate on schedule, resulting in unnecessary empty runs and resource waste.

[0003] In addition, the existing dispatching system has a weak ability to respond to traffic conditions, and route planning is mostly based on static map information, making it difficult to dynamically adjust the driving route according to real-time traffic conditions, resulting in low waste collection efficiency, especially during peak hours or when sudden traffic incidents occur.

[0004] In summary, the existing waste collection and dispatching methods have technical problems, such as the inability to dynamically optimize transportation routes based on waste loading status and real-time road conditions, resulting in low collection efficiency and poor resource utilization. Summary of the Invention

[0005] The purpose of this invention is to provide a dynamic optimization system and method for the transportation route of hooklift garbage trucks, which effectively improves the response speed and execution efficiency of garbage collection tasks, reduces vehicle empty running rate and energy consumption, realizes intelligent and refined management of the garbage collection process, and solves the problem of low efficiency caused by information lag and fixed routes in traditional scheduling methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for dynamic optimization of the transportation route of a hooklift garbage truck, comprising the following steps:

[0007] The system monitors the garbage bin's loading level using sensors, triggering a collection command when the loading level reaches a preset threshold. Upon receiving the collection command, the intelligent dispatch system assigns tasks to the hooklift garbage truck based on real-time road condition information. The intelligent dispatch system uses a combination of reinforcement learning and Transformer architecture to calculate the optimal driving path for the hooklift garbage truck. Based on a dynamic path adjustment mechanism, the system replans the driving route of the hooklift garbage truck. Simultaneously, it guides fully loaded vehicles to the garbage station to dump garbage and directs empty bin vehicles to perform resupply operations.

[0008] Preferably, the preset threshold is 80% of the maximum capacity of the trash can. When the loading reaches the preset threshold, the sensor sends a collection request signal to the intelligent scheduling system. The collection request signal includes the location information of the trash can and the current timestamp.

[0009] Preferably, the intelligent scheduling system determines the optimal task allocation scheme by analyzing the distance between the vehicle's current location and the trash can, the estimated arrival time, and the vehicle's load status;

[0010] The distance calculation uses the Euclidean algorithm, the estimated arrival time is based on historical traffic data and real-time road condition predictions, and the vehicle load status is detected by onboard sensors and uploaded to the intelligent dispatch system.

[0011] Preferably, the real-time traffic information includes traffic flow and road congestion status; the traffic flow is obtained through cameras and a traffic management platform, and the road congestion status is calculated from vehicle GPS positioning data and historical traffic speeds.

[0012] Preferably, in the event of a sudden traffic emergency, the dynamic route adjustment mechanism re-plans the driving route of the hooklift garbage truck based on the vehicle's current location and the remaining capacity of the target garbage bin.

[0013] On the other hand, this invention proposes a dynamic optimization system for the transportation route of a hooklift garbage truck, comprising:

[0014] The sensor module is used to monitor the garbage bin's load and trigger collection instructions;

[0015] The intelligent scheduling module is used to calculate the optimal path based on reinforcement learning and the Transformer architecture;

[0016] The dynamic route planning module is used to adjust the driving route according to real-time traffic conditions;

[0017] The multi-vehicle coordination module is used to allocate waste collection tasks and guide the operation of fully loaded and empty container vehicles.

[0018] Preferably, the multi-vehicle collaborative module is implemented through a task allocation optimization model. The optimization model aims to minimize the overall collection time, and the constraints include the maximum driving distance of the vehicles, the remaining capacity of the garbage bins, and the time interval between adjacent vehicles arriving at the same garbage bin.

[0019] Preferably, the system further includes an emergency response module for adjusting task allocation in special circumstances.

[0020] Preferably, the system further includes: a data privacy protection module for encrypting and anonymizing sensitive information; the data privacy protection module uses encryption standards to encrypt the location and garbage loading information of the hook-arm garbage truck, the encryption key is stored in a security chip, and access permissions are restricted through an identity authentication mechanism.

[0021] Preferably, the system also includes a regular update and maintenance mechanism, which includes software version upgrades, sensor calibration, and path planning model parameter optimization.

[0022] Technical effects and advantages of the present invention: The hooklift garbage truck transportation route dynamic optimization system and method proposed in this invention have the following advantages compared with the prior art:

[0023] This invention monitors the loading status of garbage bins using sensors and automatically triggers collection commands when a preset threshold is reached, thereby preventing garbage overflow and reducing ineffective scheduling. The intelligent scheduling system combines reinforcement learning and the Transformer architecture to comprehensively analyze real-time traffic information, dynamically calculate the optimal driving route, and adjust routes promptly based on traffic changes. Simultaneously, the system enables coordinated scheduling of fully loaded and empty bin vehicles, ensuring efficient connection between all stages. This invention effectively improves the response speed and execution efficiency of collection tasks, reduces vehicle empty-running rates and energy consumption, and achieves intelligent and refined management of the garbage collection process, solving the inefficiency problems caused by information lag and fixed routes in traditional scheduling methods. Attached Figure Description

[0024] Figure 1 This is a flowchart of the method for dynamic optimization of the transportation route of a hooklift garbage truck according to the present invention;

[0025] Figure 2 This is a block diagram of the hooklift garbage truck transportation route dynamic optimization system of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] This invention provides, for example Figure 1The method shown is a dynamic optimization method for the transportation route of hooklift garbage trucks. The core of the method is to build an intelligent scheduling system that can learn and optimize scheduling strategies autonomously, and combine real-time sensor data, reinforcement learning and a large model with Transformer architecture for path planning and task allocation.

[0028] This embodiment utilizes sensors installed on the garbage bins to monitor the garbage loading level and sets 80% as the threshold for triggering a collection command. When the garbage loading rate reaches this level, the system automatically sends a collection task to the hook-lift garbage truck, ensuring that garbage does not overflow due to overfilling and avoiding unnecessary empty runs. Based on this, the intelligent scheduling system employs reinforcement learning methods to continuously adjust the optimal driving path and task allocation strategy for vehicles through trial and error and feedback. Furthermore, the system introduces a large model based on the Transformer architecture to handle complex multivariate decision-making problems, such as garbage generation rates in different areas, road congestion conditions, and the real-time location of collection vehicles, thereby achieving more accurate task scheduling and route planning.

[0029] In actual operation, the system not only directs fully loaded vehicles to the nearest garbage station to dump their waste, but also simultaneously guides empty container vehicles to perform resupply operations, ensuring efficient coordination among all stages. Furthermore, the system possesses dynamic route planning capabilities, enabling it to adjust routes based on real-time traffic conditions, avoiding delays caused by traffic congestion or unforeseen events.

[0030] Furthermore, to ensure system stability and reliability, the embodiment also includes contingency strategies to handle unforeseen circumstances such as extreme weather, equipment failure, or temporary road closures. Finally, the entire process emphasizes data privacy protection and model interpretability, ensuring that the system meets security and compliance requirements while improving efficiency.

[0031] Through the above methods, the present invention realizes intelligent management of the transportation routes of hook-arm garbage trucks, significantly improves the efficiency and response speed of garbage collection, and enhances the rationality and credibility of the scheduling implementation.

[0032] Specifically, the dynamic optimization method for the transportation route of hooklift garbage trucks in this embodiment includes the following steps:

[0033] The system monitors the amount of trash cans loaded using sensors. When the amount of trash cans loaded reaches a preset threshold, a collection command is triggered. The preset threshold is 80% of the maximum capacity of the trash cans. When the amount of trash cans loaded reaches the preset threshold, the sensors send a collection request signal to the intelligent scheduling system. The collection request signal includes the location information of the trash cans and the current timestamp.

[0034] Upon receiving the collection instruction, the intelligent dispatch system assigns tasks to the hooklift garbage truck based on real-time traffic information. Furthermore, the intelligent dispatch system determines the optimal task allocation scheme by analyzing the distance between the vehicle's current location and the garbage bin, the estimated arrival time, and the vehicle's load status. The distance is calculated using the Euclidean algorithm, the estimated arrival time is based on historical traffic data and real-time traffic prediction, and the vehicle load status is detected by onboard sensors and uploaded to the intelligent dispatch system.

[0035] Furthermore, real-time traffic information includes traffic flow and road congestion status; the traffic flow is obtained through cameras and a traffic management platform, and the road congestion status is calculated from vehicle GPS positioning data and historical traffic speeds.

[0036] The intelligent scheduling system uses a combination of reinforcement learning and Transformer architecture to calculate the optimal driving path of the hooklift garbage truck.

[0037] Based on the dynamic route adjustment mechanism, the driving routes of hooklift garbage trucks are replanned. In the event of sudden traffic emergencies, the dynamic route adjustment mechanism replans the driving routes of hooklift garbage trucks based on the current location of the vehicles and the remaining capacity of the target garbage bins. Simultaneously, fully loaded vehicles are guided to the garbage station to dump garbage, and empty bins are directed to carry out refill operations.

[0038] On the other hand, this invention proposes a dynamic optimization system for the transportation route of hooklift garbage trucks, such as... Figure 2 As shown, it includes:

[0039] The sensor module is used to monitor the garbage bin's load and trigger collection instructions;

[0040] The intelligent scheduling module is used to calculate the optimal path based on reinforcement learning and the Transformer architecture;

[0041] The dynamic route planning module is used to adjust the driving route according to real-time traffic conditions;

[0042] The multi-vehicle coordination module is used to allocate collection tasks and guide the operation of fully loaded and empty garbage bins. This module is implemented through a task allocation optimization model, which aims to minimize the overall collection time. Constraints include the maximum driving distance of vehicles, the remaining capacity of garbage bins, and the time interval between adjacent vehicles arriving at the same garbage bin.

[0043] The emergency response module is used to adjust task allocation in special circumstances.

[0044] The data privacy protection module is used to encrypt and anonymize sensitive information. The data privacy protection module uses encryption standards to encrypt the location and garbage loading information of the hook-arm garbage truck. The encryption key is stored in a security chip and access permissions are restricted through an identity authentication mechanism.

[0045] A regular update and maintenance mechanism is in place, which includes software version upgrades, sensor calibration, and optimization of path planning model parameters.

[0046] In addition, the modules mentioned above are also used to implement other steps of the aforementioned method for dynamic optimization of hooklift garbage truck transportation routes, as follows:

[0047] In this embodiment, the intelligent scheduling of hook-lift garbage trucks relies on sensors installed on each garbage bin. These sensors continuously monitor the garbage load and trigger a collection command when a preset threshold is reached. To ensure that the garbage bins do not overflow due to overfilling and to avoid unnecessary empty runs, the system sets a garbage loading rate of 80% as the condition for triggering a collection task. When the loading capacity of a garbage bin reaches this threshold, the sensor generates a signal and transmits it to the central dispatch system so that the corresponding collection vehicle can be dispatched to perform the collection task.

[0048] Assume the current garbage capacity of the trash can is ,in To indicate time, then when hour( (Based on the maximum capacity of the trash can), the system will automatically generate a collection request. This process can be represented by the following formula: ;

[0049] like The system determines that the trash can needs to be emptied and issues a task instruction to the nearest available hooklift garbage truck; if Then continue to monitor the garbage loading status until the trigger condition is met again.

[0050] Once a garbage collection task is triggered, the system calculates the most suitable hooklift garbage truck to perform the task based on the location of the garbage bin, current traffic conditions, and the distribution of nearby vehicles. At this point, the system considers multiple factors, including the distance between the vehicle's current location and the garbage bin. Estimated arrival time Factors such as whether the vehicles are currently idle are considered to determine the optimal scheduling plan. The specific scheduling decision can be expressed as: ;

[0051] in, Indicates the first The car arrived at the The distance to each trash can Indicates the first The car arrived at the The estimated time for each trash can, Indicates the first Is the vehicle unloaded? (If it is unloaded, then...) ,otherwise Weighting coefficients Each factor corresponds to a different level of importance, and can be dynamically adjusted based on historical data during subsequent optimization.

[0052] Once the system completes task matching, the corresponding hooklift garbage truck will receive navigation instructions and proceed to the target garbage bin according to the optimal route for collection. Simultaneously, the system will update the garbage bin's status information to ensure that subsequent scheduling decisions are adjusted based on the latest garbage loading status.

[0053] This embodiment employs a combination of reinforcement learning and Transformer architecture to achieve real-time dynamic path optimization, thereby improving vehicle driving efficiency and reducing energy consumption.

[0054] In this embodiment, the hooklift garbage truck is considered an intelligent agent whose goal is to minimize travel time and energy consumption while meeting garbage collection needs. Let... Indicates the first Real-time environmental conditions, including traffic flow, road congestion, vehicle current location, and remaining battery power; Indicates the first The actions taken at any given moment, namely the chosen direction or path of travel; Indicates the first The reward received at any given moment is defined as follows: ;

[0055] in, This represents the time cost from the current location to the destination. This indicates the energy consumption during driving. and , where are weighting coefficients, representing the importance of time and energy consumption, respectively. The agent's goal is to maximize the long-term cumulative reward, i.e.: ;in, It is a discount factor used to measure the importance of future rewards. Through reinforcement learning algorithms such as Deep Q-Networks (DQN), agents can continuously optimize their path selection strategies, enabling them to make optimal decisions in complex environments.

[0056] This embodiment also introduces a large model based on the Transformer architecture to handle large-scale path optimization problems. Compared with traditional recurrent neural networks (RNNs), the Transformer can better capture long-distance dependencies and supports parallel computation, thereby improving computational efficiency. Specifically, the system models the road network as a graph structure, where each node represents an intersection or road segment, and each edge represents a road connection relationship. For any two nodes... and Its connection weight is calculated by the following formula: ;

[0057] in, Represents a node With nodes The physical distance between them This indicates the real-time traffic flow on that road segment. To adjust parameters and balance the impact of distance and traffic flow, the Transformer model allows the system to efficiently calculate the optimal path and dynamically adjust the route to cope with unexpected traffic conditions.

[0058] Furthermore, the system supports multi-vehicle collaborative path planning, ensuring that there are no path conflicts or resource waste between different hooklift garbage trucks. For example, when two trucks head to the same garbage bin simultaneously, the system will reallocate tasks based on their respective driving statuses to avoid duplicate operations. This process can be achieved by solving the following optimization problem: ;

[0059] in, Number of available vehicles The number of trash cans awaiting collection. Let be a binary variable, representing the first... Is the vehicle responsible for the first One trash can (if responsible) ,otherwise Through this optimization model, the system can find the optimal vehicle-task matching implementation on a global scale, maximizing overall waste collection efficiency.

[0060] By combining reinforcement learning with the Transformer architecture, this embodiment achieves efficient path optimization, enabling hooklift garbage trucks to quickly adapt to changes in complex traffic environments and select the optimal driving route.

[0061] During the actual operation of hooklift garbage trucks, traffic conditions may change at any time, such as sudden congestion, traffic accidents, or temporary road closures. To ensure efficient completion of the collection tasks, this embodiment introduces a dynamic route adjustment mechanism, enabling vehicles to replan their routes based on real-time traffic conditions. Furthermore, considering that multiple hooklift garbage trucks may be performing tasks in the same area, the system also needs to implement multi-vehicle collaborative scheduling to avoid route conflicts and optimize overall transportation efficiency.

[0062] Regarding dynamic route adjustment, the system receives real-time data from the traffic monitoring platform to obtain the latest traffic conditions for each road segment. Assuming the travel time for a certain road segment is... ,in and These represent the start and end points, respectively. The timestamp indicates that when a significant increase in travel time for that road segment is detected, the system will recalculate the optimal path. The new path selection can be represented as: ;

[0063] in, Represents the set of candidate paths. Indicates time Lower section The passage time, This indicates the energy consumption during the driving period. The weighting coefficients are used to weigh the importance of time and energy consumption. Through this optimization model, the system can dynamically adjust the travel route of the hooklift garbage truck to ensure that the vehicle always travels along the path with the shortest travel time or lowest energy consumption.

[0064] In multi-vehicle collaborative scheduling, the system needs to consider the interaction relationships between different vehicles to avoid path overlap or resource waste. For example, when multiple hooklift garbage trucks simultaneously head to the same garbage bin for collection, the system should reallocate tasks based on their respective locations, remaining battery power, and task priorities. Therefore, this embodiment employs a task allocation optimization model with the objective function of minimizing the overall collection time. ;

[0065] in, Number of available vehicles The number of trash cans awaiting collection. Let be a binary variable, representing the first... Is the vehicle responsible for the first One trash can (if responsible) ,otherwise Through this optimization model, the system can find the optimal vehicle-task matching implementation on a global scale, maximizing overall waste collection efficiency.

[0066] In addition, the system introduces an inter-vehicle communication mechanism, enabling hooklift garbage trucks to share information such as their location, driving status, and estimated arrival time. Assuming the vehicles... Current location is The estimated time to reach the target trash can is Other vehicles can then adjust their driving strategies based on this information to avoid path overlap or long wait times. Specifically, coordinated scheduling between vehicles can be achieved through the following constraints: ;

[0067] in, This represents the time interval threshold between adjacent vehicles arriving at the same trash can. If this condition is not met, i.e., two vehicles arrive at the same trash can almost simultaneously, the system will reassign tasks, causing some vehicles to redirect to other trash cans for collection. This mechanism effectively reduces interference between vehicles and improves the stability of the overall scheduling.

[0068] During the operation of hooklift garbage trucks, various emergencies may occur, such as extreme weather, equipment failure, or temporary road closures. To ensure that the system can maintain basic operation under abnormal circumstances, this embodiment has designed a comprehensive emergency strategy to guarantee the continuity and stability of garbage collection operations.

[0069] First, under extreme weather conditions, such as heavy rain, heavy snow, or strong winds, road capacity may be severely affected. In this case, the system will automatically adjust the travel routes of the hooklift garbage trucks, prioritizing safer alternative routes. If a main road becomes impassable due to weather, the system will remove that road segment from the global path planning and recalculate the optimal travel implementation. The new route selection can be represented as: ;

[0070] in, This represents the set of candidate routes after excluding weather-affected sections. and They represent time. Lower section Travel time and energy consumption.

[0071] Secondly, in the event of equipment failure, such as a mechanical malfunction or sensor failure in the hooklift garbage truck, the system will immediately activate the backup dispatching implementation. If a vehicle is unable to continue its task due to a malfunction, the system will reassign nearby available vehicles to the target garbage bin and adjust the original planned collection sequence. This process can be optimized by addressing the following issues: ;

[0072] in, The number of hooklift garbage trucks currently available. The number of trash cans affected. Assign a variable to the new task, representing the first... Is the vehicle responsible for the first A trash can.

[0073] Furthermore, during temporary road closures or major events, some road sections may become impassable. In such cases, the system will dynamically adjust the waste removal routes based on real-time road closure information provided by traffic management authorities. For example, if a road is closed due to temporary construction, the system will remove that road section from the route planning and find an alternative route. This adjustment can be represented by the following formula: ;

[0074] in, Represents the original set of candidate paths. This represents the set of road sections affected by road closures. This represents the adjusted set of feasible paths.

[0075] To further enhance system stability, this embodiment also introduces a regular update and maintenance mechanism to ensure that the software and hardware are always in optimal condition. The system periodically checks the operation of the hooklift garbage truck's sensors, communication modules, and route planning algorithms, and optimizes the scheduling strategy based on the latest data. For example, the system adjusts the weight parameters of the route planning model based on historical collection data. This is to improve prediction accuracy and response speed.

[0076] Through the aforementioned emergency response strategies and system maintenance mechanisms, this embodiment effectively enhances the hooklift garbage truck's ability to respond to emergencies under special circumstances, while ensuring the long-term stable operation of the system. This not only strengthens the reliability of garbage collection operations but also further optimizes the overall scheduling implementation, making garbage collection more efficient and intelligent.

[0077] In the intelligent dispatching system for hooklift garbage trucks, a large amount of data collection and analysis involves sensitive information such as vehicle location, garbage loading capacity, and traffic conditions. To ensure data security and compliance, this embodiment employs data privacy protection measures, including data encryption, access control, and anonymization.

[0078] First, during data transmission, all information collected by the sensors is encrypted end-to-end to prevent unauthorized third parties from stealing or tampering with the data. Assume the data collected by the sensors is... The encrypted data is represented as Its encryption process follows the formula below: ;

[0079] in, This refers to the Advanced Encryption Standard (AES) algorithm. This is the encryption key. Only authorized users can use the correct key to decrypt data, ensuring the confidentiality of information during transmission.

[0080] Secondly, regarding data storage and access, the system employs a hierarchical access control mechanism to ensure that users with different roles can only access data relevant to their responsibilities. For example, dispatch center operators can view the real-time location and task status of all waste collection vehicles, while ordinary maintenance personnel can only access the historical maintenance records of specific vehicles. Access control rules can be represented as follows: ;

[0081] in, Indicates user identity, This indicates the data object to be accessed. This mechanism effectively limits the risk of sensitive data leakage, ensuring that only authorized personnel can access critical information.

[0082] Furthermore, to further reduce the possibility of privacy leaks, the system anonymizes some data. For example, when storing historical collection records, the identifier of the hooklift garbage truck is replaced with a randomly generated unique number to prevent the deduction of a specific vehicle's trajectory through data analysis. Specifically, the vehicle number in the original data... Mapped to anonymous identifier The conversion relationship is defined by the following formula: ;

[0083] in, Represents a hash function. The salt value is used to enhance the irreversibility of hash results.

[0084] Through the above-mentioned data privacy protection and model interpretability design, this embodiment improves the scheduling efficiency of hooklift garbage trucks while ensuring data security and system transparency, enabling managers to more clearly understand the formation process of scheduling decisions.

[0085] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for dynamic optimization of transportation routes for hooklift garbage trucks, characterized in that, Includes the following steps: The system monitors the amount of trash cans filled by sensors and triggers a collection command when the amount reaches a preset threshold. After receiving the collection instruction, the intelligent dispatch system assigns tasks to the hooklift garbage truck based on real-time road condition information; The intelligent scheduling system uses a combination of reinforcement learning and Transformer architecture to calculate the optimal driving path of the hooklift garbage truck. Based on the dynamic route adjustment mechanism, the driving routes of hooklift garbage trucks are replanned; Simultaneously guide fully loaded vehicles to the garbage station to dump garbage, and direct empty container vehicles to carry out resupply operations.

2. The method for dynamic optimization of the transportation route of a hooklift garbage truck according to claim 1, characterized in that: The preset threshold is 80% of the maximum capacity of the trash can. When the loading reaches the preset threshold, the sensor sends a collection request signal to the intelligent scheduling system. The collection request signal includes the location information of the trash can and the current timestamp.

3. The method for dynamic optimization of transportation routes for hooklift garbage trucks according to claim 1, characterized in that: The intelligent scheduling system determines the optimal task allocation scheme by analyzing the distance between the vehicle's current location and the trash can, the estimated arrival time, and the vehicle's load status. The distance calculation uses the Euclidean algorithm, the estimated arrival time is based on historical traffic data and real-time road condition predictions, and the vehicle load status is detected by onboard sensors and uploaded to the intelligent dispatch system.

4. The method for dynamic optimization of transportation routes for hooklift garbage trucks according to claim 1, characterized in that: The real-time traffic information includes traffic flow and road congestion status; the traffic flow is obtained through cameras and a traffic management platform, and the road congestion status is calculated from vehicle GPS positioning data and historical traffic speed.

5. The method for dynamic optimization of transportation routes for hooklift garbage trucks according to claim 1, characterized in that: The dynamic route adjustment mechanism, under sudden traffic conditions, re-plans the driving route of the hooklift garbage truck based on the vehicle's current location and the remaining capacity of the target garbage bin.

6. A dynamic optimization system for the transportation route of a hooklift garbage truck for implementing the method as described in any one of claims 1-5, characterized in that, include: The sensor module is used to monitor the garbage bin's load and trigger collection instructions; The intelligent scheduling module is used to calculate the optimal path based on reinforcement learning and the Transformer architecture; The dynamic route planning module is used to adjust the driving route according to real-time traffic conditions; The multi-vehicle coordination module is used to allocate waste collection tasks and guide the operation of fully loaded and empty container vehicles.

7. The hooklift garbage truck transportation route dynamic optimization system according to claim 6, characterized in that: The multi-vehicle collaborative module is implemented through a task allocation optimization model. The optimization model aims to minimize the overall collection time, and the constraints include the maximum driving distance of the vehicles, the remaining capacity of the garbage bins, and the time interval between adjacent vehicles arriving at the same garbage bin.

8. The hooklift garbage truck transportation route dynamic optimization system according to claim 6, characterized in that: The system also includes an emergency response module, used to adjust task allocation in special circumstances.

9. The hooklift garbage truck transportation route dynamic optimization system according to claim 6, characterized in that: The system also includes a data privacy protection module for encrypting and anonymizing sensitive information. The data privacy protection module uses encryption standards to encrypt the location and garbage loading information of the hook-arm garbage truck. The encryption key is stored in a security chip, and access permissions are restricted through an identity authentication mechanism.

10. The hooklift garbage truck transportation route dynamic optimization system according to claim 6, characterized in that: The system also includes a regular update and maintenance mechanism, which includes software version upgrades, sensor calibration, and optimization of path planning model parameters.

Images