Solar unmanned patrol car cluster system

Abstract

The invention discloses a solar unmanned patrol car cluster system, which belongs to the technical field of unmanned patrol cars and comprises a solar unmanned patrol car and a car cluster cloud control device. The vehicle body of the solar unmanned patrol vehicle adopts an external expansion design, and the periphery of the vehicle body is provided with a solar cell panel. The vehicle cluster cloud control device comprises a sensing and data acquisition module used for acquiring data; the communication and data transmission module is used for realizing data transmission; the decision-making and planning module is used for making a vehicle driving strategy; the control and execution module is used for executing the generated instruction; the cloud platform module is used for data storage, advanced analysis and global scheduling support; a security and monitoring module and a user interface module; according to the solar unmanned patrol car cluster system provided by the invention, energy supply modes are enriched, and a contribution is made to a dual-carbon target by utilizing green energy solar energy; meanwhile, the patrol car cluster is flexibly combined, so that the operation task capability and efficiency are improved; and the system is easy for engineering realization.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned patrol vehicles, and in particular to a solar unmanned patrol vehicle cluster system. Background Art

[0002] Unmanned patrol vehicles are mission-critical vehicles that utilize an unmanned ground vehicle (UGV) as a platform and are equipped with optoelectronic and other detection equipment. These vehicles play a vital role in replacing human operators in forest patrols, mineral exploration, power line inspections, and ecological monitoring in mountainous areas, deserts, hills, and beaches. Their autonomy and mobility provide technical support for their expanded application in diverse scenarios. Furthermore, their ability to operate even in harsh conditions such as thunderstorms, freezing rain, high temperatures, and high radiation levels has led to their increasing popularity.

[0003] However, there are still many issues that need to be addressed for unmanned patrol vehicles in the wild. The primary issue is power supply. Unmanned patrol vehicles operate in mountainous and wilderness areas, which are long and complex tasks. They also need to be stationed for long periods of time, making power supply inconvenient. Secondly, the sensing equipment on a single unmanned patrol vehicle has limited range and range, making it impossible to carry out full-area detection and patrol. Thirdly, if a single unmanned patrol vehicle malfunctions, the mission will be unable to be carried out, affecting the overall mission progress.

[0004] In light of the above, this paper proposes a solar-powered unmanned patrol vehicle swarm system. Solar panels are placed on the patrol vehicles' bodies. In sunny outdoor environments, solar energy is used as a power source to compensate for the vehicles' lack of power during extended periods. Furthermore, the unmanned patrol vehicles are equipped with range-extending equipment to ensure reliable power supply during periods of low sunlight. The swarm is managed and controlled via a cloud platform, compensating for the inadequate detection and perception of individual vehicles and ensuring the effective execution of operational tasks. Summary of the Invention

[0005] The purpose of the present invention is to provide a solar unmanned patrol vehicle cluster system to solve the problems of insufficient power and limited single-vehicle operating capacity of unmanned vehicles operating for long periods of time in the field in the prior art.

[0006] To achieve the above-mentioned object, the present invention provides a solar unmanned patrol vehicle cluster system, comprising a solar unmanned patrol vehicle and a vehicle cluster cloud control device;

[0007] The solar unmanned patrol car adopts an outward-expanding design, with solar panels arranged on the periphery of the car body, a wheel system set under the car body, a display and control device set on the top of the car body, and a photoelectric device set above the display and control device;

[0008] The vehicle cluster cloud control device includes:

[0009] The perception and data acquisition module is used to collect real-time data on the solar-powered unmanned patrol vehicle's own status and surrounding environment, including multiple sensors and positioning systems;

[0010] The communication and data transmission module is used to realize data transmission between the unmanned patrol vehicle and the cloud, between vehicles, and between vehicles and infrastructure. It consists of a 5G terminal and a communication radio;

[0011] The decision-making and planning module formulates vehicle driving strategies based on data analysis results, including path planning, speed control, and collaborative decision-making;

[0012] The control and execution module is used to execute the instructions generated by the decision-making and planning module;

[0013] Cloud platform module for data storage, advanced analysis and global scheduling support;

[0014] Security and monitoring module, which ensures system security and reliability through data encryption, identity authentication, firewall, intrusion detection and real-time monitoring;

[0015] The user interface module provides an interactive interface for users and has remote control functions.

[0016] Preferably, for the swarm scheduling of unmanned patrol vehicles, a hybrid scheduling algorithm is adopted, including centralized global planning, distributed real-time adjustment and rule-based scheduling;

[0017] In centralized global planning, global task allocation and route planning are performed through the cloud platform. An optimization algorithm is used to divide the patrol area into several sub-areas and generate an initial patrol route for each vehicle. Simultaneously, the cloud platform dynamically monitors vehicle status and task progress, reallocating tasks based on real-time data.

[0018] In distributed real-time adjustments, each unmanned patrol vehicle autonomously adjusts its route based on real-time environmental data collected by onboard sensors;

[0019] Rule-based scheduling provides priorities and rules for task execution.

[0020] Preferably, the goal of centralized global planning is to minimize the total patrol time or maximize the area coverage, and its objective function expression is:

[0021]

[0022] Where N is the number of patrol cars; M is the number of sub-areas that need to be covered; c ij The cost of covering subregion j for patrol car i; x ij is a binary variable, x ij=1 if patrol car i is responsible for sub-area j, otherwise 0;

[0023] The constraints include:

[0024] Each sub-area must be covered:

[0025] The mission limit for each unmanned patrol vehicle is:

[0026] Among them, T i Indicates the task i that needs to be executed.

[0027] Preferably, the goal of distributed real-time adjustment is to minimize the local path cost, and its objective function expression is:

[0028]

[0029] Where K is the number of nodes in the patrol car’s current path; d k is the distance or time cost from node k to node k+1;

[0030] The constraints include:

[0031] Collision constraints:

[0032]

[0033] Among them, p i (t) is the position of patrol car i at time t; p j (t) is the position of patrol car j at time t; d safe For safe distance;

[0034] Dynamic obstacle avoidance constraints:

[0035]

[0036] Among them, b (t) is the position of obstacle b at time t; d obs The obstacle avoidance distance.

[0037] Preferably, rule-based scheduling determines the execution order of tasks through a priority function, and the expression of the priority function is:

[0038] P j =ω1urgency j +ω2distance j +ω3importance j ;

[0039] Among them, P j is the priority of task j; urgencyj The urgency of the task; distance j The distance from the patrol car to the mission location; importance j is the importance of the task; ω1, ω2, ω3 are weight coefficients;

[0040] Its rules and constraints include:

[0041] High priority task priority constraints:

[0042] If P j >P s ,Task j is assigned priority over task s;

[0043] Vehicle mission volume restriction constraints:

[0044]

[0045] Among them, P s Indicates the assigned task s; assignedtasks indicates the assigned task.

[0046] Preferably, the advantages of the traditional hybrid scheduling algorithm and the optimization-based scheduling algorithm are combined, and offline planning x is performed before the task starts through linear programming to minimize the total time for the vehicle to complete the task, maximize the area coverage or minimize energy consumption. During the operation, the scheduling strategy is continuously optimized through the machine learning model, and the efficiency of task completion is improved by learning historical data and environmental changes.

[0047] Therefore, the present invention adopts the above-mentioned solar unmanned patrol car cluster system, which has the following beneficial effects:

[0048] (1) Through the solar-powered unmanned patrol vehicle cluster control platform, the unmanned patrol vehicle cluster is controlled to ensure flexible combination and dynamic scheduling of unmanned patrol vehicles;

[0049] (2) By placing solar panels on the entire vehicle body, the light-receiving area is maximized.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a structural diagram of a vehicle cluster cloud control device according to an embodiment of the present invention;

[0052] Figure 2 This is a schematic structural diagram of a solar-powered unmanned patrol vehicle according to an embodiment of the present invention;

[0053] Figure numerals: 1. Vehicle body; 2. Wheel train; 3. Display and control device; 4. Optoelectronic equipment. DETAILED DESCRIPTION

[0054] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort shall fall within the scope of protection of the present invention.

[0055] A solar unmanned patrol vehicle cluster system, comprising a solar unmanned patrol vehicle and a vehicle cluster cloud control device;

[0056] like Figure 2 As shown, the solar-powered unmanned patrol vehicle's body 1 features an outward-expanding design to maximize its exposure to sunlight. Solar panels are arranged around the periphery of the vehicle to maximize the area receiving sunlight. A battery conversion controller converts solar energy into electrical energy for storage or to directly drive the vehicle. This energy is converted into a form suitable for battery storage. This energy is stored in a battery pack, which utilizes a thermal management system to ensure optimal battery performance. A wheel train 2 is located beneath the vehicle body 1, while a display and control device 3 is located on top. A photoelectric device 4 is located above the display and control device 3.

[0057] like Figure 1 As shown in the figure, the vehicle cluster cloud control device includes core modules such as perception and data acquisition, communication and data transmission, decision-making and planning, control and execution modules, cloud platform, security and monitoring, and user interface. These modules work together to achieve intelligent control and management of vehicle clusters, improving traffic efficiency and safety. Specifically:

[0058] The perception and data acquisition module is a core component of the vehicle cluster cloud control system. It is responsible for collecting real-time data on the vehicle's status and surrounding environment, providing basic information for subsequent decision-making and control. This module mainly includes various sensors and positioning systems, such as cameras, radar (millimeter wave radar and lidar), ultrasonic sensors, and Beidou positioning modules.

[0059] Cameras capture images and identify road signs, pedestrians, and other vehicles. Radars transmit and receive electromagnetic waves or lasers to accurately measure the distance, speed, and direction of surrounding objects, constructing a three-dimensional model of the environment. Ultrasonic sensors detect obstacles at close range, playing a particularly important role during low-speed driving or parking. Furthermore, positioning systems, combined with high-precision maps, provide precise vehicle location information, ensuring accurate positioning and navigation in complex environments. These sensors and positioning systems use data fusion technology to integrate multi-source information into a unified environmental perception output, providing reliable data support for collaborative decision-making and path planning within the vehicle swarm. The efficient operation of the perception and data acquisition modules is the foundation for intelligent control of vehicle swarms and directly determines the system's safety, real-time performance, and robustness.

[0060] The communication and data transmission module is a key component of the vehicle cluster cloud control system, responsible for efficient data transmission between vehicles and the cloud, between vehicles (V2V), and between vehicles and infrastructure (V2I). This module primarily consists of a 5G terminal and a communication radio, capable of meeting communication needs in various scenarios.

[0061] 5G terminals leverage their high bandwidth, low latency, and large connectivity to support real-time data exchange between vehicles and cloud platforms, such as uploading sensor data, downloading control commands, or map updates. Communication radios are primarily used for direct vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Especially in areas with insufficient 5G network coverage, communication radios can achieve low-latency, highly reliable data exchange through dedicated short-range communication (DSRC) technology, such as collaborative obstacle avoidance between vehicles or sharing the real-time status of traffic lights. Through the collaborative work of 5G terminals and communication radios, the communication module provides stable and efficient data transmission capabilities for vehicle clusters, which is an important guarantee for achieving multi-vehicle collaborative control and intelligent traffic management.

[0062] The decision-making and planning module formulates vehicle driving strategies based on data analysis. These include route planning, which plans the optimal route based on real-time traffic conditions and the destination; speed control, which adjusts vehicle speed to maintain safe distances and optimize traffic flow; and collaborative decision-making, which makes collective decisions in multi-vehicle collaborative scenarios to avoid collisions and optimize convoy driving.

[0063] The control and execution module executes the instructions generated by the decision-making and planning module, controlling the vehicle's movement through operations such as acceleration, deceleration, and steering. It executes control instructions by controlling the motor, braking system, and steering system. It also monitors the vehicle's status in real time to ensure accurate execution of control instructions.

[0064] The cloud platform module provides data storage, advanced analytics, and global scheduling support. Data storage: Stores data uploaded by vehicles for subsequent analysis and use. Advanced analytics: Leverages cloud computing resources for complex data analysis and model training. Control algorithm updates: Regularly update and optimize control algorithms to improve system performance.

[0065] The primary function of the security and monitoring module is to ensure system security and reliability. This is achieved through data encryption, identity authentication, firewalls, intrusion detection, and real-time monitoring. Data encryption ensures secure data transmission and storage. Identity authentication prevents unauthorized access. Firewalls and intrusion detection protect the system from cyberattacks. Real-time monitoring monitors vehicle status and system operation to promptly detect and address anomalies.

[0066] The user interface module provides users with an intuitive interactive interface for convenient monitoring and management of vehicle clusters. This module typically includes a visualization interface and remote control functions. The visualization interface graphically displays information such as vehicle status (such as location, speed, and battery level), route planning, and traffic conditions, supporting real-time monitoring and data analysis. The remote control function allows users to send remote commands via a mobile app, tablet, or web platform, such as adjusting patrol routes, initiating emergency tasks, or viewing historical data. In addition, the user interface module also provides alarm and notification functions to promptly alert users when a vehicle anomaly occurs or a task is completed. Through the user interface module, users can efficiently manage vehicle clusters and ensure the transparency and controllability of system operations.

[0067] For swarm scheduling of unmanned patrol vehicles, a hybrid scheduling algorithm is employed, effectively combining the advantages of centralized global planning and distributed real-time adjustments to meet the efficiency and flexibility requirements of patrol missions. In the centralized phase, the cloud platform is responsible for global task allocation and route planning. It utilizes an optimization algorithm to divide the patrol area into several sub-areas and generates an initial patrol route for each patrol vehicle, ensuring that all key areas are covered and duplicate patrols are avoided. Simultaneously, the cloud platform dynamically monitors vehicle status and task progress, reallocating tasks based on real-time data (such as emergencies or vehicle failures) to ensure efficient system operation.

[0068] In centralized global planning, the cloud platform assigns tasks and plans routes for each vehicle through an optimization algorithm. The goal is to minimize the total patrol time or maximize the area coverage. The objective function expression is:

[0069]

[0070] Where N is the number of patrol cars; M is the number of sub-areas that need to be covered; c ij The cost (e.g., time or distance) of covering subregion j for patrol car i; xij is a binary variable, x ij =1 if patrol car i is responsible for sub-area j, otherwise 0;

[0071] The constraints include:

[0072] Each sub-area must be covered:

[0073] The mission limit for each unmanned patrol vehicle is:

[0074] Among them, T i Indicates the task i that needs to be executed.

[0075] In distributed real-time adjustments, each unmanned patrol vehicle autonomously adjusts its route based on real-time environmental data collected by its onboard sensors, avoiding collisions and rapidly responding to emergencies. This distributed decision-making mechanism improves the robustness of the system, allowing the vehicles to independently complete their missions even if the cloud platform fails. Each patrol vehicle adjusts its route based on real-time environmental data with the goal of minimizing the local path cost. The objective function is expressed as:

[0076]

[0077] Where K is the number of nodes in the patrol car’s current path; d k is the distance or time cost from node k to node k+1;

[0078] The constraints include:

[0079] Collision constraints:

[0080]

[0081] Among them, p i (t) is the position of patrol car i at time t; p j (t) is the position of patrol car j at time t; d safe For safe distance;

[0082] Dynamic obstacle avoidance constraints:

[0083]

[0084] Among them, b (t) is the position of obstacle b at time t; d obs The obstacle avoidance distance.

[0085] At the same time, a rule-based scheduling algorithm provides clear priorities and rules for task execution. For example, when a high-priority event is detected, the nearest vehicle must respond immediately; vehicles must maintain a safe distance to avoid conflicts; and vehicles automatically return to the charging station after completing the task. These rules ensure the efficiency and safety of task execution. Rule-based scheduling determines the execution order of tasks through a priority function, which is expressed as:

[0086] P j =ω1urgency j +ω2distance j +ω3importance j ;

[0087] Among them, P j is the priority of task j; urgency j The urgency of the task (such as an emergency); distance j The distance from the patrol car to the mission location; importance j is the importance of the task (such as key area monitoring); ω1, ω2, and ω3 are all weight coefficients;

[0088] Its rules and constraints include:

[0089] High priority task priority constraints:

[0090] If P j >P s ,Task j is assigned priority over task s;

[0091] Vehicle mission volume restriction constraints:

[0092]

[0093] Among them, P s Indicates the assigned task s; assignedtasks indicates the assigned task.

[0094] To further optimize scheduling, an optimization-based scheduling algorithm is employed. Linear programming is used to perform offline planning before a mission begins, minimizing the patrol vehicle's total mission completion time, maximizing area coverage, or minimizing energy consumption. During operation, machine learning models are incorporated to continuously optimize the scheduling strategy, gradually improving mission completion efficiency by learning from historical data and environmental changes. By integrating hybrid, rule-based, and optimization-based scheduling, unmanned patrol vehicles can achieve efficient, flexible, and reliable operation in complex environments, dynamically adapting to emergencies and optimizing resource utilization.

[0095] Therefore, the present invention adopts the above-mentioned solar unmanned patrol car cluster system, enriching the energy supply mode, utilizing green energy solar energy, and contributing to the dual carbon goals; at the same time, the patrol car cluster is flexibly combined to improve the operational task capability and efficiency; and the system is easy to implement in engineering.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A solar-powered unmanned patrol vehicle cluster system, characterized by: Including solar-powered unmanned patrol vehicles and vehicle cluster cloud control devices; The solar unmanned patrol car adopts an outward-expanding design, with solar panels arranged on the periphery of the car body, a wheel system set under the car body, a display and control device set on the top of the car body, and a photoelectric device set above the display and control device; The vehicle cluster cloud control device includes: The perception and data acquisition module is used to collect real-time data on the solar-powered unmanned patrol vehicle's own status and surrounding environment, including multiple sensors and positioning systems; The communication and data transmission module is used to realize data transmission between the unmanned patrol vehicle and the cloud, between vehicles, and between vehicles and infrastructure. It consists of a 5G terminal and a communication radio; The decision-making and planning module formulates vehicle driving strategies based on data analysis results, including path planning, speed control, and collaborative decision-making; The control and execution module is used to execute the instructions generated by the decision-making and planning module; Cloud platform module for data storage, advanced analysis and global scheduling support; Security and monitoring module, which ensures system security and reliability through data encryption, identity authentication, firewall, intrusion detection and real-time monitoring; The user interface module provides an interactive interface for users and has remote control functions.

2. The solar unmanned patrol vehicle cluster system according to claim 1, characterized in that: For the swarm scheduling of unmanned patrol vehicles, a hybrid scheduling algorithm is adopted, including centralized global planning, distributed real-time adjustment and rule-based scheduling; In centralized global planning, global task allocation and route planning are performed through the cloud platform. An optimization algorithm is used to divide the patrol area into several sub-areas and generate an initial patrol route for each vehicle. Simultaneously, the cloud platform dynamically monitors vehicle status and task progress, reallocating tasks based on real-time data. In distributed real-time adjustments, each unmanned patrol vehicle autonomously adjusts its route based on real-time environmental data collected by onboard sensors; Rule-based scheduling provides priorities and rules for task execution.

3. A solar unmanned patrol car cluster system according to claim 2, characterized in that: The goal of centralized global planning is to minimize the total patrol time or maximize the area coverage. Its objective function expression is: Where N is the number of patrol cars; M is the number of sub-areas that need to be covered; c ij The cost of covering subregion j for patrol car i; x ij is a binary variable, x ij =1 if patrol car i is responsible for sub-area j, otherwise 0; The constraints include: Each sub-area must be covered: The mission limit for each unmanned patrol vehicle is: Among them, T i Indicates the task i that needs to be executed.

4. A solar unmanned patrol car cluster system according to claim 3, characterized in that: The goal of distributed real-time adjustment is to minimize the local path cost, and its objective function expression is: Where K is the number of nodes in the patrol car’s current path; d k is the distance or time cost from node k to node k+1; The constraints include: Collision constraints: Among them, p i (t) is the position of patrol car i at time t; p j (t) is the position of patrol car j at time t; d safe For safe distance; Dynamic obstacle avoidance constraints: Among them, b (t) is the position of obstacle b at time t; d obs Obstacle avoidance distance.

5. A solar unmanned patrol car cluster system according to claim 4, characterized in that: Rule-based scheduling determines the execution order of tasks through a priority function. The expression of the priority function is: P j =ω1urgency j +ω2distance j +ω3importance j ; Among them, P j is the priority of task j; urgency j The urgency of the task; distance j The distance from the patrol car to the mission location; importance j is the importance of the task; ω1, ω2, ω3 are weight coefficients; Its rules and constraints include: High priority task priority constraints: If P j >P s ,Task j is assigned priority over task s; Vehicle mission volume constraints: Among them, P s Indicates the assignment of tasks s; assignedtasks indicates the assignment of tasks.

6. The solar unmanned patrol vehicle cluster system according to claim 2, characterized in that: Combining the advantages of hybrid scheduling algorithms and optimization-based scheduling algorithms, offline planning x is performed before the task begins through linear programming to minimize the total time for vehicles to complete the task, maximize area coverage or minimize energy consumption. During operation, the scheduling strategy is continuously optimized through machine learning models, and the efficiency of task completion is improved by learning historical data and environmental changes.

Images